diff --git a/.gitignore b/.gitignore
index 7e9932e..42fa0d5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -92,3 +92,6 @@
 signing_key.priv
 signing_key.x509
 x509.genkey
+
+# Kconfig presets
+all.config
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 38f8444..07de7e1 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -29,6 +29,8 @@
 	- How to do DMA with ISA (and LPC) devices.
 DMA-attributes.txt
 	- listing of the various possible attributes a DMA region can have
+dmatest.txt
+	- how to compile, configure and use the dmatest system.
 DocBook/
 	- directory with DocBook templates etc. for kernel documentation.
 EDID/
@@ -77,6 +79,8 @@
 	- directory with info about Linux on the ARM architecture.
 arm64/
 	- directory with info about Linux on the 64 bit ARM architecture.
+assoc_array.txt
+	- generic associative array intro.
 atomic_ops.txt
 	- semantics and behavior of atomic and bitmask operations.
 auxdisplay/
@@ -87,6 +91,8 @@
 	- how to use kernel parameters to exclude bad RAM regions.
 basic_profiling.txt
 	- basic instructions for those who wants to profile Linux kernel.
+bcache.txt
+	- Block-layer cache on fast SSDs to improve slow (raid) I/O performance.
 binfmt_misc.txt
 	- info on the kernel support for extra binary formats.
 blackfin/
@@ -171,6 +177,8 @@
 	- info about initramfs, klibc, and userspace early during boot.
 edac.txt
 	- information on EDAC - Error Detection And Correction
+efi-stub.txt
+	- How to use the EFI boot stub to bypass GRUB or elilo on EFI systems.
 eisa.txt
 	- info on EISA bus support.
 email-clients.txt
@@ -195,8 +203,8 @@
 	- info on requeueing of tasks from a non-PI futex to a PI futex
 gcov.txt
 	- use of GCC's coverage testing tool "gcov" with the Linux kernel
-gpio.txt
-	- overview of GPIO (General Purpose Input/Output) access conventions.
+gpio/
+	- gpio related documentation
 hid/
 	- directory with information on human interface devices
 highuid.txt
@@ -255,6 +263,8 @@
 	- listing of various WWW + books that document kernel internals.
 kernel-parameters.txt
 	- summary listing of command line / boot prompt args for the kernel.
+kernel-per-CPU-kthreads.txt
+	- List of all per-CPU kthreads and how they introduce jitter.
 kmemcheck.txt
 	- info on dynamic checker that detects uses of uninitialized memory.
 kmemleak.txt
@@ -299,8 +309,6 @@
 	- directory with info on parts like the Texas Instruments EMIF driver
 memory-hotplug.txt
 	- Hotpluggable memory support, how to use and current status.
-memory.txt
-	- info on typical Linux memory problems.
 metag/
 	- directory with info about Linux on Meta architecture.
 mips/
@@ -311,6 +319,8 @@
 	- directory with info about the MMC subsystem
 mn10300/
 	- directory with info about the mn10300 architecture port
+module-signing.txt
+	- Kernel module signing for increased security when loading modules.
 mtd/
 	- directory with info about memory technology devices (flash)
 mono.txt
@@ -343,6 +353,8 @@
 	- info on the Linux PCMCIA driver.
 percpu-rw-semaphore.txt
 	- RCU based read-write semaphore optimized for locking for reading
+phy.txt
+	- Description of the generic PHY framework.
 pi-futex.txt
 	- documentation on lightweight priority inheritance futexes.
 pinctrl.txt
@@ -431,6 +443,8 @@
 	- info on the magic SysRq key.
 target/
 	- directory with info on generating TCM v4 fabric .ko modules
+this_cpu_ops.txt
+	- List rationale behind and the way to use this_cpu operations.
 thermal/
 	- directory with information on managing thermal issues (CPU/temp)
 trace/
@@ -469,6 +483,8 @@
 	- directory with info about Intel Wireless Wimax Connections
 workqueue.txt
 	- information on the Concurrency Managed Workqueue implementation
+ww-mutex-design.txt
+	- Intro to Mutex wait/would deadlock handling.s
 x86/x86_64/
 	- directory with info on Linux support for AMD x86-64 (Hammer) machines.
 xtensa/
diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt
index a8d0100..10a9369 100644
--- a/Documentation/PCI/MSI-HOWTO.txt
+++ b/Documentation/PCI/MSI-HOWTO.txt
@@ -82,7 +82,19 @@
 has to request that the PCI layer set up the MSI capability for this
 device.
 
-4.2.1 pci_enable_msi_range
+4.2.1 pci_enable_msi
+
+int pci_enable_msi(struct pci_dev *dev)
+
+A successful call allocates ONE interrupt to the device, regardless
+of how many MSIs the device supports.  The device is switched from
+pin-based interrupt mode to MSI mode.  The dev->irq number is changed
+to a new number which represents the message signaled interrupt;
+consequently, this function should be called before the driver calls
+request_irq(), because an MSI is delivered via a vector that is
+different from the vector of a pin-based interrupt.
+
+4.2.2 pci_enable_msi_range
 
 int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
 
@@ -147,6 +159,11 @@
 	return pci_enable_msi_range(pdev, nvec, nvec);
 }
 
+Note, unlike pci_enable_msi_exact() function, which could be also used to
+enable a particular number of MSI-X interrupts, pci_enable_msi_range()
+returns either a negative errno or 'nvec' (not negative errno or 0 - as
+pci_enable_msi_exact() does).
+
 4.2.1.3 Single MSI mode
 
 The most notorious example of the request type described above is
@@ -158,7 +175,27 @@
 	return pci_enable_msi_range(pdev, 1, 1);
 }
 
-4.2.2 pci_disable_msi
+Note, unlike pci_enable_msi() function, which could be also used to
+enable the single MSI mode, pci_enable_msi_range() returns either a
+negative errno or 1 (not negative errno or 0 - as pci_enable_msi()
+does).
+
+4.2.3 pci_enable_msi_exact
+
+int pci_enable_msi_exact(struct pci_dev *dev, int nvec)
+
+This variation on pci_enable_msi_range() call allows a device driver to
+request exactly 'nvec' MSIs.
+
+If this function returns a negative number, it indicates an error and
+the driver should not attempt to request any more MSI interrupts for
+this device.
+
+By contrast with pci_enable_msi_range() function, pci_enable_msi_exact()
+returns zero in case of success, which indicates MSI interrupts have been
+successfully allocated.
+
+4.2.4 pci_disable_msi
 
 void pci_disable_msi(struct pci_dev *dev)
 
@@ -172,7 +209,7 @@
 Failure to do so results in a BUG_ON(), leaving the device with
 MSI enabled and thus leaking its vector.
 
-4.2.3 pci_msi_vec_count
+4.2.4 pci_msi_vec_count
 
 int pci_msi_vec_count(struct pci_dev *dev)
 
@@ -257,8 +294,8 @@
 
 static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
 {
-	return pci_enable_msi_range(adapter->pdev, adapter->msix_entries,
-				    1, nvec);
+	return pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+				     1, nvec);
 }
 
 Note the value of 'minvec' parameter is 1.  As 'minvec' is inclusive,
@@ -269,8 +306,8 @@
 
 static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
 {
-	return pci_enable_msi_range(adapter->pdev, adapter->msix_entries,
-				    FOO_DRIVER_MINIMUM_NVEC, nvec);
+	return pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+				     FOO_DRIVER_MINIMUM_NVEC, nvec);
 }
 
 4.3.1.2 Exact number of MSI-X interrupts
@@ -282,10 +319,15 @@
 
 static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
 {
-	return pci_enable_msi_range(adapter->pdev, adapter->msix_entries,
-				    nvec, nvec);
+	return pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+				     nvec, nvec);
 }
 
+Note, unlike pci_enable_msix_exact() function, which could be also used to
+enable a particular number of MSI-X interrupts, pci_enable_msix_range()
+returns either a negative errno or 'nvec' (not negative errno or 0 - as
+pci_enable_msix_exact() does).
+
 4.3.1.3 Specific requirements to the number of MSI-X interrupts
 
 As noted above, there could be devices that can not operate with just any
@@ -332,7 +374,64 @@
 any error code other than -ENOSPC indicates a fatal error and should not
 be retried.
 
-4.3.2 pci_disable_msix
+4.3.2 pci_enable_msix_exact
+
+int pci_enable_msix_exact(struct pci_dev *dev,
+			  struct msix_entry *entries, int nvec)
+
+This variation on pci_enable_msix_range() call allows a device driver to
+request exactly 'nvec' MSI-Xs.
+
+If this function returns a negative number, it indicates an error and
+the driver should not attempt to allocate any more MSI-X interrupts for
+this device.
+
+By contrast with pci_enable_msix_range() function, pci_enable_msix_exact()
+returns zero in case of success, which indicates MSI-X interrupts have been
+successfully allocated.
+
+Another version of a routine that enables MSI-X mode for a device with
+specific requirements described in chapter 4.3.1.3 might look like this:
+
+/*
+ * Assume 'minvec' and 'maxvec' are non-zero
+ */
+static int foo_driver_enable_msix(struct foo_adapter *adapter,
+				  int minvec, int maxvec)
+{
+	int rc;
+
+	minvec = roundup_pow_of_two(minvec);
+	maxvec = rounddown_pow_of_two(maxvec);
+
+	if (minvec > maxvec)
+		return -ERANGE;
+
+retry:
+	rc = pci_enable_msix_exact(adapter->pdev,
+				   adapter->msix_entries, maxvec);
+
+	/*
+	 * -ENOSPC is the only error code allowed to be analyzed
+	 */
+	if (rc == -ENOSPC) {
+		if (maxvec == 1)
+			return -ENOSPC;
+
+		maxvec /= 2;
+
+		if (minvec > maxvec)
+			return -ENOSPC;
+
+		goto retry;
+	} else if (rc < 0) {
+		return rc;
+	}
+
+	return maxvec;
+}
+
+4.3.3 pci_disable_msix
 
 void pci_disable_msix(struct pci_dev *dev)
 
diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX
index 1d7a885..fa57139 100644
--- a/Documentation/RCU/00-INDEX
+++ b/Documentation/RCU/00-INDEX
@@ -8,6 +8,8 @@
 	- Using RCU to Protect Read-Mostly Linked Lists
 lockdep.txt
 	- RCU and lockdep checking
+lockdep-splat.txt
+	- RCU Lockdep splats explained.
 NMI-RCU.txt
 	- Using RCU to Protect Dynamic NMI Handlers
 rcubarrier.txt
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index 273e654d..2f0fcb2 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/Documentation/RCU/RTFP.txt
@@ -31,6 +31,14 @@
 (In contrast, implementation of RCU is permitted only in software licensed
 under either GPL or LGPL.  Sorry!!!)
 
+In 1987, Rashid et al. described lazy TLB-flush [RichardRashid87a].
+At first glance, this has nothing to do with RCU, but nevertheless
+this paper helped inspire the update-side batching used in the later
+RCU implementation in DYNIX/ptx.  In 1988, Barbara Liskov published
+a description of Argus that noted that use of out-of-date values can
+be tolerated in some situations.  Thus, this paper provides some early
+theoretical justification for use of stale data.
+
 In 1990, Pugh [Pugh90] noted that explicitly tracking which threads
 were reading a given data structure permitted deferred free to operate
 in the presence of non-terminating threads.  However, this explicit
@@ -41,11 +49,11 @@
 to see how much of the performance advantage reported in 1990 remains
 today.
 
-At about this same time, Adams [Adams91] described ``chaotic relaxation'',
-where the normal barriers between successive iterations of convergent
-numerical algorithms are relaxed, so that iteration $n$ might use
-data from iteration $n-1$ or even $n-2$.  This introduces error,
-which typically slows convergence and thus increases the number of
+At about this same time, Andrews [Andrews91textbook] described ``chaotic
+relaxation'', where the normal barriers between successive iterations
+of convergent numerical algorithms are relaxed, so that iteration $n$
+might use data from iteration $n-1$ or even $n-2$.  This introduces
+error, which typically slows convergence and thus increases the number of
 iterations required.  However, this increase is sometimes more than made
 up for by a reduction in the number of expensive barrier operations,
 which are otherwise required to synchronize the threads at the end
@@ -55,7 +63,8 @@
 
 In 1992, Henry (now Alexia) Massalin completed a dissertation advising
 parallel programmers to defer processing when feasible to simplify
-synchronization.  RCU makes extremely heavy use of this advice.
+synchronization [HMassalinPhD].  RCU makes extremely heavy use of
+this advice.
 
 In 1993, Jacobson [Jacobson93] verbally described what is perhaps the
 simplest deferred-free technique: simply waiting a fixed amount of time
@@ -90,27 +99,29 @@
 systems made pervasive use of RCU in place of "existence locks", which
 greatly simplifies locking hierarchies and helps avoid deadlocks.
 
-2001 saw the first RCU presentation involving Linux [McKenney01a]
-at OLS.  The resulting abundance of RCU patches was presented the
-following year [McKenney02a], and use of RCU in dcache was first
-described that same year [Linder02a].
+The year 2000 saw an email exchange that would likely have
+led to yet another independent invention of something like RCU
+[RustyRussell2000a,RustyRussell2000b].  Instead, 2001 saw the first
+RCU presentation involving Linux [McKenney01a] at OLS.  The resulting
+abundance of RCU patches was presented the following year [McKenney02a],
+and use of RCU in dcache was first described that same year [Linder02a].
 
 Also in 2002, Michael [Michael02b,Michael02a] presented "hazard-pointer"
 techniques that defer the destruction of data structures to simplify
 non-blocking synchronization (wait-free synchronization, lock-free
 synchronization, and obstruction-free synchronization are all examples of
-non-blocking synchronization).  In particular, this technique eliminates
-locking, reduces contention, reduces memory latency for readers, and
-parallelizes pipeline stalls and memory latency for writers.  However,
-these techniques still impose significant read-side overhead in the
-form of memory barriers.  Researchers at Sun worked along similar lines
-in the same timeframe [HerlihyLM02].  These techniques can be thought
-of as inside-out reference counts, where the count is represented by the
-number of hazard pointers referencing a given data structure rather than
-the more conventional counter field within the data structure itself.
-The key advantage of inside-out reference counts is that they can be
-stored in immortal variables, thus allowing races between access and
-deletion to be avoided.
+non-blocking synchronization).  The corresponding journal article appeared
+in 2004 [MagedMichael04a].  This technique eliminates locking, reduces
+contention, reduces memory latency for readers, and parallelizes pipeline
+stalls and memory latency for writers.  However, these techniques still
+impose significant read-side overhead in the form of memory barriers.
+Researchers at Sun worked along similar lines in the same timeframe
+[HerlihyLM02].  These techniques can be thought of as inside-out reference
+counts, where the count is represented by the number of hazard pointers
+referencing a given data structure rather than the more conventional
+counter field within the data structure itself.  The key advantage
+of inside-out reference counts is that they can be stored in immortal
+variables, thus allowing races between access and deletion to be avoided.
 
 By the same token, RCU can be thought of as a "bulk reference count",
 where some form of reference counter covers all reference by a given CPU
@@ -123,8 +134,10 @@
 
 In 2003, the K42 group described how RCU could be used to create
 hot-pluggable implementations of operating-system functions [Appavoo03a].
-Later that year saw a paper describing an RCU implementation of System
-V IPC [Arcangeli03], and an introduction to RCU in Linux Journal
+Later that year saw a paper describing an RCU implementation
+of System V IPC [Arcangeli03] (following up on a suggestion by
+Hugh Dickins [Dickins02a] and an implementation by Mingming Cao
+[MingmingCao2002IPCRCU]), and an introduction to RCU in Linux Journal
 [McKenney03a].
 
 2004 has seen a Linux-Journal article on use of RCU in dcache
@@ -383,6 +396,21 @@
 }
 }
 
+@phdthesis{HMassalinPhD
+,author="H. Massalin"
+,title="Synthesis: An Efficient Implementation of Fundamental Operating
+System Services"
+,school="Columbia University"
+,address="New York, NY"
+,year="1992"
+,annotation={
+	Mondo optimizing compiler.
+	Wait-free stuff.
+	Good advice: defer work to avoid synchronization.  See page 90
+		(PDF page 106), Section 5.4, fourth bullet point.
+}
+}
+
 @unpublished{Jacobson93
 ,author="Van Jacobson"
 ,title="Avoid Read-Side Locking Via Delayed Free"
@@ -671,6 +699,20 @@
 [Viewed October 18, 2004]"
 }
 
+@conference{Michael02b
+,author="Maged M. Michael"
+,title="High Performance Dynamic Lock-Free Hash Tables and List-Based Sets"
+,Year="2002"
+,Month="August"
+,booktitle="{Proceedings of the 14\textsuperscript{th} Annual ACM
+Symposium on Parallel
+Algorithms and Architecture}"
+,pages="73-82"
+,annotation={
+Like the title says...
+}
+}
+
 @Conference{Linder02a
 ,Author="Hanna Linder and Dipankar Sarma and Maneesh Soni"
 ,Title="Scalability of the Directory Entry Cache"
@@ -727,6 +769,24 @@
 }
 }
 
+@conference{Michael02a
+,author="Maged M. Michael"
+,title="Safe Memory Reclamation for Dynamic Lock-Free Objects Using Atomic
+Reads and Writes"
+,Year="2002"
+,Month="August"
+,booktitle="{Proceedings of the 21\textsuperscript{st} Annual ACM
+Symposium on Principles of Distributed Computing}"
+,pages="21-30"
+,annotation={
+	Each thread keeps an array of pointers to items that it is
+	currently referencing.	Sort of an inside-out garbage collection
+	mechanism, but one that requires the accessing code to explicitly
+	state its needs.  Also requires read-side memory barriers on
+	most architectures.
+}
+}
+
 @unpublished{Dickins02a
 ,author="Hugh Dickins"
 ,title="Use RCU for System-V IPC"
@@ -735,6 +795,17 @@
 ,note="private communication"
 }
 
+@InProceedings{HerlihyLM02
+,author={Maurice Herlihy and Victor Luchangco and Mark Moir}
+,title="The Repeat Offender Problem: A Mechanism for Supporting Dynamic-Sized,
+Lock-Free Data Structures"
+,booktitle={Proceedings of 16\textsuperscript{th} International
+Symposium on Distributed Computing}
+,year=2002
+,month="October"
+,pages="339-353"
+}
+
 @unpublished{Sarma02b
 ,Author="Dipankar Sarma"
 ,Title="Some dcache\_rcu benchmark numbers"
@@ -749,6 +820,19 @@
 }
 }
 
+@unpublished{MingmingCao2002IPCRCU
+,Author="Mingming Cao"
+,Title="[PATCH]updated ipc lock patch"
+,month="October"
+,year="2002"
+,note="Available:
+\url{https://lkml.org/lkml/2002/10/24/262}
+[Viewed February 15, 2014]"
+,annotation={
+	Mingming Cao's patch to introduce RCU to SysV IPC.
+}
+}
+
 @unpublished{LinusTorvalds2003a
 ,Author="Linus Torvalds"
 ,Title="Re: {[PATCH]} small fixes in brlock.h"
@@ -982,6 +1066,23 @@
 }
 }
 
+@article{MagedMichael04a
+,author="Maged M. Michael"
+,title="Hazard Pointers: Safe Memory Reclamation for Lock-Free Objects"
+,Year="2004"
+,Month="June"
+,journal="IEEE Transactions on Parallel and Distributed Systems"
+,volume="15"
+,number="6"
+,pages="491-504"
+,url="Available:
+\url{http://www.research.ibm.com/people/m/michael/ieeetpds-2004.pdf}
+[Viewed March 1, 2005]"
+,annotation={
+	New canonical hazard-pointer citation.
+}
+}
+
 @phdthesis{PaulEdwardMcKenneyPhD
 ,author="Paul E. McKenney"
 ,title="Exploiting Deferred Destruction:
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 9126619..9d10d1d 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -256,10 +256,10 @@
 		variations on this theme.
 
 	b.	Limiting update rate.  For example, if updates occur only
-		once per hour, then no explicit rate limiting is required,
-		unless your system is already badly broken.  The dcache
-		subsystem takes this approach -- updates are guarded
-		by a global lock, limiting their rate.
+		once per hour, then no explicit rate limiting is
+		required, unless your system is already badly broken.
+		Older versions of the dcache subsystem take this approach,
+		guarding updates with a global lock, limiting their rate.
 
 	c.	Trusted update -- if updates can only be done manually by
 		superuser or some other trusted user, then it might not
@@ -268,7 +268,8 @@
 		the machine.
 
 	d.	Use call_rcu_bh() rather than call_rcu(), in order to take
-		advantage of call_rcu_bh()'s faster grace periods.
+		advantage of call_rcu_bh()'s faster grace periods.  (This
+		is only a partial solution, though.)
 
 	e.	Periodically invoke synchronize_rcu(), permitting a limited
 		number of updates per grace period.
@@ -276,6 +277,13 @@
 	The same cautions apply to call_rcu_bh(), call_rcu_sched(),
 	call_srcu(), and kfree_rcu().
 
+	Note that although these primitives do take action to avoid memory
+	exhaustion when any given CPU has too many callbacks, a determined
+	user could still exhaust memory.  This is especially the case
+	if a system with a large number of CPUs has been configured to
+	offload all of its RCU callbacks onto a single CPU, or if the
+	system has relatively little free memory.
+
 9.	All RCU list-traversal primitives, which include
 	rcu_dereference(), list_for_each_entry_rcu(), and
 	list_for_each_safe_rcu(), must be either within an RCU read-side
diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX
index 36420e1..a94090c 100644
--- a/Documentation/arm/00-INDEX
+++ b/Documentation/arm/00-INDEX
@@ -4,6 +4,8 @@
 	- requirements for booting
 Interrupts
 	- ARM Interrupt subsystem documentation
+IXP4xx
+	- Intel IXP4xx Network processor.
 msm
 	- MSM specific documentation
 Netwinder
@@ -24,8 +26,16 @@
 	- ST SPEAr platform Linux Overview
 VFP/
 	- Release notes for Linux Kernel Vector Floating Point support code
+cluster-pm-race-avoidance.txt
+	- Algorithm for CPU and Cluster setup/teardown
 empeg/
 	- Ltd's Empeg MP3 Car Audio Player
+firmware.txt
+	- Secure firmware registration and calling.
+kernel_mode_neon.txt
+	- How to use NEON instructions in kernel mode
+kernel_user_helpers.txt
+	- Helper functions in kernel space made available for userspace.
 mem_alignment
 	- alignment abort handler documentation
 memory.txt
@@ -34,3 +44,7 @@
 	- NWFPE floating point emulator documentation
 swp_emulation
 	- SWP/SWPB emulation handler/logging description
+tcm.txt
+	- ARM Tightly Coupled Memory
+vlocks.txt
+	- Voting locks, low-level mechanism relying on memory system atomic writes.
diff --git a/Documentation/arm64/memory.txt b/Documentation/arm64/memory.txt
index 5e054bf..85e24c4 100644
--- a/Documentation/arm64/memory.txt
+++ b/Documentation/arm64/memory.txt
@@ -35,11 +35,13 @@
 
 ffffffbe00000000	ffffffbffbbfffff	  ~8GB		[guard, future vmmemap]
 
+ffffffbffa000000	ffffffbffaffffff	  16MB		PCI I/O space
+
+ffffffbffb000000	ffffffbffbbfffff	  12MB		[guard]
+
 ffffffbffbc00000	ffffffbffbdfffff	   2MB		earlyprintk device
 
-ffffffbffbe00000	ffffffbffbe0ffff	  64KB		PCI I/O space
-
-ffffffbffbe10000	ffffffbcffffffff	  ~2MB		[guard]
+ffffffbffbe00000	ffffffbffbffffff	   2MB		[guard]
 
 ffffffbffc000000	ffffffbfffffffff	  64MB		modules
 
@@ -60,11 +62,13 @@
 
 fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[guard, future vmmemap]
 
+fffffdfffa000000	fffffdfffaffffff	  16MB		PCI I/O space
+
+fffffdfffb000000	fffffdfffbbfffff	  12MB		[guard]
+
 fffffdfffbc00000	fffffdfffbdfffff	   2MB		earlyprintk device
 
-fffffdfffbe00000	fffffdfffbe0ffff	  64KB		PCI I/O space
-
-fffffdfffbe10000	fffffdfffbffffff	  ~2MB		[guard]
+fffffdfffbe00000	fffffdfffbffffff	   2MB		[guard]
 
 fffffdfffc000000	fffffdffffffffff	  64MB		modules
 
diff --git a/Documentation/blackfin/00-INDEX b/Documentation/blackfin/00-INDEX
index 2df0365..c54fcdd 100644
--- a/Documentation/blackfin/00-INDEX
+++ b/Documentation/blackfin/00-INDEX
@@ -1,8 +1,10 @@
 00-INDEX
 	- This file
-
+Makefile
+	- Makefile for gptimers example file.
 bfin-gpio-notes.txt
 	- Notes in developing/using bfin-gpio driver.
-
 bfin-spi-notes.txt
 	- Notes for using bfin spi bus driver.
+gptimers-example.c
+	- gptimers example
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index 929d990..e840b47 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -14,6 +14,8 @@
 	- Deadline IO scheduler tunables
 ioprio.txt
 	- Block io priorities (in CFQ scheduler)
+null_blk.txt
+	- Null block for block-layer benchmarking.
 queue-sysfs.txt
 	- Queue's sysfs entries
 request.txt
diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt
index e6b72d3..68c0f51 100644
--- a/Documentation/device-mapper/cache.txt
+++ b/Documentation/device-mapper/cache.txt
@@ -124,12 +124,11 @@
 Updating on-disk metadata
 -------------------------
 
-On-disk metadata is committed every time a REQ_SYNC or REQ_FUA bio is
-written.  If no such requests are made then commits will occur every
-second.  This means the cache behaves like a physical disk that has a
-write cache (the same is true of the thin-provisioning target).  If
-power is lost you may lose some recent writes.  The metadata should
-always be consistent in spite of any crash.
+On-disk metadata is committed every time a FLUSH or FUA bio is written.
+If no such requests are made then commits will occur every second.  This
+means the cache behaves like a physical disk that has a volatile write
+cache.  If power is lost you may lose some recent writes.  The metadata
+should always be consistent in spite of any crash.
 
 The 'dirty' state for a cache block changes far too frequently for us
 to keep updating it on the fly.  So we treat it as a hint.  In normal
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 8a7a3d4..05a27e9 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -116,6 +116,35 @@
 userspace daemon can use this to detect a situation where a new table
 already exceeds the threshold.
 
+A low water mark for the metadata device is maintained in the kernel and
+will trigger a dm event if free space on the metadata device drops below
+it.
+
+Updating on-disk metadata
+-------------------------
+
+On-disk metadata is committed every time a FLUSH or FUA bio is written.
+If no such requests are made then commits will occur every second.  This
+means the thin-provisioning target behaves like a physical disk that has
+a volatile write cache.  If power is lost you may lose some recent
+writes.  The metadata should always be consistent in spite of any crash.
+
+If data space is exhausted the pool will either error or queue IO
+according to the configuration (see: error_if_no_space).  If metadata
+space is exhausted or a metadata operation fails: the pool will error IO
+until the pool is taken offline and repair is performed to 1) fix any
+potential inconsistencies and 2) clear the flag that imposes repair.
+Once the pool's metadata device is repaired it may be resized, which
+will allow the pool to return to normal operation.  Note that if a pool
+is flagged as needing repair, the pool's data and metadata devices
+cannot be resized until repair is performed.  It should also be noted
+that when the pool's metadata space is exhausted the current metadata
+transaction is aborted.  Given that the pool will cache IO whose
+completion may have already been acknowledged to upper IO layers
+(e.g. filesystem) it is strongly suggested that consistency checks
+(e.g. fsck) be performed on those layers when repair of the pool is
+required.
+
 Thin provisioning
 -----------------
 
@@ -258,10 +287,9 @@
 	should register for the event and then check the target's status.
 
     held metadata root:
-	The location, in sectors, of the metadata root that has been
+	The location, in blocks, of the metadata root that has been
 	'held' for userspace read access.  '-' indicates there is no
-	held root.  This feature is not yet implemented so '-' is
-	always returned.
+	held root.
 
     discard_passdown|no_discard_passdown
 	Whether or not discards are actually being passed down to the
diff --git a/Documentation/devicetree/00-INDEX b/Documentation/devicetree/00-INDEX
index b78f691..8c4102c 100644
--- a/Documentation/devicetree/00-INDEX
+++ b/Documentation/devicetree/00-INDEX
@@ -8,3 +8,5 @@
 	- this file
 booting-without-of.txt
 	- Booting Linux without Open Firmware, describes history and format of device trees.
+usage-model.txt
+	- How Linux uses DT and what DT aims to solve.
\ No newline at end of file
diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt
index 34dc40c..af9b4a0 100644
--- a/Documentation/devicetree/bindings/arm/omap/omap.txt
+++ b/Documentation/devicetree/bindings/arm/omap/omap.txt
@@ -91,7 +91,7 @@
   compatible = "ti,omap3-beagle", "ti,omap3"
 
 - OMAP3 Tobi with Overo : Commercial expansion board with daughter board
-  compatible = "ti,omap3-tobi", "ti,omap3-overo", "ti,omap3"
+  compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap3"
 
 - OMAP4 SDP : Software Development Board
   compatible = "ti,omap4-sdp", "ti,omap4430"
diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt
index 89de156..48b285f 100644
--- a/Documentation/devicetree/bindings/ata/ahci-platform.txt
+++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt
@@ -4,17 +4,33 @@
 Each SATA controller should have its own node.
 
 Required properties:
-- compatible        : compatible list, contains "snps,spear-ahci"
+- compatible        : compatible list, one of "snps,spear-ahci",
+                      "snps,exynos5440-ahci", "ibm,476gtr-ahci",
+                      "allwinner,sun4i-a10-ahci", "fsl,imx53-ahci"
+                      "fsl,imx6q-ahci" or "snps,dwc-ahci"
 - interrupts        : <interrupt mapping for SATA IRQ>
 - reg               : <registers mapping>
 
 Optional properties:
 - dma-coherent      : Present if dma operations are coherent
+- clocks            : a list of phandle + clock specifier pairs
+- target-supply     : regulator for SATA target power
 
-Example:
+"fsl,imx53-ahci", "fsl,imx6q-ahci" required properties:
+- clocks            : must contain the sata, sata_ref and ahb clocks
+- clock-names       : must contain "ahb" for the ahb clock
+
+Examples:
         sata@ffe08000 {
 		compatible = "snps,spear-ahci";
 		reg = <0xffe08000 0x1000>;
 		interrupts = <115>;
-
         };
+
+	ahci: sata@01c18000 {
+		compatible = "allwinner,sun4i-a10-ahci";
+		reg = <0x01c18000 0x1000>;
+		interrupts = <56>;
+		clocks = <&pll6 0>, <&ahb_gates 25>;
+		target-supply = <&reg_ahci_5v>;
+	};
diff --git a/Documentation/devicetree/bindings/ata/apm-xgene.txt b/Documentation/devicetree/bindings/ata/apm-xgene.txt
new file mode 100644
index 0000000..7bcfbf5
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/apm-xgene.txt
@@ -0,0 +1,76 @@
+* APM X-Gene 6.0 Gb/s SATA host controller nodes
+
+SATA host controller nodes are defined to describe on-chip Serial ATA
+controllers. Each SATA controller (pair of ports) have its own node.
+
+Required properties:
+- compatible		: Shall contain:
+  * "apm,xgene-ahci"
+- reg			: First memory resource shall be the AHCI memory
+			  resource.
+			  Second memory resource shall be the host controller
+			  core memory resource.
+			  Third memory resource shall be the host controller
+			  diagnostic memory resource.
+			  4th memory resource shall be the host controller
+			  AXI memory resource.
+			  5th optional memory resource shall be the host
+			  controller MUX memory resource if required.
+- interrupts		: Interrupt-specifier for SATA host controller IRQ.
+- clocks		: Reference to the clock entry.
+- phys			: A list of phandles + phy-specifiers, one for each
+			  entry in phy-names.
+- phy-names		: Should contain:
+  * "sata-phy" for the SATA 6.0Gbps PHY
+
+Optional properties:
+- status		: Shall be "ok" if enabled or "disabled" if disabled.
+			  Default is "ok".
+
+Example:
+		sataclk: sataclk {
+			compatible = "fixed-clock";
+			#clock-cells = <1>;
+			clock-frequency = <100000000>;
+			clock-output-names = "sataclk";
+		};
+
+		phy2: phy@1f22a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f22a000 0x0 0x100>;
+			#phy-cells = <1>;
+		};
+
+		phy3: phy@1f23a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f23a000 0x0 0x100>;
+			#phy-cells = <1>;
+		};
+
+		sata2: sata@1a400000 {
+			compatible = "apm,xgene-ahci";
+			reg = <0x0 0x1a400000 0x0 0x1000>,
+			      <0x0 0x1f220000 0x0 0x1000>,
+			      <0x0 0x1f22d000 0x0 0x1000>,
+			      <0x0 0x1f22e000 0x0 0x1000>,
+			      <0x0 0x1f227000 0x0 0x1000>;
+			interrupts = <0x0 0x87 0x4>;
+			status = "ok";
+			clocks = <&sataclk 0>;
+			phys = <&phy2 0>;
+			phy-names = "sata-phy";
+		};
+
+		sata3: sata@1a800000 {
+			compatible = "apm,xgene-ahci-pcie";
+			reg = <0x0 0x1a800000 0x0 0x1000>,
+			      <0x0 0x1f230000 0x0 0x1000>,
+			      <0x0 0x1f23d000 0x0 0x1000>,
+			      <0x0 0x1f23e000 0x0 0x1000>,
+			      <0x0 0x1f237000 0x0 0x1000>;
+			interrupts = <0x0 0x88 0x4>;
+			status = "ok";
+			clocks = <&sataclk 0>;
+			phys = <&phy3 0>;
+			phy-names = "sata-phy";
+		};
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
index a6a352c..5992dce 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
@@ -21,9 +21,9 @@
     must appear in the same order as the output clocks.
   - #clock-cells: Must be 1
   - clock-output-names: The name of the clocks as free-form strings
-  - renesas,indices: Indices of the gate clocks into the group (0 to 31)
+  - renesas,clock-indices: Indices of the gate clocks into the group (0 to 31)
 
-The clocks, clock-output-names and renesas,indices properties contain one
+The clocks, clock-output-names and renesas,clock-indices properties contain one
 entry per gate clock. The MSTP groups are sparsely populated. Unimplemented
 gate clocks must not be declared.
 
diff --git a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
index 68b83ec..ee9be99 100644
--- a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
+++ b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
@@ -1,12 +1,16 @@
 * Freescale Smart Direct Memory Access (SDMA) Controller for i.MX
 
 Required properties:
-- compatible : Should be "fsl,imx31-sdma", "fsl,imx31-to1-sdma",
-  "fsl,imx31-to2-sdma", "fsl,imx35-sdma", "fsl,imx35-to1-sdma",
-  "fsl,imx35-to2-sdma", "fsl,imx51-sdma", "fsl,imx53-sdma" or
-  "fsl,imx6q-sdma". The -to variants should be preferred since they
-  allow to determnine the correct ROM script addresses needed for
-  the driver to work without additional firmware.
+- compatible : Should be one of
+      "fsl,imx25-sdma"
+      "fsl,imx31-sdma", "fsl,imx31-to1-sdma", "fsl,imx31-to2-sdma"
+      "fsl,imx35-sdma", "fsl,imx35-to1-sdma", "fsl,imx35-to2-sdma"
+      "fsl,imx51-sdma"
+      "fsl,imx53-sdma"
+      "fsl,imx6q-sdma"
+  The -to variants should be preferred since they allow to determnine the
+  correct ROM script addresses needed for the driver to work without additional
+  firmware.
 - reg : Should contain SDMA registers location and length
 - interrupts : Should contain SDMA interrupt
 - #dma-cells : Must be <3>.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/lsi,zevio-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/lsi,zevio-intc.txt
new file mode 100644
index 0000000..aee38e7
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/lsi,zevio-intc.txt
@@ -0,0 +1,18 @@
+TI-NSPIRE interrupt controller
+
+Required properties:
+- compatible: Compatible property value should be "lsi,zevio-intc".
+
+- reg: Physical base address of the controller and length of memory mapped
+	region.
+
+- interrupt-controller : Identifies the node as an interrupt controller
+
+Example:
+
+interrupt-controller {
+	compatible = "lsi,zevio-intc";
+	interrupt-controller;
+	reg = <0xDC000000 0x1000>;
+	#interrupt-cells = <1>;
+};
diff --git a/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt b/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt
index 0a85c70..07ad020 100644
--- a/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt
+++ b/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt
@@ -13,6 +13,9 @@
 - #address-cells: should be one. The cell is the slot id.
 - #size-cells: should be zero.
 - at least one slot node
+- clock-names: tuple listing input clock names.
+	Required elements: "mci_clk"
+- clocks: phandles to input clocks.
 
 The node contains child nodes for each slot that the platform uses
 
@@ -24,6 +27,8 @@
 	interrupts = <12 4>;
 	#address-cells = <1>;
 	#size-cells = <0>;
+	clock-names = "mci_clk";
+	clocks = <&mci0_clk>;
 
 	[ child node definitions...]
 };
diff --git a/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt b/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt
index b90bfcd..863d5b81 100644
--- a/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt
+++ b/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt
@@ -1,7 +1,8 @@
 * Allwinner EMAC ethernet controller
 
 Required properties:
-- compatible: should be "allwinner,sun4i-emac".
+- compatible: should be "allwinner,sun4i-a10-emac" (Deprecated:
+              "allwinner,sun4i-emac")
 - reg: address and length of the register set for the device.
 - interrupts: interrupt for the device
 - phy: A phandle to a phy node defining the PHY address (as the reg
@@ -14,7 +15,7 @@
 Example:
 
 emac: ethernet@01c0b000 {
-       compatible = "allwinner,sun4i-emac";
+       compatible = "allwinner,sun4i-a10-emac";
        reg = <0x01c0b000 0x1000>;
        interrupts = <55>;
        clocks = <&ahb_gates 17>;
diff --git a/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt b/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt
index 00b9f9a..4ec5641 100644
--- a/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt
+++ b/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt
@@ -1,7 +1,8 @@
 * Allwinner A10 MDIO Ethernet Controller interface
 
 Required properties:
-- compatible: should be "allwinner,sun4i-mdio".
+- compatible: should be "allwinner,sun4i-a10-mdio"
+              (Deprecated: "allwinner,sun4i-mdio").
 - reg: address and length of the register set for the device.
 
 Optional properties:
@@ -9,7 +10,7 @@
 
 Example at the SoC level:
 mdio@01c0b080 {
-	compatible = "allwinner,sun4i-mdio";
+	compatible = "allwinner,sun4i-a10-mdio";
 	reg = <0x01c0b080 0x14>;
 	#address-cells = <1>;
 	#size-cells = <0>;
diff --git a/Documentation/devicetree/bindings/net/micrel-ks8851.txt b/Documentation/devicetree/bindings/net/micrel-ks8851.txt
index 11ace3c..4fc3927 100644
--- a/Documentation/devicetree/bindings/net/micrel-ks8851.txt
+++ b/Documentation/devicetree/bindings/net/micrel-ks8851.txt
@@ -7,3 +7,4 @@
 
 Optional properties:
 - local-mac-address : Ethernet mac address to use
+- vdd-supply:	supply for Ethernet mac
diff --git a/Documentation/devicetree/bindings/net/opencores-ethoc.txt b/Documentation/devicetree/bindings/net/opencores-ethoc.txt
new file mode 100644
index 0000000..2dc127c
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/opencores-ethoc.txt
@@ -0,0 +1,22 @@
+* OpenCores MAC 10/100 Mbps
+
+Required properties:
+- compatible: Should be "opencores,ethoc".
+- reg: two memory regions (address and length),
+  first region is for the device registers and descriptor rings,
+  second is for the device packet memory.
+- interrupts: interrupt for the device.
+
+Optional properties:
+- clocks: phandle to refer to the clk used as per
+  Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Examples:
+
+	enet0: ethoc@fd030000 {
+		compatible = "opencores,ethoc";
+		reg = <0xfd030000 0x4000 0xfd800000 0x4000>;
+		interrupts = <1>;
+		local-mac-address = [00 50 c2 13 6f 00];
+		clocks = <&osc>;
+        };
diff --git a/Documentation/devicetree/bindings/net/sti-dwmac.txt b/Documentation/devicetree/bindings/net/sti-dwmac.txt
new file mode 100644
index 0000000..3dd3d0b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/sti-dwmac.txt
@@ -0,0 +1,58 @@
+STMicroelectronics SoC DWMAC glue layer controller
+
+The device node has following properties.
+
+Required properties:
+ - compatible	: Can be "st,stih415-dwmac", "st,stih416-dwmac" or
+   "st,stid127-dwmac".
+ - reg		: Offset of the glue configuration register map in system
+   configuration regmap pointed by st,syscon property and size.
+
+ - reg-names	: Should be "sti-ethconf".
+
+ - st,syscon	: Should be phandle to system configuration node which
+   encompases this glue registers.
+
+ - st,tx-retime-src: On STi Parts for Giga bit speeds, 125Mhz clocks can be
+   wired up in from different sources. One via TXCLK pin and other via CLK_125
+   pin. This wiring is totally board dependent. However the retiming glue
+   logic should be configured accordingly. Possible values for this property
+
+	   "txclk" - if 125Mhz clock is wired up via txclk line.
+	   "clk_125" - if 125Mhz clock is wired up via clk_125 line.
+
+   This property is only valid for Giga bit setup( GMII, RGMII), and it is
+   un-used for non-giga bit (MII and RMII) setups. Also note that internal
+   clockgen can not generate stable 125Mhz clock.
+
+ - st,ext-phyclk: This boolean property indicates who is generating the clock
+  for tx and rx. This property is only valid for RMII case where the clock can
+  be generated from the MAC or PHY.
+
+ - clock-names: should be "sti-ethclk".
+ - clocks: Should point to ethernet clockgen which can generate phyclk.
+
+
+Example:
+
+ethernet0: dwmac@fe810000 {
+	device_type 	= "network";
+	compatible	= "st,stih416-dwmac", "snps,dwmac", "snps,dwmac-3.710";
+	reg 		= <0xfe810000 0x8000>, <0x8bc 0x4>;
+	reg-names	= "stmmaceth", "sti-ethconf";
+	interrupts	= <0 133 0>, <0 134 0>, <0 135 0>;
+	interrupt-names	= "macirq", "eth_wake_irq", "eth_lpi";
+	phy-mode	= "mii";
+
+	st,syscon	= <&syscfg_rear>;
+
+	snps,pbl 	= <32>;
+	snps,mixed-burst;
+
+	resets		= <&softreset STIH416_ETH0_SOFTRESET>;
+	reset-names	= "stmmaceth";
+	pinctrl-0	= <&pinctrl_mii0>;
+	pinctrl-names 	= "default";
+	clocks		= <&CLK_S_GMAC0_PHY>;
+	clock-names	= "stmmaceth";
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt
similarity index 98%
rename from Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt
rename to Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt
index 9e9e9ef..c119deb 100644
--- a/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt
@@ -1,4 +1,4 @@
-Broadcom Capri Pin Controller
+Broadcom BCM281xx Pin Controller
 
 This is a pin controller for the Broadcom BCM281xx SoC family, which includes
 BCM11130, BCM11140, BCM11351, BCM28145, and BCM28155 SoCs.
@@ -7,14 +7,14 @@
 
 Required Properties:
 
-- compatible:	Must be "brcm,capri-pinctrl".
+- compatible:	Must be "brcm,bcm11351-pinctrl"
 - reg:		Base address of the PAD Controller register block and the size
 		of the block.
 
 For example, the following is the bare minimum node:
 
 	pinctrl@35004800 {
-		compatible = "brcm,capri-pinctrl";
+		compatible = "brcm,bcm11351-pinctrl";
 		reg = <0x35004800 0x430>;
 	};
 
@@ -119,7 +119,7 @@
 Example:
 // pin controller node
 pinctrl@35004800 {
-	compatible = "brcm,capri-pinctrl";
+	compatible = "brcmbcm11351-pinctrl";
 	reg = <0x35004800 0x430>;
 
 	// pin configuration node
diff --git a/Documentation/devicetree/bindings/power/bq2415x.txt b/Documentation/devicetree/bindings/power/bq2415x.txt
new file mode 100644
index 0000000..d0327f0
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/bq2415x.txt
@@ -0,0 +1,47 @@
+Binding for TI bq2415x Li-Ion Charger
+
+Required properties:
+- compatible: Should contain one of the following:
+ * "ti,bq24150"
+ * "ti,bq24150"
+ * "ti,bq24150a"
+ * "ti,bq24151"
+ * "ti,bq24151a"
+ * "ti,bq24152"
+ * "ti,bq24153"
+ * "ti,bq24153a"
+ * "ti,bq24155"
+ * "ti,bq24156"
+ * "ti,bq24156a"
+ * "ti,bq24158"
+- reg:			   integer, i2c address of the device.
+- ti,current-limit:	   integer, initial maximum current charger can pull
+			   from power supply in mA.
+- ti,weak-battery-voltage: integer, weak battery voltage threshold in mV.
+			   The chip will use slow precharge if battery voltage
+			   is below this value.
+- ti,battery-regulation-voltage: integer, maximum charging voltage in mV.
+- ti,charge-current:	   integer, maximum charging current in mA.
+- ti,termination-current:  integer, charge will be terminated when current in
+			   constant-voltage phase drops below this value (in mA).
+- ti,resistor-sense:	   integer, value of sensing resistor in milliohm.
+
+Optional properties:
+- ti,usb-charger-detection: phandle to usb charger detection device.
+			    (required for auto mode)
+
+Example from Nokia N900:
+
+bq24150a {
+	compatible = "ti,bq24150a";
+	reg = <0x6b>;
+
+	ti,current-limit = <100>;
+	ti,weak-battery-voltage = <3400>;
+	ti,battery-regulation-voltage = <4200>;
+	ti,charge-current = <650>;
+	ti,termination-current = <100>;
+	ti,resistor-sense = <68>;
+
+	ti,usb-charger-detection = <&isp1704>;
+};
diff --git a/Documentation/devicetree/bindings/spi/spi_atmel.txt b/Documentation/devicetree/bindings/spi/spi_atmel.txt
index 07e04cd..4f8184d 100644
--- a/Documentation/devicetree/bindings/spi/spi_atmel.txt
+++ b/Documentation/devicetree/bindings/spi/spi_atmel.txt
@@ -5,6 +5,9 @@
 - reg: Address and length of the register set for the device
 - interrupts: Should contain spi interrupt
 - cs-gpios: chipselects
+- clock-names: tuple listing input clock names.
+	Required elements: "spi_clk"
+- clocks: phandles to input clocks.
 
 Example:
 
@@ -14,6 +17,8 @@
 	interrupts = <13 4 5>;
 	#address-cells = <1>;
 	#size-cells = <0>;
+	clocks = <&spi1_clk>;
+	clock-names = "spi_clk";
 	cs-gpios = <&pioB 3 0>;
 	status = "okay";
 
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 3f900cd..40ce2df 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -8,6 +8,7 @@
 adi	Analog Devices, Inc.
 aeroflexgaisler	Aeroflex Gaisler AB
 ak	Asahi Kasei Corp.
+allwinner	Allwinner Technology Co., Ltd.
 altr	Altera Corp.
 amcc	Applied Micro Circuits Corporation (APM, formally AMCC)
 amstaos	AMS-Taos Inc.
@@ -40,6 +41,7 @@
 gumstix	Gumstix, Inc.
 haoyu	Haoyu Microelectronic Co. Ltd.
 hisilicon	Hisilicon Limited.
+honeywell	Honeywell
 hp	Hewlett Packard
 ibm	International Business Machines (IBM)
 idt	Integrated Device Technologies, Inc.
@@ -55,6 +57,7 @@
 microchip	Microchip Technology Inc.
 mosaixtech	Mosaix Technologies, Inc.
 national	National Semiconductor
+neonode		Neonode Inc.
 nintendo	Nintendo
 nvidia	NVIDIA
 nxp	NXP Semiconductors
@@ -64,7 +67,7 @@
 picochip	Picochip Ltd
 powervr	PowerVR (deprecated, use img)
 qca	Qualcomm Atheros, Inc.
-qcom	Qualcomm, Inc.
+qcom	Qualcomm Technologies, Inc
 ralink	Mediatek/Ralink Technology Corp.
 ramtron	Ramtron International
 realtek Realtek Semiconductor Corp.
@@ -78,6 +81,7 @@
 simtek
 sirf	SiRF Technology, Inc.
 snps 	Synopsys, Inc.
+spansion	Spansion Inc.
 st	STMicroelectronics
 ste	ST-Ericsson
 stericsson	ST-Ericsson
diff --git a/Documentation/dvb/contributors.txt b/Documentation/dvb/contributors.txt
index 47c3009..731a009 100644
--- a/Documentation/dvb/contributors.txt
+++ b/Documentation/dvb/contributors.txt
@@ -78,7 +78,7 @@
 Wilson Michaels <wilsonmichaels@earthlink.net>
   for the lgdt330x frontend driver, and various bugfixes
 
-Michael Krufky <mkrufky@m1k.net>
+Michael Krufky <mkrufky@linuxtv.org>
   for maintaining v4l/dvb inter-tree dependencies
 
 Taylor Jacob <rtjacob@earthlink.net>
diff --git a/Documentation/fb/00-INDEX b/Documentation/fb/00-INDEX
index 30a7054..fe85e7c 100644
--- a/Documentation/fb/00-INDEX
+++ b/Documentation/fb/00-INDEX
@@ -5,6 +5,8 @@
 
 00-INDEX
 	- this file.
+api.txt
+	- The frame buffer API between applications and buffer devices.
 arkfb.txt
 	- info on the fbdev driver for ARK Logic chips.
 aty128fb.txt
@@ -51,12 +53,16 @@
 	- info on the SH7760/SH7763 integrated LCDC Framebuffer driver.
 sisfb.txt
 	- info on the framebuffer device driver for various SiS chips.
+sm501.txt
+	- info on the framebuffer device driver for sm501 videoframebuffer.
 sstfb.txt
 	- info on the frame buffer driver for 3dfx' Voodoo Graphics boards.
 tgafb.txt
 	- info on the TGA (DECChip 21030) frame buffer driver.
 tridentfb.txt
 	info on the framebuffer driver for some Trident chip based cards.
+udlfb.txt
+	- Driver for DisplayLink USB 2.0 chips.
 uvesafb.txt
 	- info on the userspace VESA (VBE2+ compliant) frame buffer device.
 vesafb.txt
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 632211c..ac28149 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -2,6 +2,8 @@
 	- this file (info on some of the filesystems supported by linux).
 Locking
 	- info on locking rules as they pertain to Linux VFS.
+Makefile
+	- Makefile for building the filsystems-part of DocBook.
 9p.txt
 	- 9p (v9fs) is an implementation of the Plan 9 remote fs protocol.
 adfs.txt
diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX
index 66eb6c8..53f3b59 100644
--- a/Documentation/filesystems/nfs/00-INDEX
+++ b/Documentation/filesystems/nfs/00-INDEX
@@ -12,6 +12,8 @@
 	- info on the Linux server implementation of NFSv4 minor version 1.
 nfs-rdma.txt
 	- how to install and setup the Linux NFS/RDMA client and server software
+nfsd-admin-interfaces.txt
+	- Administrative interfaces for nfsd.
 nfsroot.txt
 	- short guide on setting up a diskless box with NFS root filesystem.
 pnfs.txt
@@ -20,5 +22,5 @@
 	- introduction to the caching mechanisms in the sunrpc layer.
 idmapper.txt
 	- information for configuring request-keys to be used by idmapper
-knfsd-rpcgss.txt
+rpc-server-gss.txt
 	- Information on GSS authentication support in the NFS Server
diff --git a/Documentation/i2c/instantiating-devices b/Documentation/i2c/instantiating-devices
index c70e7a7..0d85ac19 100644
--- a/Documentation/i2c/instantiating-devices
+++ b/Documentation/i2c/instantiating-devices
@@ -8,8 +8,8 @@
 several ways to achieve this, depending on the context and requirements.
 
 
-Method 1: Declare the I2C devices by bus number
------------------------------------------------
+Method 1a: Declare the I2C devices by bus number
+------------------------------------------------
 
 This method is appropriate when the I2C bus is a system bus as is the case
 for many embedded systems. On such systems, each I2C bus has a number
@@ -51,6 +51,43 @@
 they sit on goes away (if ever.)
 
 
+Method 1b: Declare the I2C devices via devicetree
+-------------------------------------------------
+
+This method has the same implications as method 1a. The declaration of I2C
+devices is here done via devicetree as subnodes of the master controller.
+
+Example:
+
+	i2c1: i2c@400a0000 {
+		/* ... master properties skipped ... */
+		clock-frequency = <100000>;
+
+		flash@50 {
+			compatible = "atmel,24c256";
+			reg = <0x50>;
+		};
+
+		pca9532: gpio@60 {
+			compatible = "nxp,pca9532";
+			gpio-controller;
+			#gpio-cells = <2>;
+			reg = <0x60>;
+		};
+	};
+
+Here, two devices are attached to the bus using a speed of 100kHz. For
+additional properties which might be needed to set up the device, please refer
+to its devicetree documentation in Documentation/devicetree/bindings/.
+
+
+Method 1c: Declare the I2C devices via ACPI
+-------------------------------------------
+
+ACPI can also describe I2C devices. There is special documentation for this
+which is currently located at Documentation/acpi/enumeration.txt.
+
+
 Method 2: Instantiate the devices explicitly
 --------------------------------------------
 
diff --git a/Documentation/ide/00-INDEX b/Documentation/ide/00-INDEX
index d6b7788..22f98ca 100644
--- a/Documentation/ide/00-INDEX
+++ b/Documentation/ide/00-INDEX
@@ -10,3 +10,5 @@
 	- info on the IDE ATAPI streaming tape driver
 ide.txt
 	- important info for users of ATA devices (IDE/EIDE disks and CD-ROMS).
+warm-plug-howto.txt
+	- using sysfs to remove and add IDE devices.
\ No newline at end of file
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 8f441da..67755ea 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1011,6 +1011,13 @@
 			parameter will force ia64_sal_cache_flush to call
 			ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
 
+	forcepae [X86-32]
+			Forcefully enable Physical Address Extension (PAE).
+			Many Pentium M systems disable PAE but may have a
+			functionally usable PAE implementation.
+			Warning: use of this parameter will taint the kernel
+			and may cause unknown problems.
+
 	ftrace=[tracer]
 			[FTRACE] will set and start the specified tracer
 			as early as possible in order to facilitate early
@@ -1726,16 +1733,16 @@
 			option description.
 
 	memmap=nn[KMG]@ss[KMG]
-			[KNL] Force usage of a specific region of memory
-			Region of memory to be used, from ss to ss+nn.
+			[KNL] Force usage of a specific region of memory.
+			Region of memory to be used is from ss to ss+nn.
 
 	memmap=nn[KMG]#ss[KMG]
 			[KNL,ACPI] Mark specific memory as ACPI data.
-			Region of memory to be used, from ss to ss+nn.
+			Region of memory to be marked is from ss to ss+nn.
 
 	memmap=nn[KMG]$ss[KMG]
 			[KNL,ACPI] Mark specific memory as reserved.
-			Region of memory to be used, from ss to ss+nn.
+			Region of memory to be reserved is from ss to ss+nn.
 			Example: Exclude memory from 0x18690000-0x1869ffff
 			         memmap=64K$0x18690000
 			         or
@@ -2053,8 +2060,8 @@
 			IOAPICs that may be present in the system.
 
 	nokaslr		[X86]
-			Disable kernel base offset ASLR (Address Space
-			Layout Randomization) if built into the kernel.
+			Disable kernel and module base offset ASLR (Address
+			Space Layout Randomization) if built into the kernel.
 
 	noautogroup	Disable scheduler automatic task group creation.
 
diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt
index 827104f..f3cd299 100644
--- a/Documentation/kernel-per-CPU-kthreads.txt
+++ b/Documentation/kernel-per-CPU-kthreads.txt
@@ -162,7 +162,18 @@
 To reduce its OS jitter, do any of the following:
 1.	Run your workload at a real-time priority, which will allow
 	preempting the kworker daemons.
-2.	Do any of the following needed to avoid jitter that your
+2.	A given workqueue can be made visible in the sysfs filesystem
+	by passing the WQ_SYSFS to that workqueue's alloc_workqueue().
+	Such a workqueue can be confined to a given subset of the
+	CPUs using the /sys/devices/virtual/workqueue/*/cpumask sysfs
+	files.	The set of WQ_SYSFS workqueues can be displayed using
+	"ls sys/devices/virtual/workqueue".  That said, the workqueues
+	maintainer would like to caution people against indiscriminately
+	sprinkling WQ_SYSFS across all the workqueues.	The reason for
+	caution is that it is easy to add WQ_SYSFS, but because sysfs is
+	part of the formal user/kernel API, it can be nearly impossible
+	to remove it, even if its addition was a mistake.
+3.	Do any of the following needed to avoid jitter that your
 	application cannot tolerate:
 	a.	Build your kernel with CONFIG_SLUB=y rather than
 		CONFIG_SLAB=y, thus avoiding the slab allocator's periodic
diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX
index fa68853..d13b9a9 100644
--- a/Documentation/laptops/00-INDEX
+++ b/Documentation/laptops/00-INDEX
@@ -1,13 +1,15 @@
 00-INDEX
 	- This file
-acer-wmi.txt
-	- information on the Acer Laptop WMI Extras driver.
+Makefile
+	- Makefile for building dslm example program.
 asus-laptop.txt
 	- information on the Asus Laptop Extras driver.
 disk-shock-protection.txt
 	- information on hard disk shock protection.
 dslm.c
 	- Simple Disk Sleep Monitor program
+hpfall.c
+	- (HP) laptop accelerometer program for disk protection.
 laptop-mode.txt
 	- how to conserve battery power using laptop-mode.
 sony-laptop.txt
diff --git a/Documentation/leds/00-INDEX b/Documentation/leds/00-INDEX
index 1ecd159..b4ef1f3 100644
--- a/Documentation/leds/00-INDEX
+++ b/Documentation/leds/00-INDEX
@@ -1,3 +1,7 @@
+00-INDEX
+	- This file
+leds-blinkm.txt
+	- Driver for BlinkM LED-devices.
 leds-class.txt
 	- documents LED handling under Linux.
 leds-lp3944.txt
@@ -12,3 +16,7 @@
 	- description about lp55xx common driver.
 leds-lm3556.txt
 	- notes on how to use the leds-lm3556 driver.
+ledtrig-oneshot.txt
+	- One-shot LED trigger for both sporadic and dense events.
+ledtrig-transient.txt
+	- LED Transient Trigger, one shot timer activation.
diff --git a/Documentation/m68k/00-INDEX b/Documentation/m68k/00-INDEX
index a014e9f..2be8c6b 100644
--- a/Documentation/m68k/00-INDEX
+++ b/Documentation/m68k/00-INDEX
@@ -1,5 +1,7 @@
 00-INDEX
 	- this file
+README.buddha
+	- Amiga Buddha and Catweasel IDE Driver
 kernel-options.txt
 	- command line options for Linux/m68k
 
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 102dc19..11c1d20 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -608,26 +608,30 @@
 	b = p;  /* BUG: Compiler can reorder!!! */
 	do_something();
 
-The solution is again ACCESS_ONCE(), which preserves the ordering between
-the load from variable 'a' and the store to variable 'b':
+The solution is again ACCESS_ONCE() and barrier(), which preserves the
+ordering between the load from variable 'a' and the store to variable 'b':
 
 	q = ACCESS_ONCE(a);
 	if (q) {
+		barrier();
 		ACCESS_ONCE(b) = p;
 		do_something();
 	} else {
+		barrier();
 		ACCESS_ONCE(b) = p;
 		do_something_else();
 	}
 
-You could also use barrier() to prevent the compiler from moving
-the stores to variable 'b', but barrier() would not prevent the
-compiler from proving to itself that a==1 always, so ACCESS_ONCE()
-is also needed.
+The initial ACCESS_ONCE() is required to prevent the compiler from
+proving the value of 'a', and the pair of barrier() invocations are
+required to prevent the compiler from pulling the two identical stores
+to 'b' out from the legs of the "if" statement.
 
 It is important to note that control dependencies absolutely require a
 a conditional.  For example, the following "optimized" version of
-the above example breaks ordering:
+the above example breaks ordering, which is why the barrier() invocations
+are absolutely required if you have identical stores in both legs of
+the "if" statement:
 
 	q = ACCESS_ONCE(a);
 	ACCESS_ONCE(b) = p;  /* BUG: No ordering vs. load from a!!! */
@@ -643,9 +647,11 @@
 for example, as follows:
 
 	if (ACCESS_ONCE(a) > 0) {
+		barrier();
 		ACCESS_ONCE(b) = q / 2;
 		do_something();
 	} else {
+		barrier();
 		ACCESS_ONCE(b) = q / 3;
 		do_something_else();
 	}
@@ -659,9 +665,11 @@
 
 	q = ACCESS_ONCE(a);
 	if (q % MAX) {
+		barrier();
 		ACCESS_ONCE(b) = p;
 		do_something();
 	} else {
+		barrier();
 		ACCESS_ONCE(b) = p;
 		do_something_else();
 	}
@@ -723,8 +731,13 @@
       use smb_rmb(), smp_wmb(), or, in the case of prior stores and
       later loads, smp_mb().
 
+  (*) If both legs of the "if" statement begin with identical stores
+      to the same variable, a barrier() statement is required at the
+      beginning of each leg of the "if" statement.
+
   (*) Control dependencies require at least one run-time conditional
-      between the prior load and the subsequent store.  If the compiler
+      between the prior load and the subsequent store, and this
+      conditional must involve the prior load.  If the compiler
       is able to optimize the conditional away, it will have also
       optimized away the ordering.  Careful use of ACCESS_ONCE() can
       help to preserve the needed conditional.
@@ -1249,6 +1262,23 @@
 while perfectly safe in single-threaded code, can be fatal in concurrent
 code.  Here are some examples of these sorts of optimizations:
 
+ (*) The compiler is within its rights to reorder loads and stores
+     to the same variable, and in some cases, the CPU is within its
+     rights to reorder loads to the same variable.  This means that
+     the following code:
+
+	a[0] = x;
+	a[1] = x;
+
+     Might result in an older value of x stored in a[1] than in a[0].
+     Prevent both the compiler and the CPU from doing this as follows:
+
+	a[0] = ACCESS_ONCE(x);
+	a[1] = ACCESS_ONCE(x);
+
+     In short, ACCESS_ONCE() provides cache coherence for accesses from
+     multiple CPUs to a single variable.
+
  (*) The compiler is within its rights to merge successive loads from
      the same variable.  Such merging can cause the compiler to "optimize"
      the following code:
@@ -1644,12 +1674,12 @@
      Memory operations issued after the ACQUIRE will be completed after the
      ACQUIRE operation has completed.
 
-     Memory operations issued before the ACQUIRE may be completed after the
-     ACQUIRE operation has completed.  An smp_mb__before_spinlock(), combined
-     with a following ACQUIRE, orders prior loads against subsequent stores and
-     stores and prior stores against subsequent stores.  Note that this is
-     weaker than smp_mb()!  The smp_mb__before_spinlock() primitive is free on
-     many architectures.
+     Memory operations issued before the ACQUIRE may be completed after
+     the ACQUIRE operation has completed.  An smp_mb__before_spinlock(),
+     combined with a following ACQUIRE, orders prior loads against
+     subsequent loads and stores and also orders prior stores against
+     subsequent stores.  Note that this is weaker than smp_mb()!  The
+     smp_mb__before_spinlock() primitive is free on many architectures.
 
  (2) RELEASE operation implication:
 
@@ -1694,24 +1724,21 @@
 
 	ACQUIRE M, STORE *B, STORE *A, RELEASE M
 
-This same reordering can of course occur if the lock's ACQUIRE and RELEASE are
-to the same lock variable, but only from the perspective of another CPU not
-holding that lock.
+When the ACQUIRE and RELEASE are a lock acquisition and release,
+respectively, this same reordering can occur if the lock's ACQUIRE and
+RELEASE are to the same lock variable, but only from the perspective of
+another CPU not holding that lock.  In short, a ACQUIRE followed by an
+RELEASE may -not- be assumed to be a full memory barrier.
 
-In short, a RELEASE followed by an ACQUIRE may -not- be assumed to be a full
-memory barrier because it is possible for a preceding RELEASE to pass a
-later ACQUIRE from the viewpoint of the CPU, but not from the viewpoint
-of the compiler.  Note that deadlocks cannot be introduced by this
-interchange because if such a deadlock threatened, the RELEASE would
-simply complete.
-
-If it is necessary for a RELEASE-ACQUIRE pair to produce a full barrier, the
-ACQUIRE can be followed by an smp_mb__after_unlock_lock() invocation.  This
-will produce a full barrier if either (a) the RELEASE and the ACQUIRE are
-executed by the same CPU or task, or (b) the RELEASE and ACQUIRE act on the
-same variable.  The smp_mb__after_unlock_lock() primitive is free on many
-architectures.  Without smp_mb__after_unlock_lock(), the critical sections
-corresponding to the RELEASE and the ACQUIRE can cross:
+Similarly, the reverse case of a RELEASE followed by an ACQUIRE does not
+imply a full memory barrier.  If it is necessary for a RELEASE-ACQUIRE
+pair to produce a full barrier, the ACQUIRE can be followed by an
+smp_mb__after_unlock_lock() invocation.  This will produce a full barrier
+if either (a) the RELEASE and the ACQUIRE are executed by the same
+CPU or task, or (b) the RELEASE and ACQUIRE act on the same variable.
+The smp_mb__after_unlock_lock() primitive is free on many architectures.
+Without smp_mb__after_unlock_lock(), the CPU's execution of the critical
+sections corresponding to the RELEASE and the ACQUIRE can cross, so that:
 
 	*A = a;
 	RELEASE M
@@ -1722,7 +1749,36 @@
 
 	ACQUIRE N, STORE *B, STORE *A, RELEASE M
 
-With smp_mb__after_unlock_lock(), they cannot, so that:
+It might appear that this reordering could introduce a deadlock.
+However, this cannot happen because if such a deadlock threatened,
+the RELEASE would simply complete, thereby avoiding the deadlock.
+
+	Why does this work?
+
+	One key point is that we are only talking about the CPU doing
+	the reordering, not the compiler.  If the compiler (or, for
+	that matter, the developer) switched the operations, deadlock
+	-could- occur.
+
+	But suppose the CPU reordered the operations.  In this case,
+	the unlock precedes the lock in the assembly code.  The CPU
+	simply elected to try executing the later lock operation first.
+	If there is a deadlock, this lock operation will simply spin (or
+	try to sleep, but more on that later).	The CPU will eventually
+	execute the unlock operation (which preceded the lock operation
+	in the assembly code), which will unravel the potential deadlock,
+	allowing the lock operation to succeed.
+
+	But what if the lock is a sleeplock?  In that case, the code will
+	try to enter the scheduler, where it will eventually encounter
+	a memory barrier, which will force the earlier unlock operation
+	to complete, again unraveling the deadlock.  There might be
+	a sleep-unlock race, but the locking primitive needs to resolve
+	such races properly in any case.
+
+With smp_mb__after_unlock_lock(), the two critical sections cannot overlap.
+For example, with the following code, the store to *A will always be
+seen by other CPUs before the store to *B:
 
 	*A = a;
 	RELEASE M
@@ -1730,13 +1786,18 @@
 	smp_mb__after_unlock_lock();
 	*B = b;
 
-will always occur as either of the following:
+The operations will always occur in one of the following orders:
 
-	STORE *A, RELEASE, ACQUIRE, STORE *B
-	STORE *A, ACQUIRE, RELEASE, STORE *B
+	STORE *A, RELEASE, ACQUIRE, smp_mb__after_unlock_lock(), STORE *B
+	STORE *A, ACQUIRE, RELEASE, smp_mb__after_unlock_lock(), STORE *B
+	ACQUIRE, STORE *A, RELEASE, smp_mb__after_unlock_lock(), STORE *B
 
 If the RELEASE and ACQUIRE were instead both operating on the same lock
-variable, only the first of these two alternatives can occur.
+variable, only the first of these alternatives can occur.  In addition,
+the more strongly ordered systems may rule out some of the above orders.
+But in any case, as noted earlier, the smp_mb__after_unlock_lock()
+ensures that the store to *A will always be seen as happening before
+the store to *B.
 
 Locks and semaphores may not provide any guarantee of ordering on UP compiled
 systems, and so cannot be counted on in such a situation to actually achieve
@@ -2757,7 +2818,7 @@
 combination of elements combined or discarded, provided the program's view of
 the world remains consistent.  Note that ACCESS_ONCE() is -not- optional
 in the above example, as there are architectures where a given CPU might
-interchange successive loads to the same location.  On such architectures,
+reorder successive loads to the same location.  On such architectures,
 ACCESS_ONCE() does whatever is necessary to prevent this, for example, on
 Itanium the volatile casts used by ACCESS_ONCE() cause GCC to emit the
 special ld.acq and st.rel instructions that prevent such reordering.
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index f11580f..557b6ef 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -6,8 +6,14 @@
 	- information on the 3Com Etherlink III Series Ethernet cards.
 6pack.txt
 	- info on the 6pack protocol, an alternative to KISS for AX.25
-DLINK.txt
-	- info on the D-Link DE-600/DE-620 parallel port pocket adapters
+LICENSE.qla3xxx
+	- GPLv2 for QLogic Linux Networking HBA Driver
+LICENSE.qlge
+	- GPLv2 for QLogic Linux qlge NIC Driver
+LICENSE.qlcnic
+	- GPLv2 for QLogic Linux qlcnic NIC Driver
+Makefile
+	- Makefile for docsrc.
 PLIP.txt
 	- PLIP: The Parallel Line Internet Protocol device driver
 README.ipw2100
@@ -17,7 +23,7 @@
 README.sb1000
 	- info on General Instrument/NextLevel SURFboard1000 cable modem.
 alias.txt
-	- info on using alias network devices 
+	- info on using alias network devices.
 arcnet-hardware.txt
 	- tons of info on ARCnet, hubs, jumper settings for ARCnet cards, etc.
 arcnet.txt
@@ -80,7 +86,7 @@
 	- info on using Frame Relay/Data Link Connection Identifier (DLCI).
 gen_stats.txt
 	- Generic networking statistics for netlink users.
-generic_hdlc.txt
+generic-hdlc.txt
 	- The generic High Level Data Link Control (HDLC) layer.
 generic_netlink.txt
 	- info on Generic Netlink
@@ -88,6 +94,8 @@
 	- Gianfar Ethernet Driver.
 i40e.txt
 	- README for the Intel Ethernet Controller XL710 Driver (i40e).
+i40evf.txt
+	- Short note on the Driver for the Intel(R) XL710 X710 Virtual Function
 ieee802154.txt
 	- Linux IEEE 802.15.4 implementation, API and drivers
 igb.txt
@@ -102,6 +110,8 @@
 	- AppleTalk-IP Decapsulation and AppleTalk-IP Encapsulation
 iphase.txt
 	- Interphase PCI ATM (i)Chip IA Linux driver info.
+ipsec.txt
+	- Note on not compressing IPSec payload and resulting failed policy check.
 ipv6.txt
 	- Options to the ipv6 kernel module.
 ipvs-sysctl.txt
@@ -120,6 +130,8 @@
 	- programming information of the LAPB module.
 ltpc.txt
 	- the Apple or Farallon LocalTalk PC card driver
+mac80211-auth-assoc-deauth.txt
+	- authentication and association / deauth-disassoc with max80211
 mac80211-injection.txt
 	- HOWTO use packet injection with mac80211
 multiqueue.txt
@@ -134,6 +146,10 @@
 	- info on network device driver functions exported to the kernel.
 netif-msg.txt
 	- Design of the network interface message level setting (NETIF_MSG_*).
+netlink_mmap.txt
+	- memory mapped I/O with netlink
+nf_conntrack-sysctl.txt
+	- list of netfilter-sysctl knobs.
 nfc.txt
 	- The Linux Near Field Communication (NFS) subsystem.
 openvswitch.txt
@@ -176,7 +192,7 @@
 	- SysKonnect FDDI (SK-5xxx, Compaq Netelligent) driver info.
 smc9.txt
 	- the driver for SMC's 9000 series of Ethernet cards
-spider-net.txt
+spider_net.txt
 	- README for the Spidernet Driver (as found in PS3 / Cell BE).
 stmmac.txt
 	- README for the STMicro Synopsys Ethernet driver.
@@ -188,6 +204,8 @@
 	- short blurb on how TCP output takes place.
 tcp-thin.txt
 	- kernel tuning options for low rate 'thin' TCP streams.
+team.txt
+	- pointer to information for ethernet teaming devices.
 tlan.txt
 	- ThunderLAN (Compaq Netelligent 10/100, Olicom OC-2xxx) driver info.
 tproxy.txt
@@ -200,6 +218,8 @@
 	- info on using 3Com Vortex (3c590, 3c592, 3c595, 3c597) Ethernet cards.
 vxge.txt
 	- README for the Neterion X3100 PCIe Server Adapter.
+vxlan.txt
+	- Virtual extensible LAN overview
 x25.txt
 	- general info on X.25 development.
 x25-iface.txt
diff --git a/Documentation/networking/3c505.txt b/Documentation/networking/3c505.txt
deleted file mode 100644
index 72f38b1..0000000
--- a/Documentation/networking/3c505.txt
+++ /dev/null
@@ -1,45 +0,0 @@
-The 3Com Etherlink Plus (3c505) driver.
-
-This driver now uses DMA.  There is currently no support for PIO operation.
-The default DMA channel is 6; this is _not_ autoprobed, so you must
-make sure you configure it correctly.  If loading the driver as a
-module, you can do this with "modprobe 3c505 dma=n".  If the driver is
-linked statically into the kernel, you must either use an "ether="
-statement on the command line, or change the definition of ELP_DMA in 3c505.h.
-
-The driver will warn you if it has to fall back on the compiled in
-default DMA channel. 
-
-If no base address is given at boot time, the driver will autoprobe
-ports 0x300, 0x280 and 0x310 (in that order).  If no IRQ is given, the driver
-will try to probe for it.
-
-The driver can be used as a loadable module.
-
-Theoretically, one instance of the driver can now run multiple cards,
-in the standard way (when loading a module, say "modprobe 3c505
-io=0x300,0x340 irq=10,11 dma=6,7" or whatever).  I have not tested
-this, though.
-
-The driver may now support revision 2 hardware; the dependency on
-being able to read the host control register has been removed.  This
-is also untested, since I don't have a suitable card.
-
-Known problems:
- I still see "DMA upload timed out" messages from time to time.  These
-seem to be fairly non-fatal though.
- The card is old and slow.
-
-To do:
- Improve probe/setup code
- Test multicast and promiscuous operation
-
-Authors:
- The driver is mainly written by Craig Southeren, email
- <craigs@ineluki.apana.org.au>.
- Parts of the driver (adapting the driver to 1.1.4+ kernels,
- IRQ/address detection, some changes) and this README by
- Juha Laiho <jlaiho@ichaos.nullnet.fi>.
- DMA mode, more fixes, etc, by Philip Blundell <pjb27@cam.ac.uk>
- Multicard support, Software configurable DMA, etc., by
- Christopher Collins <ccollins@pcug.org.au>
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index f3089d4..0cbe6ec 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -554,12 +554,6 @@
   not specified in the struct can_frame and therefore it is only valid in
   CANFD_MTU sized CAN FD frames.
 
-  As long as the payload length is <=8 the received CAN frames from CAN FD
-  capable CAN devices can be received and read by legacy sockets too. When
-  user-generated CAN FD frames have a payload length <=8 these can be send
-  by legacy CAN network interfaces too. Sending CAN FD frames with payload
-  length > 8 to a legacy CAN network interface returns an -EMSGSIZE error.
-
   Implementation hint for new CAN applications:
 
   To build a CAN FD aware application use struct canfd_frame as basic CAN
diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt
index b261229..c6af4ba 100644
--- a/Documentation/networking/netlink_mmap.txt
+++ b/Documentation/networking/netlink_mmap.txt
@@ -226,9 +226,9 @@
 	void *rx_ring, *tx_ring;
 
 	/* Configure ring parameters */
-	if (setsockopt(fd, NETLINK_RX_RING, &req, sizeof(req)) < 0)
+	if (setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &req, sizeof(req)) < 0)
 		exit(1);
-	if (setsockopt(fd, NETLINK_TX_RING, &req, sizeof(req)) < 0)
+	if (setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &req, sizeof(req)) < 0)
 		exit(1)
 
 	/* Calculate size of each individual ring */
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 1404674..6fea79e 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -453,7 +453,7 @@
                         enabled previously with setsockopt() and 
                         the PACKET_COPY_THRESH option. 
 
-                        The number of frames than can be buffered to 
+                        The number of frames that can be buffered to
                         be read with recvfrom is limited like a normal socket.
                         See the SO_RCVBUF option in the socket (7) man page.
 
diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index 661d3c3..048c92b 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -21,26 +21,38 @@
 
 SO_TIMESTAMPING:
 
-Instructs the socket layer which kind of information is wanted. The
-parameter is an integer with some of the following bits set. Setting
-other bits is an error and doesn't change the current state.
+Instructs the socket layer which kind of information should be collected
+and/or reported.  The parameter is an integer with some of the following
+bits set. Setting other bits is an error and doesn't change the current
+state.
 
-SOF_TIMESTAMPING_TX_HARDWARE:  try to obtain send time stamp in hardware
-SOF_TIMESTAMPING_TX_SOFTWARE:  if SOF_TIMESTAMPING_TX_HARDWARE is off or
-                               fails, then do it in software
-SOF_TIMESTAMPING_RX_HARDWARE:  return the original, unmodified time stamp
-                               as generated by the hardware
-SOF_TIMESTAMPING_RX_SOFTWARE:  if SOF_TIMESTAMPING_RX_HARDWARE is off or
-                               fails, then do it in software
-SOF_TIMESTAMPING_RAW_HARDWARE: return original raw hardware time stamp
-SOF_TIMESTAMPING_SYS_HARDWARE: return hardware time stamp transformed to
-                               the system time base
-SOF_TIMESTAMPING_SOFTWARE:     return system time stamp generated in
-                               software
+Four of the bits are requests to the stack to try to generate
+timestamps.  Any combination of them is valid.
 
-SOF_TIMESTAMPING_TX/RX determine how time stamps are generated.
-SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the
-following control message:
+SOF_TIMESTAMPING_TX_HARDWARE:  try to obtain send time stamps in hardware
+SOF_TIMESTAMPING_TX_SOFTWARE:  try to obtain send time stamps in software
+SOF_TIMESTAMPING_RX_HARDWARE:  try to obtain receive time stamps in hardware
+SOF_TIMESTAMPING_RX_SOFTWARE:  try to obtain receive time stamps in software
+
+The other three bits control which timestamps will be reported in a
+generated control message.  If none of these bits are set or if none of
+the set bits correspond to data that is available, then the control
+message will not be generated:
+
+SOF_TIMESTAMPING_SOFTWARE:     report systime if available
+SOF_TIMESTAMPING_SYS_HARDWARE: report hwtimetrans if available
+SOF_TIMESTAMPING_RAW_HARDWARE: report hwtimeraw if available
+
+It is worth noting that timestamps may be collected for reasons other
+than being requested by a particular socket with
+SOF_TIMESTAMPING_[TR]X_(HARD|SOFT)WARE.  For example, most drivers that
+can generate hardware receive timestamps ignore
+SOF_TIMESTAMPING_RX_HARDWARE.  It is still a good idea to set that flag
+in case future drivers pay attention.
+
+If timestamps are reported, they will appear in a control message with
+cmsg_level==SOL_SOCKET, cmsg_type==SO_TIMESTAMPING, and a payload like
+this:
 
 struct scm_timestamping {
 	struct timespec systime;
diff --git a/Documentation/phy.txt b/Documentation/phy.txt
index 0103e4b..ebff6ee 100644
--- a/Documentation/phy.txt
+++ b/Documentation/phy.txt
@@ -75,14 +75,26 @@
 it. This framework provides the following APIs to get a reference to the PHY.
 
 struct phy *phy_get(struct device *dev, const char *string);
+struct phy *phy_optional_get(struct device *dev, const char *string);
 struct phy *devm_phy_get(struct device *dev, const char *string);
+struct phy *devm_phy_optional_get(struct device *dev, const char *string);
 
-phy_get and devm_phy_get can be used to get the PHY. In the case of dt boot,
-the string arguments should contain the phy name as given in the dt data and
-in the case of non-dt boot, it should contain the label of the PHY.
-The only difference between the two APIs is that devm_phy_get associates the
-device with the PHY using devres on successful PHY get. On driver detach,
-release function is invoked on the the devres data and devres data is freed.
+phy_get, phy_optional_get, devm_phy_get and devm_phy_optional_get can
+be used to get the PHY. In the case of dt boot, the string arguments
+should contain the phy name as given in the dt data and in the case of
+non-dt boot, it should contain the label of the PHY.  The two
+devm_phy_get associates the device with the PHY using devres on
+successful PHY get. On driver detach, release function is invoked on
+the the devres data and devres data is freed. phy_optional_get and
+devm_phy_optional_get should be used when the phy is optional. These
+two functions will never return -ENODEV, but instead returns NULL when
+the phy cannot be found.
+
+It should be noted that NULL is a valid phy reference. All phy
+consumer calls on the NULL phy become NOPs. That is the release calls,
+the phy_init() and phy_exit() calls, and phy_power_on() and
+phy_power_off() calls are all NOP when applied to a NULL phy. The NULL
+phy is useful in devices for handling optional phy devices.
 
 5. Releasing a reference to the PHY
 
diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX
index a4d682f..ad04cc8 100644
--- a/Documentation/power/00-INDEX
+++ b/Documentation/power/00-INDEX
@@ -4,6 +4,8 @@
 	- basic info about the APM and ACPI support.
 basic-pm-debugging.txt
 	- Debugging suspend and resume
+charger-manager.txt
+	- Battery charger management.
 devices.txt
 	- How drivers interact with system-wide power management
 drivers-testing.txt
@@ -22,6 +24,8 @@
 	- info on Linux PM Quality of Service interface
 power_supply_class.txt
 	- Tells userspace about battery, UPS, AC or DC power supply properties
+runtime_pm.txt
+	- Power management framework for I/O devices.
 s2ram.txt
 	- How to get suspend to ram working (and debug it when it isn't)
 states.txt
@@ -38,7 +42,5 @@
 	- How to trick software suspend (to disk) into working when it isn't
 userland-swsusp.txt
 	- Experimental implementation of software suspend in userspace
-video_extension.txt
-	- ACPI video extensions
 video.txt
 	- Video issues during resume from suspend
diff --git a/Documentation/ptp/testptp.c b/Documentation/ptp/testptp.c
index a74d0a8..4aba043 100644
--- a/Documentation/ptp/testptp.c
+++ b/Documentation/ptp/testptp.c
@@ -117,6 +117,7 @@
 		" -f val     adjust the ptp clock frequency by 'val' ppb\n"
 		" -g         get the ptp clock time\n"
 		" -h         prints this message\n"
+		" -i val     index for event/trigger\n"
 		" -k val     measure the time offset between system and phc clock\n"
 		"            for 'val' times (Maximum 25)\n"
 		" -p val     enable output with a period of 'val' nanoseconds\n"
@@ -154,6 +155,7 @@
 	int capabilities = 0;
 	int extts = 0;
 	int gettime = 0;
+	int index = 0;
 	int oneshot = 0;
 	int pct_offset = 0;
 	int n_samples = 0;
@@ -167,7 +169,7 @@
 
 	progname = strrchr(argv[0], '/');
 	progname = progname ? 1+progname : argv[0];
-	while (EOF != (c = getopt(argc, argv, "a:A:cd:e:f:ghk:p:P:sSt:v"))) {
+	while (EOF != (c = getopt(argc, argv, "a:A:cd:e:f:ghi:k:p:P:sSt:v"))) {
 		switch (c) {
 		case 'a':
 			oneshot = atoi(optarg);
@@ -190,6 +192,9 @@
 		case 'g':
 			gettime = 1;
 			break;
+		case 'i':
+			index = atoi(optarg);
+			break;
 		case 'k':
 			pct_offset = 1;
 			n_samples = atoi(optarg);
@@ -301,7 +306,7 @@
 
 	if (extts) {
 		memset(&extts_request, 0, sizeof(extts_request));
-		extts_request.index = 0;
+		extts_request.index = index;
 		extts_request.flags = PTP_ENABLE_FEATURE;
 		if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) {
 			perror("PTP_EXTTS_REQUEST");
@@ -375,7 +380,7 @@
 			return -1;
 		}
 		memset(&perout_request, 0, sizeof(perout_request));
-		perout_request.index = 0;
+		perout_request.index = index;
 		perout_request.start.sec = ts.tv_sec + 2;
 		perout_request.start.nsec = 0;
 		perout_request.period.sec = 0;
diff --git a/Documentation/s390/00-INDEX b/Documentation/s390/00-INDEX
index 3a2b963..10c874e 100644
--- a/Documentation/s390/00-INDEX
+++ b/Documentation/s390/00-INDEX
@@ -16,11 +16,13 @@
 	- hints for debugging on s390 systems.
 driver-model.txt
 	- information on s390 devices and the driver model.
+kvm.txt
+	- ioctl calls to /dev/kvm on s390.
 monreader.txt
 	- information on accessing the z/VM monitor stream from Linux.
+qeth.txt
+	- HiperSockets Bridge Port Support.
 s390dbf.txt
 	- information on using the s390 debug feature.
-TAPE
-	- information on the driver for channel-attached tapes.
-zfcpdump
+zfcpdump.txt
 	- information on the s390 SCSI dump tool.
diff --git a/Documentation/scheduler/00-INDEX b/Documentation/scheduler/00-INDEX
index 46702e4..eccf7ad 100644
--- a/Documentation/scheduler/00-INDEX
+++ b/Documentation/scheduler/00-INDEX
@@ -2,6 +2,8 @@
 	- this file.
 sched-arch.txt
 	- CPU Scheduler implementation hints for architecture specific code.
+sched-bwc.txt
+	- CFS bandwidth control overview.
 sched-design-CFS.txt
 	- goals, design and implementation of the Completely Fair Scheduler.
 sched-domains.txt
diff --git a/Documentation/scsi/00-INDEX b/Documentation/scsi/00-INDEX
index 2044be5..c4b978a 100644
--- a/Documentation/scsi/00-INDEX
+++ b/Documentation/scsi/00-INDEX
@@ -36,6 +36,8 @@
 	- info on WorkBiT NinjaSCSI-32/32Bi driver
 aacraid.txt
 	- Driver supporting Adaptec RAID controllers
+advansys.txt
+	- List of Advansys Host Adapters
 aha152x.txt
 	- info on driver for Adaptec AHA152x based adapters
 aic79xx.txt
@@ -44,6 +46,12 @@
 	- info on driver for Adaptec controllers
 arcmsr_spec.txt
 	- ARECA FIRMWARE SPEC (for IOP331 adapter)
+bfa.txt
+	- Brocade FC/FCOE adapter driver.
+bnx2fc.txt
+	- FCoE hardware offload for Broadcom network interfaces.
+cxgb3i.txt
+	- Chelsio iSCSI Linux Driver
 dc395x.txt
 	- README file for the dc395x SCSI driver
 dpti.txt
@@ -52,18 +60,24 @@
 	- info on driver for DTC 2x80 based adapters
 g_NCR5380.txt
 	- info on driver for NCR5380 and NCR53c400 based adapters
+hpsa.txt
+	- HP Smart Array Controller SCSI driver.
 hptiop.txt
 	- HIGHPOINT ROCKETRAID 3xxx RAID DRIVER
 in2000.txt
 	- info on in2000 driver
 libsas.txt
 	- Serial Attached SCSI management layer.
+link_power_management_policy.txt
+	- Link power management options.
 lpfc.txt
 	- LPFC driver release notes
 megaraid.txt
 	- Common Management Module, shared code handling ioctls for LSI drivers
 ncr53c8xx.txt
 	- info on driver for NCR53c8xx based adapters
+osd.txt
+	Object-Based Storage Device, command set introduction.
 osst.txt
 	- info on driver for OnStream SC-x0 SCSI tape
 ppa.txt
@@ -74,6 +88,8 @@
 	- README for the SCSI media changer driver
 scsi-generic.txt
 	- info on the sg driver for generic (non-disk/CD/tape) SCSI devices.
+scsi-parameters.txt
+	- List of SCSI-parameters to pass to the kernel at module load-time.
 scsi.txt
 	- short blurb on using SCSI support as a module.
 scsi_mid_low_api.txt
diff --git a/Documentation/serial/00-INDEX b/Documentation/serial/00-INDEX
index 1f1b22f..f9c6b5e 100644
--- a/Documentation/serial/00-INDEX
+++ b/Documentation/serial/00-INDEX
@@ -4,10 +4,12 @@
 	- info on Cyclades-Z firmware loading.
 digiepca.txt
 	- info on Digi Intl. {PC,PCI,EISA}Xx and Xem series cards.
-hayes-esp.txt
-	- info on using the Hayes ESP serial driver.
+driver
+	- intro to the low level serial driver.
 moxa-smartio
 	- file with info on installing/using Moxa multiport serial driver.
+n_gsm.txt
+	- GSM 0710 tty multiplexer howto.
 riscom8.txt
 	- notes on using the RISCom/8 multi-port serial driver.
 rocket.txt
diff --git a/Documentation/spi/00-INDEX b/Documentation/spi/00-INDEX
new file mode 100644
index 0000000..a128fa8
--- /dev/null
+++ b/Documentation/spi/00-INDEX
@@ -0,0 +1,22 @@
+00-INDEX
+	- this file.
+Makefile
+	- Makefile for the example sourcefiles.
+butterfly
+	- AVR Butterfly SPI driver overview and pin configuration.
+ep93xx_spi
+	- Basic EP93xx SPI driver configuration.
+pxa2xx
+	- PXA2xx SPI master controller build by spi_message fifo wq
+spidev
+	- Intro to the userspace API for spi devices
+spidev_fdx.c
+	- spidev example file
+spi-lm70llp
+	- Connecting an LM70-LLP sensor to the kernel via the SPI subsys.
+spi-sc18is602
+	- NXP SC18IS602/603 I2C-bus to SPI bridge
+spi-summary
+	- (Linux) SPI overview. If unsure about SPI or SPI in Linux, start here.
+spidev_test.c
+	- SPI testing utility.
diff --git a/Documentation/spi/spi-summary b/Documentation/spi/spi-summary
index f72e0d1..7982bcc 100644
--- a/Documentation/spi/spi-summary
+++ b/Documentation/spi/spi-summary
@@ -543,7 +543,22 @@
 	queuing transfers that arrive in the meantime. When the driver is
 	finished with this message, it must call
 	spi_finalize_current_message() so the subsystem can issue the next
-	transfer. This may sleep.
+	message. This may sleep.
+
+    master->transfer_one(struct spi_master *master, struct spi_device *spi,
+			 struct spi_transfer *transfer)
+	The subsystem calls the driver to transfer a single transfer while
+	queuing transfers that arrive in the meantime. When the driver is
+	finished with this transfer, it must call
+	spi_finalize_current_transfer() so the subsystem can issue the next
+	transfer. This may sleep. Note: transfer_one and transfer_one_message
+	are mutually exclusive; when both are set, the generic subsystem does
+	not call your transfer_one callback.
+
+	Return values:
+	negative errno: error
+	0: transfer is finished
+	1: transfer is still in progress
 
     DEPRECATED METHODS
 
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index e1d28fb..ec8be46 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -442,8 +442,7 @@
 feature is too high then the rate the kernel samples for NUMA hinting
 faults may be controlled by the numa_balancing_scan_period_min_ms,
 numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms,
-numa_balancing_scan_size_mb, numa_balancing_settle_count sysctls and
-numa_balancing_migrate_deferred.
+numa_balancing_scan_size_mb, and numa_balancing_settle_count sysctls.
 
 ==============================================================
 
@@ -484,13 +483,6 @@
 numa_balancing_scan_size_mb is how many megabytes worth of pages are
 scanned for a given scan.
 
-numa_balancing_migrate_deferred is how many page migrations get skipped
-unconditionally, after a page migration is skipped because a page is shared
-with other tasks. This reduces page migration overhead, and determines
-how much stronger the "move task near its memory" policy scheduler becomes,
-versus the "move memory near its task" memory management policy, for workloads
-with shared memory.
-
 ==============================================================
 
 osrelease, ostype & version:
diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX
index ef2ccbf..6d042dc 100644
--- a/Documentation/timers/00-INDEX
+++ b/Documentation/timers/00-INDEX
@@ -8,6 +8,8 @@
 	- sample hpet timer test program
 hrtimers.txt
 	- subsystem for high-resolution kernel timers
+Makefile
+	- Build and link hpet_example
 NO_HZ.txt
 	- Summary of the different methods for the scheduler clock-interrupts management.
 timers-howto.txt
diff --git a/Documentation/virtual/kvm/00-INDEX b/Documentation/virtual/kvm/00-INDEX
index 641ec92..fee9f2b 100644
--- a/Documentation/virtual/kvm/00-INDEX
+++ b/Documentation/virtual/kvm/00-INDEX
@@ -20,5 +20,7 @@
 	- the paravirtualization interface on PowerPC.
 review-checklist.txt
 	- review checklist for KVM patches.
+s390-diag.txt
+	- Diagnose hypercall description (for IBM S/390)
 timekeeping.txt
 	- timekeeping virtualization for x86-based architectures.
diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
index a39d066..081c497 100644
--- a/Documentation/vm/00-INDEX
+++ b/Documentation/vm/00-INDEX
@@ -16,8 +16,6 @@
 	- explains what hwpoison is
 ksm.txt
 	- how to use the Kernel Samepage Merging feature.
-locking
-	- info on how locking and synchronization is done in the Linux vm code.
 numa
 	- information about NUMA specific code in the Linux vm.
 numa_memory_policy.txt
@@ -32,6 +30,8 @@
 	- a short users guide for SLUB.
 soft-dirty.txt
 	- short explanation for soft-dirty PTEs
+split_page_table_lock
+	- Separate per-table lock to improve scalability of the old page_table_lock.
 transhuge.txt
 	- Transparent Hugepage Support, alternative way of using hugepages.
 unevictable-lru.txt
diff --git a/Documentation/w1/masters/00-INDEX b/Documentation/w1/masters/00-INDEX
index d63fa02..8330cf9 100644
--- a/Documentation/w1/masters/00-INDEX
+++ b/Documentation/w1/masters/00-INDEX
@@ -4,7 +4,9 @@
 	- The Maxim/Dallas Semiconductor DS2482 provides 1-wire busses.
 ds2490
 	- The Maxim/Dallas Semiconductor DS2490 builds USB <-> W1 bridges.
-mxc_w1
+mxc-w1
 	- W1 master controller driver found on Freescale MX2/MX3 SoCs
+omap-hdq
+	- HDQ/1-wire module of TI OMAP 2430/3430.
 w1-gpio
 	- GPIO 1-wire bus master driver.
diff --git a/Documentation/w1/slaves/00-INDEX b/Documentation/w1/slaves/00-INDEX
index 75613c9..6e18c70 100644
--- a/Documentation/w1/slaves/00-INDEX
+++ b/Documentation/w1/slaves/00-INDEX
@@ -4,3 +4,5 @@
 	- The Maxim/Dallas Semiconductor ds18*20 temperature sensor.
 w1_ds2423
 	- The Maxim/Dallas Semiconductor ds2423 counter device.
+w1_ds28e04
+	- The Maxim/Dallas Semiconductor ds28e04 eeprom.
diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX
index f37b46d..6922644 100644
--- a/Documentation/x86/00-INDEX
+++ b/Documentation/x86/00-INDEX
@@ -1,6 +1,20 @@
 00-INDEX
 	- this file
-mtrr.txt
-	- how to use x86 Memory Type Range Registers to increase performance
+boot.txt
+	- List of boot protocol versions
+early-microcode.txt
+	- How to load microcode from an initrd-CPIO archive early to fix CPU issues.
+earlyprintk.txt
+	- Using earlyprintk with a USB2 debug port key.
+entry_64.txt
+	- Describe (some of the) kernel entry points for x86.
 exception-tables.txt
 	- why and how Linux kernel uses exception tables on x86
+mtrr.txt
+	- how to use x86 Memory Type Range Registers to increase performance
+pat.txt
+	- Page Attribute Table intro and API
+usb-legacy-support.txt
+	- how to fix/avoid quirks when using emulated PS/2 mouse/keyboard.
+zero-page.txt
+	- layout of the first page of memory.
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index cb81741d..a75e3ad 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -182,7 +182,7 @@
 0226/1	2.02+(3 ext_loader_ver	Extended boot loader version
 0227/1	2.02+(3	ext_loader_type	Extended boot loader ID
 0228/4	2.02+	cmd_line_ptr	32-bit pointer to the kernel command line
-022C/4	2.03+	ramdisk_max	Highest legal initrd address
+022C/4	2.03+	initrd_addr_max	Highest legal initrd address
 0230/4	2.05+	kernel_alignment Physical addr alignment required for kernel
 0234/1	2.05+	relocatable_kernel Whether kernel is relocatable or not
 0235/1	2.10+	min_alignment	Minimum alignment, as a power of two
@@ -534,7 +534,7 @@
   zero, the kernel will assume that your boot loader does not support
   the 2.02+ protocol.
 
-Field name:	ramdisk_max
+Field name:	initrd_addr_max
 Type:		read
 Offset/size:	0x22c/4
 Protocol:	2.03+
diff --git a/Documentation/zh_CN/arm64/booting.txt b/Documentation/zh_CN/arm64/booting.txt
index 28fa325..6f6d956 100644
--- a/Documentation/zh_CN/arm64/booting.txt
+++ b/Documentation/zh_CN/arm64/booting.txt
@@ -7,7 +7,7 @@
 or if there is a problem with the translation.
 
 Maintainer: Will Deacon <will.deacon@arm.com>
-Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
+Chinese maintainer: Fu Wei <wefu@redhat.com>
 ---------------------------------------------------------------------
 Documentation/arm64/booting.txt 的中文翻译
 
@@ -16,9 +16,9 @@
 译存在问题，请联系中文版维护者。
 
 英文版维护者： Will Deacon <will.deacon@arm.com>
-中文版维护者： 傅炜  Fu Wei <tekkamanninja@gmail.com>
-中文版翻译者： 傅炜  Fu Wei <tekkamanninja@gmail.com>
-中文版校译者： 傅炜  Fu Wei <tekkamanninja@gmail.com>
+中文版维护者： 傅炜  Fu Wei <wefu@redhat.com>
+中文版翻译者： 傅炜  Fu Wei <wefu@redhat.com>
+中文版校译者： 傅炜  Fu Wei <wefu@redhat.com>
 
 以下为正文
 ---------------------------------------------------------------------
@@ -64,8 +64,8 @@
 
 必要性: 强制
 
-设备树数据块（dtb）大小必须不大于 2 MB，且位于从内核映像起始算起第一个
-512MB 内的 2MB 边界上。这使得内核可以通过初始页表中的单个节描述符来
+设备树数据块（dtb）必须 8 字节对齐，并位于从内核映像起始算起第一个 512MB
+内，且不得跨越 2MB 对齐边界。这使得内核可以通过初始页表中的单个节描述符来
 映射此数据块。
 
 
@@ -84,13 +84,23 @@
 
 必要性: 强制
 
-已解压的内核映像包含一个 32 字节的头，内容如下：
+已解压的内核映像包含一个 64 字节的头，内容如下：
 
-  u32 magic	= 0x14000008;	/* 跳转到 stext, 小端 */
-  u32 res0	= 0;		/* 保留 */
+  u32 code0;			/* 可执行代码 */
+  u32 code1;			/* 可执行代码 */
   u64 text_offset;		/* 映像装载偏移 */
+  u64 res0	= 0;		/* 保留 */
   u64 res1	= 0;		/* 保留 */
   u64 res2	= 0;		/* 保留 */
+  u64 res3	= 0;		/* 保留 */
+  u64 res4	= 0;		/* 保留 */
+  u32 magic	= 0x644d5241;	/* 魔数, 小端, "ARM\x64" */
+  u32 res5 = 0;      		/* 保留 */
+
+
+映像头注释：
+
+- code0/code1 负责跳转到 stext.
 
 映像必须位于系统 RAM 起始处的特定偏移（当前是 0x80000）。系统 RAM
 的起始地址必须是以 2MB 对齐的。
@@ -118,9 +128,9 @@
   外部高速缓存（如果存在）必须配置并禁用。
 
 - 架构计时器
-  CNTFRQ 必须设定为计时器的频率。
-  如果在 EL1 模式下进入内核，则 CNTHCTL_EL2 中的 EL1PCTEN (bit 0)
-  必须置位。
+  CNTFRQ 必须设定为计时器的频率，且 CNTVOFF 必须设定为对所有 CPU
+  都一致的值。如果在 EL1 模式下进入内核，则 CNTHCTL_EL2 中的
+  EL1PCTEN (bit 0) 必须置位。
 
 - 一致性
   通过内核启动的所有 CPU 在内核入口地址上必须处于相同的一致性域中。
@@ -131,23 +141,40 @@
   在进入内核映像的异常级中，所有构架中可写的系统寄存器必须通过软件
   在一个更高的异常级别下初始化，以防止在 未知 状态下运行。
 
+以上对于 CPU 模式、高速缓存、MMU、架构计时器、一致性、系统寄存器的
+必要条件描述适用于所有 CPU。所有 CPU 必须在同一异常级别跳入内核。
+
 引导装载程序必须在每个 CPU 处于以下状态时跳入内核入口：
 
 - 主 CPU 必须直接跳入内核映像的第一条指令。通过此 CPU 传递的设备树
-  数据块必须在每个 CPU 节点中包含以下内容：
-
-    1、‘enable-method’属性。目前，此字段支持的值仅为字符串“spin-table”。
-
-    2、‘cpu-release-addr’标识一个 64-bit、初始化为零的内存位置。
+  数据块必须在每个 CPU 节点中包含一个 ‘enable-method’ 属性，所
+  支持的 enable-method 请见下文。
 
   引导装载程序必须生成这些设备树属性，并在跳入内核入口之前将其插入
   数据块。
 
-- 任何辅助 CPU 必须在内存保留区（通过设备树中的 /memreserve/ 域传递
+- enable-method 为 “spin-table” 的 CPU 必须在它们的 CPU
+  节点中包含一个 ‘cpu-release-addr’ 属性。这个属性标识了一个
+  64 位自然对齐且初始化为零的内存位置。
+
+  这些 CPU 必须在内存保留区（通过设备树中的 /memreserve/ 域传递
   给内核）中自旋于内核之外，轮询它们的 cpu-release-addr 位置（必须
   包含在保留区中）。可通过插入 wfe 指令来降低忙循环开销，而主 CPU 将
   发出 sev 指令。当对 cpu-release-addr 所指位置的读取操作返回非零值
-  时，CPU 必须直接跳入此值所指向的地址。
+  时，CPU 必须跳入此值所指向的地址。此值为一个单独的 64 位小端值，
+  因此 CPU 须在跳转前将所读取的值转换为其本身的端模式。
+
+- enable-method 为 “psci” 的 CPU 保持在内核外（比如，在
+  memory 节点中描述为内核空间的内存区外，或在通过设备树 /memreserve/
+  域中描述为内核保留区的空间中）。内核将会发起在 ARM 文档（编号
+  ARM DEN 0022A：用于 ARM 上的电源状态协调接口系统软件）中描述的
+  CPU_ON 调用来将 CPU 带入内核。
+
+  *译者注:到文档翻译时，此文档已更新为 ARM DEN 0022B。
+
+  设备树必须包含一个 ‘psci’ 节点，请参考以下文档：
+  Documentation/devicetree/bindings/arm/psci.txt
+
 
 - 辅助 CPU 通用寄存器设置
   x0 = 0 (保留，将来可能使用)
diff --git a/Documentation/zh_CN/arm64/memory.txt b/Documentation/zh_CN/arm64/memory.txt
index a5f6283..a782704 100644
--- a/Documentation/zh_CN/arm64/memory.txt
+++ b/Documentation/zh_CN/arm64/memory.txt
@@ -7,7 +7,7 @@
 or if there is a problem with the translation.
 
 Maintainer: Catalin Marinas <catalin.marinas@arm.com>
-Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
+Chinese maintainer: Fu Wei <wefu@redhat.com>
 ---------------------------------------------------------------------
 Documentation/arm64/memory.txt 的中文翻译
 
@@ -16,9 +16,9 @@
 译存在问题，请联系中文版维护者。
 
 英文版维护者： Catalin Marinas <catalin.marinas@arm.com>
-中文版维护者： 傅炜  Fu Wei <tekkamanninja@gmail.com>
-中文版翻译者： 傅炜  Fu Wei <tekkamanninja@gmail.com>
-中文版校译者： 傅炜  Fu Wei <tekkamanninja@gmail.com>
+中文版维护者： 傅炜  Fu Wei <wefu@redhat.com>
+中文版翻译者： 傅炜  Fu Wei <wefu@redhat.com>
+中文版校译者： 傅炜  Fu Wei <wefu@redhat.com>
 
 以下为正文
 ---------------------------------------------------------------------
@@ -41,7 +41,7 @@
 TTBR1 中，且从不写入 TTBR0。
 
 
-AArch64 Linux 内存布局：
+AArch64 Linux 在页大小为 4KB 时的内存布局：
 
 起始地址			结束地址			大小		用途
 -----------------------------------------------------------------------
@@ -55,15 +55,42 @@
 
 ffffffbe00000000	ffffffbffbbfffff	  ~8GB		[防护页，未来用于 vmmemap]
 
+ffffffbffbc00000	ffffffbffbdfffff	   2MB		earlyprintk 设备
+
 ffffffbffbe00000	ffffffbffbe0ffff	  64KB		PCI I/O 空间
 
-ffffffbbffff0000	ffffffbcffffffff	  ~2MB		[防护页]
+ffffffbffbe10000	ffffffbcffffffff	  ~2MB		[防护页]
 
 ffffffbffc000000	ffffffbfffffffff	  64MB		模块
 
 ffffffc000000000	ffffffffffffffff	 256GB		内核逻辑内存映射
 
 
+AArch64 Linux 在页大小为 64KB 时的内存布局：
+
+起始地址			结束地址			大小		用途
+-----------------------------------------------------------------------
+0000000000000000	000003ffffffffff	   4TB		用户空间
+
+fffffc0000000000	fffffdfbfffeffff	  ~2TB		vmalloc
+
+fffffdfbffff0000	fffffdfbffffffff	  64KB		[防护页]
+
+fffffdfc00000000	fffffdfdffffffff	   8GB		vmemmap
+
+fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[防护页，未来用于 vmmemap]
+
+fffffdfffbc00000	fffffdfffbdfffff	   2MB		earlyprintk 设备
+
+fffffdfffbe00000	fffffdfffbe0ffff	  64KB		PCI I/O 空间
+
+fffffdfffbe10000	fffffdfffbffffff	  ~2MB		[防护页]
+
+fffffdfffc000000	fffffdffffffffff	  64MB		模块
+
+fffffe0000000000	ffffffffffffffff	   2TB		内核逻辑内存映射
+
+
 4KB 页大小的转换表查找：
 
 +--------+--------+--------+--------+--------+--------+--------+--------+
@@ -91,3 +118,10 @@
  |                 |    +--------------------------> [41:29] L2 索引 (仅使用 38:29 )
  |                 +-------------------------------> [47:42] L1 索引 (未使用)
  +-------------------------------------------------> [63] TTBR0/1
+
+当使用 KVM 时, 管理程序（hypervisor）在 EL2 中通过相对内核虚拟地址的
+一个固定偏移来映射内核页（内核虚拟地址的高 24 位设为零）:
+
+起始地址			结束地址			大小		用途
+-----------------------------------------------------------------------
+0000004000000000	0000007fffffffff	 256GB		在 HYP 中映射的内核对象
diff --git a/Documentation/zh_CN/arm64/tagged-pointers.txt b/Documentation/zh_CN/arm64/tagged-pointers.txt
new file mode 100644
index 0000000..2664d1b
--- /dev/null
+++ b/Documentation/zh_CN/arm64/tagged-pointers.txt
@@ -0,0 +1,52 @@
+Chinese translated version of Documentation/arm64/tagged-pointers.txt
+
+If you have any comment or update to the content, please contact the
+original document maintainer directly.  However, if you have a problem
+communicating in English you can also ask the Chinese maintainer for
+help.  Contact the Chinese maintainer if this translation is outdated
+or if there is a problem with the translation.
+
+Maintainer: Will Deacon <will.deacon@arm.com>
+Chinese maintainer: Fu Wei <wefu@redhat.com>
+---------------------------------------------------------------------
+Documentation/arm64/tagged-pointers.txt 的中文翻译
+
+如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
+交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
+译存在问题，请联系中文版维护者。
+
+英文版维护者： Will Deacon <will.deacon@arm.com>
+中文版维护者： 傅炜  Fu Wei <wefu@redhat.com>
+中文版翻译者： 傅炜  Fu Wei <wefu@redhat.com>
+中文版校译者： 傅炜  Fu Wei <wefu@redhat.com>
+
+以下为正文
+---------------------------------------------------------------------
+		Linux 在 AArch64 中带标记的虚拟地址
+		=================================
+
+作者: Will Deacon <will.deacon@arm.com>
+日期: 2013 年 06 月 12 日
+
+本文档简述了在 AArch64 地址转换系统中提供的带标记的虚拟地址及其在
+AArch64 Linux 中的潜在用途。
+
+内核提供的地址转换表配置使通过 TTBR0 完成的虚拟地址转换（即用户空间
+映射），其虚拟地址的最高 8 位（63:56）会被转换硬件所忽略。这种机制
+让这些位可供应用程序自由使用，其注意事项如下：
+
+	(1) 内核要求所有传递到 EL1 的用户空间地址带有 0x00 标记。
+	    这意味着任何携带用户空间虚拟地址的系统调用（syscall）
+	    参数 *必须* 在陷入内核前使它们的最高字节被清零。
+
+	(2) 非零标记在传递信号时不被保存。这意味着在应用程序中利用了
+	    标记的信号处理函数无法依赖 siginfo_t 的用户空间虚拟
+	    地址所携带的包含其内部域信息的标记。此规则的一个例外是
+	    当信号是在调试观察点的异常处理程序中产生的，此时标记的
+	    信息将被保存。
+
+	(3) 当使用带标记的指针时需特别留心，因为仅对两个虚拟地址
+	    的高字节，C 编译器很可能无法判断它们是不同的。
+
+此构架会阻止对带标记的 PC 指针的利用，因此在异常返回时，其高字节
+将被设置成一个为 “55” 的扩展符。
diff --git a/MAINTAINERS b/MAINTAINERS
index dc2fd22..79031a5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -73,7 +73,8 @@
 	L: Mailing list that is relevant to this area
 	W: Web-page with status/info
 	Q: Patchwork web based patch tracking system site
-	T: SCM tree type and location.  Type is one of: git, hg, quilt, stgit, topgit.
+	T: SCM tree type and location.
+	   Type is one of: git, hg, quilt, stgit, topgit
 	S: Status, one of the following:
 	   Supported:	Someone is actually paid to look after this.
 	   Maintained:	Someone actually looks after it.
@@ -473,7 +474,7 @@
 
 AGPGART DRIVER
 M:	David Airlie <airlied@linux.ie>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6.git
+T:	git git://people.freedesktop.org/~airlied/linux (part of drm maint)
 S:	Maintained
 F:	drivers/char/agp/
 F:	include/linux/agp*
@@ -538,7 +539,7 @@
 ALTERA UART/JTAG UART SERIAL DRIVERS
 M:	Tobias Klauser <tklauser@distanz.ch>
 L:	linux-serial@vger.kernel.org
-L:	nios2-dev@sopc.et.ntust.edu.tw (moderated for non-subscribers)
+L:	nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/tty/serial/altera_uart.c
 F:	drivers/tty/serial/altera_jtaguart.c
@@ -868,14 +869,7 @@
 F:	drivers/clk/clk-prima2.c
 F:	drivers/clocksource/timer-prima2.c
 F:	drivers/clocksource/timer-marco.c
-F:	drivers/dma/sirf-dma.c
-F:	drivers/i2c/busses/i2c-sirf.c
-F:	drivers/input/misc/sirfsoc-onkey.c
-F:	drivers/irqchip/irq-sirfsoc.c
-F:	drivers/mmc/host/sdhci-sirf.c
-F:	drivers/pinctrl/sirf/
-F:	drivers/rtc/rtc-sirfsoc.c
-F:	drivers/spi/spi-sirf.c
+N:	[^a-z]sirf
 
 ARM/EBSA110 MACHINE SUPPORT
 M:	Russell King <linux@arm.linux.org.uk>
@@ -917,11 +911,11 @@
 F:	arch/arm/mach-footbridge/
 
 ARM/FREESCALE IMX / MXC ARM ARCHITECTURE
-M:	Shawn Guo <shawn.guo@linaro.org>
+M:	Shawn Guo <shawn.guo@freescale.com>
 M:	Sascha Hauer <kernel@pengutronix.de>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-T:	git git://git.linaro.org/people/shawnguo/linux-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
 F:	arch/arm/mach-imx/
 F:	arch/arm/boot/dts/imx*
 F:	arch/arm/configs/imx*_defconfig
@@ -1619,11 +1613,11 @@
 F:	drivers/net/wireless/atmel*
 
 ATTO EXPRESSSAS SAS/SATA RAID SCSI DRIVER
-M:      Bradley Grove <linuxdrivers@attotech.com>
-L:      linux-scsi@vger.kernel.org
-W:      http://www.attotech.com
-S:      Supported
-F:      drivers/scsi/esas2r
+M:	Bradley Grove <linuxdrivers@attotech.com>
+L:	linux-scsi@vger.kernel.org
+W:	http://www.attotech.com
+S:	Supported
+F:	drivers/scsi/esas2r
 
 AUDIT SUBSYSTEM
 M:	Eric Paris <eparis@redhat.com>
@@ -1744,6 +1738,7 @@
 BLACKFIN ARCHITECTURE
 M:	Steven Miao <realmz6@gmail.com>
 L:	adi-buildroot-devel@lists.sourceforge.net
+T:	git git://git.code.sf.net/p/adi-linux/code
 W:	http://blackfin.uclinux.org
 S:	Supported
 F:	arch/blackfin/
@@ -1837,8 +1832,8 @@
 F:	include/net/bluetooth/
 
 BONDING DRIVER
-M:	Jay Vosburgh <fubar@us.ibm.com>
-M:	Veaceslav Falico <vfalico@redhat.com>
+M:	Jay Vosburgh <j.vosburgh@gmail.com>
+M:	Veaceslav Falico <vfalico@gmail.com>
 M:	Andy Gospodarek <andy@greyhouse.net>
 L:	netdev@vger.kernel.org
 W:	http://sourceforge.net/projects/bonding/
@@ -1867,6 +1862,7 @@
 
 BROADCOM BCM281XX/BCM11XXX ARM ARCHITECTURE
 M:	Christian Daudt <bcm@fixthebug.org>
+M:	Matt Porter <mporter@linaro.org>
 L:	bcm-kernel-feedback-list@broadcom.com
 T:	git git://git.github.com/broadcom/bcm11351
 S:	Maintained
@@ -2165,7 +2161,7 @@
 
 CHIPIDEA USB HIGH SPEED DUAL ROLE CONTROLLER
 M:	Peter Chen <Peter.Chen@freescale.com>
-T:	git://github.com/hzpeterchen/linux-usb.git
+T:	git git://github.com/hzpeterchen/linux-usb.git
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/chipidea/
@@ -2185,9 +2181,9 @@
 F:	drivers/net/ethernet/cisco/enic/
 
 CISCO VIC LOW LATENCY NIC DRIVER
-M:      Upinder Malhi <umalhi@cisco.com>
-S:      Supported
-F:      drivers/infiniband/hw/usnic
+M:	Upinder Malhi <umalhi@cisco.com>
+S:	Supported
+F:	drivers/infiniband/hw/usnic
 
 CIRRUS LOGIC EP93XX ETHERNET DRIVER
 M:	Hartley Sweeten <hsweeten@visionengravers.com>
@@ -2374,7 +2370,7 @@
 
 CPU FREQUENCY DRIVERS - ARM BIG LITTLE
 M:	Viresh Kumar <viresh.kumar@linaro.org>
-M:	Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
+M:	Sudeep Holla <sudeep.holla@arm.com>
 L:	cpufreq@vger.kernel.org
 L:	linux-pm@vger.kernel.org
 W:	http://www.arm.com/products/processors/technologies/biglittleprocessing.php
@@ -2384,20 +2380,20 @@
 F:	drivers/cpufreq/arm_big_little_dt.c
 
 CPUIDLE DRIVER - ARM BIG LITTLE
-M:      Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
-M:      Daniel Lezcano <daniel.lezcano@linaro.org>
-L:      linux-pm@vger.kernel.org
-L:      linux-arm-kernel@lists.infradead.org
-T:      git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
-S:      Maintained
-F:      drivers/cpuidle/cpuidle-big_little.c
+M:	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+L:	linux-pm@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
+S:	Maintained
+F:	drivers/cpuidle/cpuidle-big_little.c
 
 CPUIDLE DRIVERS
 M:	Rafael J. Wysocki <rjw@rjwysocki.net>
 M:	Daniel Lezcano <daniel.lezcano@linaro.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
-T:	git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
 F:	drivers/cpuidle/*
 F:	include/linux/cpuidle.h
 
@@ -2415,8 +2411,10 @@
 
 CPUSETS
 M:	Li Zefan <lizefan@huawei.com>
+L:	cgroups@vger.kernel.org
 W:	http://www.bullopensource.org/cpuset/
 W:	http://oss.sgi.com/projects/cpusets/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
 S:	Maintained
 F:	Documentation/cgroups/cpusets.txt
 F:	include/linux/cpuset.h
@@ -2462,9 +2460,9 @@
 F:	sound/pci/cs5535audio/
 
 CW1200 WLAN driver
-M:     Solomon Peachy <pizza@shaftnet.org>
-S:     Maintained
-F:     drivers/net/wireless/cw1200/
+M:	Solomon Peachy <pizza@shaftnet.org>
+S:	Maintained
+F:	drivers/net/wireless/cw1200/
 
 CX18 VIDEO4LINUX DRIVER
 M:	Andy Walls <awalls@md.metrocast.net>
@@ -2615,9 +2613,9 @@
 M:	Oliver Neukum <oliver@neukum.org>
 M:	Ali Akcaagac <aliakc@web.de>
 M:	Jamie Lenehan <lenehan@twibble.org>
-W:	http://twibble.org/dist/dc395x/
 L:	dc395x@twibble.org
-L:	http://lists.twibble.org/mailman/listinfo/dc395x/
+W:	http://twibble.org/dist/dc395x/
+W:	http://lists.twibble.org/mailman/listinfo/dc395x/
 S:	Maintained
 F:	Documentation/scsi/dc395x.txt
 F:	drivers/scsi/dc395x.*
@@ -2803,9 +2801,9 @@
 F:	drivers/acpi/dock.c
 
 DOCUMENTATION
-M:	Rob Landley <rob@landley.net>
+M:	Randy Dunlap <rdunlap@infradead.org>
 L:	linux-doc@vger.kernel.org
-T:	TBD
+T:	quilt http://www.infradead.org/~rdunlap/Doc/patches/
 S:	Maintained
 F:	Documentation/
 
@@ -2852,19 +2850,29 @@
 DRM DRIVERS
 M:	David Airlie <airlied@linux.ie>
 L:	dri-devel@lists.freedesktop.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6.git
+T:	git git://people.freedesktop.org/~airlied/linux
 S:	Maintained
 F:	drivers/gpu/drm/
 F:	include/drm/
 F:	include/uapi/drm/
 
+RADEON DRM DRIVERS
+M:	Alex Deucher <alexander.deucher@amd.com>
+M:	Christian König <christian.koenig@amd.com>
+L:	dri-devel@lists.freedesktop.org
+T:	git git://people.freedesktop.org/~agd5f/linux
+S:	Supported
+F:	drivers/gpu/drm/radeon/
+F:	include/drm/radeon*
+F:	include/uapi/drm/radeon*
+
 INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets)
 M:	Daniel Vetter <daniel.vetter@ffwll.ch>
 M:	Jani Nikula <jani.nikula@linux.intel.com>
 L:	intel-gfx@lists.freedesktop.org
 L:	dri-devel@lists.freedesktop.org
 Q:	http://patchwork.freedesktop.org/project/intel-gfx/
-T:	git git://people.freedesktop.org/~danvet/drm-intel
+T:	git git://anongit.freedesktop.org/drm-intel
 S:	Supported
 F:	drivers/gpu/drm/i915/
 F:	include/drm/i915*
@@ -3089,6 +3097,8 @@
 
 EDAC-CORE
 M:	Doug Thompson <dougthompson@xmission.com>
+M:	Borislav Petkov <bp@alien8.de>
+M:	Mauro Carvalho Chehab <m.chehab@samsung.com>
 L:	linux-edac@vger.kernel.org
 W:	bluesmoke.sourceforge.net
 S:	Supported
@@ -3331,6 +3341,17 @@
 F:	include/linux/netfilter_bridge/
 F:	net/bridge/
 
+ETHERNET PHY LIBRARY
+M:	Florian Fainelli <f.fainelli@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	include/linux/phy.h
+F:	include/linux/phy_fixed.h
+F:	drivers/net/phy/
+F:	Documentation/networking/phy.txt
+F:	drivers/of/of_mdio.c
+F:	drivers/of/of_net.c
+
 EXT2 FILE SYSTEM
 M:	Jan Kara <jack@suse.cz>
 L:	linux-ext4@vger.kernel.org
@@ -4524,6 +4545,7 @@
 M:	Alex Duyck <alexander.h.duyck@intel.com>
 M:	John Ronciak <john.ronciak@intel.com>
 M:	Mitch Williams <mitch.a.williams@intel.com>
+M:	Linux NICS <linux.nics@intel.com>
 L:	e1000-devel@lists.sourceforge.net
 W:	http://www.intel.com/support/feedback.htm
 W:	http://e1000.sourceforge.net/
@@ -4541,6 +4563,7 @@
 F:	Documentation/networking/i40e.txt
 F:	Documentation/networking/i40evf.txt
 F:	drivers/net/ethernet/intel/
+F:	drivers/net/ethernet/intel/*/
 
 INTEL-MID GPIO DRIVER
 M:	David Cohen <david.a.cohen@linux.intel.com>
@@ -4897,7 +4920,7 @@
 KCONFIG
 M:	"Yann E. MORIN" <yann.morin.1998@free.fr>
 L:	linux-kbuild@vger.kernel.org
-T:	git://gitorious.org/linux-kconfig/linux-kconfig
+T:	git git://gitorious.org/linux-kconfig/linux-kconfig
 S:	Maintained
 F:	Documentation/kbuild/kconfig-language.txt
 F:	scripts/kconfig/
@@ -5454,11 +5477,11 @@
 F:	drivers/media/tuners/m88ts2022*
 
 MA901 MASTERKIT USB FM RADIO DRIVER
-M:      Alexey Klimov <klimov.linux@gmail.com>
-L:      linux-media@vger.kernel.org
-T:      git git://linuxtv.org/media_tree.git
-S:      Maintained
-F:      drivers/media/radio/radio-ma901.c
+M:	Alexey Klimov <klimov.linux@gmail.com>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	drivers/media/radio/radio-ma901.c
 
 MAC80211
 M:	Johannes Berg <johannes@sipsolutions.net>
@@ -5494,6 +5517,11 @@
 L:	linux-man@vger.kernel.org
 S:	Maintained
 
+MARVELL ARMADA DRM SUPPORT
+M:	Russell King <rmk+kernel@arm.linux.org.uk>
+S:	Maintained
+F:	drivers/gpu/drm/armada/
+
 MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
 M:	Mirko Lindner <mlindner@marvell.com>
 M:	Stephen Hemminger <stephen@networkplumber.org>
@@ -5614,7 +5642,7 @@
 
 MELLANOX ETHERNET DRIVER (mlx4_en)
 M:	Amir Vadai <amirv@mellanox.com>
-L: 	netdev@vger.kernel.org
+L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
@@ -5655,7 +5683,7 @@
 F:	include/uapi/mtd/
 
 MEN A21 WATCHDOG DRIVER
-M:  	Johannes Thumshirn <johannes.thumshirn@men.de>
+M:	Johannes Thumshirn <johannes.thumshirn@men.de>
 L:	linux-watchdog@vger.kernel.org
 S:	Supported
 F:	drivers/watchdog/mena21_wdt.c
@@ -5711,20 +5739,20 @@
 W:	http://www.mellanox.com
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
-T:	git://openfabrics.org/~eli/connect-ib.git
+T:	git git://openfabrics.org/~eli/connect-ib.git
 S:	Supported
 F:	drivers/net/ethernet/mellanox/mlx5/core/
 F:	include/linux/mlx5/
 
 Mellanox MLX5 IB driver
-M:      Eli Cohen <eli@mellanox.com>
-L:      linux-rdma@vger.kernel.org
-W:      http://www.mellanox.com
-Q:      http://patchwork.kernel.org/project/linux-rdma/list/
-T:      git://openfabrics.org/~eli/connect-ib.git
-S:      Supported
-F:      include/linux/mlx5/
-F:      drivers/infiniband/hw/mlx5/
+M:	Eli Cohen <eli@mellanox.com>
+L:	linux-rdma@vger.kernel.org
+W:	http://www.mellanox.com
+Q:	http://patchwork.kernel.org/project/linux-rdma/list/
+T:	git git://openfabrics.org/~eli/connect-ib.git
+S:	Supported
+F:	include/linux/mlx5/
+F:	drivers/infiniband/hw/mlx5/
 
 MODULE SUPPORT
 M:	Rusty Russell <rusty@rustcorp.com.au>
@@ -5976,6 +6004,9 @@
 F:	include/uapi/linux/in.h
 F:	include/uapi/linux/net.h
 F:	include/uapi/linux/netdevice.h
+F:	tools/net/
+F:	tools/testing/selftests/net/
+F:	lib/random32.c
 
 NETWORKING [IPv4/IPv6]
 M:	"David S. Miller" <davem@davemloft.net>
@@ -6149,6 +6180,12 @@
 F:	drivers/block/nvme*
 F:	include/linux/nvme.h
 
+NXP TDA998X DRM DRIVER
+M:	Russell King <rmk+kernel@arm.linux.org.uk>
+S:	Supported
+F:	drivers/gpu/drm/i2c/tda998x_drv.c
+F:	include/drm/i2c/tda998x.h
+
 OMAP SUPPORT
 M:	Tony Lindgren <tony@atomide.com>
 L:	linux-omap@vger.kernel.org
@@ -7203,7 +7240,7 @@
 F:	drivers/net/ethernet/rdc/r6040.c
 
 RDS - RELIABLE DATAGRAM SOCKETS
-M:	Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
+M:	Chien Yen <chien.yen@oracle.com>
 L:	rds-devel@oss.oracle.com (moderated for non-subscribers)
 S:	Supported
 F:	net/rds/
@@ -7368,10 +7405,26 @@
 S:	Supported
 F:	arch/s390/
 F:	drivers/s390/
-F:	block/partitions/ibm.c
 F:	Documentation/s390/
 F:	Documentation/DocBook/s390*
 
+S390 COMMON I/O LAYER
+M:	Sebastian Ott <sebott@linux.vnet.ibm.com>
+M:	Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+L:	linux-s390@vger.kernel.org
+W:	http://www.ibm.com/developerworks/linux/linux390/
+S:	Supported
+F:	drivers/s390/cio/
+
+S390 DASD DRIVER
+M:	Stefan Weinhuber <wein@de.ibm.com>
+M:	Stefan Haberland <stefan.haberland@de.ibm.com>
+L:	linux-s390@vger.kernel.org
+W:	http://www.ibm.com/developerworks/linux/linux390/
+S:	Supported
+F:	drivers/s390/block/dasd*
+F:	block/partitions/ibm.c
+
 S390 NETWORK DRIVERS
 M:	Ursula Braun <ursula.braun@de.ibm.com>
 M:	Frank Blaschka <blaschka@linux.vnet.ibm.com>
@@ -7381,6 +7434,15 @@
 S:	Supported
 F:	drivers/s390/net/
 
+S390 PCI SUBSYSTEM
+M:	Sebastian Ott <sebott@linux.vnet.ibm.com>
+M:	Gerald Schaefer <gerald.schaefer@de.ibm.com>
+L:	linux-s390@vger.kernel.org
+W:	http://www.ibm.com/developerworks/linux/linux390/
+S:	Supported
+F:	arch/s390/pci/
+F:	drivers/pci/hotplug/s390_pci_hpc.c
+
 S390 ZCRYPT DRIVER
 M:	Ingo Tuchscherer <ingo.tuchscherer@de.ibm.com>
 M:	linux390@de.ibm.com
@@ -8436,8 +8498,8 @@
 M:	Nicholas A. Bellinger <nab@linux-iscsi.org>
 L:	linux-scsi@vger.kernel.org
 L:	target-devel@vger.kernel.org
-L:	http://groups.google.com/group/linux-iscsi-target-dev
 W:	http://www.linux-iscsi.org
+W:	http://groups.google.com/group/linux-iscsi-target-dev
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git master
 S:	Supported
 F:	drivers/target/
@@ -8678,17 +8740,17 @@
 F:	drivers/media/radio/radio-raremono.c
 
 THERMAL
-M:      Zhang Rui <rui.zhang@intel.com>
-M:      Eduardo Valentin <eduardo.valentin@ti.com>
-L:      linux-pm@vger.kernel.org
-T:      git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git
-T:      git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git
-Q:      https://patchwork.kernel.org/project/linux-pm/list/
-S:      Supported
-F:      drivers/thermal/
-F:      include/linux/thermal.h
-F:      include/linux/cpu_cooling.h
-F:      Documentation/devicetree/bindings/thermal/
+M:	Zhang Rui <rui.zhang@intel.com>
+M:	Eduardo Valentin <eduardo.valentin@ti.com>
+L:	linux-pm@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git
+Q:	https://patchwork.kernel.org/project/linux-pm/list/
+S:	Supported
+F:	drivers/thermal/
+F:	include/linux/thermal.h
+F:	include/linux/cpu_cooling.h
+F:	Documentation/devicetree/bindings/thermal/
 
 THINGM BLINK(1) USB RGB LED DRIVER
 M:	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
@@ -9722,7 +9784,6 @@
 XFS FILESYSTEM
 P:	Silicon Graphics Inc
 M:	Dave Chinner <david@fromorbit.com>
-M:	Ben Myers <bpm@sgi.com>
 M:	xfs@oss.sgi.com
 L:	xfs@oss.sgi.com
 W:	http://oss.sgi.com/projects/xfs
@@ -9791,7 +9852,7 @@
 L:	mjpeg-users@lists.sourceforge.net
 L:	linux-media@vger.kernel.org
 W:	http://mjpeg.sourceforge.net/driver-zoran/
-T:	Mercurial http://linuxtv.org/hg/v4l-dvb
+T:	hg http://linuxtv.org/hg/v4l-dvb
 S:	Odd Fixes
 F:	drivers/media/pci/zoran/
 
diff --git a/Makefile b/Makefile
index 4231023..e5ac8a6 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 VERSION = 3
-PATCHLEVEL = 13
+PATCHLEVEL = 14
 SUBLEVEL = 0
 EXTRAVERSION =
-NAME = One Giant Leap for Frogkind
+NAME = Shuffling Zombie Juror
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
@@ -605,10 +605,11 @@
 ifdef CONFIG_CC_STACKPROTECTOR_REGULAR
   stackp-flag := -fstack-protector
   ifeq ($(call cc-option, $(stackp-flag)),)
-    $(warning Cannot use CONFIG_CC_STACKPROTECTOR: \
-	      -fstack-protector not supported by compiler))
+    $(warning Cannot use CONFIG_CC_STACKPROTECTOR_REGULAR: \
+             -fstack-protector not supported by compiler)
   endif
-else ifdef CONFIG_CC_STACKPROTECTOR_STRONG
+else
+ifdef CONFIG_CC_STACKPROTECTOR_STRONG
   stackp-flag := -fstack-protector-strong
   ifeq ($(call cc-option, $(stackp-flag)),)
     $(warning Cannot use CONFIG_CC_STACKPROTECTOR_STRONG: \
@@ -618,6 +619,7 @@
   # Force off for distro compilers that enable stack protector by default.
   stackp-flag := $(call cc-option, -fno-stack-protector)
 endif
+endif
 KBUILD_CFLAGS += $(stackp-flag)
 
 # This warning generated too much noise in a regular build.
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index 6b58c1d..400c663 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -282,7 +282,7 @@
 #else
 	/* if V-P const for loop, PTAG can be written once outside loop */
 	if (full_page_op)
-		write_aux_reg(ARC_REG_DC_PTAG, paddr);
+		write_aux_reg(aux_tag, paddr);
 #endif
 
 	while (num_lines-- > 0) {
@@ -296,7 +296,7 @@
 		write_aux_reg(aux_cmd, vaddr);
 		vaddr += L1_CACHE_BYTES;
 #else
-		write_aux_reg(aux, paddr);
+		write_aux_reg(aux_cmd, paddr);
 		paddr += L1_CACHE_BYTES;
 #endif
 	}
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e254198..1594945 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1578,6 +1578,7 @@
 
 choice
 	prompt "Memory split"
+	depends on MMU
 	default VMSPLIT_3G
 	help
 	  Select the desired split between kernel and user memory.
@@ -1595,6 +1596,7 @@
 
 config PAGE_OFFSET
 	hex
+	default PHYS_OFFSET if !MMU
 	default 0x40000000 if VMSPLIT_1G
 	default 0x80000000 if VMSPLIT_2G
 	default 0xC0000000
@@ -1903,6 +1905,7 @@
 	depends on ARM && AEABI && OF
 	depends on CPU_V7 && !CPU_V6
 	depends on !GENERIC_ATOMIC64
+	depends on MMU
 	select ARM_PSCI
 	select SWIOTLB_XEN
 	select ARCH_DMA_ADDR_T_64BIT
diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore
index 47279aa..0714e03 100644
--- a/arch/arm/boot/compressed/.gitignore
+++ b/arch/arm/boot/compressed/.gitignore
@@ -1,4 +1,5 @@
 ashldi3.S
+bswapsdi2.S
 font.c
 lib1funcs.S
 hyp-stub.S
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index b9d6a8b..0320303 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -38,6 +38,7 @@
 dtb-$(CONFIG_ARCH_AT91) += at91sam9x25ek.dtb
 dtb-$(CONFIG_ARCH_AT91) += at91sam9x35ek.dtb
 # sama5d3
+dtb-$(CONFIG_ARCH_AT91)	+= at91-sama5d3_xplained.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d31ek.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d33ek.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d34ek.dtb
@@ -208,7 +209,8 @@
 	omap3-n900.dtb \
 	omap3-n9.dtb \
 	omap3-n950.dtb \
-	omap3-tobi.dtb \
+	omap3-overo-tobi.dtb \
+	omap3-overo-storm-tobi.dtb \
 	omap3-gta04.dtb \
 	omap3-igep0020.dtb \
 	omap3-igep0030.dtb \
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 4718ec4..486880b 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -121,7 +121,7 @@
 		ti,model = "AM335x-EVMSK";
 		ti,audio-codec = <&tlv320aic3106>;
 		ti,mcasp-controller = <&mcasp1>;
-		ti,codec-clock-rate = <24576000>;
+		ti,codec-clock-rate = <24000000>;
 		ti,audio-routing =
 			"Headphone Jack",       "HPLOUT",
 			"Headphone Jack",       "HPROUT";
@@ -256,6 +256,12 @@
 		>;
 	};
 
+	mmc1_pins: pinmux_mmc1_pins {
+		pinctrl-single,pins = <
+			0x160 (PIN_INPUT | MUX_MODE7) /* spi0_cs1.gpio0_6 */
+		>;
+	};
+
 	mcasp1_pins: mcasp1_pins {
 		pinctrl-single,pins = <
 			0x10c (PIN_INPUT_PULLDOWN | MUX_MODE4) /* mii1_crs.mcasp1_aclkx */
@@ -456,6 +462,9 @@
 	status = "okay";
 	vmmc-supply = <&vmmc_reg>;
 	bus-width = <4>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins>;
+	cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>;
 };
 
 &sham {
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 6660968..9480cf8 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -23,6 +23,7 @@
 		gpio0 = &gpio0;
 		gpio1 = &gpio1;
 		gpio2 = &gpio2;
+		eth3 = &eth3;
 	};
 
 	cpus {
@@ -291,7 +292,7 @@
 				interrupts = <91>;
 			};
 
-			ethernet@34000 {
+			eth3: ethernet@34000 {
 				compatible = "marvell,armada-370-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
new file mode 100644
index 0000000..ce13755
--- /dev/null
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -0,0 +1,229 @@
+/*
+ * at91-sama5d3_xplained.dts - Device Tree file for the SAMA5D3 Xplained board
+ *
+ *  Copyright (C) 2014 Atmel,
+ *		  2014 Nicolas Ferre <nicolas.ferre@atmel.com>
+ *
+ * Licensed under GPLv2 or later.
+ */
+/dts-v1/;
+#include "sama5d36.dtsi"
+
+/ {
+	model = "SAMA5D3 Xplained";
+	compatible = "atmel,sama5d3-xplained", "atmel,sama5d3", "atmel,sama5";
+
+	chosen {
+		bootargs = "console=ttyS0,115200";
+	};
+
+	memory {
+		reg = <0x20000000 0x10000000>;
+	};
+
+	ahb {
+		apb {
+			mmc0: mmc@f0000000 {
+				pinctrl-0 = <&pinctrl_mmc0_clk_cmd_dat0 &pinctrl_mmc0_dat1_3 &pinctrl_mmc0_dat4_7 &pinctrl_mmc0_cd>;
+				status = "okay";
+				slot@0 {
+					reg = <0>;
+					bus-width = <8>;
+					cd-gpios = <&pioE 0 GPIO_ACTIVE_LOW>;
+				};
+			};
+
+			spi0: spi@f0004000 {
+				cs-gpios = <&pioD 13 0>;
+				status = "okay";
+			};
+
+			can0: can@f000c000 {
+				status = "okay";
+			};
+
+			i2c0: i2c@f0014000 {
+				status = "okay";
+			};
+
+			i2c1: i2c@f0018000 {
+				status = "okay";
+			};
+
+			macb0: ethernet@f0028000 {
+				phy-mode = "rgmii";
+				status = "okay";
+			};
+
+			usart0: serial@f001c000 {
+				status = "okay";
+			};
+
+			usart1: serial@f0020000 {
+				pinctrl-0 = <&pinctrl_usart1 &pinctrl_usart1_rts_cts>;
+				status = "okay";
+			};
+
+			uart0: serial@f0024000 {
+				status = "okay";
+			};
+
+			mmc1: mmc@f8000000 {
+				pinctrl-0 = <&pinctrl_mmc1_clk_cmd_dat0 &pinctrl_mmc1_dat1_3 &pinctrl_mmc1_cd>;
+				status = "okay";
+				slot@0 {
+					reg = <0>;
+					bus-width = <4>;
+					cd-gpios = <&pioE 1 GPIO_ACTIVE_HIGH>;
+				};
+			};
+
+			spi1: spi@f8008000 {
+				cs-gpios = <&pioC 25 0>, <0>, <0>, <&pioD 16 0>;
+				status = "okay";
+			};
+
+			adc0: adc@f8018000 {
+				pinctrl-0 = <
+					&pinctrl_adc0_adtrg
+					&pinctrl_adc0_ad0
+					&pinctrl_adc0_ad1
+					&pinctrl_adc0_ad2
+					&pinctrl_adc0_ad3
+					&pinctrl_adc0_ad4
+					&pinctrl_adc0_ad5
+					&pinctrl_adc0_ad6
+					&pinctrl_adc0_ad7
+					&pinctrl_adc0_ad8
+					&pinctrl_adc0_ad9
+					>;
+				status = "okay";
+			};
+
+			i2c2: i2c@f801c000 {
+				dmas = <0>, <0>;	/* Do not use DMA for i2c2 */
+				status = "okay";
+			};
+
+			macb1: ethernet@f802c000 {
+				phy-mode = "rmii";
+				status = "okay";
+			};
+
+			dbgu: serial@ffffee00 {
+				status = "okay";
+			};
+
+			pinctrl@fffff200 {
+				board {
+					pinctrl_mmc0_cd: mmc0_cd {
+						atmel,pins =
+							<AT91_PIOE 0 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
+
+					pinctrl_mmc1_cd: mmc1_cd {
+						atmel,pins =
+							<AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
+
+					pinctrl_usba_vbus: usba_vbus {
+						atmel,pins =
+							<AT91_PIOE 9 AT91_PERIPH_GPIO AT91_PINCTRL_DEGLITCH>;	/* PE9, conflicts with A9 */
+					};
+				};
+			};
+
+			pmc: pmc@fffffc00 {
+				main: mainck {
+					clock-frequency = <12000000>;
+				};
+			};
+		};
+
+		nand0: nand@60000000 {
+			nand-bus-width = <8>;
+			nand-ecc-mode = "hw";
+			atmel,has-pmecc;
+			atmel,pmecc-cap = <4>;
+			atmel,pmecc-sector-size = <512>;
+			nand-on-flash-bbt;
+			status = "okay";
+
+			at91bootstrap@0 {
+				label = "at91bootstrap";
+				reg = <0x0 0x40000>;
+			};
+
+			bootloader@40000 {
+				label = "bootloader";
+				reg = <0x40000 0x80000>;
+			};
+
+			bootloaderenv@c0000 {
+				label = "bootloader env";
+				reg = <0xc0000 0xc0000>;
+			};
+
+			dtb@180000 {
+				label = "device tree";
+				reg = <0x180000 0x80000>;
+			};
+
+			kernel@200000 {
+				label = "kernel";
+				reg = <0x200000 0x600000>;
+			};
+
+			rootfs@800000 {
+				label = "rootfs";
+				reg = <0x800000 0x0f800000>;
+			};
+		};
+
+		usb0: gadget@00500000 {
+			atmel,vbus-gpio = <&pioE 9 GPIO_ACTIVE_HIGH>;	/* PE9, conflicts with A9 */
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usba_vbus>;
+			status = "okay";
+		};
+
+		usb1: ohci@00600000 {
+			num-ports = <3>;
+			atmel,vbus-gpio = <0
+					   &pioE 3 GPIO_ACTIVE_LOW
+					   &pioE 4 GPIO_ACTIVE_LOW
+					  >;
+			status = "okay";
+		};
+
+		usb2: ehci@00700000 {
+			status = "okay";
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+
+		bp3 {
+			label = "PB_USER";
+			gpios = <&pioE 29 GPIO_ACTIVE_LOW>;
+			linux,code = <0x104>;
+			gpio-key,wakeup;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		d2 {
+			label = "d2";
+			gpios = <&pioE 23 GPIO_ACTIVE_LOW>;	/* PE23, conflicts with A23, CTS2 */
+			linux,default-trigger = "heartbeat";
+		};
+
+		d3 {
+			label = "d3";
+			gpios = <&pioE 24 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index 0042f73..fece866 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -523,7 +523,7 @@
 			};
 
 			i2c0: i2c@fff88000 {
-				compatible = "atmel,at91sam9263-i2c";
+				compatible = "atmel,at91sam9260-i2c";
 				reg = <0xfff88000 0x100>;
 				interrupts = <13 IRQ_TYPE_LEVEL_HIGH 6>;
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index e9487f6..924a6a6 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -124,6 +124,10 @@
 			nand-on-flash-bbt;
 			status = "okay";
 		};
+
+		usb0: ohci@00500000 {
+			status = "okay";
+		};
 	};
 
 	leds {
diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi
index e491b82..792fde1 100644
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@@ -147,7 +147,7 @@
 	};
 
 	pinctrl@35004800 {
-		compatible = "brcm,capri-pinctrl";
+		compatible = "brcm,bcm11351-pinctrl";
 		reg = <0x35004800 0x430>;
 	};
 
diff --git a/arch/arm/boot/dts/bcm28155-ap.dts b/arch/arm/boot/dts/bcm28155-ap.dts
index c7fa9fb..5ff2382 100644
--- a/arch/arm/boot/dts/bcm28155-ap.dts
+++ b/arch/arm/boot/dts/bcm28155-ap.dts
@@ -13,6 +13,8 @@
 
 /dts-v1/;
 
+#include <dt-bindings/gpio/gpio.h>
+
 #include "bcm11351.dtsi"
 
 / {
@@ -60,7 +62,7 @@
 
 	sdio4: sdio@3f1b0000 {
 		max-frequency = <48000000>;
-		cd-gpios = <&gpio 14 0>;
+		cd-gpios = <&gpio 14 GPIO_ACTIVE_LOW>;
 		status = "okay";
 	};
 
diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi
index 2b76524..187fd46 100644
--- a/arch/arm/boot/dts/dove.dtsi
+++ b/arch/arm/boot/dts/dove.dtsi
@@ -379,15 +379,6 @@
 				#clock-cells = <1>;
 			};
 
-			pmu_intc: pmu-interrupt-ctrl@d0050 {
-				compatible = "marvell,dove-pmu-intc";
-				interrupt-controller;
-				#interrupt-cells = <1>;
-				reg = <0xd0050 0x8>;
-				interrupts = <33>;
-				marvell,#interrupts = <7>;
-			};
-
 			pinctrl: pin-ctrl@d0200 {
 				compatible = "marvell,dove-pinctrl";
 				reg = <0xd0200 0x10>;
@@ -610,8 +601,6 @@
 			rtc: real-time-clock@d8500 {
 				compatible = "marvell,orion-rtc";
 				reg = <0xd8500 0x20>;
-				interrupt-parent = <&pmu_intc>;
-				interrupts = <5>;
 			};
 
 			gpio2: gpio-ctrl@e8400 {
diff --git a/arch/arm/boot/dts/imx6dl-hummingboard.dts b/arch/arm/boot/dts/imx6dl-hummingboard.dts
index fd8fc7c..5bfae54 100644
--- a/arch/arm/boot/dts/imx6dl-hummingboard.dts
+++ b/arch/arm/boot/dts/imx6dl-hummingboard.dts
@@ -52,12 +52,6 @@
 		};
 	};
 
-	codec: spdif-transmitter {
-		compatible = "linux,spdif-dit";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_hummingboard_spdif>;
-	};
-
 	sound-spdif {
 		compatible = "fsl,imx-audio-spdif";
 		model = "imx-spdif";
@@ -111,7 +105,7 @@
 		};
 
 		pinctrl_hummingboard_spdif: hummingboard-spdif {
-			fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x1b0b0>;
+			fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x13091>;
 		};
 
 		pinctrl_hummingboard_usbh1_vbus: hummingboard-usbh1-vbus {
@@ -142,6 +136,8 @@
 };
 
 &spdif {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard_spdif>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
index 64daa3b..c2a2488 100644
--- a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
@@ -46,12 +46,6 @@
 		};
 	};
 
-	codec: spdif-transmitter {
-		compatible = "linux,spdif-dit";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_cubox_i_spdif>;
-	};
-
 	sound-spdif {
 		compatible = "fsl,imx-audio-spdif";
 		model = "imx-spdif";
@@ -89,7 +83,7 @@
 		};
 
 		pinctrl_cubox_i_spdif: cubox-i-spdif {
-			fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x1b0b0>;
+			fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x13091>;
 		};
 
 		pinctrl_cubox_i_usbh1_vbus: cubox-i-usbh1-vbus {
@@ -121,6 +115,8 @@
 };
 
 &spdif {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_cubox_i_spdif>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/keystone-clocks.dtsi b/arch/arm/boot/dts/keystone-clocks.dtsi
index 2363593..ef58d1c 100644
--- a/arch/arm/boot/dts/keystone-clocks.dtsi
+++ b/arch/arm/boot/dts/keystone-clocks.dtsi
@@ -612,7 +612,7 @@
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
 		clock-output-names = "vcp-3";
-		reg = <0x0235000a8 0xb00>, <0x02350060 0x400>;
+		reg = <0x023500a8 0xb00>, <0x02350060 0x400>;
 		reg-names = "control", "domain";
 		domain-id = <24>;
 	};
diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts
index b9b55c9..d3b253b 100644
--- a/arch/arm/boot/dts/omap3-gta04.dts
+++ b/arch/arm/boot/dts/omap3-gta04.dts
@@ -13,7 +13,7 @@
 
 / {
 	model = "OMAP3 GTA04";
-	compatible = "ti,omap3-gta04", "ti,omap3";
+	compatible = "ti,omap3-gta04", "ti,omap36xx", "ti,omap3";
 
 	cpus {
 		cpu@0 {
@@ -32,7 +32,7 @@
 		aux-button {
 			label = "aux";
 			linux,code = <169>;
-			gpios = <&gpio1 7 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
 			gpio-key,wakeup;
 		};
 	};
@@ -92,6 +92,8 @@
 	bmp085@77 {
 		compatible = "bosch,bmp085";
 		reg = <0x77>;
+		interrupt-parent = <&gpio4>;
+		interrupts = <17 IRQ_TYPE_EDGE_RISING>;
 	};
 
 	/* leds */
@@ -141,8 +143,8 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc1_pins>;
 	vmmc-supply = <&vmmc1>;
-	vmmc_aux-supply = <&vsim>;
 	bus-width = <4>;
+	ti,non-removable;
 };
 
 &mmc2 {
diff --git a/arch/arm/boot/dts/omap3-igep0020.dts b/arch/arm/boot/dts/omap3-igep0020.dts
index 25a2b5f..f2779ac 100644
--- a/arch/arm/boot/dts/omap3-igep0020.dts
+++ b/arch/arm/boot/dts/omap3-igep0020.dts
@@ -14,7 +14,7 @@
 
 / {
 	model = "IGEPv2 (TI OMAP AM/DM37x)";
-	compatible = "isee,omap3-igep0020", "ti,omap3";
+	compatible = "isee,omap3-igep0020", "ti,omap36xx", "ti,omap3";
 
 	leds {
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/omap3-igep0030.dts b/arch/arm/boot/dts/omap3-igep0030.dts
index 145c58c..2793749 100644
--- a/arch/arm/boot/dts/omap3-igep0030.dts
+++ b/arch/arm/boot/dts/omap3-igep0030.dts
@@ -13,7 +13,7 @@
 
 / {
 	model = "IGEP COM MODULE (TI OMAP AM/DM37x)";
-	compatible = "isee,omap3-igep0030", "ti,omap3";
+	compatible = "isee,omap3-igep0030", "ti,omap36xx", "ti,omap3";
 
 	leds {
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/omap3-n9.dts b/arch/arm/boot/dts/omap3-n9.dts
index 39828ce..9938b5d 100644
--- a/arch/arm/boot/dts/omap3-n9.dts
+++ b/arch/arm/boot/dts/omap3-n9.dts
@@ -14,5 +14,5 @@
 
 / {
 	model = "Nokia N9";
-	compatible = "nokia,omap3-n9", "ti,omap3";
+	compatible = "nokia,omap3-n9", "ti,omap36xx", "ti,omap3";
 };
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 6fc85f9..0bf40c9 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2013 Pavel Machek <pavel@ucw.cz>
- * Copyright 2013 Aaro Koskinen <aaro.koskinen@iki.fi>
+ * Copyright (C) 2013-2014 Aaro Koskinen <aaro.koskinen@iki.fi>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 (or later) as
@@ -13,7 +13,7 @@
 
 / {
 	model = "Nokia N900";
-	compatible = "nokia,omap3-n900", "ti,omap3";
+	compatible = "nokia,omap3-n900", "ti,omap3430", "ti,omap3";
 
 	cpus {
 		cpu@0 {
diff --git a/arch/arm/boot/dts/omap3-n950.dts b/arch/arm/boot/dts/omap3-n950.dts
index b076a52..261c558 100644
--- a/arch/arm/boot/dts/omap3-n950.dts
+++ b/arch/arm/boot/dts/omap3-n950.dts
@@ -14,5 +14,5 @@
 
 / {
 	model = "Nokia N950";
-	compatible = "nokia,omap3-n950", "ti,omap3";
+	compatible = "nokia,omap3-n950", "ti,omap36xx", "ti,omap3";
 };
diff --git a/arch/arm/boot/dts/omap3-overo-storm-tobi.dts b/arch/arm/boot/dts/omap3-overo-storm-tobi.dts
new file mode 100644
index 0000000..966b5c9
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-storm-tobi.dts
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2012 Florian Vaussard, EPFL Mobots group
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Tobi expansion board is manufactured by Gumstix Inc.
+ */
+
+/dts-v1/;
+
+#include "omap36xx.dtsi"
+#include "omap3-overo-tobi-common.dtsi"
+
+/ {
+	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Tobi";
+	compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+};
+
diff --git a/arch/arm/boot/dts/omap3-tobi.dts b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
similarity index 93%
rename from arch/arm/boot/dts/omap3-tobi.dts
rename to arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
index 7e4ad2a..4edc013 100644
--- a/arch/arm/boot/dts/omap3-tobi.dts
+++ b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
@@ -13,9 +13,6 @@
 #include "omap3-overo.dtsi"
 
 / {
-	model = "TI OMAP3 Gumstix Overo on Tobi";
-	compatible = "ti,omap3-tobi", "ti,omap3-overo", "ti,omap3";
-
 	leds {
 		compatible = "gpio-leds";
 		heartbeat {
diff --git a/arch/arm/boot/dts/omap3-overo-tobi.dts b/arch/arm/boot/dts/omap3-overo-tobi.dts
new file mode 100644
index 0000000..de5653e
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-tobi.dts
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2012 Florian Vaussard, EPFL Mobots group
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Tobi expansion board is manufactured by Gumstix Inc.
+ */
+
+/dts-v1/;
+
+#include "omap34xx.dtsi"
+#include "omap3-overo-tobi-common.dtsi"
+
+/ {
+	model = "OMAP35xx Gumstix Overo on Tobi";
+	compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap3430", "ti,omap3";
+};
+
diff --git a/arch/arm/boot/dts/omap3-overo.dtsi b/arch/arm/boot/dts/omap3-overo.dtsi
index a461d2f..5970999 100644
--- a/arch/arm/boot/dts/omap3-overo.dtsi
+++ b/arch/arm/boot/dts/omap3-overo.dtsi
@@ -9,9 +9,6 @@
 /*
  * The Gumstix Overo must be combined with an expansion board.
  */
-/dts-v1/;
-
-#include "omap34xx.dtsi"
 
 / {
 	pwmleds {
diff --git a/arch/arm/boot/dts/qcom-msm8660-surf.dts b/arch/arm/boot/dts/qcom-msm8660-surf.dts
index 1187185..68a72f5 100644
--- a/arch/arm/boot/dts/qcom-msm8660-surf.dts
+++ b/arch/arm/boot/dts/qcom-msm8660-surf.dts
@@ -2,6 +2,8 @@
 
 /include/ "skeleton.dtsi"
 
+#include <dt-bindings/clock/qcom,gcc-msm8660.h>
+
 / {
 	model = "Qualcomm MSM8660 SURF";
 	compatible = "qcom,msm8660-surf", "qcom,msm8660";
@@ -37,11 +39,20 @@
 		#interrupt-cells = <2>;
 	};
 
+	gcc: clock-controller@900000 {
+		compatible = "qcom,gcc-msm8660";
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+		reg = <0x900000 0x4000>;
+	};
+
 	serial@19c40000 {
 		compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 		reg = <0x19c40000 0x1000>,
 		      <0x19c00000 0x1000>;
 		interrupts = <0 195 0x0>;
+		clocks = <&gcc GSBI12_UART_CLK>, <&gcc GSBI12_H_CLK>;
+		clock-names = "core", "iface";
 	};
 
 	qcom,ssbi@500000 {
diff --git a/arch/arm/boot/dts/qcom-msm8960-cdp.dts b/arch/arm/boot/dts/qcom-msm8960-cdp.dts
index 6ccbac7..7c30de4 100644
--- a/arch/arm/boot/dts/qcom-msm8960-cdp.dts
+++ b/arch/arm/boot/dts/qcom-msm8960-cdp.dts
@@ -2,6 +2,8 @@
 
 /include/ "skeleton.dtsi"
 
+#include <dt-bindings/clock/qcom,gcc-msm8960.h>
+
 / {
 	model = "Qualcomm MSM8960 CDP";
 	compatible = "qcom,msm8960-cdp", "qcom,msm8960";
@@ -37,11 +39,27 @@
 		reg = <0x800000 0x4000>;
 	};
 
+	gcc: clock-controller@900000 {
+		compatible = "qcom,gcc-msm8960";
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+		reg = <0x900000 0x4000>;
+	};
+
+	clock-controller@4000000 {
+		compatible = "qcom,mmcc-msm8960";
+		reg = <0x4000000 0x1000>;
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
 	serial@16440000 {
 		compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 		reg = <0x16440000 0x1000>,
 		      <0x16400000 0x1000>;
 		interrupts = <0 154 0x0>;
+		clocks = <&gcc GSBI5_UART_CLK>, <&gcc GSBI5_H_CLK>;
+		clock-names = "core", "iface";
 	};
 
 	qcom,ssbi@500000 {
diff --git a/arch/arm/boot/dts/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom-msm8974.dtsi
index 6ac9496..9e5dadb 100644
--- a/arch/arm/boot/dts/qcom-msm8974.dtsi
+++ b/arch/arm/boot/dts/qcom-msm8974.dtsi
@@ -2,6 +2,8 @@
 
 #include "skeleton.dtsi"
 
+#include <dt-bindings/clock/qcom,gcc-msm8974.h>
+
 / {
 	model = "Qualcomm MSM8974";
 	compatible = "qcom,msm8974";
@@ -93,5 +95,27 @@
 			compatible = "qcom,pshold";
 			reg = <0xfc4ab000 0x4>;
 		};
+
+		gcc: clock-controller@fc400000 {
+			compatible = "qcom,gcc-msm8974";
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			reg = <0xfc400000 0x4000>;
+		};
+
+		mmcc: clock-controller@fd8c0000 {
+			compatible = "qcom,mmcc-msm8974";
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			reg = <0xfd8c0000 0x6000>;
+		};
+
+		serial@f991e000 {
+			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
+			reg = <0xf991e000 0x1000>;
+			interrupts = <0 108 0x0>;
+			clocks = <&gcc GCC_BLSP1_UART2_APPS_CLK>, <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index f48487c..71b1251 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -197,7 +197,7 @@
 		reg = <0 0xe6508000 0 0x40>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 287 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&mstp3_clks R8A7790_CLK_I2C0>;
+		clocks = <&mstp9_clks R8A7790_CLK_I2C0>;
 		status = "disabled";
 	};
 
@@ -208,7 +208,7 @@
 		reg = <0 0xe6518000 0 0x40>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 288 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&mstp3_clks R8A7790_CLK_I2C1>;
+		clocks = <&mstp9_clks R8A7790_CLK_I2C1>;
 		status = "disabled";
 	};
 
@@ -219,7 +219,7 @@
 		reg = <0 0xe6530000 0 0x40>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 286 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&mstp3_clks R8A7790_CLK_I2C2>;
+		clocks = <&mstp9_clks R8A7790_CLK_I2C2>;
 		status = "disabled";
 	};
 
@@ -230,7 +230,7 @@
 		reg = <0 0xe6540000 0 0x40>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 290 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&mstp3_clks R8A7790_CLK_I2C3>;
+		clocks = <&mstp9_clks R8A7790_CLK_I2C3>;
 		status = "disabled";
 	};
 
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 52447c1..3d5faf8 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -1228,7 +1228,7 @@
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00600000 0x100000>;
 			interrupts = <32 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>,
+			clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>,
 				 <&uhpck>;
 			clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck";
 			status = "disabled";
diff --git a/arch/arm/boot/dts/sama5d36.dtsi b/arch/arm/boot/dts/sama5d36.dtsi
index 6c31c26..db58cad 100644
--- a/arch/arm/boot/dts/sama5d36.dtsi
+++ b/arch/arm/boot/dts/sama5d36.dtsi
@@ -8,8 +8,8 @@
  */
 #include "sama5d3.dtsi"
 #include "sama5d3_can.dtsi"
-#include "sama5d3_emac.dtsi"
 #include "sama5d3_gmac.dtsi"
+#include "sama5d3_emac.dtsi"
 #include "sama5d3_lcd.dtsi"
 #include "sama5d3_mci2.dtsi"
 #include "sama5d3_tcb1.dtsi"
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index 0c1e8d8..6cb9b68 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -188,7 +188,6 @@
 		msp2: msp@80117000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&msp2_default_mode>;
-			status = "okay";
 		};
 
 		msp3: msp@80125000 {
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 040bb0e..d4d2763 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -315,7 +315,7 @@
 		ranges;
 
 		emac: ethernet@01c0b000 {
-			compatible = "allwinner,sun4i-emac";
+			compatible = "allwinner,sun4i-a10-emac";
 			reg = <0x01c0b000 0x1000>;
 			interrupts = <55>;
 			clocks = <&ahb_gates 17>;
@@ -323,7 +323,7 @@
 		};
 
 		mdio@01c0b080 {
-			compatible = "allwinner,sun4i-mdio";
+			compatible = "allwinner,sun4i-a10-mdio";
 			reg = <0x01c0b080 0x14>;
 			status = "disabled";
 			#address-cells = <1>;
@@ -426,7 +426,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <29>;
 		};
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index ea16054..79fd412 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -278,7 +278,7 @@
 		ranges;
 
 		emac: ethernet@01c0b000 {
-			compatible = "allwinner,sun4i-emac";
+			compatible = "allwinner,sun4i-a10-emac";
 			reg = <0x01c0b000 0x1000>;
 			interrupts = <55>;
 			clocks = <&ahb_gates 17>;
@@ -286,7 +286,7 @@
 		};
 
 		mdio@01c0b080 {
-			compatible = "allwinner,sun4i-mdio";
+			compatible = "allwinner,sun4i-a10-mdio";
 			reg = <0x01c0b080 0x14>;
 			status = "disabled";
 			#address-cells = <1>;
@@ -383,7 +383,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <29>;
 		};
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index 320335a..c463fd7 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -346,7 +346,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <29>;
 		};
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 119f066..6f25cf5 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -340,7 +340,7 @@
 		ranges;
 
 		emac: ethernet@01c0b000 {
-			compatible = "allwinner,sun4i-emac";
+			compatible = "allwinner,sun4i-a10-emac";
 			reg = <0x01c0b000 0x1000>;
 			interrupts = <0 55 4>;
 			clocks = <&ahb_gates 17>;
@@ -348,7 +348,7 @@
 		};
 
 		mdio@01c0b080 {
-			compatible = "allwinner,sun4i-mdio";
+			compatible = "allwinner,sun4i-a10-mdio";
 			reg = <0x01c0b080 0x14>;
 			status = "disabled";
 			#address-cells = <1>;
@@ -454,7 +454,7 @@
 		rtc: rtc@01c20d00 {
 			compatible = "allwinner,sun7i-a20-rtc";
 			reg = <0x01c20d00 0x20>;
-			interrupts = <0 24 1>;
+			interrupts = <0 24 4>;
 		};
 
 		sid: eeprom@01c23800 {
@@ -463,7 +463,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <0 29 4>;
 		};
@@ -596,10 +596,10 @@
 		hstimer@01c60000 {
 			compatible = "allwinner,sun7i-a20-hstimer";
 			reg = <0x01c60000 0x1000>;
-			interrupts = <0 81 1>,
-				     <0 82 1>,
-				     <0 83 1>,
-				     <0 84 1>;
+			interrupts = <0 81 4>,
+				     <0 82 4>,
+				     <0 83 4>,
+				     <0 84 4>;
 			clocks = <&ahb_gates 28>;
 		};
 
diff --git a/arch/arm/boot/dts/tegra114.dtsi b/arch/arm/boot/dts/tegra114.dtsi
index 389e987..44ec401 100644
--- a/arch/arm/boot/dts/tegra114.dtsi
+++ b/arch/arm/boot/dts/tegra114.dtsi
@@ -57,6 +57,8 @@
 			resets = <&tegra_car 27>;
 			reset-names = "dc";
 
+			nvidia,head = <0>;
+
 			rgb {
 				status = "disabled";
 			};
@@ -72,6 +74,8 @@
 			resets = <&tegra_car 26>;
 			reset-names = "dc";
 
+			nvidia,head = <1>;
+
 			rgb {
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index 480ecda..48d2a7f 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -94,6 +94,8 @@
 			resets = <&tegra_car 27>;
 			reset-names = "dc";
 
+			nvidia,head = <0>;
+
 			rgb {
 				status = "disabled";
 			};
@@ -109,6 +111,8 @@
 			resets = <&tegra_car 26>;
 			reset-names = "dc";
 
+			nvidia,head = <1>;
+
 			rgb {
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/tegra30-cardhu.dtsi b/arch/arm/boot/dts/tegra30-cardhu.dtsi
index 9104224..1e156d9 100644
--- a/arch/arm/boot/dts/tegra30-cardhu.dtsi
+++ b/arch/arm/boot/dts/tegra30-cardhu.dtsi
@@ -28,7 +28,7 @@
 	compatible = "nvidia,cardhu", "nvidia,tegra30";
 
 	aliases {
-		rtc0 = "/i2c@7000d000/tps6586x@34";
+		rtc0 = "/i2c@7000d000/tps65911@2d";
 		rtc1 = "/rtc@7000e000";
 	};
 
diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi
index ed8e770..19a84e9 100644
--- a/arch/arm/boot/dts/tegra30.dtsi
+++ b/arch/arm/boot/dts/tegra30.dtsi
@@ -170,6 +170,8 @@
 			resets = <&tegra_car 27>;
 			reset-names = "dc";
 
+			nvidia,head = <0>;
+
 			rgb {
 				status = "disabled";
 			};
@@ -185,6 +187,8 @@
 			resets = <&tegra_car 26>;
 			reset-names = "dc";
 
+			nvidia,head = <1>;
+
 			rgb {
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/testcases/tests.dtsi b/arch/arm/boot/dts/testcases/tests.dtsi
deleted file mode 100644
index 3f123ec..0000000
--- a/arch/arm/boot/dts/testcases/tests.dtsi
+++ /dev/null
@@ -1,2 +0,0 @@
-/include/ "tests-phandle.dtsi"
-/include/ "tests-interrupts.dtsi"
diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts
index f43907c..65f6577 100644
--- a/arch/arm/boot/dts/versatile-pb.dts
+++ b/arch/arm/boot/dts/versatile-pb.dts
@@ -1,4 +1,4 @@
-/include/ "versatile-ab.dts"
+#include <versatile-ab.dts>
 
 / {
 	model = "ARM Versatile PB";
@@ -47,4 +47,4 @@
 	};
 };
 
-/include/ "testcases/tests.dtsi"
+#include <testcases.dtsi>
diff --git a/arch/arm/boot/dts/zynq-7000.dtsi b/arch/arm/boot/dts/zynq-7000.dtsi
index 5d7681b..8b67b19 100644
--- a/arch/arm/boot/dts/zynq-7000.dtsi
+++ b/arch/arm/boot/dts/zynq-7000.dtsi
@@ -102,6 +102,26 @@
 			clock-names = "pclk", "hclk", "tx_clk";
 		};
 
+		sdhci0: ps7-sdhci@e0100000 {
+			compatible = "arasan,sdhci-8.9a";
+			status = "disabled";
+			clock-names = "clk_xin", "clk_ahb";
+			clocks = <&clkc 21>, <&clkc 32>;
+			interrupt-parent = <&intc>;
+			interrupts = <0 24 4>;
+			reg = <0xe0100000 0x1000>;
+		} ;
+
+		sdhci1: ps7-sdhci@e0101000 {
+			compatible = "arasan,sdhci-8.9a";
+			status = "disabled";
+			clock-names = "clk_xin", "clk_ahb";
+			clocks = <&clkc 22>, <&clkc 33>;
+			interrupt-parent = <&intc>;
+			interrupts = <0 47 4>;
+			reg = <0xe0101000 0x1000>;
+		} ;
+
 		slcr: slcr@f8000000 {
 			compatible = "xlnx,zynq-slcr";
 			reg = <0xF8000000 0x1000>;
diff --git a/arch/arm/boot/dts/zynq-zc702.dts b/arch/arm/boot/dts/zynq-zc702.dts
index 34d680a..c913f77 100644
--- a/arch/arm/boot/dts/zynq-zc702.dts
+++ b/arch/arm/boot/dts/zynq-zc702.dts
@@ -34,6 +34,10 @@
 	phy-mode = "rgmii";
 };
 
+&sdhci0 {
+	status = "okay";
+};
+
 &uart1 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/zynq-zc706.dts b/arch/arm/boot/dts/zynq-zc706.dts
index b2835d5..88f62c5 100644
--- a/arch/arm/boot/dts/zynq-zc706.dts
+++ b/arch/arm/boot/dts/zynq-zc706.dts
@@ -35,6 +35,10 @@
 	phy-mode = "rgmii";
 };
 
+&sdhci0 {
+	status = "okay";
+};
+
 &uart1 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/zynq-zed.dts b/arch/arm/boot/dts/zynq-zed.dts
index 2eda068..82d7ef1 100644
--- a/arch/arm/boot/dts/zynq-zed.dts
+++ b/arch/arm/boot/dts/zynq-zed.dts
@@ -35,6 +35,10 @@
 	phy-mode = "rgmii";
 };
 
+&sdhci0 {
+	status = "okay";
+};
+
 &uart1 {
 	status = "okay";
 };
diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig
index a018244..4582e16 100644
--- a/arch/arm/configs/keystone_defconfig
+++ b/arch/arm/configs/keystone_defconfig
@@ -142,6 +142,7 @@
 CONFIG_USB_DWC3_VERBOSE=y
 CONFIG_KEYSTONE_USB_PHY=y
 CONFIG_DMADEVICES=y
+CONFIG_TI_EDMA=y
 CONFIG_COMMON_CLK_DEBUG=y
 CONFIG_MEMORY=y
 CONFIG_EXT4_FS=y
diff --git a/arch/arm/configs/msm_defconfig b/arch/arm/configs/msm_defconfig
index 0219c65..c5858b9 100644
--- a/arch/arm/configs/msm_defconfig
+++ b/arch/arm/configs/msm_defconfig
@@ -114,6 +114,10 @@
 CONFIG_NEW_LEDS=y
 CONFIG_RTC_CLASS=y
 CONFIG_STAGING=y
+CONFIG_COMMON_CLK_QCOM=y
+CONFIG_MSM_GCC_8660=y
+CONFIG_MSM_MMCC_8960=y
+CONFIG_MSM_MMCC_8974=y
 CONFIG_MSM_IOMMU=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 687e4e8..ee69829 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -1,7 +1,12 @@
+CONFIG_SYSVIPC=y
 CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_EMBEDDED=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
 CONFIG_ARCH_MVEBU=y
 CONFIG_MACH_ARMADA_370=y
 CONFIG_MACH_ARMADA_XP=y
@@ -24,6 +29,7 @@
 CONFIG_ARCH_OMAP4=y
 CONFIG_SOC_OMAP5=y
 CONFIG_SOC_AM33XX=y
+CONFIG_SOC_DRA7XX=y
 CONFIG_SOC_AM43XX=y
 CONFIG_ARCH_ROCKCHIP=y
 CONFIG_ARCH_SOCFPGA=y
@@ -38,7 +44,7 @@
 CONFIG_ARCH_TEGRA_2x_SOC=y
 CONFIG_ARCH_TEGRA_3x_SOC=y
 CONFIG_ARCH_TEGRA_114_SOC=y
-CONFIG_TEGRA_PCI=y
+CONFIG_ARCH_TEGRA_124_SOC=y
 CONFIG_TEGRA_EMC_SCALING_ENABLE=y
 CONFIG_ARCH_U8500=y
 CONFIG_MACH_HREFV60=y
@@ -49,19 +55,55 @@
 CONFIG_ARCH_VIRT=y
 CONFIG_ARCH_WM8850=y
 CONFIG_ARCH_ZYNQ=y
+CONFIG_TRUSTED_FOUNDATIONS=y
+CONFIG_PCI=y
+CONFIG_PCI_MSI=y
+CONFIG_PCI_MVEBU=y
+CONFIG_PCI_TEGRA=y
 CONFIG_SMP=y
 CONFIG_HIGHPTE=y
+CONFIG_CMA=y
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
+CONFIG_KEXEC=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_STAT_DETAILS=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
+CONFIG_CPU_IDLE=y
 CONFIG_NET=y
+CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_INET6_AH=m
+CONFIG_INET6_ESP=m
+CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_MIP6=m
+CONFIG_IPV6_TUNNEL=m
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_CFG80211=m
+CONFIG_MAC80211=m
+CONFIG_RFKILL=y
+CONFIG_RFKILL_INPUT=y
+CONFIG_RFKILL_GPIO=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DMA_CMA=y
 CONFIG_OMAP_OCP2SCP=y
+CONFIG_MTD=y
+CONFIG_MTD_M25P80=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_ICS932S401=y
+CONFIG_APDS9802ALS=y
+CONFIG_ISL29003=y
 CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_SCSI_MULTI_LUN=y
 CONFIG_ATA=y
 CONFIG_SATA_AHCI_PLATFORM=y
 CONFIG_SATA_HIGHBANK=y
@@ -69,13 +111,30 @@
 CONFIG_NETDEVICES=y
 CONFIG_SUN4I_EMAC=y
 CONFIG_NET_CALXEDA_XGMAC=y
+CONFIG_MVNETA=y
 CONFIG_KS8851=y
+CONFIG_R8169=y
 CONFIG_SMSC911X=y
 CONFIG_STMMAC_ETH=y
-CONFIG_ICPLUS_PHY=y
-CONFIG_MDIO_SUN4I=y
 CONFIG_TI_CPSW=y
+CONFIG_AT803X_PHY=y
+CONFIG_MARVELL_PHY=y
+CONFIG_ICPLUS_PHY=y
+CONFIG_USB_PEGASUS=y
+CONFIG_USB_USBNET=y
+CONFIG_USB_NET_SMSC75XX=y
+CONFIG_USB_NET_SMSC95XX=y
+CONFIG_BRCMFMAC=m
+CONFIG_RT2X00=m
+CONFIG_RT2800USB=m
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
+CONFIG_KEYBOARD_TEGRA=y
 CONFIG_KEYBOARD_SPEAR=y
+CONFIG_KEYBOARD_CROS_EC=y
+CONFIG_MOUSE_PS2_ELANTECH=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_MPU3050=y
 CONFIG_SERIO_AMBAKMI=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
@@ -98,30 +157,81 @@
 CONFIG_SERIAL_FSL_LPUART_CONSOLE=y
 CONFIG_SERIAL_ST_ASC=y
 CONFIG_SERIAL_ST_ASC_CONSOLE=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_MUX=y
+CONFIG_I2C_MUX_PINCTRL=y
 CONFIG_I2C_DESIGNWARE_PLATFORM=y
+CONFIG_I2C_MV64XXX=y
 CONFIG_I2C_SIRF=y
 CONFIG_I2C_TEGRA=y
 CONFIG_SPI=y
 CONFIG_SPI_OMAP24XX=y
+CONFIG_SPI_ORION=y
 CONFIG_SPI_PL022=y
 CONFIG_SPI_SIRF=y
 CONFIG_SPI_TEGRA114=y
+CONFIG_SPI_TEGRA20_SFLASH=y
 CONFIG_SPI_TEGRA20_SLINK=y
-CONFIG_PINCTRL_SINGLE=y
+CONFIG_PINCTRL_AS3722=y
+CONFIG_PINCTRL_PALMAS=y
+CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_GENERIC_PLATFORM=y
+CONFIG_GPIO_PCA953X_IRQ=y
 CONFIG_GPIO_TWL4030=y
-CONFIG_REGULATOR_GPIO=y
+CONFIG_GPIO_PALMAS=y
+CONFIG_GPIO_TPS6586X=y
+CONFIG_GPIO_TPS65910=y
+CONFIG_BATTERY_SBS=y
+CONFIG_CHARGER_TPS65090=y
+CONFIG_POWER_RESET_AS3722=y
+CONFIG_POWER_RESET_GPIO=y
+CONFIG_SENSORS_LM90=y
+CONFIG_THERMAL=y
+CONFIG_ARMADA_THERMAL=y
+CONFIG_MFD_AS3722=y
+CONFIG_MFD_CROS_EC=y
+CONFIG_MFD_CROS_EC_SPI=y
+CONFIG_MFD_MAX8907=y
+CONFIG_MFD_PALMAS=y
+CONFIG_MFD_TPS65090=y
+CONFIG_MFD_TPS6586X=y
+CONFIG_MFD_TPS65910=y
+CONFIG_REGULATOR_VIRTUAL_CONSUMER=y
 CONFIG_REGULATOR_AB8500=y
+CONFIG_REGULATOR_AS3722=y
+CONFIG_REGULATOR_GPIO=y
+CONFIG_REGULATOR_MAX8907=y
+CONFIG_REGULATOR_PALMAS=y
 CONFIG_REGULATOR_TPS51632=y
 CONFIG_REGULATOR_TPS62360=y
+CONFIG_REGULATOR_TPS65090=y
+CONFIG_REGULATOR_TPS6586X=y
+CONFIG_REGULATOR_TPS65910=y
 CONFIG_REGULATOR_TWL4030=y
 CONFIG_REGULATOR_VEXPRESS=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_MEDIA_USB_SUPPORT=y
 CONFIG_DRM=y
-CONFIG_TEGRA_HOST1X=y
 CONFIG_DRM_TEGRA=y
+CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_FB_ARMCLCD=y
 CONFIG_FB_WM8505=y
 CONFIG_FB_SIMPLE=y
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
+CONFIG_BACKLIGHT_PWM=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_SOC=y
+CONFIG_SND_SOC_TEGRA=y
+CONFIG_SND_SOC_TEGRA_RT5640=y
+CONFIG_SND_SOC_TEGRA_WM8753=y
+CONFIG_SND_SOC_TEGRA_WM8903=y
+CONFIG_SND_SOC_TEGRA_TRIMSLICE=y
+CONFIG_SND_SOC_TEGRA_ALC5632=y
+CONFIG_SND_SOC_TEGRA_MAX98090=y
 CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
@@ -132,8 +242,6 @@
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_HOST=y
 CONFIG_AB8500_USB=y
-CONFIG_NOP_USB_XCEIV=y
-CONFIG_OMAP_USB2=y
 CONFIG_OMAP_USB3=y
 CONFIG_SAMSUNG_USB2PHY=y
 CONFIG_SAMSUNG_USB3PHY=y
@@ -144,24 +252,32 @@
 CONFIG_MMC_BLOCK_MINORS=16
 CONFIG_MMC_ARMMMCI=y
 CONFIG_MMC_SDHCI=y
-CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_ESDHC_IMX=y
 CONFIG_MMC_SDHCI_TEGRA=y
 CONFIG_MMC_SDHCI_SPEAR=y
 CONFIG_MMC_SDHCI_BCM_KONA=y
 CONFIG_MMC_OMAP=y
 CONFIG_MMC_OMAP_HS=y
+CONFIG_MMC_MVSDIO=y
 CONFIG_EDAC=y
 CONFIG_EDAC_MM_EDAC=y
 CONFIG_EDAC_HIGHBANK_MC=y
 CONFIG_EDAC_HIGHBANK_L2=y
 CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_AS3722=y
+CONFIG_RTC_DRV_MAX8907=y
+CONFIG_RTC_DRV_PALMAS=y
 CONFIG_RTC_DRV_TWL4030=y
+CONFIG_RTC_DRV_TPS6586X=y
+CONFIG_RTC_DRV_TPS65910=y
+CONFIG_RTC_DRV_EM3027=y
 CONFIG_RTC_DRV_PL031=y
 CONFIG_RTC_DRV_VT8500=y
+CONFIG_RTC_DRV_MV=y
 CONFIG_RTC_DRV_TEGRA=y
 CONFIG_DMADEVICES=y
 CONFIG_DW_DMAC=y
+CONFIG_MV_XOR=y
 CONFIG_TEGRA20_APB_DMA=y
 CONFIG_STE_DMA40=y
 CONFIG_SIRF_DMA=y
@@ -171,15 +287,34 @@
 CONFIG_IMX_DMA=y
 CONFIG_MXS_DMA=y
 CONFIG_DMA_OMAP=y
+CONFIG_STAGING=y
+CONFIG_SENSORS_ISL29018=y
+CONFIG_SENSORS_ISL29028=y
+CONFIG_MFD_NVEC=y
+CONFIG_KEYBOARD_NVEC=y
+CONFIG_SERIO_NVEC_PS2=y
+CONFIG_NVEC_POWER=y
+CONFIG_TEGRA_IOMMU_GART=y
+CONFIG_TEGRA_IOMMU_SMMU=y
+CONFIG_MEMORY=y
+CONFIG_IIO=y
+CONFIG_AK8975=y
 CONFIG_PWM=y
+CONFIG_PWM_TEGRA=y
 CONFIG_PWM_VT8500=y
+CONFIG_OMAP_USB2=y
 CONFIG_EXT4_FS=y
+CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
+CONFIG_SQUASHFS=y
+CONFIG_SQUASHFS_LZO=y
+CONFIG_SQUASHFS_XZ=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
+CONFIG_MAGIC_SYSRQ=y
 CONFIG_LOCKUP_DETECTOR=y
+CONFIG_CRYPTO_DEV_TEGRA_AES=y
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 5fdc9a0..27d69b5 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -29,11 +29,11 @@
 CONFIG_ARCH_TEGRA_114_SOC=y
 CONFIG_ARCH_TEGRA_124_SOC=y
 CONFIG_TEGRA_EMC_SCALING_ENABLE=y
+CONFIG_TRUSTED_FOUNDATIONS=y
 CONFIG_PCI=y
 CONFIG_PCI_MSI=y
 CONFIG_PCI_TEGRA=y
 CONFIG_PCIEPORTBUS=y
-CONFIG_TRUSTED_FOUNDATIONS=y
 CONFIG_SMP=y
 CONFIG_PREEMPT=y
 CONFIG_AEABI=y
@@ -125,7 +125,6 @@
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_I2C_COMPAT is not set
-CONFIG_I2C_MUX=y
 CONFIG_I2C_MUX_PINCTRL=y
 CONFIG_I2C_TEGRA=y
 CONFIG_SPI=y
@@ -169,9 +168,8 @@
 CONFIG_MEDIA_USB_SUPPORT=y
 CONFIG_USB_VIDEO_CLASS=m
 CONFIG_DRM=y
-CONFIG_DRM_PANEL=y
-CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_DRM_TEGRA=y
+CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
@@ -235,7 +233,6 @@
 CONFIG_SERIO_NVEC_PS2=y
 CONFIG_NVEC_POWER=y
 CONFIG_NVEC_PAZ00=y
-CONFIG_COMMON_CLK_DEBUG=y
 CONFIG_TEGRA_IOMMU_GART=y
 CONFIG_TEGRA_IOMMU_SMMU=y
 CONFIG_MEMORY=y
@@ -265,6 +262,7 @@
 CONFIG_NLS_ISO8859_1=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_SLAB=y
 CONFIG_DEBUG_VM=y
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index e9a49fe..8b8b616 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -212,6 +212,7 @@
 static inline void __flush_icache_all(void)
 {
 	__flush_icache_preferred();
+	dsb();
 }
 
 /*
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 8756e4b..4afb376 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -30,14 +30,15 @@
  */
 #define UL(x) _AC(x, UL)
 
+/* PAGE_OFFSET - the virtual address of the start of the kernel image */
+#define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
+
 #ifdef CONFIG_MMU
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
  */
-#define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
 #define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M))
 #define TASK_UNMAPPED_BASE	ALIGN(TASK_SIZE / 3, SZ_16M)
 
@@ -104,10 +105,6 @@
 #define END_MEM     		(UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE)
 #endif
 
-#ifndef PAGE_OFFSET
-#define PAGE_OFFSET		PLAT_PHYS_OFFSET
-#endif
-
 /*
  * The module can be at any place in ram in nommu mode.
  */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 03243f7..85c60ad 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -120,13 +120,16 @@
 /*
  * 2nd stage PTE definitions for LPAE.
  */
-#define L_PTE_S2_MT_UNCACHED	 (_AT(pteval_t, 0x5) << 2) /* MemAttr[3:0] */
-#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */
-#define L_PTE_S2_MT_WRITEBACK	 (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */
-#define L_PTE_S2_RDONLY		 (_AT(pteval_t, 1) << 6)   /* HAP[1]   */
-#define L_PTE_S2_RDWR		 (_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
+#define L_PTE_S2_MT_UNCACHED		(_AT(pteval_t, 0x0) << 2) /* strongly ordered */
+#define L_PTE_S2_MT_WRITETHROUGH	(_AT(pteval_t, 0xa) << 2) /* normal inner write-through */
+#define L_PTE_S2_MT_WRITEBACK		(_AT(pteval_t, 0xf) << 2) /* normal inner write-back */
+#define L_PTE_S2_MT_DEV_SHARED		(_AT(pteval_t, 0x1) << 2) /* device */
+#define L_PTE_S2_MT_MASK		(_AT(pteval_t, 0xf) << 2)
 
-#define L_PMD_S2_RDWR		 (_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
+#define L_PTE_S2_RDONLY			(_AT(pteval_t, 1) << 6)   /* HAP[1]   */
+#define L_PTE_S2_RDWR			(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
+
+#define L_PMD_S2_RDWR			(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
 
 /*
  * Hyp-mode PL2 PTE definitions for LPAE.
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index ef3c607..ac4bfae 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -37,18 +37,9 @@
 
 static inline void dsb_sev(void)
 {
-#if __LINUX_ARM_ARCH__ >= 7
-	__asm__ __volatile__ (
-		"dsb ishst\n"
-		SEV
-	);
-#else
-	__asm__ __volatile__ (
-		"mcr p15, 0, %0, c7, c10, 4\n"
-		SEV
-		: : "r" (0)
-	);
-#endif
+
+	dsb(ishst);
+	__asm__(SEV);
 }
 
 /*
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 58b8b84..2fe85ff 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -20,9 +20,6 @@
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
 #define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
-#define mc_capable()	(cpu_topology[0].socket_id != -1)
-#define smt_capable()	(cpu_topology[0].thread_id != -1)
-
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 47cd974..c96ecac 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -177,6 +177,18 @@
 	.long	__proc_info_end
 	.size	__lookup_processor_type_data, . - __lookup_processor_type_data
 
+__error_lpae:
+#ifdef CONFIG_DEBUG_LL
+	adr	r0, str_lpae
+	bl 	printascii
+	b	__error
+str_lpae: .asciz "\nError: Kernel with LPAE support, but CPU does not support LPAE.\n"
+#else
+	b	__error
+#endif
+	.align
+ENDPROC(__error_lpae)
+
 __error_p:
 #ifdef CONFIG_DEBUG_LL
 	adr	r0, str_p1
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 914616e..f5f381d 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -102,7 +102,7 @@
 	and	r3, r3, #0xf			@ extract VMSA support
 	cmp	r3, #5				@ long-descriptor translation table format?
  THUMB( it	lo )				@ force fixup-able long branch encoding
-	blo	__error_p			@ only classic page table format
+	blo	__error_lpae			@ only classic page table format
 #endif
 
 #ifndef CONFIG_XIP_KERNEL
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 92f7b15..adabeab 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -30,7 +30,6 @@
 #include <linux/uaccess.h>
 #include <linux/random.h>
 #include <linux/hw_breakpoint.h>
-#include <linux/cpuidle.h>
 #include <linux/leds.h>
 #include <linux/reboot.h>
 
@@ -133,7 +132,11 @@
 
 void (*arm_pm_idle)(void);
 
-static void default_idle(void)
+/*
+ * Called from the core idle loop.
+ */
+
+void arch_cpu_idle(void)
 {
 	if (arm_pm_idle)
 		arm_pm_idle();
@@ -168,15 +171,6 @@
 #endif
 
 /*
- * Called from the core idle loop.
- */
-void arch_cpu_idle(void)
-{
-	if (cpuidle_idle_call())
-		default_idle();
-}
-
-/*
  * Called by kexec, immediately prior to machine_kexec().
  *
  * This must completely disable all secondary CPUs; simply causing those CPUs
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index b0df976..1e8b030 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -731,7 +731,7 @@
 	kernel_data.end     = virt_to_phys(_end - 1);
 
 	for_each_memblock(memory, region) {
-		res = memblock_virt_alloc_low(sizeof(*res), 0);
+		res = memblock_virt_alloc(sizeof(*res), 0);
 		res->name  = "System RAM";
 		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
 		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 1d8248e..bd18bb8 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -878,7 +878,8 @@
 				    unsigned long cmd,
 				    void *v)
 {
-	if (cmd == CPU_PM_EXIT) {
+	if (cmd == CPU_PM_EXIT &&
+	    __hyp_get_vectors() == hyp_default_vectors) {
 		cpu_init_hyp_mode(NULL);
 		return NOTIFY_OK;
 	}
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index ddc1553..0d68d40 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -220,6 +220,10 @@
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in r0 and r1.
  *
+ * A function pointer with a value of 0xffffffff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
+ * arch/arm/kernel/hyp_stub.S.
+ *
  * The calling convention follows the standard AAPCS:
  *   r0 - r3: caller save
  *   r12:     caller save
@@ -363,6 +367,11 @@
 host_switch_to_hyp:
 	pop	{r0, r1, r2}
 
+	/* Check for __hyp_get_vectors */
+	cmp	r0, #-1
+	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
+	beq	1f
+
 	push	{lr}
 	mrs	lr, SPSR
 	push	{lr}
@@ -378,7 +387,7 @@
 	pop	{lr}
 	msr	SPSR_csxf, lr
 	pop	{lr}
-	eret
+1:	eret
 
 guest_trap:
 	load_vcpu			@ Load VCPU pointer to r0
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 2ab0043..85399c9 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -472,7 +472,7 @@
 	CLK("spi_davinci.0",	NULL,		&spi0_clk),
 	CLK("spi_davinci.1",	NULL,		&spi1_clk),
 	CLK("vpif",		NULL,		&vpif_clk),
-	CLK("ahci",		NULL,		&sata_clk),
+	CLK("ahci_da850",		NULL,		&sata_clk),
 	CLK("davinci-rproc.0",	NULL,		&dsp_clk),
 	CLK("ehrpwm",		"fck",		&ehrpwm_clk),
 	CLK("ehrpwm",		"tbclk",	&ehrpwm_tbclk),
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 0486cdf..56ea41d 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -1020,7 +1020,6 @@
 }
 
 #ifdef CONFIG_ARCH_DAVINCI_DA850
-
 static struct resource da850_sata_resources[] = {
 	{
 		.start	= DA850_SATA_BASE,
@@ -1028,103 +1027,22 @@
 		.flags	= IORESOURCE_MEM,
 	},
 	{
+		.start	= DA8XX_SYSCFG1_BASE + DA8XX_PWRDN_REG,
+		.end	= DA8XX_SYSCFG1_BASE + DA8XX_PWRDN_REG + 0x3,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
 		.start	= IRQ_DA850_SATAINT,
 		.flags	= IORESOURCE_IRQ,
 	},
 };
 
-/* SATA PHY Control Register offset from AHCI base */
-#define SATA_P0PHYCR_REG	0x178
-
-#define SATA_PHY_MPY(x)		((x) << 0)
-#define SATA_PHY_LOS(x)		((x) << 6)
-#define SATA_PHY_RXCDR(x)	((x) << 10)
-#define SATA_PHY_RXEQ(x)	((x) << 13)
-#define SATA_PHY_TXSWING(x)	((x) << 19)
-#define SATA_PHY_ENPLL(x)	((x) << 31)
-
-static struct clk *da850_sata_clk;
-static unsigned long da850_sata_refclkpn;
-
-/* Supported DA850 SATA crystal frequencies */
-#define KHZ_TO_HZ(freq) ((freq) * 1000)
-static unsigned long da850_sata_xtal[] = {
-	KHZ_TO_HZ(300000),
-	KHZ_TO_HZ(250000),
-	0,			/* Reserved */
-	KHZ_TO_HZ(187500),
-	KHZ_TO_HZ(150000),
-	KHZ_TO_HZ(125000),
-	KHZ_TO_HZ(120000),
-	KHZ_TO_HZ(100000),
-	KHZ_TO_HZ(75000),
-	KHZ_TO_HZ(60000),
-};
-
-static int da850_sata_init(struct device *dev, void __iomem *addr)
-{
-	int i, ret;
-	unsigned int val;
-
-	da850_sata_clk = clk_get(dev, NULL);
-	if (IS_ERR(da850_sata_clk))
-		return PTR_ERR(da850_sata_clk);
-
-	ret = clk_prepare_enable(da850_sata_clk);
-	if (ret)
-		goto err0;
-
-	/* Enable SATA clock receiver */
-	val = __raw_readl(DA8XX_SYSCFG1_VIRT(DA8XX_PWRDN_REG));
-	val &= ~BIT(0);
-	__raw_writel(val, DA8XX_SYSCFG1_VIRT(DA8XX_PWRDN_REG));
-
-	/* Get the multiplier needed for 1.5GHz PLL output */
-	for (i = 0; i < ARRAY_SIZE(da850_sata_xtal); i++)
-		if (da850_sata_xtal[i] == da850_sata_refclkpn)
-			break;
-
-	if (i == ARRAY_SIZE(da850_sata_xtal)) {
-		ret = -EINVAL;
-		goto err1;
-	}
-
-	val = SATA_PHY_MPY(i + 1) |
-		SATA_PHY_LOS(1) |
-		SATA_PHY_RXCDR(4) |
-		SATA_PHY_RXEQ(1) |
-		SATA_PHY_TXSWING(3) |
-		SATA_PHY_ENPLL(1);
-
-	__raw_writel(val, addr + SATA_P0PHYCR_REG);
-
-	return 0;
-
-err1:
-	clk_disable_unprepare(da850_sata_clk);
-err0:
-	clk_put(da850_sata_clk);
-	return ret;
-}
-
-static void da850_sata_exit(struct device *dev)
-{
-	clk_disable_unprepare(da850_sata_clk);
-	clk_put(da850_sata_clk);
-}
-
-static struct ahci_platform_data da850_sata_pdata = {
-	.init	= da850_sata_init,
-	.exit	= da850_sata_exit,
-};
-
 static u64 da850_sata_dmamask = DMA_BIT_MASK(32);
 
 static struct platform_device da850_sata_device = {
-	.name	= "ahci",
+	.name	= "ahci_da850",
 	.id	= -1,
 	.dev	= {
-		.platform_data		= &da850_sata_pdata,
 		.dma_mask		= &da850_sata_dmamask,
 		.coherent_dma_mask	= DMA_BIT_MASK(32),
 	},
@@ -1134,9 +1052,8 @@
 
 int __init da850_register_sata(unsigned long refclkpn)
 {
-	da850_sata_refclkpn = refclkpn;
-	if (!da850_sata_refclkpn)
-		return -EINVAL;
+	/* please see comment in drivers/ata/ahci_da850.c */
+	BUG_ON(refclkpn != 100 * 1000 * 1000);
 
 	return platform_device_register(&da850_sata_device);
 }
diff --git a/arch/arm/mach-hisi/Kconfig b/arch/arm/mach-hisi/Kconfig
index 018ad67..1abae5f 100644
--- a/arch/arm/mach-hisi/Kconfig
+++ b/arch/arm/mach-hisi/Kconfig
@@ -8,10 +8,9 @@
 	select CLKSRC_OF
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU
-	select HAVE_ARM_TWD
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select PINCTRL
 	select PINCTRL_SINGLE
-	select SMP
 	help
 	  Support for Hisilicon Hi36xx/Hi37xx processor family
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index befcaf5..ec41964 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -101,11 +101,9 @@
 obj-$(CONFIG_SOC_IMX6Q) += clk-imx6q.o mach-imx6q.o
 obj-$(CONFIG_SOC_IMX6SL) += clk-imx6sl.o mach-imx6sl.o
 
-ifeq ($(CONFIG_PM),y)
 obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o headsmp.o
 # i.MX6SL reuses i.MX6Q code
 obj-$(CONFIG_SOC_IMX6SL) += pm-imx6q.o headsmp.o
-endif
 
 # i.MX5 based machines
 obj-$(CONFIG_MACH_MX51_BABBAGE) += mach-mx51_babbage.o
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index af2e582..4d677f4 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -482,6 +482,9 @@
 	if (IS_ENABLED(CONFIG_PCI_IMX6))
 		clk_set_parent(clk[lvds1_sel], clk[sata_ref]);
 
+	/* Set initial power mode */
+	imx6q_set_lpm(WAIT_CLOCKED);
+
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpt");
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
diff --git a/arch/arm/mach-imx/clk-imx6sl.c b/arch/arm/mach-imx/clk-imx6sl.c
index 3781a18..4c86f30 100644
--- a/arch/arm/mach-imx/clk-imx6sl.c
+++ b/arch/arm/mach-imx/clk-imx6sl.c
@@ -266,6 +266,9 @@
 	/* Audio-related clocks configuration */
 	clk_set_parent(clks[IMX6SL_CLK_SPDIF0_SEL], clks[IMX6SL_CLK_PLL3_PFD3]);
 
+	/* Set initial power mode */
+	imx6q_set_lpm(WAIT_CLOCKED);
+
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6sl-gpt");
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 59c3b9b..baf439d 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -144,13 +144,11 @@
 void imx_cpu_die(unsigned int cpu);
 int imx_cpu_kill(unsigned int cpu);
 
-#ifdef CONFIG_PM
 void imx6q_pm_init(void);
 void imx6q_pm_set_ccm_base(void __iomem *base);
+#ifdef CONFIG_PM
 void imx5_pm_init(void);
 #else
-static inline void imx6q_pm_init(void) {}
-static inline void imx6q_pm_set_ccm_base(void __iomem *base) {}
 static inline void imx5_pm_init(void) {}
 #endif
 
diff --git a/arch/arm/mach-imx/pm-imx6q.c b/arch/arm/mach-imx/pm-imx6q.c
index 9d47adc..7a9b985 100644
--- a/arch/arm/mach-imx/pm-imx6q.c
+++ b/arch/arm/mach-imx/pm-imx6q.c
@@ -236,8 +236,6 @@
 		regmap_update_bits(gpr, IOMUXC_GPR1, IMX6Q_GPR1_GINT,
 				   IMX6Q_GPR1_GINT);
 
-	/* Set initial power mode */
-	imx6q_set_lpm(WAIT_CLOCKED);
 
 	suspend_set_ops(&imx6q_pm_ops);
 }
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index 5e84149..a3ef961 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -64,6 +64,7 @@
 
 /*
  * Logical      Physical
+ * f1000000	10000000	Core module registers
  * f1300000	13000000	Counter/Timer
  * f1400000	14000000	Interrupt controller
  * f1600000	16000000	UART 0
@@ -75,6 +76,11 @@
 
 static struct map_desc intcp_io_desc[] __initdata __maybe_unused = {
 	{
+		.virtual	= IO_ADDRESS(INTEGRATOR_HDR_BASE),
+		.pfn		= __phys_to_pfn(INTEGRATOR_HDR_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE
+	}, {
 		.virtual	= IO_ADDRESS(INTEGRATOR_CT_BASE),
 		.pfn		= __phys_to_pfn(INTEGRATOR_CT_BASE),
 		.length		= SZ_4K,
diff --git a/arch/arm/mach-iop32x/em7210.c b/arch/arm/mach-iop32x/em7210.c
index 177cd07..77e1ff0 100644
--- a/arch/arm/mach-iop32x/em7210.c
+++ b/arch/arm/mach-iop32x/em7210.c
@@ -23,6 +23,7 @@
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
+#include <linux/gpio.h>
 #include <mach/hardware.h>
 #include <linux/io.h>
 #include <linux/irq.h>
@@ -176,12 +177,36 @@
 	.resource	= &em7210_uart_resource,
 };
 
+#define EM7210_HARDWARE_POWER 0
+
 void em7210_power_off(void)
 {
-	*IOP3XX_GPOE &= 0xfe;
-	*IOP3XX_GPOD |= 0x01;
+	int ret;
+
+	ret = gpio_direction_output(EM7210_HARDWARE_POWER, 1);
+	if (ret)
+		pr_crit("could not drive power off GPIO high\n");
 }
 
+static int __init em7210_request_gpios(void)
+{
+	int ret;
+
+	if (!machine_is_em7210())
+		return 0;
+
+	ret = gpio_request(EM7210_HARDWARE_POWER, "power");
+	if (ret) {
+		pr_err("could not request power off GPIO\n");
+		return 0;
+	}
+
+	pm_power_off = em7210_power_off;
+
+	return 0;
+}
+device_initcall(em7210_request_gpios);
+
 static void __init em7210_init_machine(void)
 {
 	register_iop32x_gpio();
@@ -194,9 +219,6 @@
 
 	i2c_register_board_info(0, em7210_i2c_devices,
 		ARRAY_SIZE(em7210_i2c_devices));
-
-
-	pm_power_off = em7210_power_off;
 }
 
 MACHINE_START(EM7210, "Lanner EM7210")
diff --git a/arch/arm/mach-keystone/Kconfig b/arch/arm/mach-keystone/Kconfig
index dabc5ee..90a708f 100644
--- a/arch/arm/mach-keystone/Kconfig
+++ b/arch/arm/mach-keystone/Kconfig
@@ -10,7 +10,6 @@
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_ERRATA_798181 if SMP
 	select COMMON_CLK_KEYSTONE
-	select TI_EDMA
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ZONE_DMA if ARM_LPAE
 	help
diff --git a/arch/arm/mach-kirkwood/pm.c b/arch/arm/mach-kirkwood/pm.c
index 8783a71..c6ab8d9 100644
--- a/arch/arm/mach-kirkwood/pm.c
+++ b/arch/arm/mach-kirkwood/pm.c
@@ -18,6 +18,7 @@
 #include <linux/suspend.h>
 #include <linux/io.h>
 #include <mach/bridge-regs.h>
+#include "common.h"
 
 static void __iomem *ddr_operation_base;
 
@@ -65,9 +66,8 @@
 	.valid = kirkwood_pm_valid_standby,
 };
 
-int __init kirkwood_pm_init(void)
+void __init kirkwood_pm_init(void)
 {
 	ddr_operation_base = ioremap(DDR_OPERATION_BASE, 4);
 	suspend_set_ops(&kirkwood_suspend_ops);
-	return 0;
 }
diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig
index ba470d6..3795ae2 100644
--- a/arch/arm/mach-moxart/Kconfig
+++ b/arch/arm/mach-moxart/Kconfig
@@ -2,7 +2,6 @@
 	bool "MOXA ART SoC" if ARCH_MULTI_V4T
 	select CPU_FA526
 	select ARM_DMA_MEM_BUFFERABLE
-	select DMA_OF
 	select USE_OF
 	select CLKSRC_OF
 	select CLKSRC_MMIO
diff --git a/arch/arm/mach-mvebu/mvebu-soc-id.c b/arch/arm/mach-mvebu/mvebu-soc-id.c
index fe4fc1c..f3b325f 100644
--- a/arch/arm/mach-mvebu/mvebu-soc-id.c
+++ b/arch/arm/mach-mvebu/mvebu-soc-id.c
@@ -88,7 +88,7 @@
 	}
 
 	pci_base = of_iomap(child, 0);
-	if (IS_ERR(pci_base)) {
+	if (pci_base == NULL) {
 		pr_err("cannot map registers\n");
 		ret = -ENOMEM;
 		goto res_ioremap;
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index 91449c5..85089d8 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -156,6 +156,7 @@
 	.register_dev	= 1,
 	.hmc_mode	= 16,
 	.pins[0]	= 6,
+	.extcon		= "tahvo-usb",
 };
 
 #if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE)
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 653b489..0af7ca0 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -50,11 +50,12 @@
 	bool "TI OMAP5"
 	depends on ARCH_MULTI_V7
 	select ARCH_OMAP2PLUS
+	select ARCH_HAS_OPP
 	select ARM_CPU_SUSPEND if PM
 	select ARM_GIC
 	select CPU_V7
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select HAVE_ARM_ARCH_TIMER
 	select ARM_ERRATA_798181 if SMP
@@ -63,6 +64,7 @@
 	bool "TI AM33XX"
 	depends on ARCH_MULTI_V7
 	select ARCH_OMAP2PLUS
+	select ARCH_HAS_OPP
 	select ARM_CPU_SUSPEND if PM
 	select CPU_V7
 	select MULTI_IRQ_HANDLER
@@ -72,6 +74,7 @@
 	depends on ARCH_MULTI_V7
 	select CPU_V7
 	select ARCH_OMAP2PLUS
+	select ARCH_HAS_OPP
 	select MULTI_IRQ_HANDLER
 	select ARM_GIC
 	select MACH_OMAP_GENERIC
@@ -80,6 +83,7 @@
 	bool "TI DRA7XX"
 	depends on ARCH_MULTI_V7
 	select ARCH_OMAP2PLUS
+	select ARCH_HAS_OPP
 	select ARM_CPU_SUSPEND if PM
 	select ARM_GIC
 	select CPU_V7
@@ -268,9 +272,6 @@
 	default y
 	select OMAP_PACKAGE_CBB
 
-config MACH_NOKIA_N800
-       bool
-
 config MACH_NOKIA_N810
        bool
 
@@ -281,7 +282,6 @@
 	bool "Nokia N800/N810"
 	depends on SOC_OMAP2420
 	default y
-	select MACH_NOKIA_N800
 	select MACH_NOKIA_N810
 	select MACH_NOKIA_N810_WIMAX
 	select OMAP_PACKAGE_ZAC
diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c
index 3b05aea..11ed915 100644
--- a/arch/arm/mach-omap2/cclock3xxx_data.c
+++ b/arch/arm/mach-omap2/cclock3xxx_data.c
@@ -433,7 +433,9 @@
 	.enable		= &omap2_dflt_clk_enable,
 	.disable	= &omap2_dflt_clk_disable,
 	.is_enabled	= &omap2_dflt_clk_is_enabled,
+	.set_rate	= &omap3_clkoutx2_set_rate,
 	.recalc_rate	= &omap3_clkoutx2_recalc,
+	.round_rate	= &omap3_clkoutx2_round_rate,
 };
 
 static const struct clk_ops dpll4_m5x2_ck_3630_ops = {
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index e515278..a6aae30 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -62,11 +62,17 @@
 
 #if defined(CONFIG_PM) && defined(CONFIG_ARCH_OMAP4)
 int omap4_pm_init(void);
+int omap4_pm_init_early(void);
 #else
 static inline int omap4_pm_init(void)
 {
 	return 0;
 }
+
+static inline int omap4_pm_init_early(void)
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_OMAP_MUX
@@ -236,6 +242,7 @@
 
 extern void __init gic_init_irq(void);
 extern void gic_dist_disable(void);
+extern void gic_dist_enable(void);
 extern bool gic_dist_disabled(void);
 extern void gic_timer_retrigger(void);
 extern void omap_smc1(u32 fn, u32 arg);
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 4c8982a..01fc710 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -23,6 +23,8 @@
 #include "prm.h"
 #include "clockdomain.h"
 
+#define MAX_CPUS	2
+
 /* Machine specific information */
 struct idle_statedata {
 	u32 cpu_state;
@@ -48,11 +50,11 @@
 	},
 };
 
-static struct powerdomain *mpu_pd, *cpu_pd[NR_CPUS];
-static struct clockdomain *cpu_clkdm[NR_CPUS];
+static struct powerdomain *mpu_pd, *cpu_pd[MAX_CPUS];
+static struct clockdomain *cpu_clkdm[MAX_CPUS];
 
 static atomic_t abort_barrier;
-static bool cpu_done[NR_CPUS];
+static bool cpu_done[MAX_CPUS];
 static struct idle_statedata *state_ptr = &omap4_idle_data[0];
 
 /* Private functions */
@@ -80,6 +82,7 @@
 			int index)
 {
 	struct idle_statedata *cx = state_ptr + index;
+	u32 mpuss_can_lose_context = 0;
 
 	/*
 	 * CPU0 has to wait and stay ON until CPU1 is OFF state.
@@ -104,6 +107,9 @@
 		}
 	}
 
+	mpuss_can_lose_context = (cx->mpu_state == PWRDM_POWER_RET) &&
+				 (cx->mpu_logic_state == PWRDM_POWER_OFF);
+
 	/*
 	 * Call idle CPU PM enter notifier chain so that
 	 * VFP and per CPU interrupt context is saved.
@@ -118,9 +124,8 @@
 		 * Call idle CPU cluster PM enter notifier chain
 		 * to save GIC and wakeupgen context.
 		 */
-		if ((cx->mpu_state == PWRDM_POWER_RET) &&
-			(cx->mpu_logic_state == PWRDM_POWER_OFF))
-				cpu_cluster_pm_enter();
+		if (mpuss_can_lose_context)
+			cpu_cluster_pm_enter();
 	}
 
 	omap4_enter_lowpower(dev->cpu, cx->cpu_state);
@@ -128,9 +133,23 @@
 
 	/* Wakeup CPU1 only if it is not offlined */
 	if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) {
+
+		if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD) &&
+		    mpuss_can_lose_context)
+			gic_dist_disable();
+
 		clkdm_wakeup(cpu_clkdm[1]);
 		omap_set_pwrdm_state(cpu_pd[1], PWRDM_POWER_ON);
 		clkdm_allow_idle(cpu_clkdm[1]);
+
+		if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD) &&
+		    mpuss_can_lose_context) {
+			while (gic_dist_disabled()) {
+				udelay(1);
+				cpu_relax();
+			}
+			gic_timer_retrigger();
+		}
 	}
 
 	/*
@@ -143,8 +162,7 @@
 	 * Call idle CPU cluster PM exit notifier chain
 	 * to restore GIC and wakeupgen context.
 	 */
-	if (dev->cpu == 0 && (cx->mpu_state == PWRDM_POWER_RET) &&
-		(cx->mpu_logic_state == PWRDM_POWER_OFF))
+	if (dev->cpu == 0 && mpuss_can_lose_context)
 		cpu_cluster_pm_exit();
 
 fail:
diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index 3185ced..3c418ea 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -623,25 +623,12 @@
 
 /* Clock control for DPLL outputs */
 
-/**
- * omap3_clkoutx2_recalc - recalculate DPLL X2 output virtual clock rate
- * @clk: DPLL output struct clk
- *
- * Using parent clock DPLL data, look up DPLL state.  If locked, set our
- * rate to the dpll_clk * 2; otherwise, just use dpll_clk.
- */
-unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
-				    unsigned long parent_rate)
+/* Find the parent DPLL for the given clkoutx2 clock */
+static struct clk_hw_omap *omap3_find_clkoutx2_dpll(struct clk_hw *hw)
 {
-	const struct dpll_data *dd;
-	unsigned long rate;
-	u32 v;
 	struct clk_hw_omap *pclk = NULL;
 	struct clk *parent;
 
-	if (!parent_rate)
-		return 0;
-
 	/* Walk up the parents of clk, looking for a DPLL */
 	do {
 		do {
@@ -656,9 +643,35 @@
 	/* clk does not have a DPLL as a parent?  error in the clock data */
 	if (!pclk) {
 		WARN_ON(1);
-		return 0;
+		return NULL;
 	}
 
+	return pclk;
+}
+
+/**
+ * omap3_clkoutx2_recalc - recalculate DPLL X2 output virtual clock rate
+ * @clk: DPLL output struct clk
+ *
+ * Using parent clock DPLL data, look up DPLL state.  If locked, set our
+ * rate to the dpll_clk * 2; otherwise, just use dpll_clk.
+ */
+unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
+				    unsigned long parent_rate)
+{
+	const struct dpll_data *dd;
+	unsigned long rate;
+	u32 v;
+	struct clk_hw_omap *pclk = NULL;
+
+	if (!parent_rate)
+		return 0;
+
+	pclk = omap3_find_clkoutx2_dpll(hw);
+
+	if (!pclk)
+		return 0;
+
 	dd = pclk->dpll_data;
 
 	WARN_ON(!dd->enable_mask);
@@ -672,6 +685,55 @@
 	return rate;
 }
 
+int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long parent_rate)
+{
+	return 0;
+}
+
+long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *prate)
+{
+	const struct dpll_data *dd;
+	u32 v;
+	struct clk_hw_omap *pclk = NULL;
+
+	if (!*prate)
+		return 0;
+
+	pclk = omap3_find_clkoutx2_dpll(hw);
+
+	if (!pclk)
+		return 0;
+
+	dd = pclk->dpll_data;
+
+	/* TYPE J does not have a clkoutx2 */
+	if (dd->flags & DPLL_J_TYPE) {
+		*prate = __clk_round_rate(__clk_get_parent(pclk->hw.clk), rate);
+		return *prate;
+	}
+
+	WARN_ON(!dd->enable_mask);
+
+	v = omap2_clk_readl(pclk, dd->control_reg) & dd->enable_mask;
+	v >>= __ffs(dd->enable_mask);
+
+	/* If in bypass, the rate is fixed to the bypass rate*/
+	if (v != OMAP3XXX_EN_DPLL_LOCKED)
+		return *prate;
+
+	if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+		unsigned long best_parent;
+
+		best_parent = (rate / 2);
+		*prate = __clk_round_rate(__clk_get_parent(hw->clk),
+				best_parent);
+	}
+
+	return *prate * 2;
+}
+
 /* OMAP3/4 non-CORE DPLL clkops */
 const struct clk_hw_omap_ops clkhwops_omap3_dpll = {
 	.allow_idle	= omap3_dpll_allow_idle,
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index d24926e..ab43755 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -1339,7 +1339,7 @@
 		of_property_read_bool(np, "gpmc,time-para-granularity");
 }
 
-#ifdef CONFIG_MTD_NAND
+#if IS_ENABLED(CONFIG_MTD_NAND)
 
 static const char * const nand_xfer_types[] = {
 	[NAND_OMAP_PREFETCH_POLLED]		= "prefetch-polled",
@@ -1429,7 +1429,7 @@
 }
 #endif
 
-#ifdef CONFIG_MTD_ONENAND
+#if IS_ENABLED(CONFIG_MTD_ONENAND)
 static int gpmc_probe_onenand_child(struct platform_device *pdev,
 				 struct device_node *child)
 {
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 47381fd..af432b1 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -179,15 +179,6 @@
 		.length		= L4_EMU_34XX_SIZE,
 		.type		= MT_DEVICE
 	},
-#if defined(CONFIG_DEBUG_LL) &&							\
-	(defined(CONFIG_MACH_OMAP_ZOOM2) || defined(CONFIG_MACH_OMAP_ZOOM3))
-	{
-		.virtual	= ZOOM_UART_VIRT,
-		.pfn		= __phys_to_pfn(ZOOM_UART_BASE),
-		.length		= SZ_1M,
-		.type		= MT_DEVICE
-	},
-#endif
 };
 #endif
 
@@ -641,6 +632,7 @@
 	omap_cm_base_init();
 	omap4xxx_check_revision();
 	omap4xxx_check_features();
+	omap4_pm_init_early();
 	omap44xx_prm_init();
 	omap44xx_voltagedomains_init();
 	omap44xx_powerdomains_init();
diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
index f991016..667915d 100644
--- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c
+++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -271,6 +271,9 @@
 	else
 		omap_pm_ops.finish_suspend(save_state);
 
+	if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD) && cpu)
+		gic_dist_enable();
+
 	/*
 	 * Restore the CPUx power state to ON otherwise CPUx
 	 * power domain can transitions to programmed low power
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 75e95d4..17550aa 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -39,8 +39,6 @@
 
 #define OMAP5_CORE_COUNT	0x2
 
-u16 pm44xx_errata;
-
 /* SCU base address */
 static void __iomem *scu_base;
 
@@ -217,10 +215,8 @@
 	if (scu_base)
 		scu_enable(scu_base);
 
-	if (cpu_is_omap446x()) {
+	if (cpu_is_omap446x())
 		startup_addr = omap4460_secondary_startup;
-		pm44xx_errata |= PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD;
-	}
 
 	/*
 	 * Write the address of secondary startup routine into the
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index dd893ec..6cd3f37 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -127,6 +127,12 @@
 		__raw_writel(0x0, gic_dist_base_addr + GIC_DIST_CTRL);
 }
 
+void gic_dist_enable(void)
+{
+	if (gic_dist_base_addr)
+		__raw_writel(0x1, gic_dist_base_addr + GIC_DIST_CTRL);
+}
+
 bool gic_dist_disabled(void)
 {
 	return !(__raw_readl(gic_dist_base_addr + GIC_DIST_CTRL) & 0x1);
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 42d8188..1f33f5d 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1947,29 +1947,31 @@
 		goto dis_opt_clks;
 
 	_write_sysconfig(v, oh);
+
+	if (oh->class->sysc->srst_udelay)
+		udelay(oh->class->sysc->srst_udelay);
+
+	c = _wait_softreset_complete(oh);
+	if (c == MAX_MODULE_SOFTRESET_WAIT) {
+		pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
+			   oh->name, MAX_MODULE_SOFTRESET_WAIT);
+		ret = -ETIMEDOUT;
+		goto dis_opt_clks;
+	} else {
+		pr_debug("omap_hwmod: %s: softreset in %d usec\n", oh->name, c);
+	}
+
 	ret = _clear_softreset(oh, &v);
 	if (ret)
 		goto dis_opt_clks;
 
 	_write_sysconfig(v, oh);
 
-	if (oh->class->sysc->srst_udelay)
-		udelay(oh->class->sysc->srst_udelay);
-
-	c = _wait_softreset_complete(oh);
-	if (c == MAX_MODULE_SOFTRESET_WAIT)
-		pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
-			   oh->name, MAX_MODULE_SOFTRESET_WAIT);
-	else
-		pr_debug("omap_hwmod: %s: softreset in %d usec\n", oh->name, c);
-
 	/*
 	 * XXX add _HWMOD_STATE_WEDGED for modules that don't come back from
 	 * _wait_target_ready() or _reset()
 	 */
 
-	ret = (c == MAX_MODULE_SOFTRESET_WAIT) ? -ETIMEDOUT : 0;
-
 dis_opt_clks:
 	if (oh->flags & HWMOD_CONTROL_OPT_CLKS_IN_RESET)
 		_disable_optional_clocks(oh);
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 18f333c..810c205 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1365,11 +1365,10 @@
 	.rev_offs	= 0x0000,
 	.sysc_offs	= 0x0010,
 	.syss_offs	= 0x0014,
-	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
-			   SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
-			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
-	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
-			   SIDLE_SMART_WKUP),
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_ENAWAKEUP |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+			   SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
 	.sysc_fields	= &omap_hwmod_sysc_type1,
 };
 
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 3d5b24d..c33e07e 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -22,6 +22,8 @@
 #include "common-board-devices.h"
 #include "dss-common.h"
 #include "control.h"
+#include "omap-secure.h"
+#include "soc.h"
 
 struct pdata_init {
 	const char *compatible;
@@ -169,6 +171,22 @@
 	omap_ctrl_writel(v, AM35XX_CONTROL_IP_SW_RESET);
 	omap_ctrl_readl(AM35XX_CONTROL_IP_SW_RESET); /* OCP barrier */
 }
+
+static void __init nokia_n900_legacy_init(void)
+{
+	hsmmc2_internal_input_clk();
+
+	if (omap_type() == OMAP2_DEVICE_TYPE_SEC) {
+		if (IS_ENABLED(CONFIG_ARM_ERRATA_430973)) {
+			pr_info("RX-51: Enabling ARM errata 430973 workaround\n");
+			/* set IBE to 1 */
+			rx51_secure_update_aux_cr(BIT(6), 0);
+		} else {
+			pr_warning("RX-51: Not enabling ARM errata 430973 workaround\n");
+			pr_warning("Thumb binaries may crash randomly without this workaround\n");
+		}
+	}
+}
 #endif /* CONFIG_ARCH_OMAP3 */
 
 #ifdef CONFIG_ARCH_OMAP4
@@ -239,6 +257,7 @@
 #endif
 #ifdef CONFIG_ARCH_OMAP3
 	OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002030, "48002030.pinmux", &pcs_pdata),
+	OF_DEV_AUXDATA("ti,omap3-padconf", 0x480025a0, "480025a0.pinmux", &pcs_pdata),
 	OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002a00, "48002a00.pinmux", &pcs_pdata),
 	/* Only on am3517 */
 	OF_DEV_AUXDATA("ti,davinci_mdio", 0x5c030000, "davinci_mdio.0", NULL),
@@ -259,7 +278,7 @@
 static struct pdata_init pdata_quirks[] __initdata = {
 #ifdef CONFIG_ARCH_OMAP3
 	{ "compulab,omap3-sbc-t3730", omap3_sbc_t3730_legacy_init, },
-	{ "nokia,omap3-n900", hsmmc2_internal_input_clk, },
+	{ "nokia,omap3-n900", nokia_n900_legacy_init, },
 	{ "nokia,omap3-n9", hsmmc2_internal_input_clk, },
 	{ "nokia,omap3-n950", hsmmc2_internal_input_clk, },
 	{ "isee,omap3-igep0020", omap3_igep0020_legacy_init, },
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index 82f06989..eefb30c 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -24,6 +24,8 @@
 #include "powerdomain.h"
 #include "pm.h"
 
+u16 pm44xx_errata;
+
 struct power_state {
 	struct powerdomain *pwrdm;
 	u32 next_state;
@@ -199,6 +201,19 @@
 }
 
 /**
+ * omap4_pm_init_early - Does early initialization necessary for OMAP4+ devices
+ *
+ * Initializes basic stuff for power management functionality.
+ */
+int __init omap4_pm_init_early(void)
+{
+	if (cpu_is_omap446x())
+		pm44xx_errata |= PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD;
+
+	return 0;
+}
+
+/**
  * omap4_pm_init - Init routine for OMAP4+ devices
  *
  * Initializes all powerdomain and clockdomain target states
diff --git a/arch/arm/mach-omap2/prminst44xx.c b/arch/arm/mach-omap2/prminst44xx.c
index 6334b96..280f3c5 100644
--- a/arch/arm/mach-omap2/prminst44xx.c
+++ b/arch/arm/mach-omap2/prminst44xx.c
@@ -183,11 +183,11 @@
 					OMAP4_PRM_RSTCTRL_OFFSET);
 	v |= OMAP4430_RST_GLOBAL_WARM_SW_MASK;
 	omap4_prminst_write_inst_reg(v, OMAP4430_PRM_PARTITION,
-				 OMAP4430_PRM_DEVICE_INST,
+				 dev_inst,
 				 OMAP4_PRM_RSTCTRL_OFFSET);
 
 	/* OCP barrier */
 	v = omap4_prminst_read_inst_reg(OMAP4430_PRM_PARTITION,
-				    OMAP4430_PRM_DEVICE_INST,
+				    dev_inst,
 				    OMAP4_PRM_RSTCTRL_OFFSET);
 }
diff --git a/arch/arm/mach-pxa/am300epd.c b/arch/arm/mach-pxa/am300epd.c
index c9f309a..8b90c4f 100644
--- a/arch/arm/mach-pxa/am300epd.c
+++ b/arch/arm/mach-pxa/am300epd.c
@@ -30,6 +30,7 @@
 
 #include <mach/gumstix.h>
 #include <mach/mfp-pxa25x.h>
+#include <mach/irqs.h>
 #include <linux/platform_data/video-pxafb.h>
 
 #include "generic.h"
diff --git a/arch/arm/mach-pxa/include/mach/balloon3.h b/arch/arm/mach-pxa/include/mach/balloon3.h
index 954641e..1b08259 100644
--- a/arch/arm/mach-pxa/include/mach/balloon3.h
+++ b/arch/arm/mach-pxa/include/mach/balloon3.h
@@ -14,6 +14,8 @@
 #ifndef ASM_ARCH_BALLOON3_H
 #define ASM_ARCH_BALLOON3_H
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
+
 enum balloon3_features {
 	BALLOON3_FEATURE_OHCI,
 	BALLOON3_FEATURE_MMC,
diff --git a/arch/arm/mach-pxa/include/mach/corgi.h b/arch/arm/mach-pxa/include/mach/corgi.h
index f3c3493..c030d95 100644
--- a/arch/arm/mach-pxa/include/mach/corgi.h
+++ b/arch/arm/mach-pxa/include/mach/corgi.h
@@ -13,6 +13,7 @@
 #ifndef __ASM_ARCH_CORGI_H
 #define __ASM_ARCH_CORGI_H  1
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
 
 /*
  * Corgi (Non Standard) GPIO Definitions
diff --git a/arch/arm/mach-pxa/include/mach/csb726.h b/arch/arm/mach-pxa/include/mach/csb726.h
index 2628e7b..00cfbbb 100644
--- a/arch/arm/mach-pxa/include/mach/csb726.h
+++ b/arch/arm/mach-pxa/include/mach/csb726.h
@@ -11,6 +11,8 @@
 #ifndef CSB726_H
 #define CSB726_H
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 #define CSB726_GPIO_IRQ_LAN	52
 #define CSB726_GPIO_IRQ_SM501	53
 #define CSB726_GPIO_MMC_DETECT	100
diff --git a/arch/arm/mach-pxa/include/mach/gumstix.h b/arch/arm/mach-pxa/include/mach/gumstix.h
index dba14b6..f7df27b 100644
--- a/arch/arm/mach-pxa/include/mach/gumstix.h
+++ b/arch/arm/mach-pxa/include/mach/gumstix.h
@@ -6,6 +6,7 @@
  * published by the Free Software Foundation.
  */
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
 
 /* BTRESET - Reset line to Bluetooth module, active low signal. */
 #define GPIO_GUMSTIX_BTRESET          7
diff --git a/arch/arm/mach-pxa/include/mach/idp.h b/arch/arm/mach-pxa/include/mach/idp.h
index 22a96f8..7e63f46 100644
--- a/arch/arm/mach-pxa/include/mach/idp.h
+++ b/arch/arm/mach-pxa/include/mach/idp.h
@@ -23,6 +23,7 @@
  * IDP hardware.
  */
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
 
 #define IDP_FLASH_PHYS		(PXA_CS0_PHYS)
 #define IDP_ALT_FLASH_PHYS	(PXA_CS1_PHYS)
diff --git a/arch/arm/mach-pxa/include/mach/palmld.h b/arch/arm/mach-pxa/include/mach/palmld.h
index 2c44713..b184f29 100644
--- a/arch/arm/mach-pxa/include/mach/palmld.h
+++ b/arch/arm/mach-pxa/include/mach/palmld.h
@@ -13,6 +13,8 @@
 #ifndef _INCLUDE_PALMLD_H_
 #define _INCLUDE_PALMLD_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmt5.h b/arch/arm/mach-pxa/include/mach/palmt5.h
index 0bd4f03..e342c59 100644
--- a/arch/arm/mach-pxa/include/mach/palmt5.h
+++ b/arch/arm/mach-pxa/include/mach/palmt5.h
@@ -15,6 +15,8 @@
 #ifndef _INCLUDE_PALMT5_H_
 #define _INCLUDE_PALMT5_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmtc.h b/arch/arm/mach-pxa/include/mach/palmtc.h
index c383a21..81c727b 100644
--- a/arch/arm/mach-pxa/include/mach/palmtc.h
+++ b/arch/arm/mach-pxa/include/mach/palmtc.h
@@ -16,6 +16,8 @@
 #ifndef _INCLUDE_PALMTC_H_
 #define _INCLUDE_PALMTC_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmtx.h b/arch/arm/mach-pxa/include/mach/palmtx.h
index f2e5303..92bc1f0 100644
--- a/arch/arm/mach-pxa/include/mach/palmtx.h
+++ b/arch/arm/mach-pxa/include/mach/palmtx.h
@@ -16,6 +16,8 @@
 #ifndef _INCLUDE_PALMTX_H_
 #define _INCLUDE_PALMTX_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /** HERE ARE GPIOs **/
 
 /* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/pcm027.h b/arch/arm/mach-pxa/include/mach/pcm027.h
index 6bf28de..86ebd7b 100644
--- a/arch/arm/mach-pxa/include/mach/pcm027.h
+++ b/arch/arm/mach-pxa/include/mach/pcm027.h
@@ -23,6 +23,8 @@
  * Definitions of CPU card resources only
  */
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /* phyCORE-PXA270 (PCM027) Interrupts */
 #define PCM027_IRQ(x)          (IRQ_BOARD_START + (x))
 #define PCM027_BTDET_IRQ       PCM027_IRQ(0)
diff --git a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
index 0260aaa..7e544c1 100644
--- a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
+++ b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
@@ -20,6 +20,7 @@
  */
 
 #include <mach/pcm027.h>
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
 
 /*
  * definitions relevant only when the PCM-990
diff --git a/arch/arm/mach-pxa/include/mach/poodle.h b/arch/arm/mach-pxa/include/mach/poodle.h
index f32ff75..b56b193 100644
--- a/arch/arm/mach-pxa/include/mach/poodle.h
+++ b/arch/arm/mach-pxa/include/mach/poodle.h
@@ -15,6 +15,8 @@
 #ifndef __ASM_ARCH_POODLE_H
 #define __ASM_ARCH_POODLE_H  1
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /*
  * GPIOs
  */
diff --git a/arch/arm/mach-pxa/include/mach/spitz.h b/arch/arm/mach-pxa/include/mach/spitz.h
index 0bfe650..25c9f62 100644
--- a/arch/arm/mach-pxa/include/mach/spitz.h
+++ b/arch/arm/mach-pxa/include/mach/spitz.h
@@ -15,8 +15,8 @@
 #define __ASM_ARCH_SPITZ_H  1
 #endif
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO, PXA_GPIO_TO_IRQ */
 #include <linux/fb.h>
-#include <linux/gpio.h>
 
 /* Spitz/Akita GPIOs */
 
diff --git a/arch/arm/mach-pxa/include/mach/tosa.h b/arch/arm/mach-pxa/include/mach/tosa.h
index 2bb0e86..0497d95 100644
--- a/arch/arm/mach-pxa/include/mach/tosa.h
+++ b/arch/arm/mach-pxa/include/mach/tosa.h
@@ -13,6 +13,8 @@
 #ifndef _ASM_ARCH_TOSA_H_
 #define _ASM_ARCH_TOSA_H_ 1
 
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
+
 /*  TOSA Chip selects  */
 #define TOSA_LCDC_PHYS		PXA_CS4_PHYS
 /* Internel Scoop */
diff --git a/arch/arm/mach-pxa/include/mach/trizeps4.h b/arch/arm/mach-pxa/include/mach/trizeps4.h
index d2ca010..ae3ca01 100644
--- a/arch/arm/mach-pxa/include/mach/trizeps4.h
+++ b/arch/arm/mach-pxa/include/mach/trizeps4.h
@@ -10,6 +10,8 @@
 #ifndef _TRIPEPS4_H_
 #define _TRIPEPS4_H_
 
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
 /* physical memory regions */
 #define TRIZEPS4_FLASH_PHYS	(PXA_CS0_PHYS)  /* Flash region */
 #define TRIZEPS4_DISK_PHYS	(PXA_CS1_PHYS)  /* Disk On Chip region */
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index f70583f..29997bd 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -38,6 +38,7 @@
 #include <linux/mtd/physmap.h>
 #include <linux/usb/gpio_vbus.h>
 #include <linux/reboot.h>
+#include <linux/regulator/fixed.h>
 #include <linux/regulator/max1586.h>
 #include <linux/slab.h>
 #include <linux/i2c/pxa-i2c.h>
@@ -714,6 +715,10 @@
 	{ GPIO56_MT9M111_nOE, GPIOF_OUT_INIT_LOW, "Camera nOE" },
 };
 
+static struct regulator_consumer_supply fixed_5v0_consumers[] = {
+	REGULATOR_SUPPLY("power", "pwm-backlight"),
+};
+
 static void __init mioa701_machine_init(void)
 {
 	int rc;
@@ -753,6 +758,10 @@
 	pxa_set_i2c_info(&i2c_pdata);
 	pxa27x_set_i2c_power_info(NULL);
 	pxa_set_camera_info(&mioa701_pxacamera_platform_data);
+
+	regulator_register_always_on(0, "fixed-5.0V", fixed_5v0_consumers,
+				     ARRAY_SIZE(fixed_5v0_consumers),
+				     5000000);
 }
 
 static void mioa701_machine_exit(void)
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index f33679d..50e1d85 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -13,6 +13,8 @@
 #ifndef __ASM_ARCH_COLLIE_H
 #define __ASM_ARCH_COLLIE_H
 
+#include "hardware.h" /* Gives GPIO_MAX */
+
 extern void locomolcd_power(int on);
 
 #define COLLIE_SCOOP_GPIO_BASE	(GPIO_MAX + 1)
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 3386406..05fa505 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -8,7 +8,7 @@
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select ARM_GIC
 	select MIGHT_HAVE_CACHE_L2X0
diff --git a/arch/arm/mach-tegra/pm.c b/arch/arm/mach-tegra/pm.c
index 4ae0286..f55b05a 100644
--- a/arch/arm/mach-tegra/pm.c
+++ b/arch/arm/mach-tegra/pm.c
@@ -24,6 +24,7 @@
 #include <linux/cpu_pm.h>
 #include <linux/suspend.h>
 #include <linux/err.h>
+#include <linux/slab.h>
 #include <linux/clk/tegra.h>
 
 #include <asm/smp_plat.h>
diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c
index 303a285..6191603 100644
--- a/arch/arm/mach-tegra/tegra.c
+++ b/arch/arm/mach-tegra/tegra.c
@@ -73,10 +73,20 @@
 static void __init tegra_init_cache(void)
 {
 #ifdef CONFIG_CACHE_L2X0
+	static const struct of_device_id pl310_ids[] __initconst = {
+		{ .compatible = "arm,pl310-cache",  },
+		{}
+	};
+
+	struct device_node *np;
 	int ret;
 	void __iomem *p = IO_ADDRESS(TEGRA_ARM_PERIF_BASE) + 0x3000;
 	u32 aux_ctrl, cache_type;
 
+	np = of_find_matching_node(NULL, pl310_ids);
+	if (!np)
+		return;
+
 	cache_type = readl(p + L2X0_CACHE_TYPE);
 	aux_ctrl = (cache_type & 0x700) << (17-8);
 	aux_ctrl |= 0x7C400001;
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 1db2a5ca..8c09a83 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -25,6 +25,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/of.h>
+#include <linux/memblock.h>
 #include <linux/irqchip.h>
 #include <linux/irqchip/arm-gic.h>
 
@@ -41,6 +42,18 @@
 
 void __iomem *zynq_scu_base;
 
+/**
+ * zynq_memory_init - Initialize special memory
+ *
+ * We need to stop things allocating the low memory as DMA can't work in
+ * the 1st 512K of memory.
+ */
+static void __init zynq_memory_init(void)
+{
+	if (!__pa(PAGE_OFFSET))
+		memblock_reserve(__pa(PAGE_OFFSET), __pa(swapper_pg_dir));
+}
+
 static struct platform_device zynq_cpuidle_device = {
 	.name = "cpuidle-zynq",
 };
@@ -117,5 +130,6 @@
 	.init_machine	= zynq_init_machine,
 	.init_time	= zynq_timer_init,
 	.dt_compat	= zynq_dt_match,
+	.reserve	= zynq_memory_init,
 	.restart	= zynq_system_reset,
 MACHINE_END
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1a77450..11b3914 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1358,7 +1358,7 @@
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
-	if (gfp & GFP_ATOMIC)
+	if (!(gfp & __GFP_WAIT))
 		return __iommu_alloc_atomic(dev, size, handle);
 
 	/*
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 2b3a564..ef69152 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -264,6 +264,9 @@
 			note_page(st, addr, 3, pmd_val(*pmd));
 		else
 			walk_pte(st, pmd, addr);
+
+		if (SECTION_SIZE < PMD_SIZE && pmd_large(pmd[1]))
+			note_page(st, addr + SECTION_SIZE, 3, pmd_val(pmd[1]));
 	}
 }
 
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index d5a982d..7ea641b 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -38,6 +38,7 @@
 
 struct mem_type {
 	pteval_t prot_pte;
+	pteval_t prot_pte_s2;
 	pmdval_t prot_l1;
 	pmdval_t prot_sect;
 	unsigned int domain;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4f08c13..a623cb3 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -232,12 +232,16 @@
 #endif /* ifdef CONFIG_CPU_CP15 / else */
 
 #define PROT_PTE_DEVICE		L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_XN
+#define PROT_PTE_S2_DEVICE	PROT_PTE_DEVICE
 #define PROT_SECT_DEVICE	PMD_TYPE_SECT|PMD_SECT_AP_WRITE
 
 static struct mem_type mem_types[] = {
 	[MT_DEVICE] = {		  /* Strongly ordered / ARMv6 shared device */
 		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED |
 				  L_PTE_SHARED,
+		.prot_pte_s2	= s2_policy(PROT_PTE_S2_DEVICE) |
+				  s2_policy(L_PTE_S2_MT_DEV_SHARED) |
+				  L_PTE_SHARED,
 		.prot_l1	= PMD_TYPE_TABLE,
 		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_S,
 		.domain		= DOMAIN_IO,
@@ -508,7 +512,8 @@
 	cp = &cache_policies[cachepolicy];
 	vecs_pgprot = kern_pgprot = user_pgprot = cp->pte;
 	s2_pgprot = cp->pte_s2;
-	hyp_device_pgprot = s2_device_pgprot = mem_types[MT_DEVICE].prot_pte;
+	hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte;
+	s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2;
 
 	/*
 	 * ARMv6 and above have extended page tables.
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 45dc29f..32b3558 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -208,7 +208,6 @@
 	mcr	p15, 0, r0, c7, c14, 0		@ clean+invalidate D cache
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 	mcr	p15, 0, r0, c7, c15, 0		@ clean+invalidate cache
-	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r0, c8, c7, 0		@ invalidate I + D TLBs
 	mcr	p15, 0, r0, c2, c0, 2		@ TTB control register
@@ -218,6 +217,8 @@
 	ALT_UP(orr	r8, r8, #TTB_FLAGS_UP)
 	mcr	p15, 0, r8, c2, c0, 1		@ load TTB1
 #endif /* CONFIG_MMU */
+	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer and
+						@ complete invalidations
 	adr	r5, v6_crval
 	ldmia	r5, {r5, r6}
  ARM_BE8(orr	r6, r6, #1 << 25)		@ big-endian page tables
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index bd17819..74f6033 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -351,7 +351,6 @@
 
 4:	mov	r10, #0
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
-	dsb
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs
 	v7_ttb_setup r10, r4, r8, r5		@ TTBCR, TTBRx setup
@@ -360,6 +359,7 @@
 	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
 	mcr	p15, 0, r6, c10, c2, 1		@ write NMRR
 #endif
+	dsb					@ Complete invalidations
 #ifndef CONFIG_ARM_THUMBEE
 	mrc	p15, 0, r0, c0, c1, 0		@ read ID_PFR0 for ThumbEE
 	and	r0, r0, #(0xf << 12)		@ ThumbEE enabled field
diff --git a/arch/arm/plat-orion/irq.c b/arch/arm/plat-orion/irq.c
index c492e1b..807df14 100644
--- a/arch/arm/plat-orion/irq.c
+++ b/arch/arm/plat-orion/irq.c
@@ -15,8 +15,51 @@
 #include <linux/io.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <asm/exception.h>
 #include <plat/irq.h>
 #include <plat/orion-gpio.h>
+#include <mach/bridge-regs.h>
+
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+/*
+ * Compiling with both non-DT and DT support enabled, will
+ * break asm irq handler used by non-DT boards. Therefore,
+ * we provide a C-style irq handler even for non-DT boards,
+ * if MULTI_IRQ_HANDLER is set.
+ *
+ * Notes:
+ * - this is prepared for Kirkwood and Dove only, update
+ *   accordingly if you add Orion5x or MV78x00.
+ * - Orion5x uses different macro names and has only one
+ *   set of CAUSE/MASK registers.
+ * - MV78x00 uses the same macro names but has a third
+ *   set of CAUSE/MASK registers.
+ *
+ */
+
+static void __iomem *orion_irq_base = IRQ_VIRT_BASE;
+
+asmlinkage void
+__exception_irq_entry orion_legacy_handle_irq(struct pt_regs *regs)
+{
+	u32 stat;
+
+	stat = readl_relaxed(orion_irq_base + IRQ_CAUSE_LOW_OFF);
+	stat &= readl_relaxed(orion_irq_base + IRQ_MASK_LOW_OFF);
+	if (stat) {
+		unsigned int hwirq = __fls(stat);
+		handle_IRQ(hwirq, regs);
+		return;
+	}
+	stat = readl_relaxed(orion_irq_base + IRQ_CAUSE_HIGH_OFF);
+	stat &= readl_relaxed(orion_irq_base + IRQ_MASK_HIGH_OFF);
+	if (stat) {
+		unsigned int hwirq = 32 + __fls(stat);
+		handle_IRQ(hwirq, regs);
+		return;
+	}
+}
+#endif
 
 void __init orion_irq_init(unsigned int irq_start, void __iomem *maskaddr)
 {
@@ -35,6 +78,10 @@
 	ct->chip.irq_unmask = irq_gc_mask_set_bit;
 	irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_MASK_CACHE,
 			       IRQ_NOREQUEST, IRQ_LEVEL | IRQ_NOPROBE);
+
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+	set_handle_irq(orion_legacy_handle_irq);
+#endif
 }
 
 #ifdef CONFIG_OF
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index dd4327f..516d8a7 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -16,6 +16,7 @@
 	select DCACHE_WORD_ACCESS
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -26,6 +27,7 @@
 	select GENERIC_TIME_VSYSCALL
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
@@ -36,7 +38,10 @@
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_MEMBLOCK
+	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
 	select NO_BOOTMEM
@@ -72,7 +77,7 @@
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
+config RWSEM_XCHGADD_ALGORITHM
 	def_bool y
 
 config GENERIC_HWEIGHT
@@ -84,7 +89,7 @@
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
-config ZONE_DMA32
+config ZONE_DMA
 	def_bool y
 
 config ARCH_DMA_ADDR_T_64BIT
@@ -163,6 +168,22 @@
 
 	  If you don't know what to do here, say N.
 
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on SMP
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on SMP
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
@@ -300,6 +321,8 @@
 
 source "drivers/cpuidle/Kconfig"
 
+source "drivers/cpufreq/Kconfig"
+
 endmenu
 
 source "net/Kconfig"
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
index d37d736..93f4b2d 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -176,6 +176,87 @@
 				reg-names = "csr-reg";
 				clock-output-names = "eth8clk";
 			};
+
+			sataphy1clk: sataphy1clk@1f21c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f21c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sataphy1clk";
+				status = "disabled";
+				csr-offset = <0x4>;
+				csr-mask = <0x00>;
+				enable-offset = <0x0>;
+				enable-mask = <0x06>;
+			};
+
+			sataphy2clk: sataphy1clk@1f22c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f22c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sataphy2clk";
+				status = "ok";
+				csr-offset = <0x4>;
+				csr-mask = <0x3a>;
+				enable-offset = <0x0>;
+				enable-mask = <0x06>;
+			};
+
+			sataphy3clk: sataphy1clk@1f23c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f23c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sataphy3clk";
+				status = "ok";
+				csr-offset = <0x4>;
+				csr-mask = <0x3a>;
+				enable-offset = <0x0>;
+				enable-mask = <0x06>;
+			};
+
+			sata01clk: sata01clk@1f21c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f21c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sata01clk";
+				csr-offset = <0x4>;
+				csr-mask = <0x05>;
+				enable-offset = <0x0>;
+				enable-mask = <0x39>;
+			};
+
+			sata23clk: sata23clk@1f22c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f22c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sata23clk";
+				csr-offset = <0x4>;
+				csr-mask = <0x05>;
+				enable-offset = <0x0>;
+				enable-mask = <0x39>;
+			};
+
+			sata45clk: sata45clk@1f23c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f23c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sata45clk";
+				csr-offset = <0x4>;
+				csr-mask = <0x05>;
+				enable-offset = <0x0>;
+				enable-mask = <0x39>;
+			};
 		};
 
 		serial0: serial@1c020000 {
@@ -187,5 +268,76 @@
 			interrupt-parent = <&gic>;
 			interrupts = <0x0 0x4c 0x4>;
 		};
+
+		phy1: phy@1f21a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f21a000 0x0 0x100>;
+			#phy-cells = <1>;
+			clocks = <&sataphy1clk 0>;
+			status = "disabled";
+			apm,tx-boost-gain = <30 30 30 30 30 30>;
+			apm,tx-eye-tuning = <2 10 10 2 10 10>;
+		};
+
+		phy2: phy@1f22a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f22a000 0x0 0x100>;
+			#phy-cells = <1>;
+			clocks = <&sataphy2clk 0>;
+			status = "ok";
+			apm,tx-boost-gain = <30 30 30 30 30 30>;
+			apm,tx-eye-tuning = <1 10 10 2 10 10>;
+		};
+
+		phy3: phy@1f23a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f23a000 0x0 0x100>;
+			#phy-cells = <1>;
+			clocks = <&sataphy3clk 0>;
+			status = "ok";
+			apm,tx-boost-gain = <31 31 31 31 31 31>;
+			apm,tx-eye-tuning = <2 10 10 2 10 10>;
+		};
+
+		sata1: sata@1a000000 {
+			compatible = "apm,xgene-ahci";
+			reg = <0x0 0x1a000000 0x0 0x1000>,
+			      <0x0 0x1f210000 0x0 0x1000>,
+			      <0x0 0x1f21d000 0x0 0x1000>,
+			      <0x0 0x1f21e000 0x0 0x1000>,
+			      <0x0 0x1f217000 0x0 0x1000>;
+			interrupts = <0x0 0x86 0x4>;
+			status = "disabled";
+			clocks = <&sata01clk 0>;
+			phys = <&phy1 0>;
+			phy-names = "sata-phy";
+		};
+
+		sata2: sata@1a400000 {
+			compatible = "apm,xgene-ahci";
+			reg = <0x0 0x1a400000 0x0 0x1000>,
+			      <0x0 0x1f220000 0x0 0x1000>,
+			      <0x0 0x1f22d000 0x0 0x1000>,
+			      <0x0 0x1f22e000 0x0 0x1000>,
+			      <0x0 0x1f227000 0x0 0x1000>;
+			interrupts = <0x0 0x87 0x4>;
+			status = "ok";
+			clocks = <&sata23clk 0>;
+			phys = <&phy2 0>;
+			phy-names = "sata-phy";
+		};
+
+		sata3: sata@1a800000 {
+			compatible = "apm,xgene-ahci";
+			reg = <0x0 0x1a800000 0x0 0x1000>,
+			      <0x0 0x1f230000 0x0 0x1000>,
+			      <0x0 0x1f23d000 0x0 0x1000>,
+			      <0x0 0x1f23e000 0x0 0x1000>;
+			interrupts = <0x0 0x88 0x4>;
+			status = "ok";
+			clocks = <&sata45clk 0>;
+			phys = <&phy3 0>;
+			phy-names = "sata-phy";
+		};
 	};
 };
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 84139be..7959dd0 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1,4 +1,3 @@
-CONFIG_EXPERIMENTAL=y
 # CONFIG_LOCALVERSION_AUTO is not set
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
@@ -19,6 +18,7 @@
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
+CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
@@ -27,6 +27,7 @@
 CONFIG_ARCH_XGENE=y
 CONFIG_SMP=y
 CONFIG_PREEMPT=y
+CONFIG_CMA=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
@@ -42,14 +43,17 @@
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
-CONFIG_BLK_DEV=y
+CONFIG_DMA_CMA=y
 CONFIG_SCSI=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
 # CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_ATA=y
+CONFIG_PATA_PLATFORM=y
+CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
-CONFIG_MII=y
 CONFIG_SMC91X=y
+CONFIG_SMSC911X=y
 # CONFIG_WLAN is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_SERIO_I8042 is not set
@@ -62,13 +66,19 @@
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_FB=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_USB_SUPPORT is not set
+CONFIG_USB=y
+CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 3bdfdda..4bca4923 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -32,6 +32,7 @@
 generic-y += posix_types.h
 generic-y += preempt.h
 generic-y += resource.h
+generic-y += rwsem.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += segment.h
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 01de5aa..0237f08 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -54,8 +54,7 @@
 "	stxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline int atomic_add_return(int i, atomic_t *v)
@@ -64,14 +63,15 @@
 	int result;
 
 	asm volatile("// atomic_add_return\n"
-"1:	ldaxr	%w0, %2\n"
+"1:	ldxr	%w0, %2\n"
 "	add	%w0, %w0, %w3\n"
 "	stlxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -86,8 +86,7 @@
 "	stxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline int atomic_sub_return(int i, atomic_t *v)
@@ -96,14 +95,15 @@
 	int result;
 
 	asm volatile("// atomic_sub_return\n"
-"1:	ldaxr	%w0, %2\n"
+"1:	ldxr	%w0, %2\n"
 "	sub	%w0, %w0, %w3\n"
 "	stlxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -112,17 +112,20 @@
 	unsigned long tmp;
 	int oldval;
 
+	smp_mb();
+
 	asm volatile("// atomic_cmpxchg\n"
-"1:	ldaxr	%w1, %2\n"
+"1:	ldxr	%w1, %2\n"
 "	cmp	%w1, %w3\n"
 "	b.ne	2f\n"
-"	stlxr	%w0, %w4, %2\n"
+"	stxr	%w0, %w4, %2\n"
 "	cbnz	%w0, 1b\n"
 "2:"
 	: "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter)
 	: "Ir" (old), "r" (new)
-	: "cc", "memory");
+	: "cc");
 
+	smp_mb();
 	return oldval;
 }
 
@@ -173,8 +176,7 @@
 "	stxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline long atomic64_add_return(long i, atomic64_t *v)
@@ -183,14 +185,15 @@
 	unsigned long tmp;
 
 	asm volatile("// atomic64_add_return\n"
-"1:	ldaxr	%0, %2\n"
+"1:	ldxr	%0, %2\n"
 "	add	%0, %0, %3\n"
 "	stlxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -205,8 +208,7 @@
 "	stxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline long atomic64_sub_return(long i, atomic64_t *v)
@@ -215,14 +217,15 @@
 	unsigned long tmp;
 
 	asm volatile("// atomic64_sub_return\n"
-"1:	ldaxr	%0, %2\n"
+"1:	ldxr	%0, %2\n"
 "	sub	%0, %0, %3\n"
 "	stlxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -231,17 +234,20 @@
 	long oldval;
 	unsigned long res;
 
+	smp_mb();
+
 	asm volatile("// atomic64_cmpxchg\n"
-"1:	ldaxr	%1, %2\n"
+"1:	ldxr	%1, %2\n"
 "	cmp	%1, %3\n"
 "	b.ne	2f\n"
-"	stlxr	%w0, %4, %2\n"
+"	stxr	%w0, %4, %2\n"
 "	cbnz	%w0, 1b\n"
 "2:"
 	: "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter)
 	: "Ir" (old), "r" (new)
-	: "cc", "memory");
+	: "cc");
 
+	smp_mb();
 	return oldval;
 }
 
@@ -253,11 +259,12 @@
 	unsigned long tmp;
 
 	asm volatile("// atomic64_dec_if_positive\n"
-"1:	ldaxr	%0, %2\n"
+"1:	ldxr	%0, %2\n"
 "	subs	%0, %0, #1\n"
 "	b.mi	2f\n"
 "	stlxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b\n"
+"	dmb	ish\n"
 "2:"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	:
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 78e20ba..66eb764 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -25,7 +25,8 @@
 #define wfi()		asm volatile("wfi" : : : "memory")
 
 #define isb()		asm volatile("isb" : : : "memory")
-#define dsb()		asm volatile("dsb sy" : : : "memory")
+#define dmb(opt)	asm volatile("dmb sy" : : : "memory")
+#define dsb(opt)	asm volatile("dsb sy" : : : "memory")
 
 #define mb()		dsb()
 #define rmb()		asm volatile("dsb ld" : : : "memory")
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index fea9ee3..4c60e64 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -85,6 +85,13 @@
 }
 
 /*
+ * Cache maintenance functions used by the DMA API. No to be used directly.
+ */
+extern void __dma_map_area(const void *, size_t, int);
+extern void __dma_unmap_area(const void *, size_t, int);
+extern void __dma_flush_range(const void *, const void *);
+
+/*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user
  * space" model to handle this.
@@ -116,6 +123,7 @@
 static inline void __flush_icache_all(void)
 {
 	asm("ic	ialluis");
+	dsb();
 }
 
 #define flush_dcache_mmap_lock(mapping) \
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 56166d7..57c0fa7 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -29,44 +29,45 @@
 	switch (size) {
 	case 1:
 		asm volatile("//	__xchg1\n"
-		"1:	ldaxrb	%w0, %2\n"
+		"1:	ldxrb	%w0, %2\n"
 		"	stlxrb	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	case 2:
 		asm volatile("//	__xchg2\n"
-		"1:	ldaxrh	%w0, %2\n"
+		"1:	ldxrh	%w0, %2\n"
 		"	stlxrh	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	case 4:
 		asm volatile("//	__xchg4\n"
-		"1:	ldaxr	%w0, %2\n"
+		"1:	ldxr	%w0, %2\n"
 		"	stlxr	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	case 8:
 		asm volatile("//	__xchg8\n"
-		"1:	ldaxr	%0, %2\n"
+		"1:	ldxr	%0, %2\n"
 		"	stlxr	%w1, %3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	default:
 		BUILD_BUG();
 	}
 
+	smp_mb();
 	return ret;
 }
 
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index fda2704..e71f81f 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -228,7 +228,7 @@
 	return (u32)(unsigned long)uptr;
 }
 
-#define compat_user_stack_pointer() (current_pt_regs()->compat_sp)
+#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
new file mode 100644
index 0000000..cd4ac05
--- /dev/null
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_CPUFEATURE_H
+#define __ASM_CPUFEATURE_H
+
+#include <asm/hwcap.h>
+
+/*
+ * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
+ * in the kernel and for user space to keep track of which optional features
+ * are supported by the current system. So let's map feature 'x' to HWCAP_x.
+ * Note that HWCAP_x constants are bit fields so we need to take the log.
+ */
+
+#define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
+#define cpu_feature(x)		ilog2(HWCAP_ ## x)
+
+static inline bool cpu_have_feature(unsigned int num)
+{
+	return elf_hwcap & (1UL << num);
+}
+
+#endif
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 6231479..6e9b5b3 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -26,6 +26,53 @@
 #define DBG_ESR_EVT_HWWP	0x2
 #define DBG_ESR_EVT_BRK		0x6
 
+/*
+ * Break point instruction encoding
+ */
+#define BREAK_INSTR_SIZE		4
+
+/*
+ * ESR values expected for dynamic and compile time BRK instruction
+ */
+#define DBG_ESR_VAL_BRK(x)	(0xf2000000 | ((x) & 0xfffff))
+
+/*
+ * #imm16 values used for BRK instruction generation
+ * Allowed values for kgbd are 0x400 - 0x7ff
+ * 0x400: for dynamic BRK instruction
+ * 0x401: for compile time BRK instruction
+ */
+#define KGDB_DYN_DGB_BRK_IMM		0x400
+#define KDBG_COMPILED_DBG_BRK_IMM	0x401
+
+/*
+ * BRK instruction encoding
+ * The #imm16 value should be placed at bits[20:5] within BRK ins
+ */
+#define AARCH64_BREAK_MON	0xd4200000
+
+/*
+ * Extract byte from BRK instruction
+ */
+#define KGDB_DYN_DGB_BRK_INS_BYTE(x) \
+	((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff)
+
+/*
+ * Extract byte from BRK #imm16
+ */
+#define KGBD_DYN_DGB_BRK_IMM_BYTE(x) \
+	(((((KGDB_DYN_DGB_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
+
+#define KGDB_DYN_DGB_BRK_BYTE(x) \
+	(KGDB_DYN_DGB_BRK_INS_BYTE(x) | KGBD_DYN_DGB_BRK_IMM_BYTE(x))
+
+#define  KGDB_DYN_BRK_INS_BYTE0  KGDB_DYN_DGB_BRK_BYTE(0)
+#define  KGDB_DYN_BRK_INS_BYTE1  KGDB_DYN_DGB_BRK_BYTE(1)
+#define  KGDB_DYN_BRK_INS_BYTE2  KGDB_DYN_DGB_BRK_BYTE(2)
+#define  KGDB_DYN_BRK_INS_BYTE3  KGDB_DYN_DGB_BRK_BYTE(3)
+
+#define CACHE_FLUSH_IS_SAFE		1
+
 enum debug_el {
 	DBG_ACTIVE_EL0 = 0,
 	DBG_ACTIVE_EL1,
@@ -43,23 +90,6 @@
 #ifndef __ASSEMBLY__
 struct task_struct;
 
-#define local_dbg_save(flags)							\
-	do {									\
-		typecheck(unsigned long, flags);				\
-		asm volatile(							\
-		"mrs	%0, daif			// local_dbg_save\n"	\
-		"msr	daifset, #8"						\
-		: "=r" (flags) : : "memory");					\
-	} while (0)
-
-#define local_dbg_restore(flags)						\
-	do {									\
-		typecheck(unsigned long, flags);				\
-		asm volatile(							\
-		"msr	daif, %0			// local_dbg_restore\n"	\
-		: : "r" (flags) : "memory");					\
-	} while (0)
-
 #define DBG_ARCH_ID_RESERVED	0	/* In case of ptrace ABI updates. */
 
 #define DBG_HOOK_HANDLED	0
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index fd0c0c0..3a4572e 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -30,6 +30,8 @@
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
+extern struct dma_map_ops coherent_swiotlb_dma_ops;
+extern struct dma_map_ops noncoherent_swiotlb_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
@@ -47,6 +49,11 @@
 		return __generic_dma_ops(dev);
 }
 
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+	dev->archdata.dma_ops = ops;
+}
+
 #include <asm-generic/dma-mapping-common.h>
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 7883412..c4a7f94 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -42,7 +42,7 @@
 #define ESR_EL1_EC_SP_ALIGN	(0x26)
 #define ESR_EL1_EC_FP_EXC32	(0x28)
 #define ESR_EL1_EC_FP_EXC64	(0x2C)
-#define ESR_EL1_EC_SERRROR	(0x2F)
+#define ESR_EL1_EC_SERROR	(0x2F)
 #define ESR_EL1_EC_BREAKPT_EL0	(0x30)
 #define ESR_EL1_EC_BREAKPT_EL1	(0x31)
 #define ESR_EL1_EC_SOFTSTP_EL0	(0x32)
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 78cc3ab..5f750dc 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -24,10 +24,11 @@
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
 	asm volatile(							\
-"1:	ldaxr	%w1, %2\n"						\
+"1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
 "2:	stlxr	%w3, %w0, %2\n"						\
 "	cbnz	%w3, 1b\n"						\
+"	dmb	ish\n"							\
 "3:\n"									\
 "	.pushsection .fixup,\"ax\"\n"					\
 "	.align	2\n"							\
@@ -40,7 +41,7 @@
 "	.popsection\n"							\
 	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
 	: "r" (oparg), "Ir" (-EFAULT)					\
-	: "cc", "memory")
+	: "memory")
 
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
@@ -111,11 +112,12 @@
 		return -EFAULT;
 
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
-"1:	ldaxr	%w1, %2\n"
+"1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
 "	cbnz	%w3, 3f\n"
 "2:	stlxr	%w3, %w5, %2\n"
 "	cbnz	%w3, 1b\n"
+"	dmb	ish\n"
 "3:\n"
 "	.pushsection .fixup,\"ax\"\n"
 "4:	mov	%w0, %w6\n"
@@ -127,7 +129,7 @@
 "	.popsection\n"
 	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
 	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
-	: "cc", "memory");
+	: "memory");
 
 	*uval = val;
 	return ret;
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 6cddbb0..024c461 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -32,6 +32,12 @@
 #define COMPAT_HWCAP_IDIV	(COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
 #define COMPAT_HWCAP_EVTSTRM	(1 << 21)
 
+#define COMPAT_HWCAP2_AES	(1 << 0)
+#define COMPAT_HWCAP2_PMULL	(1 << 1)
+#define COMPAT_HWCAP2_SHA1	(1 << 2)
+#define COMPAT_HWCAP2_SHA2	(1 << 3)
+#define COMPAT_HWCAP2_CRC32	(1 << 4)
+
 #ifndef __ASSEMBLY__
 /*
  * This yields a mask that user programs can use to figure out what
@@ -41,7 +47,8 @@
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP	(compat_elf_hwcap)
-extern unsigned int compat_elf_hwcap;
+#define COMPAT_ELF_HWCAP2	(compat_elf_hwcap2)
+extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
 #endif
 
 extern unsigned long elf_hwcap;
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 4cc813e..7846a6b 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -121,7 +121,7 @@
  *  I/O port access primitives.
  */
 #define IO_SPACE_LIMIT		0xffff
-#define PCI_IOBASE		((void __iomem *)(MODULES_VADDR - SZ_2M))
+#define PCI_IOBASE		((void __iomem *)(MODULES_VADDR - SZ_32M))
 
 static inline u8 inb(unsigned long addr)
 {
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index b2fcfbc..11cc941 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -90,5 +90,28 @@
 	return flags & PSR_I_BIT;
 }
 
+/*
+ * save and restore debug state
+ */
+#define local_dbg_save(flags)						\
+	do {								\
+		typecheck(unsigned long, flags);			\
+		asm volatile(						\
+		"mrs    %0, daif		// local_dbg_save\n"	\
+		"msr    daifset, #8"					\
+		: "=r" (flags) : : "memory");				\
+	} while (0)
+
+#define local_dbg_restore(flags)					\
+	do {								\
+		typecheck(unsigned long, flags);			\
+		asm volatile(						\
+		"msr    daif, %0		// local_dbg_restore\n"	\
+		: : "r" (flags) : "memory");				\
+	} while (0)
+
+#define local_dbg_enable()	asm("msr	daifclr, #8" : : : "memory")
+#define local_dbg_disable()	asm("msr	daifset, #8" : : : "memory")
+
 #endif
 #endif
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
new file mode 100644
index 0000000..3c8aafc
--- /dev/null
+++ b/arch/arm64/include/asm/kgdb.h
@@ -0,0 +1,84 @@
+/*
+ * AArch64 KGDB support
+ *
+ * Based on arch/arm/include/kgdb.h
+ *
+ * Copyright (C) 2013 Cavium Inc.
+ * Author: Vijaya Kumar K <vijaya.kumar@caviumnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KGDB_H
+#define __ARM_KGDB_H
+
+#include <linux/ptrace.h>
+#include <asm/debug-monitors.h>
+
+#ifndef	__ASSEMBLY__
+
+static inline void arch_kgdb_breakpoint(void)
+{
+	asm ("brk %0" : : "I" (KDBG_COMPILED_DBG_BRK_IMM));
+}
+
+extern void kgdb_handle_bus_error(void);
+extern int kgdb_fault_expected;
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * gdb is expecting the following registers layout.
+ *
+ * General purpose regs:
+ *     r0-r30: 64 bit
+ *     sp,pc : 64 bit
+ *     pstate  : 64 bit
+ *     Total: 34
+ * FPU regs:
+ *     f0-f31: 128 bit
+ *     Total: 32
+ * Extra regs
+ *     fpsr & fpcr: 32 bit
+ *     Total: 2
+ *
+ */
+
+#define _GP_REGS		34
+#define _FP_REGS		32
+#define _EXTRA_REGS		2
+/*
+ * general purpose registers size in bytes.
+ * pstate is only 4 bytes. subtract 4 bytes
+ */
+#define GP_REG_BYTES		(_GP_REGS * 8)
+#define DBG_MAX_REG_NUM		(_GP_REGS + _FP_REGS + _EXTRA_REGS)
+
+/*
+ * Size of I/O buffer for gdb packet.
+ * considering to hold all register contents, size is set
+ */
+
+#define BUFMAX			2048
+
+/*
+ * Number of bytes required for gdb_regs buffer.
+ * _GP_REGS: 8 bytes, _FP_REGS: 16 bytes and _EXTRA_REGS: 4 bytes each
+ * GDB fails to connect for size beyond this with error
+ * "'g' packet reply is too long"
+ */
+
+#define NUMREGBYTES	((_GP_REGS * 8) + (_FP_REGS * 16) + \
+			(_EXTRA_REGS * 4))
+
+#endif /* __ASM_KGDB_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index c98ef47..21ef48d 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -106,7 +106,6 @@
 
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_PS_MASK	(7 << 16)
-#define VTCR_EL2_PS_40B		(2 << 16)
 #define VTCR_EL2_TG0_MASK	(1 << 14)
 #define VTCR_EL2_TG0_4K		(0 << 14)
 #define VTCR_EL2_TG0_64K	(1 << 14)
@@ -129,10 +128,9 @@
  * 64kB pages (TG0 = 1)
  * 2 level page tables (SL = 1)
  */
-#define VTCR_EL2_FLAGS		(VTCR_EL2_PS_40B | VTCR_EL2_TG0_64K | \
-				 VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
-				 VTCR_EL2_IRGN0_WBWA | VTCR_EL2_SL0_LVL1 | \
-				 VTCR_EL2_T0SZ_40B)
+#define VTCR_EL2_FLAGS		(VTCR_EL2_TG0_64K | VTCR_EL2_SH0_INNER | \
+				 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
+				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B)
 #define VTTBR_X		(38 - VTCR_EL2_T0SZ_40B)
 #else
 /*
@@ -142,10 +140,9 @@
  * 4kB pages (TG0 = 0)
  * 3 level page tables (SL = 1)
  */
-#define VTCR_EL2_FLAGS		(VTCR_EL2_PS_40B | VTCR_EL2_TG0_4K | \
-				 VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
-				 VTCR_EL2_IRGN0_WBWA | VTCR_EL2_SL0_LVL1 | \
-				 VTCR_EL2_T0SZ_40B)
+#define VTCR_EL2_FLAGS		(VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \
+				 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
+				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B)
 #define VTTBR_X		(37 - VTCR_EL2_T0SZ_40B)
 #endif
 
@@ -231,7 +228,7 @@
 #define ESR_EL2_EC_SP_ALIGN	(0x26)
 #define ESR_EL2_EC_FP_EXC32	(0x28)
 #define ESR_EL2_EC_FP_EXC64	(0x2C)
-#define ESR_EL2_EC_SERRROR	(0x2F)
+#define ESR_EL2_EC_SERROR	(0x2F)
 #define ESR_EL2_EC_BREAKPT	(0x30)
 #define ESR_EL2_EC_BREAKPT_HYP	(0x31)
 #define ESR_EL2_EC_SOFTSTP	(0x32)
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 13fb0b3..453a179 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
+#ifdef CONFIG_SMP
+
 static inline void set_my_cpu_offset(unsigned long off)
 {
 	asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
@@ -36,6 +38,12 @@
 }
 #define __my_cpu_offset __my_cpu_offset()
 
+#else	/* !CONFIG_SMP */
+
+#define set_my_cpu_offset(x)	do { } while (0)
+
+#endif /* CONFIG_SMP */
+
 #include <asm-generic/percpu.h>
 
 #endif /* __ASM_PERCPU_H */
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index b1d2e26..f7af66b 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -100,9 +100,9 @@
 #define PTE_HYP			PTE_USER
 
 /*
- * 40-bit physical address supported.
+ * Highest possible physical address supported.
  */
-#define PHYS_MASK_SHIFT		(40)
+#define PHYS_MASK_SHIFT		(48)
 #define PHYS_MASK		((UL(1) << PHYS_MASK_SHIFT) - 1)
 
 /*
@@ -122,7 +122,6 @@
 #define TCR_SHARED		((UL(3) << 12) | (UL(3) << 28))
 #define TCR_TG0_64K		(UL(1) << 14)
 #define TCR_TG1_64K		(UL(1) << 30)
-#define TCR_IPS_40BIT		(UL(2) << 32)
 #define TCR_ASID16		(UL(1) << 36)
 #define TCR_TBI0		(UL(1) << 37)
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b524dcd..90c811f 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -136,11 +136,11 @@
 /*
  * The following only work if pte_present(). Undefined behaviour otherwise.
  */
-#define pte_present(pte)	(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))
-#define pte_dirty(pte)		(pte_val(pte) & PTE_DIRTY)
-#define pte_young(pte)		(pte_val(pte) & PTE_AF)
-#define pte_special(pte)	(pte_val(pte) & PTE_SPECIAL)
-#define pte_write(pte)		(pte_val(pte) & PTE_WRITE)
+#define pte_present(pte)	(!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)))
+#define pte_dirty(pte)		(!!(pte_val(pte) & PTE_DIRTY))
+#define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
+#define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
+#define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 
 #define pte_valid_user(pte) \
@@ -199,7 +199,7 @@
 			      pte_t *ptep, pte_t pte)
 {
 	if (pte_valid_user(pte)) {
-		if (pte_exec(pte))
+		if (!pte_special(pte) && pte_exec(pte))
 			__sync_icache_dcache(pte, addr);
 		if (pte_dirty(pte) && pte_write(pte))
 			pte_val(pte) &= ~PTE_RDONLY;
@@ -227,36 +227,36 @@
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
-/*
- * Software PMD bits for THP
- */
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
 
-#define PMD_SECT_DIRTY		(_AT(pmdval_t, 1) << 55)
-#define PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 57)
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
 
 /*
  * THP definitions.
  */
-#define pmd_young(pmd)		(pmd_val(pmd) & PMD_SECT_AF)
-
-#define __HAVE_ARCH_PMD_WRITE
-#define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
-#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#define pmd_trans_splitting(pmd)	pte_special(pmd_pte(pmd))
 #endif
 
-#define PMD_BIT_FUNC(fn,op) \
-static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
+#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mksplitting(pmd)	pte_pmd(pte_mkspecial(pmd_pte(pmd)))
+#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) &= ~PMD_TYPE_MASK))
 
-PMD_BIT_FUNC(wrprotect,	|= PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
-PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
-PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
-PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
-PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK);
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
 
@@ -266,15 +266,6 @@
 
 #define pmd_page(pmd)           pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
 
-static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
-{
-	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_PXN | PMD_SECT_UXN |
-			      PMD_SECT_RDONLY | PMD_SECT_PROT_NONE |
-			      PMD_SECT_VALID;
-	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
-	return pmd;
-}
-
 #define set_pmd_at(mm, addr, pmdp, pmd)	set_pmd(pmdp, pmd)
 
 static inline int has_transparent_hugepage(void)
@@ -286,11 +277,9 @@
  * Mark the prot value as uncacheable and unbufferable.
  */
 #define pgprot_noncached(prot) \
-	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN)
 #define pgprot_writecombine(prot) \
-	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
-#define pgprot_dmacoherent(prot) \
-	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 struct file;
 extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -383,6 +372,11 @@
 	return pte;
 }
 
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
+}
+
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
diff --git a/arch/arm64/include/asm/psci.h b/arch/arm64/include/asm/psci.h
index e5312ea..d15ab8b4 100644
--- a/arch/arm64/include/asm/psci.h
+++ b/arch/arm64/include/asm/psci.h
@@ -14,6 +14,6 @@
 #ifndef __ASM_PSCI_H
 #define __ASM_PSCI_H
 
-int psci_init(void);
+void psci_init(void);
 
 #endif /* __ASM_PSCI_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 0e7fa49..c7ba261 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -68,6 +68,7 @@
 
 /* Architecturally defined mapping between AArch32 and AArch64 registers */
 #define compat_usr(x)	regs[(x)]
+#define compat_fp	regs[11]
 #define compat_sp	regs[13]
 #define compat_lr	regs[14]
 #define compat_sp_hyp	regs[15]
@@ -132,7 +133,7 @@
 	(!((regs)->pstate & PSR_F_BIT))
 
 #define user_stack_pointer(regs) \
-	((regs)->sp)
+	(!compat_user_mode(regs)) ? ((regs)->sp) : ((regs)->compat_sp)
 
 /*
  * Are the current registers suitable for user mode? (used to maintain
@@ -164,7 +165,7 @@
 	return 0;
 }
 
-#define instruction_pointer(regs)	(regs)->pc
+#define instruction_pointer(regs)	((unsigned long)(regs)->pc)
 
 #ifdef CONFIG_SMP
 extern unsigned long profile_pc(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 3d5cf06..c45b7b1 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -132,7 +132,7 @@
 	"	cbnz	%w0, 2b\n"
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
-	: "cc", "memory");
+	: "memory");
 }
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
@@ -146,7 +146,7 @@
 	"1:\n"
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
-	: "cc", "memory");
+	: "memory");
 
 	return !tmp;
 }
@@ -187,7 +187,7 @@
 	"	cbnz	%w1, 2b\n"
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
-	: "cc", "memory");
+	: "memory");
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
@@ -201,7 +201,7 @@
 	"	cbnz	%w1, 1b\n"
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
-	: "cc", "memory");
+	: "memory");
 }
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
@@ -216,7 +216,7 @@
 	"1:\n"
 	: "=&r" (tmp), "+r" (tmp2), "+Q" (rw->lock)
 	:
-	: "cc", "memory");
+	: "memory");
 
 	return !tmp2;
 }
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 717031a..72cadf5 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -19,115 +19,44 @@
 #ifndef __ASM_TLB_H
 #define __ASM_TLB_H
 
-#include <linux/pagemap.h>
-#include <linux/swap.h>
 
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-
-#define MMU_GATHER_BUNDLE	8
+#include <asm-generic/tlb.h>
 
 /*
- * TLB handling.  This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		fullmm;
-	struct vm_area_struct	*vma;
-	unsigned long		start, end;
-	unsigned long		range_start;
-	unsigned long		range_end;
-	unsigned int		nr;
-	unsigned int		max;
-	struct page		**pages;
-	struct page		*local[MMU_GATHER_BUNDLE];
-};
-
-/*
- * This is unnecessarily complex.  There's three ways the TLB shootdown
- * code is used:
+ * There's three ways the TLB shootdown code is used:
  *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
  *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.
  *  2. Unmapping all vmas.  See exit_mmap().
  *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.  Additionally, page tables will be freed.
+ *     Page tables will be freed.
  *  3. Unmapping argument pages.  See shift_arg_pages().
  *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- *     tlb->vma will be NULL.
  */
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	if (tlb->fullmm || !tlb->vma)
+	if (tlb->fullmm) {
 		flush_tlb_mm(tlb->mm);
-	else if (tlb->range_end > 0) {
-		flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
-		tlb->range_start = TASK_SIZE;
-		tlb->range_end = 0;
+	} else if (tlb->end > 0) {
+		struct vm_area_struct vma = { .vm_mm = tlb->mm, };
+		flush_tlb_range(&vma, tlb->start, tlb->end);
+		tlb->start = TASK_SIZE;
+		tlb->end = 0;
 	}
 }
 
 static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
 {
 	if (!tlb->fullmm) {
-		if (addr < tlb->range_start)
-			tlb->range_start = addr;
-		if (addr + PAGE_SIZE > tlb->range_end)
-			tlb->range_end = addr + PAGE_SIZE;
+		tlb->start = min(tlb->start, addr);
+		tlb->end = max(tlb->end, addr + PAGE_SIZE);
 	}
 }
 
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
-	if (addr) {
-		tlb->pages = (void *)addr;
-		tlb->max = PAGE_SIZE / sizeof(struct page *);
-	}
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush(tlb);
-	free_pages_and_swap_cache(tlb->pages, tlb->nr);
-	tlb->nr = 0;
-	if (tlb->pages == tlb->local)
-		__tlb_alloc_page(tlb);
-}
-
-static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->fullmm = !(start | (end+1));
-	tlb->start = start;
-	tlb->end = end;
-	tlb->vma = NULL;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->pages = tlb->local;
-	tlb->nr = 0;
-	__tlb_alloc_page(tlb);
-}
-
-static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->pages != tlb->local)
-		free_pages((unsigned long)tlb->pages, 0);
-}
-
 /*
  * Memorize the range for the TLB flush.
  */
-static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
+static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
+					  unsigned long addr)
 {
 	tlb_add_flush(tlb, addr);
 }
@@ -137,38 +66,24 @@
  * case where we're doing a full MM flush.  When we're doing a munmap,
  * the vmas are adjusted to only cover the region to be torn down.
  */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+static inline void tlb_start_vma(struct mmu_gather *tlb,
+				 struct vm_area_struct *vma)
 {
 	if (!tlb->fullmm) {
-		tlb->vma = vma;
-		tlb->range_start = TASK_SIZE;
-		tlb->range_end = 0;
+		tlb->start = TASK_SIZE;
+		tlb->end = 0;
 	}
 }
 
-static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+static inline void tlb_end_vma(struct mmu_gather *tlb,
+			       struct vm_area_struct *vma)
 {
 	if (!tlb->fullmm)
 		tlb_flush(tlb);
 }
 
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->pages[tlb->nr++] = page;
-	VM_BUG_ON(tlb->nr > tlb->max);
-	return tlb->max - tlb->nr;
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (!__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
-
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
-	unsigned long addr)
+				  unsigned long addr)
 {
 	pgtable_page_dtor(pte);
 	tlb_add_flush(tlb, addr);
@@ -184,16 +99,5 @@
 }
 #endif
 
-#define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
-#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm)		do { } while (0)
-
-static inline void
-tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
 
 #endif
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
new file mode 100644
index 0000000..0172e6d
--- /dev/null
+++ b/arch/arm64/include/asm/topology.h
@@ -0,0 +1,39 @@
+#ifndef __ASM_TOPOLOGY_H
+#define __ASM_TOPOLOGY_H
+
+#ifdef CONFIG_SMP
+
+#include <linux/cpumask.h>
+
+struct cpu_topology {
+	int thread_id;
+	int core_id;
+	int cluster_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cpu_topology cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].cluster_id)
+#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable()	(cpu_topology[0].cluster_id != -1)
+#define smt_capable()	(cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(int cpu);
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 6c0f684..3bf8f4e 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -83,7 +83,7 @@
  * Returns 1 if the range is valid, 0 otherwise.
  *
  * This is equivalent to the following test:
- * (u65)addr + (u65)size < (u65)current->addr_limit
+ * (u65)addr + (u65)size <= current->addr_limit
  *
  * This needs 65-bit arithmetic.
  */
@@ -91,7 +91,7 @@
 ({									\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
-	asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, cc"		\
+	asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls"		\
 		: "=&r" (flag), "=&r" (roksum)				\
 		: "1" (addr), "Ir" (size),				\
 		  "r" (current_thread_info()->addr_limit)		\
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 82ce217..a4654c6 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -14,6 +14,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #ifdef CONFIG_COMPAT
+#define __ARCH_WANT_COMPAT_SYS_GETDENTS64
 #define __ARCH_WANT_COMPAT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
 #define __ARCH_WANT_SYS_PAUSE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 58125bf..bb8eb8a 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -399,7 +399,10 @@
 __SYSCALL(375, sys_setns)
 __SYSCALL(376, compat_sys_process_vm_readv)
 __SYSCALL(377, compat_sys_process_vm_writev)
-__SYSCALL(378, sys_ni_syscall)			/* 378 for kcmp */
+__SYSCALL(378, sys_kcmp)
+__SYSCALL(379, sys_finit_module)
+__SYSCALL(380, sys_sched_setattr)
+__SYSCALL(381, sys_sched_getattr)
 
 #define __NR_compat_syscalls		379
 
diff --git a/arch/arm64/include/uapi/asm/Kbuild b/arch/arm64/include/uapi/asm/Kbuild
index e4b78bd..942376d 100644
--- a/arch/arm64/include/uapi/asm/Kbuild
+++ b/arch/arm64/include/uapi/asm/Kbuild
@@ -9,6 +9,7 @@
 header-y += fcntl.h
 header-y += hwcap.h
 header-y += kvm_para.h
+header-y += perf_regs.h
 header-y += param.h
 header-y += ptrace.h
 header-y += setup.h
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 495ab6f..eaf54a3 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -148,6 +148,15 @@
 #define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
 
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR	0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
+#define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
+#define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
+#define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
 #define KVM_ARM_IRQ_TYPE_MASK		0xff
diff --git a/arch/arm64/include/uapi/asm/perf_regs.h b/arch/arm64/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000..172b831
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/perf_regs.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_ARM64_PERF_REGS_H
+#define _ASM_ARM64_PERF_REGS_H
+
+enum perf_event_arm_regs {
+	PERF_REG_ARM64_X0,
+	PERF_REG_ARM64_X1,
+	PERF_REG_ARM64_X2,
+	PERF_REG_ARM64_X3,
+	PERF_REG_ARM64_X4,
+	PERF_REG_ARM64_X5,
+	PERF_REG_ARM64_X6,
+	PERF_REG_ARM64_X7,
+	PERF_REG_ARM64_X8,
+	PERF_REG_ARM64_X9,
+	PERF_REG_ARM64_X10,
+	PERF_REG_ARM64_X11,
+	PERF_REG_ARM64_X12,
+	PERF_REG_ARM64_X13,
+	PERF_REG_ARM64_X14,
+	PERF_REG_ARM64_X15,
+	PERF_REG_ARM64_X16,
+	PERF_REG_ARM64_X17,
+	PERF_REG_ARM64_X18,
+	PERF_REG_ARM64_X19,
+	PERF_REG_ARM64_X20,
+	PERF_REG_ARM64_X21,
+	PERF_REG_ARM64_X22,
+	PERF_REG_ARM64_X23,
+	PERF_REG_ARM64_X24,
+	PERF_REG_ARM64_X25,
+	PERF_REG_ARM64_X26,
+	PERF_REG_ARM64_X27,
+	PERF_REG_ARM64_X28,
+	PERF_REG_ARM64_X29,
+	PERF_REG_ARM64_LR,
+	PERF_REG_ARM64_SP,
+	PERF_REG_ARM64_PC,
+	PERF_REG_ARM64_MAX,
+};
+#endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2d4554b..7d811d9 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -14,12 +14,14 @@
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
-arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o
+arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o topology.o
+arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
-arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
+arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 arm64-obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND)	+= sleep.o suspend.o
 arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
+arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 636ba8b..14ba23c 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -137,7 +137,6 @@
 static void clear_os_lock(void *unused)
 {
 	asm volatile("msr oslar_el1, %0" : : "r" (0));
-	isb();
 }
 
 static int os_lock_notify(struct notifier_block *self,
@@ -156,8 +155,9 @@
 static int debug_monitors_init(void)
 {
 	/* Clear the OS lock. */
-	smp_call_function(clear_os_lock, NULL, 1);
-	clear_os_lock(NULL);
+	on_each_cpu(clear_os_lock, NULL, 1);
+	isb();
+	local_dbg_enable();
 
 	/* Register hotplug handler. */
 	register_cpu_notifier(&os_lock_nb);
@@ -189,7 +189,7 @@
 
 /* EL1 Single Step Handler hooks */
 static LIST_HEAD(step_hook);
-DEFINE_RWLOCK(step_hook_lock);
+static DEFINE_RWLOCK(step_hook_lock);
 
 void register_step_hook(struct step_hook *hook)
 {
@@ -276,7 +276,7 @@
  * Use reader/writer locks instead of plain spinlock.
  */
 static LIST_HEAD(break_hook);
-DEFINE_RWLOCK(break_hook_lock);
+static DEFINE_RWLOCK(break_hook_lock);
 
 void register_break_hook(struct break_hook *hook)
 {
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 0b281ff..61035d6 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -384,26 +384,18 @@
  * Preserves:	tbl, flags
  * Corrupts:	phys, start, end, pstate
  */
-	.macro	create_block_map, tbl, flags, phys, start, end, idmap=0
+	.macro	create_block_map, tbl, flags, phys, start, end
 	lsr	\phys, \phys, #BLOCK_SHIFT
-	.if	\idmap
-	and	\start, \phys, #PTRS_PER_PTE - 1	// table index
-	.else
 	lsr	\start, \start, #BLOCK_SHIFT
 	and	\start, \start, #PTRS_PER_PTE - 1	// table index
-	.endif
 	orr	\phys, \flags, \phys, lsl #BLOCK_SHIFT	// table entry
-	.ifnc	\start,\end
 	lsr	\end, \end, #BLOCK_SHIFT
 	and	\end, \end, #PTRS_PER_PTE - 1		// table end index
-	.endif
 9999:	str	\phys, [\tbl, \start, lsl #3]		// store the entry
-	.ifnc	\start,\end
 	add	\start, \start, #1			// next entry
 	add	\phys, \phys, #BLOCK_SIZE		// next block
 	cmp	\start, \end
 	b.ls	9999b
-	.endif
 	.endm
 
 /*
@@ -435,9 +427,13 @@
 	 * Create the identity mapping.
 	 */
 	add	x0, x25, #PAGE_SIZE		// section table address
-	adr	x3, __turn_mmu_on		// virtual/physical address
+	ldr	x3, =KERNEL_START
+	add	x3, x3, x28			// __pa(KERNEL_START)
 	create_pgd_entry x25, x0, x3, x5, x6
-	create_block_map x0, x7, x3, x5, x5, idmap=1
+	ldr	x6, =KERNEL_END
+	mov	x5, x3				// __pa(KERNEL_START)
+	add	x6, x6, x28			// __pa(KERNEL_END)
+	create_block_map x0, x7, x3, x5, x6
 
 	/*
 	 * Map the kernel image (starting with PHYS_OFFSET).
@@ -445,7 +441,7 @@
 	add	x0, x26, #PAGE_SIZE		// section table address
 	mov	x5, #PAGE_OFFSET
 	create_pgd_entry x26, x0, x5, x3, x6
-	ldr	x6, =KERNEL_END - 1
+	ldr	x6, =KERNEL_END
 	mov	x3, x24				// phys offset
 	create_block_map x0, x7, x3, x5, x6
 
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
new file mode 100644
index 0000000..75c9cf1
--- /dev/null
+++ b/arch/arm64/kernel/kgdb.c
@@ -0,0 +1,336 @@
+/*
+ * AArch64 KGDB support
+ *
+ * Based on arch/arm/kernel/kgdb.c
+ *
+ * Copyright (C) 2013 Cavium Inc.
+ * Author: Vijaya Kumar K <vijaya.kumar@caviumnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/irq.h>
+#include <linux/kdebug.h>
+#include <linux/kgdb.h>
+#include <asm/traps.h>
+
+struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
+	{ "x0", 8, offsetof(struct pt_regs, regs[0])},
+	{ "x1", 8, offsetof(struct pt_regs, regs[1])},
+	{ "x2", 8, offsetof(struct pt_regs, regs[2])},
+	{ "x3", 8, offsetof(struct pt_regs, regs[3])},
+	{ "x4", 8, offsetof(struct pt_regs, regs[4])},
+	{ "x5", 8, offsetof(struct pt_regs, regs[5])},
+	{ "x6", 8, offsetof(struct pt_regs, regs[6])},
+	{ "x7", 8, offsetof(struct pt_regs, regs[7])},
+	{ "x8", 8, offsetof(struct pt_regs, regs[8])},
+	{ "x9", 8, offsetof(struct pt_regs, regs[9])},
+	{ "x10", 8, offsetof(struct pt_regs, regs[10])},
+	{ "x11", 8, offsetof(struct pt_regs, regs[11])},
+	{ "x12", 8, offsetof(struct pt_regs, regs[12])},
+	{ "x13", 8, offsetof(struct pt_regs, regs[13])},
+	{ "x14", 8, offsetof(struct pt_regs, regs[14])},
+	{ "x15", 8, offsetof(struct pt_regs, regs[15])},
+	{ "x16", 8, offsetof(struct pt_regs, regs[16])},
+	{ "x17", 8, offsetof(struct pt_regs, regs[17])},
+	{ "x18", 8, offsetof(struct pt_regs, regs[18])},
+	{ "x19", 8, offsetof(struct pt_regs, regs[19])},
+	{ "x20", 8, offsetof(struct pt_regs, regs[20])},
+	{ "x21", 8, offsetof(struct pt_regs, regs[21])},
+	{ "x22", 8, offsetof(struct pt_regs, regs[22])},
+	{ "x23", 8, offsetof(struct pt_regs, regs[23])},
+	{ "x24", 8, offsetof(struct pt_regs, regs[24])},
+	{ "x25", 8, offsetof(struct pt_regs, regs[25])},
+	{ "x26", 8, offsetof(struct pt_regs, regs[26])},
+	{ "x27", 8, offsetof(struct pt_regs, regs[27])},
+	{ "x28", 8, offsetof(struct pt_regs, regs[28])},
+	{ "x29", 8, offsetof(struct pt_regs, regs[29])},
+	{ "x30", 8, offsetof(struct pt_regs, regs[30])},
+	{ "sp", 8, offsetof(struct pt_regs, sp)},
+	{ "pc", 8, offsetof(struct pt_regs, pc)},
+	{ "pstate", 8, offsetof(struct pt_regs, pstate)},
+	{ "v0", 16, -1 },
+	{ "v1", 16, -1 },
+	{ "v2", 16, -1 },
+	{ "v3", 16, -1 },
+	{ "v4", 16, -1 },
+	{ "v5", 16, -1 },
+	{ "v6", 16, -1 },
+	{ "v7", 16, -1 },
+	{ "v8", 16, -1 },
+	{ "v9", 16, -1 },
+	{ "v10", 16, -1 },
+	{ "v11", 16, -1 },
+	{ "v12", 16, -1 },
+	{ "v13", 16, -1 },
+	{ "v14", 16, -1 },
+	{ "v15", 16, -1 },
+	{ "v16", 16, -1 },
+	{ "v17", 16, -1 },
+	{ "v18", 16, -1 },
+	{ "v19", 16, -1 },
+	{ "v20", 16, -1 },
+	{ "v21", 16, -1 },
+	{ "v22", 16, -1 },
+	{ "v23", 16, -1 },
+	{ "v24", 16, -1 },
+	{ "v25", 16, -1 },
+	{ "v26", 16, -1 },
+	{ "v27", 16, -1 },
+	{ "v28", 16, -1 },
+	{ "v29", 16, -1 },
+	{ "v30", 16, -1 },
+	{ "v31", 16, -1 },
+	{ "fpsr", 4, -1 },
+	{ "fpcr", 4, -1 },
+};
+
+char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	if (regno >= DBG_MAX_REG_NUM || regno < 0)
+		return NULL;
+
+	if (dbg_reg_def[regno].offset != -1)
+		memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
+		       dbg_reg_def[regno].size);
+	else
+		memset(mem, 0, dbg_reg_def[regno].size);
+	return dbg_reg_def[regno].name;
+}
+
+int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	if (regno >= DBG_MAX_REG_NUM || regno < 0)
+		return -EINVAL;
+
+	if (dbg_reg_def[regno].offset != -1)
+		memcpy((void *)regs + dbg_reg_def[regno].offset, mem,
+		       dbg_reg_def[regno].size);
+	return 0;
+}
+
+void
+sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
+{
+	struct pt_regs *thread_regs;
+
+	/* Initialize to zero */
+	memset((char *)gdb_regs, 0, NUMREGBYTES);
+	thread_regs = task_pt_regs(task);
+	memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES);
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
+{
+	regs->pc = pc;
+}
+
+static int compiled_break;
+
+static void kgdb_arch_update_addr(struct pt_regs *regs,
+				char *remcom_in_buffer)
+{
+	unsigned long addr;
+	char *ptr;
+
+	ptr = &remcom_in_buffer[1];
+	if (kgdb_hex2long(&ptr, &addr))
+		kgdb_arch_set_pc(regs, addr);
+	else if (compiled_break == 1)
+		kgdb_arch_set_pc(regs, regs->pc + 4);
+
+	compiled_break = 0;
+}
+
+int kgdb_arch_handle_exception(int exception_vector, int signo,
+			       int err_code, char *remcom_in_buffer,
+			       char *remcom_out_buffer,
+			       struct pt_regs *linux_regs)
+{
+	int err;
+
+	switch (remcom_in_buffer[0]) {
+	case 'D':
+	case 'k':
+		/*
+		 * Packet D (Detach), k (kill). No special handling
+		 * is required here. Handle same as c packet.
+		 */
+	case 'c':
+		/*
+		 * Packet c (Continue) to continue executing.
+		 * Set pc to required address.
+		 * Try to read optional parameter and set pc.
+		 * If this was a compiled breakpoint, we need to move
+		 * to the next instruction else we will just breakpoint
+		 * over and over again.
+		 */
+		kgdb_arch_update_addr(linux_regs, remcom_in_buffer);
+		atomic_set(&kgdb_cpu_doing_single_step, -1);
+		kgdb_single_step =  0;
+
+		/*
+		 * Received continue command, disable single step
+		 */
+		if (kernel_active_single_step())
+			kernel_disable_single_step();
+
+		err = 0;
+		break;
+	case 's':
+		/*
+		 * Update step address value with address passed
+		 * with step packet.
+		 * On debug exception return PC is copied to ELR
+		 * So just update PC.
+		 * If no step address is passed, resume from the address
+		 * pointed by PC. Do not update PC
+		 */
+		kgdb_arch_update_addr(linux_regs, remcom_in_buffer);
+		atomic_set(&kgdb_cpu_doing_single_step, raw_smp_processor_id());
+		kgdb_single_step =  1;
+
+		/*
+		 * Enable single step handling
+		 */
+		if (!kernel_active_single_step())
+			kernel_enable_single_step(linux_regs);
+		err = 0;
+		break;
+	default:
+		err = -1;
+	}
+	return err;
+}
+
+static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	return 0;
+}
+
+static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+	compiled_break = 1;
+	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+
+	return 0;
+}
+
+static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	return 0;
+}
+
+static struct break_hook kgdb_brkpt_hook = {
+	.esr_mask	= 0xffffffff,
+	.esr_val	= DBG_ESR_VAL_BRK(KGDB_DYN_DGB_BRK_IMM),
+	.fn		= kgdb_brk_fn
+};
+
+static struct break_hook kgdb_compiled_brkpt_hook = {
+	.esr_mask	= 0xffffffff,
+	.esr_val	= DBG_ESR_VAL_BRK(KDBG_COMPILED_DBG_BRK_IMM),
+	.fn		= kgdb_compiled_brk_fn
+};
+
+static struct step_hook kgdb_step_hook = {
+	.fn		= kgdb_step_brk_fn
+};
+
+static void kgdb_call_nmi_hook(void *ignored)
+{
+	kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
+}
+
+void kgdb_roundup_cpus(unsigned long flags)
+{
+	local_irq_enable();
+	smp_call_function(kgdb_call_nmi_hook, NULL, 0);
+	local_irq_disable();
+}
+
+static int __kgdb_notify(struct die_args *args, unsigned long cmd)
+{
+	struct pt_regs *regs = args->regs;
+
+	if (kgdb_handle_exception(1, args->signr, cmd, regs))
+		return NOTIFY_DONE;
+	return NOTIFY_STOP;
+}
+
+static int
+kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
+{
+	unsigned long flags;
+	int ret;
+
+	local_irq_save(flags);
+	ret = __kgdb_notify(ptr, cmd);
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static struct notifier_block kgdb_notifier = {
+	.notifier_call	= kgdb_notify,
+	/*
+	 * Want to be lowest priority
+	 */
+	.priority	= -INT_MAX,
+};
+
+/*
+ * kgdb_arch_init - Perform any architecture specific initalization.
+ * This function will handle the initalization of any architecture
+ * specific callbacks.
+ */
+int kgdb_arch_init(void)
+{
+	int ret = register_die_notifier(&kgdb_notifier);
+
+	if (ret != 0)
+		return ret;
+
+	register_break_hook(&kgdb_brkpt_hook);
+	register_break_hook(&kgdb_compiled_brkpt_hook);
+	register_step_hook(&kgdb_step_hook);
+	return 0;
+}
+
+/*
+ * kgdb_arch_exit - Perform any architecture specific uninitalization.
+ * This function will handle the uninitalization of any architecture
+ * specific callbacks, for dynamic registration and unregistration.
+ */
+void kgdb_arch_exit(void)
+{
+	unregister_break_hook(&kgdb_brkpt_hook);
+	unregister_break_hook(&kgdb_compiled_brkpt_hook);
+	unregister_step_hook(&kgdb_step_hook);
+	unregister_die_notifier(&kgdb_notifier);
+}
+
+/*
+ * ARM instructions are always in LE.
+ * Break instruction is encoded in LE format
+ */
+struct kgdb_arch arch_kgdb_ops = {
+	.gdb_bpt_instr = {
+		KGDB_DYN_BRK_INS_BYTE0,
+		KGDB_DYN_BRK_INS_BYTE1,
+		KGDB_DYN_BRK_INS_BYTE2,
+		KGDB_DYN_BRK_INS_BYTE3,
+	}
+};
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 63c48ff..7787208 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -38,12 +38,13 @@
 	.inst	0xe92d00f0		//	push		{r4, r5, r6, r7}
 	.inst	0xe1c040d0		//	ldrd		r4, r5, [r0]
 	.inst	0xe1c160d0		//	ldrd		r6, r7, [r1]
-	.inst	0xe1b20e9f		// 1:	ldaexd		r0, r1, [r2]
+	.inst	0xe1b20f9f		// 1:	ldrexd		r0, r1, [r2]
 	.inst	0xe0303004		//	eors		r3, r0, r4
 	.inst	0x00313005		//	eoreqs		r3, r1, r5
 	.inst	0x01a23e96		//	stlexdeq	r3, r6, [r2]
 	.inst	0x03330001		//	teqeq		r3, #1
 	.inst	0x0afffff9		//	beq		1b
+	.inst	0xf57ff05b		//	dmb		ish
 	.inst	0xe2730000		//	rsbs		r0, r3, #0
 	.inst	0xe8bd00f0		//	pop		{r4, r5, r6, r7}
 	.inst	0xe12fff1e		//	bx		lr
@@ -55,11 +56,12 @@
 
 	.align	5
 __kuser_cmpxchg:			// 0xffff0fc0
-	.inst	0xe1923e9f		// 1:	ldaex		r3, [r2]
+	.inst	0xe1923f9f		// 1:	ldrex		r3, [r2]
 	.inst	0xe0533000		//	subs		r3, r3, r0
 	.inst	0x01823e91		//	stlexeq		r3, r1, [r2]
 	.inst	0x03330001		//	teqeq		r3, #1
 	.inst	0x0afffffa		//	beq		1b
+	.inst	0xf57ff05b		//	dmb		ish
 	.inst	0xe2730000		//	rsbs		r0, r3, #0
 	.inst	0xe12fff1e		//	bx		lr
 
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 5b1cd79..e868c72 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1348,8 +1348,8 @@
  * Callchain handling code.
  */
 struct frame_tail {
-	struct frame_tail   __user *fp;
-	unsigned long	    lr;
+	struct frame_tail	__user *fp;
+	unsigned long		lr;
 } __attribute__((packed));
 
 /*
@@ -1386,22 +1386,80 @@
 	return buftail.fp;
 }
 
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct compat_frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct compat_frame_tail {
+	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
+	u32		sp;
+	u32		lr;
+} __attribute__((packed));
+
+static struct compat_frame_tail __user *
+compat_user_backtrace(struct compat_frame_tail __user *tail,
+		      struct perf_callchain_entry *entry)
+{
+	struct compat_frame_tail buftail;
+	unsigned long err;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	perf_callchain_store(entry, buftail.lr);
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail + 1 >= (struct compat_frame_tail __user *)
+			compat_ptr(buftail.fp))
+		return NULL;
+
+	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+}
+
 void perf_callchain_user(struct perf_callchain_entry *entry,
 			 struct pt_regs *regs)
 {
-	struct frame_tail __user *tail;
-
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
 
 	perf_callchain_store(entry, regs->pc);
-	tail = (struct frame_tail __user *)regs->regs[29];
 
-	while (entry->nr < PERF_MAX_STACK_DEPTH &&
-	       tail && !((unsigned long)tail & 0xf))
-		tail = user_backtrace(tail, entry);
+	if (!compat_user_mode(regs)) {
+		/* AARCH64 mode */
+		struct frame_tail __user *tail;
+
+		tail = (struct frame_tail __user *)regs->regs[29];
+
+		while (entry->nr < PERF_MAX_STACK_DEPTH &&
+		       tail && !((unsigned long)tail & 0xf))
+			tail = user_backtrace(tail, entry);
+	} else {
+		/* AARCH32 compat mode */
+		struct compat_frame_tail __user *tail;
+
+		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
+
+		while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+			tail && !((unsigned long)tail & 0x3))
+			tail = compat_user_backtrace(tail, entry);
+	}
 }
 
 /*
@@ -1429,6 +1487,7 @@
 	frame.fp = regs->regs[29];
 	frame.sp = regs->sp;
 	frame.pc = regs->pc;
+
 	walk_stackframe(&frame, callchain_trace, entry);
 }
 
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
new file mode 100644
index 0000000..f2d6f0a
--- /dev/null
+++ b/arch/arm64/kernel/perf_regs.c
@@ -0,0 +1,44 @@
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM64_MAX))
+		return 0;
+
+	/*
+	 * Compat (i.e. 32 bit) mode:
+	 * - PC has been set in the pt_regs struct in kernel_entry,
+	 * - Handle SP and LR here.
+	 */
+	if (compat_user_mode(regs)) {
+		if ((u32)idx == PERF_REG_ARM64_SP)
+			return regs->compat_sp;
+		if ((u32)idx == PERF_REG_ARM64_LR)
+			return regs->compat_lr;
+	}
+
+	return regs->regs[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_ARM64_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+	if (is_compat_thread(task_thread_info(task)))
+		return PERF_SAMPLE_REGS_ABI_32;
+	else
+		return PERF_SAMPLE_REGS_ABI_64;
+}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1c0a9be..6391485 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -33,7 +33,6 @@
 #include <linux/kallsyms.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
-#include <linux/cpuidle.h>
 #include <linux/elfcore.h>
 #include <linux/pm.h>
 #include <linux/tick.h>
@@ -72,8 +71,17 @@
 
 void soft_restart(unsigned long addr)
 {
+	typedef void (*phys_reset_t)(unsigned long);
+	phys_reset_t phys_reset;
+
 	setup_restart();
-	cpu_reset(addr);
+
+	/* Switch to the identity mapping */
+	phys_reset = (phys_reset_t)virt_to_phys(cpu_reset);
+	phys_reset(addr);
+
+	/* Should never get here */
+	BUG();
 }
 
 /*
@@ -94,10 +102,8 @@
 	 * This should do all the clock switching and wait for interrupt
 	 * tricks
 	 */
-	if (cpuidle_idle_call()) {
-		cpu_do_idle();
-		local_irq_enable();
-	}
+	cpu_do_idle();
+	local_irq_enable();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 4f97db3..ea4828a 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -176,22 +176,20 @@
 	{},
 };
 
-int __init psci_init(void)
+void __init psci_init(void)
 {
 	struct device_node *np;
 	const char *method;
 	u32 id;
-	int err = 0;
 
 	np = of_find_matching_node(NULL, psci_of_match);
 	if (!np)
-		return -ENODEV;
+		return;
 
 	pr_info("probing function IDs from device-tree\n");
 
 	if (of_property_read_string(np, "method", &method)) {
 		pr_warning("missing \"method\" property\n");
-		err = -ENXIO;
 		goto out_put_node;
 	}
 
@@ -201,7 +199,6 @@
 		invoke_psci_fn = __invoke_psci_fn_smc;
 	} else {
 		pr_warning("invalid \"method\" property: %s\n", method);
-		err = -EINVAL;
 		goto out_put_node;
 	}
 
@@ -227,7 +224,7 @@
 
 out_put_node:
 	of_node_put(np);
-	return err;
+	return;
 }
 
 #ifdef CONFIG_SMP
@@ -251,7 +248,7 @@
 {
 	int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_entry));
 	if (err)
-		pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err);
+		pr_err("failed to boot CPU%d (%d)\n", cpu, err);
 
 	return err;
 }
@@ -278,7 +275,7 @@
 
 	ret = psci_ops.cpu_off(state);
 
-	pr_crit("psci: unable to power off CPU%u (%d)\n", cpu, ret);
+	pr_crit("unable to power off CPU%u (%d)\n", cpu, ret);
 }
 #endif
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index c8e9eff..67da307 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -69,6 +69,7 @@
 				 COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
 				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
 unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
+unsigned int compat_elf_hwcap2 __read_mostly;
 #endif
 
 static const char *cpu_name;
@@ -242,6 +243,38 @@
 	block = (features >> 16) & 0xf;
 	if (block && !(block & 0x8))
 		elf_hwcap |= HWCAP_CRC32;
+
+#ifdef CONFIG_COMPAT
+	/*
+	 * ID_ISAR5_EL1 carries similar information as above, but pertaining to
+	 * the Aarch32 32-bit execution state.
+	 */
+	features = read_cpuid(ID_ISAR5_EL1);
+	block = (features >> 4) & 0xf;
+	if (!(block & 0x8)) {
+		switch (block) {
+		default:
+		case 2:
+			compat_elf_hwcap2 |= COMPAT_HWCAP2_PMULL;
+		case 1:
+			compat_elf_hwcap2 |= COMPAT_HWCAP2_AES;
+		case 0:
+			break;
+		}
+	}
+
+	block = (features >> 8) & 0xf;
+	if (block && !(block & 0x8))
+		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1;
+
+	block = (features >> 12) & 0xf;
+	if (block && !(block & 0x8))
+		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2;
+
+	block = (features >> 16) & 0xf;
+	if (block && !(block & 0x8))
+		compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32;
+#endif
 }
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 7cfb92a..f0a141d 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -114,6 +114,11 @@
 	return ret;
 }
 
+static void smp_store_cpu_info(unsigned int cpuid)
+{
+	store_cpu_topology(cpuid);
+}
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -152,6 +157,8 @@
 	 */
 	notify_cpu_starting(cpu);
 
+	smp_store_cpu_info(cpu);
+
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
 	 * the CPU migration code to notice that the CPU is online
@@ -160,6 +167,7 @@
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
+	local_dbg_enable();
 	local_irq_enable();
 	local_async_enable();
 
@@ -390,6 +398,10 @@
 	int err;
 	unsigned int cpu, ncores = num_possible_cpus();
 
+	init_cpu_topology();
+
+	smp_store_cpu_info(smp_processor_id());
+
 	/*
 	 * are we trying to boot more cores than exist?
 	 */
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 44c2280..7a530d2 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -128,7 +128,7 @@
 	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
 }
 
-void smp_spin_table_cpu_postboot(void)
+static void smp_spin_table_cpu_postboot(void)
 {
 	/*
 	 * Let the primary processor know we're out of the pen.
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index c3b6c63..38f0558 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -48,7 +48,11 @@
 
 	frame->sp = fp + 0x10;
 	frame->fp = *(unsigned long *)(fp);
-	frame->pc = *(unsigned long *)(fp + 8);
+	/*
+	 * -4 here because we care about the PC at time of bl,
+	 * not where the return will go.
+	 */
+	frame->pc = *(unsigned long *)(fp + 8) - 4;
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
new file mode 100644
index 0000000..3e06b0b
--- /dev/null
+++ b/arch/arm64/kernel/topology.c
@@ -0,0 +1,95 @@
+/*
+ * arch/arm64/kernel/topology.c
+ *
+ * Copyright (C) 2011,2013,2014 Linaro Limited.
+ *
+ * Based on the arm32 version written by Vincent Guittot in turn based on
+ * arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+
+#include <asm/topology.h>
+
+/*
+ * cpu topology table
+ */
+struct cpu_topology cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return &cpu_topology[cpu].core_sibling;
+}
+
+static void update_siblings_masks(unsigned int cpuid)
+{
+	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+	int cpu;
+
+	if (cpuid_topo->cluster_id == -1) {
+		/*
+		 * DT does not contain topology information for this cpu
+		 * reset it to default behaviour
+		 */
+		pr_debug("CPU%u: No topology information configured\n", cpuid);
+		cpuid_topo->core_id = 0;
+		cpumask_set_cpu(cpuid, &cpuid_topo->core_sibling);
+		cpumask_set_cpu(cpuid, &cpuid_topo->thread_sibling);
+		return;
+	}
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->cluster_id != cpu_topo->cluster_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+		if (cpuid_topo->core_id != cpu_topo->core_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+	}
+}
+
+void store_cpu_topology(unsigned int cpuid)
+{
+	update_siblings_masks(cpuid);
+}
+
+/*
+ * init_cpu_topology is called at boot when only one cpu is running
+ * which prevent simultaneous write access to cpu_topology array
+ */
+void __init init_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	/* init core mask and power*/
+	for_each_possible_cpu(cpu) {
+		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id =  -1;
+		cpu_topo->cluster_id = -1;
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+	}
+}
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 65d40cf..50384fe 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -106,49 +106,31 @@
 
 static int __init vdso_init(void)
 {
-	struct page *pg;
-	char *vbase;
-	int i, ret = 0;
+	int i;
+
+	if (memcmp(&vdso_start, "\177ELF", 4)) {
+		pr_err("vDSO is not a valid ELF object!\n");
+		return -EINVAL;
+	}
 
 	vdso_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT;
 	pr_info("vdso: %ld pages (%ld code, %ld data) at base %p\n",
 		vdso_pages + 1, vdso_pages, 1L, &vdso_start);
 
 	/* Allocate the vDSO pagelist, plus a page for the data. */
-	vdso_pagelist = kzalloc(sizeof(struct page *) * (vdso_pages + 1),
+	vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
 				GFP_KERNEL);
-	if (vdso_pagelist == NULL) {
-		pr_err("Failed to allocate vDSO pagelist!\n");
+	if (vdso_pagelist == NULL)
 		return -ENOMEM;
-	}
 
 	/* Grab the vDSO code pages. */
-	for (i = 0; i < vdso_pages; i++) {
-		pg = virt_to_page(&vdso_start + i*PAGE_SIZE);
-		ClearPageReserved(pg);
-		get_page(pg);
-		vdso_pagelist[i] = pg;
-	}
-
-	/* Sanity check the shared object header. */
-	vbase = vmap(vdso_pagelist, 1, 0, PAGE_KERNEL);
-	if (vbase == NULL) {
-		pr_err("Failed to map vDSO pagelist!\n");
-		return -ENOMEM;
-	} else if (memcmp(vbase, "\177ELF", 4)) {
-		pr_err("vDSO is not a valid ELF object!\n");
-		ret = -EINVAL;
-		goto unmap;
-	}
+	for (i = 0; i < vdso_pages; i++)
+		vdso_pagelist[i] = virt_to_page(&vdso_start + i * PAGE_SIZE);
 
 	/* Grab the vDSO data page. */
-	pg = virt_to_page(vdso_data);
-	get_page(pg);
-	vdso_pagelist[i] = pg;
+	vdso_pagelist[i] = virt_to_page(vdso_data);
 
-unmap:
-	vunmap(vbase);
-	return ret;
+	return 0;
 }
 arch_initcall(vdso_init);
 
@@ -238,6 +220,8 @@
 	vdso_data->use_syscall			= use_syscall;
 	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
 	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
+	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
 	if (!use_syscall) {
 		vdso_data->cs_cycle_last	= tk->clock->cycle_last;
@@ -245,8 +229,6 @@
 		vdso_data->xtime_clock_nsec	= tk->xtime_nsec;
 		vdso_data->cs_mult		= tk->mult;
 		vdso_data->cs_shift		= tk->shift;
-		vdso_data->wtm_clock_sec	= tk->wall_to_monotonic.tv_sec;
-		vdso_data->wtm_clock_nsec	= tk->wall_to_monotonic.tv_nsec;
 	}
 
 	smp_wmb();
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index d8064af..6d20b7d 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -48,7 +48,7 @@
 
 # Actual build commands
 quiet_cmd_vdsold = VDSOL $@
-      cmd_vdsold = $(CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
 quiet_cmd_vdsoas = VDSOA $@
       cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index f0a6d10..fe652ff 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -103,6 +103,8 @@
 	bl	__do_get_tspec
 	seqcnt_check w9, 1b
 
+	mov	x30, x2
+
 	cmp	w0, #CLOCK_MONOTONIC
 	b.ne	6f
 
@@ -118,6 +120,9 @@
 	ccmp	w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
 	b.ne	8f
 
+	/* xtime_coarse_nsec is already right-shifted */
+	mov	x12, #0
+
 	/* Get coarse timespec. */
 	adr	vdso_data, _vdso_data
 3:	seqcnt_acquire
@@ -156,7 +161,7 @@
 	lsr	x11, x11, x12
 	stp	x10, x11, [x1, #TSPEC_TV_SEC]
 	mov	x0, xzr
-	ret	x2
+	ret
 7:
 	mov	x30, x2
 8:	/* Syscall fallback. */
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 2b0244d..d968796 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -68,6 +68,12 @@
 	msr	tcr_el2, x4
 
 	ldr	x4, =VTCR_EL2_FLAGS
+	/*
+	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
+	 * VTCR_EL2.
+	 */
+	mrs	x5, ID_AA64MMFR0_EL1
+	bfi	x4, x5, #16, #3
 	msr	vtcr_el2, x4
 
 	mrs	x4, mair_el1
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 3b47c36..2c56012 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -694,6 +694,24 @@
 
 	.align	2
 
+/*
+ * u64 kvm_call_hyp(void *hypfn, ...);
+ *
+ * This is not really a variadic function in the classic C-way and care must
+ * be taken when calling this to ensure parameters are passed in registers
+ * only, since the stack will change between the caller and the callee.
+ *
+ * Call the function with the first argument containing a pointer to the
+ * function you wish to call in Hyp mode, and subsequent arguments will be
+ * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
+ * function pointer can be passed).  The function being called must be mapped
+ * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
+ * passed in r0 and r1.
+ *
+ * A function pointer with a value of 0 has a special meaning, and is
+ * used to implement __hyp_get_vectors in the same way as in
+ * arch/arm64/kernel/hyp_stub.S.
+ */
 ENTRY(kvm_call_hyp)
 	hvc	#0
 	ret
@@ -737,7 +755,12 @@
 	pop	x2, x3
 	pop	x0, x1
 
-	push	lr, xzr
+	/* Check for __hyp_get_vectors */
+	cbnz	x0, 1f
+	mrs	x0, vbar_el2
+	b	2f
+
+1:	push	lr, xzr
 
 	/*
 	 * Compute the function address in EL2, and shuffle the parameters.
@@ -750,7 +773,7 @@
 	blr	lr
 
 	pop	lr, xzr
-	eret
+2:	eret
 
 el1_trap:
 	/*
diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S
index e5db797..7dac371 100644
--- a/arch/arm64/lib/bitops.S
+++ b/arch/arm64/lib/bitops.S
@@ -46,11 +46,12 @@
 	mov	x2, #1
 	add	x1, x1, x0, lsr #3	// Get word offset
 	lsl	x4, x2, x3		// Create mask
-1:	ldaxr	x2, [x1]
+1:	ldxr	x2, [x1]
 	lsr	x0, x2, x3		// Save old value of bit
 	\instr	x2, x2, x4		// toggle bit
 	stlxr	w5, x2, [x1]
 	cbnz	w5, 1b
+	dmb	ish
 	and	x0, x0, #1
 3:	ret
 ENDPROC(\name	)
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 1ea9f26..c46f48b 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -30,7 +30,7 @@
  *
  *	Corrupted registers: x0-x7, x9-x11
  */
-ENTRY(__flush_dcache_all)
+__flush_dcache_all:
 	dsb	sy				// ensure ordering with previous memory accesses
 	mrs	x0, clidr_el1			// read clidr
 	and	x3, x0, #0x7000000		// extract loc from clidr
@@ -166,3 +166,81 @@
 	dsb	sy
 	ret
 ENDPROC(__flush_dcache_area)
+
+/*
+ *	__dma_inv_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+__dma_inv_range:
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	bic	x0, x0, x3
+	bic	x1, x1, x3
+1:	dc	ivac, x0			// invalidate D / U line
+	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	1b
+	dsb	sy
+	ret
+ENDPROC(__dma_inv_range)
+
+/*
+ *	__dma_clean_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+__dma_clean_range:
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	bic	x0, x0, x3
+1:	dc	cvac, x0			// clean D / U line
+	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	1b
+	dsb	sy
+	ret
+ENDPROC(__dma_clean_range)
+
+/*
+ *	__dma_flush_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(__dma_flush_range)
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	bic	x0, x0, x3
+1:	dc	civac, x0			// clean & invalidate D / U line
+	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	1b
+	dsb	sy
+	ret
+ENDPROC(__dma_flush_range)
+
+/*
+ *	__dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(__dma_map_area)
+	add	x1, x1, x0
+	cmp	w2, #DMA_FROM_DEVICE
+	b.eq	__dma_inv_range
+	b	__dma_clean_range
+ENDPROC(__dma_map_area)
+
+/*
+ *	__dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(__dma_unmap_area)
+	add	x1, x1, x0
+	cmp	w2, #DMA_TO_DEVICE
+	b.ne	__dma_inv_range
+	ret
+ENDPROC(__dma_unmap_area)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 45b5ab5..0ba347e 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -30,21 +30,30 @@
 struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
-static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
-					  dma_addr_t *dma_handle, gfp_t flags,
-					  struct dma_attrs *attrs)
+static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
+				 bool coherent)
+{
+	if (!coherent || dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
+		return pgprot_writecombine(prot);
+	return prot;
+}
+
+static void *__dma_alloc_coherent(struct device *dev, size_t size,
+				  dma_addr_t *dma_handle, gfp_t flags,
+				  struct dma_attrs *attrs)
 {
 	if (dev == NULL) {
 		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
 		return NULL;
 	}
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
-		flags |= GFP_DMA32;
+		flags |= GFP_DMA;
 	if (IS_ENABLED(CONFIG_DMA_CMA)) {
 		struct page *page;
 
+		size = PAGE_ALIGN(size);
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
 							get_order(size));
 		if (!page)
@@ -57,9 +66,9 @@
 	}
 }
 
-static void arm64_swiotlb_free_coherent(struct device *dev, size_t size,
-					void *vaddr, dma_addr_t dma_handle,
-					struct dma_attrs *attrs)
+static void __dma_free_coherent(struct device *dev, size_t size,
+				void *vaddr, dma_addr_t dma_handle,
+				struct dma_attrs *attrs)
 {
 	if (dev == NULL) {
 		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
@@ -77,9 +86,212 @@
 	}
 }
 
-static struct dma_map_ops arm64_swiotlb_dma_ops = {
-	.alloc = arm64_swiotlb_alloc_coherent,
-	.free = arm64_swiotlb_free_coherent,
+static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
+				     dma_addr_t *dma_handle, gfp_t flags,
+				     struct dma_attrs *attrs)
+{
+	struct page *page, **map;
+	void *ptr, *coherent_ptr;
+	int order, i;
+
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
+
+	ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
+	if (!ptr)
+		goto no_mem;
+	map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA);
+	if (!map)
+		goto no_map;
+
+	/* remove any dirty cache lines on the kernel alias */
+	__dma_flush_range(ptr, ptr + size);
+
+	/* create a coherent mapping */
+	page = virt_to_page(ptr);
+	for (i = 0; i < (size >> PAGE_SHIFT); i++)
+		map[i] = page + i;
+	coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP,
+			    __get_dma_pgprot(attrs, pgprot_default, false));
+	kfree(map);
+	if (!coherent_ptr)
+		goto no_map;
+
+	return coherent_ptr;
+
+no_map:
+	__dma_free_coherent(dev, size, ptr, *dma_handle, attrs);
+no_mem:
+	*dma_handle = ~0;
+	return NULL;
+}
+
+static void __dma_free_noncoherent(struct device *dev, size_t size,
+				   void *vaddr, dma_addr_t dma_handle,
+				   struct dma_attrs *attrs)
+{
+	void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
+
+	vunmap(vaddr);
+	__dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
+}
+
+static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction dir,
+				     struct dma_attrs *attrs)
+{
+	dma_addr_t dev_addr;
+
+	dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
+	__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+
+	return dev_addr;
+}
+
+
+static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
+				 size_t size, enum dma_data_direction dir,
+				 struct dma_attrs *attrs)
+{
+	__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+	swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+				  int nelems, enum dma_data_direction dir,
+				  struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i, ret;
+
+	ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
+	for_each_sg(sgl, sg, ret, i)
+		__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+			       sg->length, dir);
+
+	return ret;
+}
+
+static void __swiotlb_unmap_sg_attrs(struct device *dev,
+				     struct scatterlist *sgl, int nelems,
+				     enum dma_data_direction dir,
+				     struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+				 sg->length, dir);
+	swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs);
+}
+
+static void __swiotlb_sync_single_for_cpu(struct device *dev,
+					  dma_addr_t dev_addr, size_t size,
+					  enum dma_data_direction dir)
+{
+	__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+	swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir);
+}
+
+static void __swiotlb_sync_single_for_device(struct device *dev,
+					     dma_addr_t dev_addr, size_t size,
+					     enum dma_data_direction dir)
+{
+	swiotlb_sync_single_for_device(dev, dev_addr, size, dir);
+	__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+}
+
+static void __swiotlb_sync_sg_for_cpu(struct device *dev,
+				      struct scatterlist *sgl, int nelems,
+				      enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+				 sg->length, dir);
+	swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir);
+}
+
+static void __swiotlb_sync_sg_for_device(struct device *dev,
+					 struct scatterlist *sgl, int nelems,
+					 enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	swiotlb_sync_sg_for_device(dev, sgl, nelems, dir);
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+			       sg->length, dir);
+}
+
+/* vma->vm_page_prot must be set appropriately before calling this function */
+static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			     void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+	int ret = -ENXIO;
+	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
+					PAGE_SHIFT;
+	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
+	unsigned long off = vma->vm_pgoff;
+
+	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      vma->vm_end - vma->vm_start,
+				      vma->vm_page_prot);
+	}
+
+	return ret;
+}
+
+static int __swiotlb_mmap_noncoherent(struct device *dev,
+		struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs)
+{
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, false);
+	return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+static int __swiotlb_mmap_coherent(struct device *dev,
+		struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs)
+{
+	/* Just use whatever page_prot attributes were specified */
+	return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+struct dma_map_ops noncoherent_swiotlb_dma_ops = {
+	.alloc = __dma_alloc_noncoherent,
+	.free = __dma_free_noncoherent,
+	.mmap = __swiotlb_mmap_noncoherent,
+	.map_page = __swiotlb_map_page,
+	.unmap_page = __swiotlb_unmap_page,
+	.map_sg = __swiotlb_map_sg_attrs,
+	.unmap_sg = __swiotlb_unmap_sg_attrs,
+	.sync_single_for_cpu = __swiotlb_sync_single_for_cpu,
+	.sync_single_for_device = __swiotlb_sync_single_for_device,
+	.sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = __swiotlb_sync_sg_for_device,
+	.dma_supported = swiotlb_dma_supported,
+	.mapping_error = swiotlb_dma_mapping_error,
+};
+EXPORT_SYMBOL(noncoherent_swiotlb_dma_ops);
+
+struct dma_map_ops coherent_swiotlb_dma_ops = {
+	.alloc = __dma_alloc_coherent,
+	.free = __dma_free_coherent,
+	.mmap = __swiotlb_mmap_coherent,
 	.map_page = swiotlb_map_page,
 	.unmap_page = swiotlb_unmap_page,
 	.map_sg = swiotlb_map_sg_attrs,
@@ -91,12 +303,19 @@
 	.dma_supported = swiotlb_dma_supported,
 	.mapping_error = swiotlb_dma_mapping_error,
 };
+EXPORT_SYMBOL(coherent_swiotlb_dma_ops);
 
-void __init arm64_swiotlb_init(void)
+extern int swiotlb_late_init_with_default_size(size_t default_size);
+
+static int __init swiotlb_late_init(void)
 {
-	dma_ops = &arm64_swiotlb_dma_ops;
-	swiotlb_init(1);
+	size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
+
+	dma_ops = &coherent_swiotlb_dma_ops;
+
+	return swiotlb_late_init_with_default_size(swiotlb_size);
 }
+subsys_initcall(swiotlb_late_init);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index d0b4c2e..88627c4 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,7 @@
 #include <linux/memblock.h>
 #include <linux/sort.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 
 #include <asm/sections.h>
@@ -59,22 +60,22 @@
 early_param("initrd", early_initrd);
 #endif
 
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
-
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	unsigned long max_dma32 = min;
+	unsigned long max_dma = min;
 
 	memset(zone_size, 0, sizeof(zone_size));
 
-#ifdef CONFIG_ZONE_DMA32
 	/* 4GB maximum for 32-bit only capable devices */
-	max_dma32 = max(min, min(max, MAX_DMA32_PFN));
-	zone_size[ZONE_DMA32] = max_dma32 - min;
-#endif
-	zone_size[ZONE_NORMAL] = max - max_dma32;
+	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+		unsigned long max_dma_phys =
+			(unsigned long)dma_to_phys(NULL, DMA_BIT_MASK(32) + 1);
+		max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
+		zone_size[ZONE_DMA] = max_dma - min;
+	}
+	zone_size[ZONE_NORMAL] = max - max_dma;
 
 	memcpy(zhole_size, zone_size, sizeof(zhole_size));
 
@@ -84,15 +85,15 @@
 
 		if (start >= max)
 			continue;
-#ifdef CONFIG_ZONE_DMA32
-		if (start < max_dma32) {
-			unsigned long dma_end = min(end, max_dma32);
-			zhole_size[ZONE_DMA32] -= dma_end - start;
+
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && start < max_dma) {
+			unsigned long dma_end = min(end, max_dma);
+			zhole_size[ZONE_DMA] -= dma_end - start;
 		}
-#endif
-		if (end > max_dma32) {
+
+		if (end > max_dma) {
 			unsigned long normal_end = min(end, max);
-			unsigned long normal_start = max(start, max_dma32);
+			unsigned long normal_start = max(start, max_dma);
 			zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
 		}
 	}
@@ -261,8 +262,6 @@
  */
 void __init mem_init(void)
 {
-	arm64_swiotlb_init();
-
 	max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f557ebb..f8dc7e8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -203,10 +203,18 @@
 	do {
 		next = pmd_addr_end(addr, end);
 		/* try section mapping first */
-		if (((addr | next | phys) & ~SECTION_MASK) == 0)
+		if (((addr | next | phys) & ~SECTION_MASK) == 0) {
+			pmd_t old_pmd =*pmd;
 			set_pmd(pmd, __pmd(phys | prot_sect_kernel));
-		else
+			/*
+			 * Check for previous table entries created during
+			 * boot (__create_page_tables) and flush them.
+			 */
+			if (!pmd_none(old_pmd))
+				flush_tlb_all();
+		} else {
 			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys));
+		}
 		phys += next - addr;
 	} while (pmd++, addr = next, addr != end);
 }
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index 7083cda..62c6101 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -32,17 +32,10 @@
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	pgd_t *new_pgd;
-
 	if (PGD_SIZE == PAGE_SIZE)
-		new_pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+		return (pgd_t *)get_zeroed_page(GFP_KERNEL);
 	else
-		new_pgd = kzalloc(PGD_SIZE, GFP_KERNEL);
-
-	if (!new_pgd)
-		return NULL;
-
-	return new_pgd;
+		return kzalloc(PGD_SIZE, GFP_KERNEL);
 }
 
 void pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 1333e6f..e085ee6 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -173,12 +173,6 @@
  *	value of the SCTLR_EL1 register.
  */
 ENTRY(__cpu_setup)
-	/*
-	 * Preserve the link register across the function call.
-	 */
-	mov	x28, lr
-	bl	__flush_dcache_all
-	mov	lr, x28
 	ic	iallu				// I+BTB cache invalidate
 	tlbi	vmalle1is			// invalidate I + D TLBs
 	dsb	sy
@@ -215,8 +209,14 @@
 	 * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
 	 * both user and kernel.
 	 */
-	ldr	x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | TCR_IPS_40BIT | \
+	ldr	x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | \
 		      TCR_ASID16 | TCR_TBI0 | (1 << 31)
+	/*
+	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the IPS bits in
+	 * TCR_EL1.
+	 */
+	mrs	x9, ID_AA64MMFR0_EL1
+	bfi	x10, x9, #32, #3
 #ifdef CONFIG_ARM64_64K_PAGES
 	orr	x10, x10, TCR_TG0_64K
 	orr	x10, x10, TCR_TG1_64K
diff --git a/arch/avr32/Makefile b/arch/avr32/Makefile
index 22fb665..dba48a5 100644
--- a/arch/avr32/Makefile
+++ b/arch/avr32/Makefile
@@ -11,7 +11,7 @@
 
 KBUILD_DEFCONFIG	:= atstk1002_defconfig
 
-KBUILD_CFLAGS	+= -pipe -fno-builtin -mno-pic
+KBUILD_CFLAGS	+= -pipe -fno-builtin -mno-pic -D__linux__
 KBUILD_AFLAGS	+= -mrelax -mno-pic
 KBUILD_CFLAGS_MODULE += -mno-relax
 LDFLAGS_vmlinux	+= --relax
diff --git a/arch/avr32/boards/mimc200/fram.c b/arch/avr32/boards/mimc200/fram.c
index 9764a1a..c1466a8 100644
--- a/arch/avr32/boards/mimc200/fram.c
+++ b/arch/avr32/boards/mimc200/fram.c
@@ -11,6 +11,7 @@
 #define FRAM_VERSION	"1.0"
 
 #include <linux/miscdevice.h>
+#include <linux/module.h>
 #include <linux/proc_fs.h>
 #include <linux/mm.h>
 #include <linux/io.h>
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 8b398ff..00a0f3c 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -19,4 +19,5 @@
 generic-y += sections.h
 generic-y += topology.h
 generic-y += trace_clock.h
+generic-y += vga.h
 generic-y += xor.h
diff --git a/arch/avr32/include/asm/bugs.h b/arch/avr32/include/asm/bugs.h
index 7635e77..278661b 100644
--- a/arch/avr32/include/asm/bugs.h
+++ b/arch/avr32/include/asm/bugs.h
@@ -9,7 +9,7 @@
 
 static void __init check_bugs(void)
 {
-	cpu_data->loops_per_jiffy = loops_per_jiffy;
+	boot_cpu_data.loops_per_jiffy = loops_per_jiffy;
 }
 
 #endif /* __ASM_AVR32_BUGS_H */
diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h
index fc6483f..4f5ec2b 100644
--- a/arch/avr32/include/asm/io.h
+++ b/arch/avr32/include/asm/io.h
@@ -295,6 +295,8 @@
 #define iounmap(addr)				\
 	__iounmap(addr)
 
+#define ioremap_wc ioremap_nocache
+
 #define cached(addr) P1SEGADDR(addr)
 #define uncached(addr) P2SEGADDR(addr)
 
diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h
index 48d71c5..972adcc 100644
--- a/arch/avr32/include/asm/processor.h
+++ b/arch/avr32/include/asm/processor.h
@@ -83,13 +83,8 @@
 
 extern struct avr32_cpuinfo boot_cpu_data;
 
-#ifdef CONFIG_SMP
-extern struct avr32_cpuinfo cpu_data[];
-#define current_cpu_data cpu_data[smp_processor_id()]
-#else
-#define cpu_data (&boot_cpu_data)
+/* No SMP support so far */
 #define current_cpu_data boot_cpu_data
-#endif
 
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's
diff --git a/arch/avr32/kernel/cpu.c b/arch/avr32/kernel/cpu.c
index 2233be7..0341ae2 100644
--- a/arch/avr32/kernel/cpu.c
+++ b/arch/avr32/kernel/cpu.c
@@ -39,10 +39,12 @@
 			      size_t count)
 {
 	unsigned long val;
-	char *endp;
+	int ret;
 
-	val = simple_strtoul(buf, &endp, 0);
-	if (endp == buf || val > 0x3f)
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
+	if (val > 0x3f)
 		return -EINVAL;
 	val = (val << 12) | (sysreg_read(PCCR) & 0xfffc0fff);
 	sysreg_write(PCCR, val);
@@ -61,11 +63,11 @@
 				const char *buf, size_t count)
 {
 	unsigned long val;
-	char *endp;
+	int ret;
 
-	val = simple_strtoul(buf, &endp, 0);
-	if (endp == buf)
-		return -EINVAL;
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
 	sysreg_write(PCNT0, val);
 
 	return count;
@@ -84,10 +86,12 @@
 			      size_t count)
 {
 	unsigned long val;
-	char *endp;
+	int ret;
 
-	val = simple_strtoul(buf, &endp, 0);
-	if (endp == buf || val > 0x3f)
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
+	if (val > 0x3f)
 		return -EINVAL;
 	val = (val << 18) | (sysreg_read(PCCR) & 0xff03ffff);
 	sysreg_write(PCCR, val);
@@ -106,11 +110,11 @@
 			      size_t count)
 {
 	unsigned long val;
-	char *endp;
+	int ret;
 
-	val = simple_strtoul(buf, &endp, 0);
-	if (endp == buf)
-		return -EINVAL;
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
 	sysreg_write(PCNT1, val);
 
 	return count;
@@ -129,11 +133,11 @@
 			      size_t count)
 {
 	unsigned long val;
-	char *endp;
+	int ret;
 
-	val = simple_strtoul(buf, &endp, 0);
-	if (endp == buf)
-		return -EINVAL;
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
 	sysreg_write(PCCNT, val);
 
 	return count;
@@ -152,11 +156,11 @@
 			      size_t count)
 {
 	unsigned long pccr, val;
-	char *endp;
+	int ret;
 
-	val = simple_strtoul(buf, &endp, 0);
-	if (endp == buf)
-		return -EINVAL;
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
 	if (val)
 		val = 1;
 
diff --git a/arch/avr32/mm/cache.c b/arch/avr32/mm/cache.c
index 6a46ecd..85d635c 100644
--- a/arch/avr32/mm/cache.c
+++ b/arch/avr32/mm/cache.c
@@ -111,6 +111,7 @@
 	__flush_icache_range(start & ~(linesz - 1),
 			     (end + linesz - 1) & ~(linesz - 1));
 }
+EXPORT_SYMBOL(flush_icache_range);
 
 /*
  * This one is called from __do_fault() and do_swap_page().
diff --git a/arch/c6x/include/asm/cache.h b/arch/c6x/include/asm/cache.h
index 09c5a0f..86648c0 100644
--- a/arch/c6x/include/asm/cache.h
+++ b/arch/c6x/include/asm/cache.h
@@ -12,6 +12,7 @@
 #define _ASM_C6X_CACHE_H
 
 #include <linux/irqflags.h>
+#include <linux/init.h>
 
 /*
  * Cache line size
diff --git a/arch/cris/include/asm/bitops.h b/arch/cris/include/asm/bitops.h
index 184066c..053c17b 100644
--- a/arch/cris/include/asm/bitops.h
+++ b/arch/cris/include/asm/bitops.h
@@ -144,7 +144,7 @@
  * definition, which doesn't have the same semantics.  We don't want to
  * use -fno-builtin, so just hide the name ffs.
  */
-#define ffs kernel_ffs
+#define ffs(x) kernel_ffs(x)
 
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig
index efbd292..6404acb 100644
--- a/arch/ia64/configs/generic_defconfig
+++ b/arch/ia64/configs/generic_defconfig
@@ -30,9 +30,9 @@
 CONFIG_ACPI_FAN=m
 CONFIG_ACPI_DOCK=y
 CONFIG_ACPI_PROCESSOR=m
-CONFIG_ACPI_CONTAINER=m
+CONFIG_ACPI_CONTAINER=y
 CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_ACPI=m
+CONFIG_HOTPLUG_PCI_ACPI=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 8e858b5..30c43d3 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -1596,7 +1596,7 @@
 *
 ***************************************************************/
 
-static void __init
+static void
 ioc_iova_init(struct ioc *ioc)
 {
 	int tcnfg;
@@ -1807,7 +1807,7 @@
 	{ SX2000_IOC_ID, "sx2000", NULL },
 };
 
-static struct ioc * __init
+static struct ioc *
 ioc_init(unsigned long hpa, void *handle)
 {
 	struct ioc *ioc;
@@ -2041,7 +2041,7 @@
 #define sba_map_ioc_to_node(ioc, handle)
 #endif
 
-static int __init
+static int
 acpi_sba_ioc_add(struct acpi_device *device,
 		 const struct acpi_device_id *not_used)
 {
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index a2496e4..5cb55a1 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -77,7 +77,6 @@
 #define topology_core_id(cpu)			(cpu_data(cpu)->core_id)
 #define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
 #define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
-#define smt_capable() 				(smp_num_siblings > 1)
 #endif
 
 extern void arch_fix_phys_package_id(int num, u32 slot);
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index afd45e0..ae763d8 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -11,7 +11,7 @@
 
 
 
-#define NR_syscalls			312 /* length of syscall table */
+#define NR_syscalls			314 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h
index 34fd6fe..715e85f 100644
--- a/arch/ia64/include/uapi/asm/unistd.h
+++ b/arch/ia64/include/uapi/asm/unistd.h
@@ -325,5 +325,7 @@
 #define __NR_process_vm_writev		1333
 #define __NR_accept4			1334
 #define __NR_finit_module		1335
+#define __NR_sched_setattr		1336
+#define __NR_sched_getattr		1337
 
 #endif /* _UAPI_ASM_IA64_UNISTD_H */
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index da5b462..741b99c 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -477,6 +477,9 @@
 	char *cp, vendor[100] = "unknown";
 	int i;
 
+	set_bit(EFI_BOOT, &efi.flags);
+	set_bit(EFI_64BIT, &efi.flags);
+
 	/*
 	 * It's too early to be able to use the standard kernel command line
 	 * support...
@@ -529,6 +532,8 @@
 	       efi.systab->hdr.revision >> 16,
 	       efi.systab->hdr.revision & 0xffff, vendor);
 
+	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
 	palo_phys      = EFI_INVALID_TABLE_ADDR;
 
 	if (efi_config_init(arch_tables) != 0)
@@ -657,6 +662,8 @@
 		return;
 	}
 
+	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+
 	/*
 	 * Now that EFI is in virtual mode, we call the EFI functions more
 	 * efficiently:
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index ddea607f..fa8d61a 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1773,6 +1773,8 @@
 	data8 sys_process_vm_writev
 	data8 sys_accept4
 	data8 sys_finit_module			// 1335
+	data8 sys_sched_setattr
+	data8 sys_sched_getattr
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index b8edfa7..601502a 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -217,7 +217,7 @@
 	/* Copy the output into mlogbuf */
 	if (oops_in_progress) {
 		/* mlogbuf was abandoned, use printk directly instead. */
-		printk(temp_buf);
+		printk("%s", temp_buf);
 	} else {
 		spin_lock(&mlogbuf_wlock);
 		for (p = temp_buf; *p; p++) {
@@ -268,7 +268,7 @@
 		}
 		*p = '\0';
 		if (temp_buf[0])
-			printk(temp_buf);
+			printk("%s", temp_buf);
 		mlogbuf_start = index;
 
 		mlogbuf_timestamp = 0;
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index a96bcf8..20e8a9b 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -98,7 +98,7 @@
 	/* attempt to allocate a granule's worth of cached memory pages */
 
 	page = alloc_pages_exact_node(nid,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				IA64_GRANULE_SHIFT-PAGE_SHIFT);
 	if (!page) {
 		mutex_unlock(&uc_pool->add_chunk_mutex);
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 559ff3a..96da496 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -24,6 +24,8 @@
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68030=y
 CONFIG_M68040=y
@@ -85,6 +87,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -94,6 +97,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -126,6 +131,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -163,8 +169,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -190,7 +194,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -512,7 +515,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index cb1f55d..1b8739f 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -25,6 +25,8 @@
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68030=y
 CONFIG_M68040=y
@@ -83,6 +85,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -92,6 +95,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -124,6 +129,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -161,8 +167,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -188,7 +192,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -470,7 +473,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index e880cfb..6ea4e91 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -24,6 +24,8 @@
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68030=y
 CONFIG_M68040=y
@@ -82,6 +84,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -91,6 +94,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -123,6 +128,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -160,8 +166,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -187,7 +191,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -487,7 +490,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 4aa4f45..e5a1273 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -24,6 +24,8 @@
 CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68040=y
 CONFIG_M68060=y
 CONFIG_VME=y
@@ -81,6 +83,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -90,6 +93,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -122,6 +127,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -159,8 +165,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -186,7 +190,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -463,7 +466,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 7cd9d9f..8936d7f 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -25,6 +25,8 @@
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68030=y
 CONFIG_M68040=y
@@ -83,6 +85,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -92,6 +95,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -124,6 +129,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -161,8 +167,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -188,7 +192,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -472,7 +475,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 31f5bd0..be5342c 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -24,6 +24,8 @@
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68030=y
 CONFIG_M68040=y
@@ -82,6 +84,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -91,6 +94,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -123,6 +128,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -160,8 +166,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -187,7 +191,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -495,7 +498,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 4e5adff..f27194a 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -20,6 +20,8 @@
 CONFIG_UNIXWARE_DISKLABEL=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68040=y
 CONFIG_M68060=y
@@ -91,6 +93,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -100,6 +103,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -132,6 +137,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -169,8 +175,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -196,7 +200,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -571,7 +574,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 02cdbac..c388760 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -24,6 +24,8 @@
 CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68030=y
 CONFIG_VME=y
 CONFIG_MVME147=y
@@ -80,6 +82,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -89,6 +92,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -121,6 +126,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -158,8 +164,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -185,7 +189,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -463,7 +466,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 05a990a..f7ff784 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -24,6 +24,8 @@
 CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68040=y
 CONFIG_M68060=y
 CONFIG_VME=y
@@ -81,6 +83,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -90,6 +93,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -122,6 +127,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -159,8 +165,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -186,7 +190,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -464,7 +467,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 568e2a9..f0c72ab 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -25,6 +25,8 @@
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68040=y
 CONFIG_M68060=y
 CONFIG_Q40=y
@@ -81,6 +83,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -90,6 +93,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -122,6 +127,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -159,8 +165,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -186,7 +190,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -485,7 +488,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 60b0aea..7bca0f4 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -24,6 +24,8 @@
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_SUN3=y
 # CONFIG_COMPACTION is not set
 CONFIG_CLEANCACHE=y
@@ -78,6 +80,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -87,6 +90,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -119,6 +124,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -156,8 +162,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -183,7 +187,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -464,7 +467,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 21bda33..317f3e1 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -24,6 +24,8 @@
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_SUN3X=y
 # CONFIG_COMPACTION is not set
 CONFIG_CLEANCACHE=y
@@ -78,6 +80,7 @@
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -87,6 +90,8 @@
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -119,6 +124,7 @@
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -156,8 +162,6 @@
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -183,7 +187,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -464,7 +467,6 @@
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 86b4c17..c67c94a 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,4 +1,4 @@
-
+generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
 generic-y += cputime.h
diff --git a/arch/m68k/include/asm/barrier.h b/arch/m68k/include/asm/barrier.h
deleted file mode 100644
index 15c5f77..0000000
--- a/arch/m68k/include/asm/barrier.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _M68K_BARRIER_H
-#define _M68K_BARRIER_H
-
-#define nop()		do { asm volatile ("nop"); barrier(); } while (0)
-
-#include <asm-generic/barrier.h>
-
-#endif /* _M68K_BARRIER_H */
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 014f288..9d38b73 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		349
+#define NR_syscalls		351
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 625f321..b932dd4 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -354,5 +354,7 @@
 #define __NR_process_vm_writev	346
 #define __NR_kcmp		347
 #define __NR_finit_module	348
+#define __NR_sched_setattr	349
+#define __NR_sched_getattr	350
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S
index 4c99bab..3ab329b 100644
--- a/arch/m68k/kernel/head.S
+++ b/arch/m68k/kernel/head.S
@@ -275,7 +275,6 @@
 
 #ifdef CONFIG_FRAMEBUFFER_CONSOLE
 #define CONSOLE
-#define CONSOLE_PENGUIN
 #endif
 
 #ifdef CONFIG_EARLY_PRINTK
@@ -658,27 +657,6 @@
 	movel	%a0@,%a1@
 #endif
 
-#if 0
-	/*
-	 * Clear the screen
-	 */
-	lea	%pc@(L(mac_videobase)),%a0
-	movel	%a0@,%a1
-	lea	%pc@(L(mac_dimensions)),%a0
-	movel	%a0@,%d1
-	swap	%d1		/* #rows is high bytes */
-	andl	#0xFFFF,%d1	/* rows */
-	subl	#10,%d1
-	lea	%pc@(L(mac_rowbytes)),%a0
-loopy2:
-	movel	%a0@,%d0
-	subql	#1,%d0
-loopx2:
-	moveb	#0x55, %a1@+
-	dbra	%d0,loopx2
-	dbra	%d1,loopy2
-#endif
-
 L(test_notmac):
 #endif /* CONFIG_MAC */
 
@@ -907,15 +885,15 @@
  */
 #ifdef CONFIG_MAC
 	is_not_mac(L(nocon))
-#ifdef CONSOLE
+#  ifdef CONSOLE
 	console_init
-#ifdef CONSOLE_PENGUIN
+#    ifdef CONFIG_LOGO
 	console_put_penguin
-#endif	/* CONSOLE_PENGUIN */
+#    endif /* CONFIG_LOGO */
 	console_put_stats
-#endif	/* CONSOLE */
+#  endif /* CONSOLE */
 L(nocon):
-#endif	/* CONFIG_MAC */
+#endif /* CONFIG_MAC */
 
 
 	putc	'\n'
@@ -3324,14 +3302,13 @@
 #define Lconsole_struct_num_columns	8
 #define Lconsole_struct_num_rows	12
 #define Lconsole_struct_left_edge	16
-#define Lconsole_struct_penguin_putc	20
 
 func_start	console_init,%a0-%a4/%d0-%d7
 	/*
 	 *	Some of the register usage that follows
 	 *		a0 = pointer to boot_info
 	 *		a1 = pointer to screen
-	 *		a2 = pointer to Lconsole_globals
+	 *		a2 = pointer to console_globals
 	 *		d3 = pixel width of screen
 	 *		d4 = pixel height of screen
 	 *		(d3,d4) ~= (x,y) of a point just below
@@ -3456,7 +3433,7 @@
 
 func_return	console_put_stats
 
-#ifdef CONSOLE_PENGUIN
+#ifdef CONFIG_LOGO
 func_start	console_put_penguin,%a0-%a1/%d0-%d7
 	/*
 	 *	Get 'that_penguin' onto the screen in the upper right corner
@@ -3799,38 +3776,6 @@
 func_return	console_plot_pixel
 #endif /* CONSOLE */
 
-#if 0
-/*
- * This is some old code lying around.  I don't believe
- * it's used or important anymore.  My guess is it contributed
- * to getting to this point, but it's done for now.
- * It was still in the 2.1.77 head.S, so it's still here.
- * (And still not used!)
- */
-L(showtest):
-	moveml	%a0/%d7,%sp@-
-	puts	"A="
-	putn	%a1
-
-	.long	0xf0119f15		| ptestr	#5,%a1@,#7,%a0
-
-	puts	"DA="
-	putn	%a0
-
-	puts	"D="
-	putn	%a0@
-
-	puts	"S="
-	lea	%pc@(L(mmu)),%a0
-	.long	0xf0106200		| pmove		%psr,%a0@
-	clrl	%d7
-	movew	%a0@,%d7
-	putn	%d7
-
-	putc	'\n'
-	moveml	%sp@+,%a0/%d7
-	rts
-#endif	/* 0 */
 
 __INITDATA
 	.align	4
@@ -3849,7 +3794,6 @@
 	.long	0		/* max num columns */
 	.long	0		/* max num rows */
 	.long	0		/* left edge */
-	.long	0		/* mac putc */
 L(console_font):
 	.long	0		/* pointer to console font (struct font_desc) */
 L(console_font_data):
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 3f04ea0..b6223dc4 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -369,4 +369,6 @@
 	.long sys_process_vm_writev
 	.long sys_kcmp
 	.long sys_finit_module
+	.long sys_sched_setattr
+	.long sys_sched_getattr		/* 350 */
 
diff --git a/arch/microblaze/include/asm/delay.h b/arch/microblaze/include/asm/delay.h
index 05b7d39..66fc24c 100644
--- a/arch/microblaze/include/asm/delay.h
+++ b/arch/microblaze/include/asm/delay.h
@@ -13,6 +13,8 @@
 #ifndef _ASM_MICROBLAZE_DELAY_H
 #define _ASM_MICROBLAZE_DELAY_H
 
+#include <linux/param.h>
+
 extern inline void __delay(unsigned long loops)
 {
 	asm volatile ("# __delay		\n\t"		\
diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index a2cea72..3fbb7f1 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -89,6 +89,11 @@
 {
 	return le32_to_cpu(*(volatile unsigned int __force *)addr);
 }
+#define readq readq
+static inline u64 readq(const volatile void __iomem *addr)
+{
+	return le64_to_cpu(__raw_readq(addr));
+}
 static inline void writeb(unsigned char v, volatile void __iomem *addr)
 {
 	*(volatile unsigned char __force *)addr = v;
@@ -101,6 +106,7 @@
 {
 	*(volatile unsigned int __force *)addr = cpu_to_le32(v);
 }
+#define writeq(b, addr) __raw_writeq(cpu_to_le64(b), addr)
 
 /* ioread and iowrite variants. thease are for now same as __raw_
  * variants of accessors. we might check for endianess in the feature
diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S
index b7fb043..17645b2 100644
--- a/arch/microblaze/kernel/head.S
+++ b/arch/microblaze/kernel/head.S
@@ -66,7 +66,7 @@
 	mts	rmsr, r0
 /* Disable stack protection from bootloader */
 	mts	rslr, r0
-	addi	r8, r0, 0xFFFFFFF
+	addi	r8, r0, 0xFFFFFFFF
 	mts	rshr, r8
 /*
  * According to Xilinx, msrclr instruction behaves like 'mfs rX,rpc'
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index dcae3a7..95fa1f1 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1776,12 +1776,12 @@
 
 config FORCE_MAX_ZONEORDER
 	int "Maximum zone order"
-	range 14 64 if HUGETLB_PAGE && PAGE_SIZE_64KB
-	default "14" if HUGETLB_PAGE && PAGE_SIZE_64KB
-	range 13 64 if HUGETLB_PAGE && PAGE_SIZE_32KB
-	default "13" if HUGETLB_PAGE && PAGE_SIZE_32KB
-	range 12 64 if HUGETLB_PAGE && PAGE_SIZE_16KB
-	default "12" if HUGETLB_PAGE && PAGE_SIZE_16KB
+	range 14 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
+	default "14" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
+	range 13 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
+	default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
+	range 12 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
+	default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
 	range 11 64
 	default "11"
 	help
@@ -2353,9 +2353,8 @@
 	  If unsure, say Y. Only embedded should say N here.
 
 config MIPS_O32_FP64_SUPPORT
-	bool "Support for O32 binaries using 64-bit FP"
+	bool "Support for O32 binaries using 64-bit FP (EXPERIMENTAL)"
 	depends on 32BIT || MIPS32_O32
-	default y
 	help
 	  When this is enabled, the kernel will support use of 64-bit floating
 	  point registers with binaries using the O32 ABI along with the
@@ -2367,7 +2366,14 @@
 	  of your kernel & potentially improve FP emulation performance by
 	  saying N here.
 
-	  If unsure, say Y.
+	  Although binutils currently supports use of this flag the details
+	  concerning its effect upon the O32 ABI in userland are still being
+	  worked on. In order to avoid userland becoming dependant upon current
+	  behaviour before the details have been finalised, this option should
+	  be considered experimental and only enabled by those working upon
+	  said details.
+
+	  If unsure, say N.
 
 config USE_OF
 	bool
diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c
index 9edc35f..acf9a2a 100644
--- a/arch/mips/alchemy/board-gpr.c
+++ b/arch/mips/alchemy/board-gpr.c
@@ -53,10 +53,8 @@
 	prom_init_cmdline();
 
 	memsize_str = prom_getenv("memsize");
-	if (!memsize_str)
+	if (!memsize_str || kstrtoul(memsize_str, 0, &memsize))
 		memsize = 0x04000000;
-	else
-		strict_strtoul(memsize_str, 0, &memsize);
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index 9969dba..25a59a2 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -52,10 +52,8 @@
 	prom_init_cmdline();
 
 	memsize_str = prom_getenv("memsize");
-	if (!memsize_str)
+	if (!memsize_str || kstrtoul(memsize_str, 0, &memsize))
 		memsize = 0x04000000;
-	else
-		strict_strtoul(memsize_str, 0, &memsize);
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c
index 11f3ad2..5483906 100644
--- a/arch/mips/alchemy/devboards/db1000.c
+++ b/arch/mips/alchemy/devboards/db1000.c
@@ -534,13 +534,10 @@
 		s0 = AU1100_GPIO1_INT;
 		s1 = AU1100_GPIO4_INT;
 
+		gpio_request(19, "sd0_cd");
+		gpio_request(20, "sd1_cd");
 		gpio_direction_input(19);	/* sd0 cd# */
 		gpio_direction_input(20);	/* sd1 cd# */
-		gpio_direction_input(21);	/* touch pendown# */
-		gpio_direction_input(207);	/* SPI MISO */
-		gpio_direction_output(208, 0);	/* SPI MOSI */
-		gpio_direction_output(209, 1);	/* SPI SCK */
-		gpio_direction_output(210, 1);	/* SPI CS# */
 
 		/* spi_gpio on SSI0 pins */
 		pfc = __raw_readl((void __iomem *)SYS_PINFUNC);
diff --git a/arch/mips/bcm47xx/board.c b/arch/mips/bcm47xx/board.c
index 6d612e2..cdd8246 100644
--- a/arch/mips/bcm47xx/board.c
+++ b/arch/mips/bcm47xx/board.c
@@ -1,3 +1,4 @@
+#include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/string.h>
 #include <bcm47xx_board.h>
diff --git a/arch/mips/bcm47xx/nvram.c b/arch/mips/bcm47xx/nvram.c
index 6decb27..2bed73a 100644
--- a/arch/mips/bcm47xx/nvram.c
+++ b/arch/mips/bcm47xx/nvram.c
@@ -196,7 +196,7 @@
 	char nvram_var[10];
 	char buf[30];
 
-	for (i = 0; i < 16; i++) {
+	for (i = 0; i < 32; i++) {
 		err = snprintf(nvram_var, sizeof(nvram_var), "gpio%i", i);
 		if (err <= 0)
 			continue;
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 25fbfae..c2bb4f8 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -975,10 +975,6 @@
 	if (ciu > 1 || bit > 63)
 		return -EINVAL;
 
-	/* These are the GPIO lines */
-	if (ciu == 0 && bit >= 16 && bit < 32)
-		return -EINVAL;
-
 	*out_hwirq = (ciu << 6) | bit;
 	*out_type = 0;
 
@@ -1007,6 +1003,10 @@
 	if (!octeon_irq_virq_in_range(virq))
 		return -EINVAL;
 
+	/* Don't map irq if it is reserved for GPIO. */
+	if (line == 0 && bit >= 16 && bit <32)
+		return 0;
+
 	if (line > 1 || octeon_irq_ciu_to_irq[line][bit] != 0)
 		return -EINVAL;
 
@@ -1525,10 +1525,6 @@
 	ciu = intspec[0];
 	bit = intspec[1];
 
-	/* Line 7  are the GPIO lines */
-	if (ciu > 6 || bit > 63)
-		return -EINVAL;
-
 	*out_hwirq = (ciu << 6) | bit;
 	*out_type = 0;
 
@@ -1570,8 +1566,14 @@
 	if (!octeon_irq_virq_in_range(virq))
 		return -EINVAL;
 
-	/* Line 7  are the GPIO lines */
-	if (line > 6 || octeon_irq_ciu_to_irq[line][bit] != 0)
+	/*
+	 * Don't map irq if it is reserved for GPIO.
+	 * (Line 7 are the GPIO lines.)
+	 */
+	if (line == 7)
+		return 0;
+
+	if (line > 7 || octeon_irq_ciu_to_irq[line][bit] != 0)
 		return -EINVAL;
 
 	if (octeon_irq_ciu2_is_edge(line, bit))
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 3220c93..4225e99 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -9,6 +9,7 @@
 #define _ASM_ASMMACRO_H
 
 #include <asm/hazards.h>
+#include <asm/asm-offsets.h>
 
 #ifdef CONFIG_32BIT
 #include <asm/asmmacro-32.h>
@@ -54,11 +55,21 @@
 	.endm
 
 	.macro	local_irq_disable reg=t0
+#ifdef CONFIG_PREEMPT
+	lw      \reg, TI_PRE_COUNT($28)
+	addi    \reg, \reg, 1
+	sw      \reg, TI_PRE_COUNT($28)
+#endif
 	mfc0	\reg, CP0_STATUS
 	ori	\reg, \reg, 1
 	xori	\reg, \reg, 1
 	mtc0	\reg, CP0_STATUS
 	irq_disable_hazard
+#ifdef CONFIG_PREEMPT
+	lw      \reg, TI_PRE_COUNT($28)
+	addi    \reg, \reg, -1
+	sw      \reg, TI_PRE_COUNT($28)
+#endif
 	.endm
 #endif /* CONFIG_MIPS_MT_SMTC */
 
@@ -106,7 +117,7 @@
 	.endm
 
 	.macro	fpu_save_double thread status tmp
-#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	sll	\tmp, \status, 5
 	bgez	\tmp, 10f
 	fpu_save_16odd \thread
@@ -159,7 +170,7 @@
 	.endm
 
 	.macro	fpu_restore_double thread status tmp
-#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	sll	\tmp, \status, 5
 	bgez	\tmp, 10f				# 16 register mode?
 
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index cfe092f..58e50cb 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -57,7 +57,7 @@
 		return 0;
 
 	case FPU_64BIT:
-#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_MIPS64))
+#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_64BIT))
 		/* we only have a 32-bit FPU */
 		return SIGFPE;
 #endif
@@ -74,6 +74,8 @@
 	default:
 		BUG();
 	}
+
+	return SIGFPE;
 }
 
 #define __disable_fpu()							\
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index ce35c9a..992aaba 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -22,12 +22,12 @@
 #define safe_load(load, src, dst, error)		\
 do {							\
 	asm volatile (					\
-		"1: " load " %[" STR(dst) "], 0(%[" STR(src) "])\n"\
-		"   li %[" STR(error) "], 0\n"		\
+		"1: " load " %[tmp_dst], 0(%[tmp_src])\n"	\
+		"   li %[tmp_err], 0\n"			\
 		"2:\n"					\
 							\
 		".section .fixup, \"ax\"\n"		\
-		"3: li %[" STR(error) "], 1\n"		\
+		"3: li %[tmp_err], 1\n"			\
 		"   j 2b\n"				\
 		".previous\n"				\
 							\
@@ -35,8 +35,8 @@
 		STR(PTR) "\t1b, 3b\n\t"			\
 		".previous\n"				\
 							\
-		: [dst] "=&r" (dst), [error] "=r" (error)\
-		: [src] "r" (src)			\
+		: [tmp_dst] "=&r" (dst), [tmp_err] "=r" (error)\
+		: [tmp_src] "r" (src)			\
 		: "memory"				\
 	);						\
 } while (0)
@@ -44,12 +44,12 @@
 #define safe_store(store, src, dst, error)	\
 do {						\
 	asm volatile (				\
-		"1: " store " %[" STR(src) "], 0(%[" STR(dst) "])\n"\
-		"   li %[" STR(error) "], 0\n"	\
+		"1: " store " %[tmp_src], 0(%[tmp_dst])\n"\
+		"   li %[tmp_err], 0\n"		\
 		"2:\n"				\
 						\
 		".section .fixup, \"ax\"\n"	\
-		"3: li %[" STR(error) "], 1\n"	\
+		"3: li %[tmp_err], 1\n"		\
 		"   j 2b\n"			\
 		".previous\n"			\
 						\
@@ -57,8 +57,8 @@
 		STR(PTR) "\t1b, 3b\n\t"		\
 		".previous\n"			\
 						\
-		: [error] "=r" (error)		\
-		: [dst] "r" (dst), [src] "r" (src)\
+		: [tmp_err] "=r" (error)	\
+		: [tmp_dst] "r" (dst), [tmp_src] "r" (src)\
 		: "memory"			\
 	);					\
 } while (0)
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 33e8dbf..f35b131 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -13,6 +13,7 @@
 #ifndef __ASM_MIPS_SYSCALL_H
 #define __ASM_MIPS_SYSCALL_H
 
+#include <linux/compiler.h>
 #include <linux/audit.h>
 #include <linux/elf-em.h>
 #include <linux/kernel.h>
@@ -39,14 +40,14 @@
 
 #ifdef CONFIG_32BIT
 	case 4: case 5: case 6: case 7:
-		return get_user(*arg, (int *)usp + 4 * n);
+		return get_user(*arg, (int *)usp + n);
 #endif
 
 #ifdef CONFIG_64BIT
 	case 4: case 5: case 6: case 7:
 #ifdef CONFIG_MIPS32_O32
 		if (test_thread_flag(TIF_32BIT_REGS))
-			return get_user(*arg, (int *)usp + 4 * n);
+			return get_user(*arg, (int *)usp + n);
 		else
 #endif
 			*arg = regs->regs[4 + n];
@@ -57,6 +58,8 @@
 	default:
 		BUG();
 	}
+
+	unreachable();
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
@@ -83,11 +86,10 @@
 					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	unsigned long arg;
 	int ret;
 
 	while (n--)
-		ret |= mips_get_syscall_arg(&arg, task, regs, i++);
+		ret |= mips_get_syscall_arg(args++, task, regs, i++);
 
 	/*
 	 * No way to communicate an error because this is a void function.
diff --git a/arch/mips/include/asm/topology.h b/arch/mips/include/asm/topology.h
index 12609a1..20ea485 100644
--- a/arch/mips/include/asm/topology.h
+++ b/arch/mips/include/asm/topology.h
@@ -10,8 +10,4 @@
 
 #include <topology.h>
 
-#ifdef CONFIG_SMP
-#define smt_capable()	(smp_num_siblings > 1)
-#endif
-
 #endif /* __ASM_TOPOLOGY_H */
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index 4d3b928..413d6c6 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -24,7 +24,6 @@
 
 #ifndef __ASSEMBLY__
 
-#define __ARCH_OMIT_COMPAT_SYS_GETDENTS64
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_ALARM
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index b39ba25..f25181b 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -163,8 +163,8 @@
  */
 enum cop1x_func {
 	lwxc1_op     =	0x00, ldxc1_op	   =  0x01,
-	pfetch_op    =	0x07, swxc1_op	   =  0x08,
-	sdxc1_op     =	0x09, madd_s_op	   =  0x20,
+	swxc1_op     =  0x08, sdxc1_op	   =  0x09,
+	pfetch_op    =	0x0f, madd_s_op	   =  0x20,
 	madd_d_op    =	0x21, madd_e_op	   =  0x22,
 	msub_s_op    =	0x28, msub_d_op	   =  0x29,
 	msub_e_op    =	0x2a, nmadd_s_op   =  0x30,
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 1dee279..d6e154a 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -369,16 +369,18 @@
 #define __NR_process_vm_writev		(__NR_Linux + 346)
 #define __NR_kcmp			(__NR_Linux + 347)
 #define __NR_finit_module		(__NR_Linux + 348)
+#define __NR_sched_setattr		(__NR_Linux + 349)
+#define __NR_sched_getattr		(__NR_Linux + 350)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		348
+#define __NR_Linux_syscalls		350
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		348
+#define __NR_O32_Linux_syscalls		350
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -695,16 +697,18 @@
 #define __NR_kcmp			(__NR_Linux + 306)
 #define __NR_finit_module		(__NR_Linux + 307)
 #define __NR_getdents64			(__NR_Linux + 308)
+#define __NR_sched_setattr		(__NR_Linux + 309)
+#define __NR_sched_getattr		(__NR_Linux + 310)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		308
+#define __NR_Linux_syscalls		310
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		308
+#define __NR_64_Linux_syscalls		310
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1025,15 +1029,17 @@
 #define __NR_process_vm_writev		(__NR_Linux + 310)
 #define __NR_kcmp			(__NR_Linux + 311)
 #define __NR_finit_module		(__NR_Linux + 312)
+#define __NR_sched_setattr		(__NR_Linux + 313)
+#define __NR_sched_getattr		(__NR_Linux + 314)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		312
+#define __NR_Linux_syscalls		314
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		312
+#define __NR_N32_Linux_syscalls		314
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 185ba25..374ed74 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -111,11 +111,10 @@
 	safe_store_code(new_code1, ip, faulted);
 	if (unlikely(faulted))
 		return -EFAULT;
-	ip += 4;
-	safe_store_code(new_code2, ip, faulted);
+	safe_store_code(new_code2, ip + 4, faulted);
 	if (unlikely(faulted))
 		return -EFAULT;
-	flush_icache_range(ip, ip + 8); /* original ip + 12 */
+	flush_icache_range(ip, ip + 8);
 	return 0;
 }
 #endif
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 253b2fb..73b0ddf 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -35,9 +35,9 @@
 LEAF(_save_fp_context)
 	cfc1	t1, fcr31
 
-#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	.set	push
-#ifdef CONFIG_MIPS32_R2
+#ifdef CONFIG_CPU_MIPS32_R2
 	.set	mips64r2
 	mfc0	t0, CP0_STATUS
 	sll	t0, t0, 5
@@ -146,11 +146,11 @@
  *  - cp1 status/control register
  */
 LEAF(_restore_fp_context)
-	EX	lw t0, SC_FPC_CSR(a0)
+	EX	lw t1, SC_FPC_CSR(a0)
 
-#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	.set	push
-#ifdef CONFIG_MIPS32_R2
+#ifdef CONFIG_CPU_MIPS32_R2
 	.set	mips64r2
 	mfc0	t0, CP0_STATUS
 	sll	t0, t0, 5
@@ -191,7 +191,7 @@
 	EX	ldc1 $f26, SC_FPREGS+208(a0)
 	EX	ldc1 $f28, SC_FPREGS+224(a0)
 	EX	ldc1 $f30, SC_FPREGS+240(a0)
-	ctc1	t0, fcr31
+	ctc1	t1, fcr31
 	jr	ra
 	 li	v0, 0					# success
 	END(_restore_fp_context)
@@ -199,7 +199,7 @@
 #ifdef CONFIG_MIPS32_COMPAT
 LEAF(_restore_fp_context32)
 	/* Restore an o32 sigcontext.  */
-	EX	lw t0, SC32_FPC_CSR(a0)
+	EX	lw t1, SC32_FPC_CSR(a0)
 
 	mfc0	t0, CP0_STATUS
 	sll	t0, t0, 5
@@ -239,7 +239,7 @@
 	EX	ldc1 $f26, SC32_FPREGS+208(a0)
 	EX	ldc1 $f28, SC32_FPREGS+224(a0)
 	EX	ldc1 $f30, SC32_FPREGS+240(a0)
-	ctc1	t0, fcr31
+	ctc1	t1, fcr31
 	jr	ra
 	 li	v0, 0					# success
 	END(_restore_fp_context32)
diff --git a/arch/mips/kernel/rtlx-cmp.c b/arch/mips/kernel/rtlx-cmp.c
index 56dc696..758fb3c 100644
--- a/arch/mips/kernel/rtlx-cmp.c
+++ b/arch/mips/kernel/rtlx-cmp.c
@@ -112,5 +112,8 @@
 
 	for (i = 0; i < RTLX_CHANNELS; i++)
 		device_destroy(mt_class, MKDEV(major, i));
+
 	unregister_chrdev(major, RTLX_MODULE_NAME);
+
+	aprp_hook = NULL;
 }
diff --git a/arch/mips/kernel/rtlx-mt.c b/arch/mips/kernel/rtlx-mt.c
index 91d61ba..9c1aca0 100644
--- a/arch/mips/kernel/rtlx-mt.c
+++ b/arch/mips/kernel/rtlx-mt.c
@@ -144,5 +144,8 @@
 
 	for (i = 0; i < RTLX_CHANNELS; i++)
 		device_destroy(mt_class, MKDEV(major, i));
+
 	unregister_chrdev(major, RTLX_MODULE_NAME);
+
+	aprp_hook = NULL;
 }
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index e8e541b..a5b14f4 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -563,3 +563,5 @@
 	PTR	sys_process_vm_writev
 	PTR	sys_kcmp
 	PTR	sys_finit_module
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr		/* 4350 */
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 57e3742..b56e254 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -425,4 +425,6 @@
 	PTR	sys_kcmp
 	PTR	sys_finit_module
 	PTR	sys_getdents64
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr		/* 5310 */
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 2f48f59..f7e5b72 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -418,4 +418,6 @@
 	PTR	compat_sys_process_vm_writev	/* 6310 */
 	PTR	sys_kcmp
 	PTR	sys_finit_module
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f1acdb4..6788727 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -541,4 +541,6 @@
 	PTR	compat_sys_process_vm_writev
 	PTR	sys_kcmp
 	PTR	sys_finit_module
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr		/* 4350 */
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 506925b..0b4e2e3 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1538,10 +1538,10 @@
 		break;
 	}
 
-	case 0x7:		/* 7 */
-		if (MIPSInst_FUNC(ir) != pfetch_op) {
+	case 0x3:
+		if (MIPSInst_FUNC(ir) != pfetch_op)
 			return SIGILL;
-		}
+
 		/* ignore prefx operation */
 		break;
 
diff --git a/arch/mips/mti-malta/malta-amon.c b/arch/mips/mti-malta/malta-amon.c
index 592ac04..84ac523 100644
--- a/arch/mips/mti-malta/malta-amon.c
+++ b/arch/mips/mti-malta/malta-amon.c
@@ -72,7 +72,7 @@
 	return 0;
 }
 
-#ifdef CONFIG_MIPS_VPE_LOADER
+#ifdef CONFIG_MIPS_VPE_LOADER_CMP
 int vpe_run(struct vpe *v)
 {
 	struct vpe_notifications *n;
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index ca3e3a4..2242181 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -119,7 +119,7 @@
 
 	do_IRQ(MALTA_INT_BASE + irq);
 
-#ifdef MIPS_VPE_APSP_API
+#ifdef CONFIG_MIPS_VPE_APSP_API_MT
 	if (aprp_hook)
 		aprp_hook();
 #endif
@@ -310,7 +310,7 @@
 
 static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 {
-#ifdef MIPS_VPE_APSP_API
+#ifdef CONFIG_MIPS_VPE_APSP_API_CMP
 	if (aprp_hook)
 		aprp_hook();
 #endif
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index d37be36..2b91b0e 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -150,6 +150,7 @@
 		msg.address_lo =
 			((128ul << 20) + CVMX_PCI_MSI_RCV) & 0xffffffff;
 		msg.address_hi = ((128ul << 20) + CVMX_PCI_MSI_RCV) >> 32;
+		break;
 	case OCTEON_DMA_BAR_TYPE_BIG:
 		/* When using big bar, Bar 0 is based at 0 */
 		msg.address_lo = (0 + CVMX_PCI_MSI_RCV) & 0xffffffff;
diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c
index 88d0962..2bedafe 100644
--- a/arch/parisc/hpux/fs.c
+++ b/arch/parisc/hpux/fs.c
@@ -33,22 +33,9 @@
 
 int hpux_execve(struct pt_regs *regs)
 {
-	int error;
-	struct filename *filename;
-
-	filename = getname((const char __user *) regs->gr[26]);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-
-	error = do_execve(filename->name,
+	return  do_execve(getname((const char __user *) regs->gr[26]),
 			  (const char __user *const __user *) regs->gr[25],
 			  (const char __user *const __user *) regs->gr[24]);
-
-	putname(filename);
-
-out:
-	return error;
 }
 
 struct hpux_dirent {
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 2f9b751..de65f66 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -132,7 +132,6 @@
 static inline void *kmap(struct page *page)
 {
 	might_sleep();
-	flush_dcache_page(page);
 	return page_address(page);
 }
 
@@ -144,7 +143,6 @@
 static inline void *kmap_atomic(struct page *page)
 {
 	pagefault_disable();
-	flush_dcache_page(page);
 	return page_address(page);
 }
 
diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h
index ad2b503..3391d06 100644
--- a/arch/parisc/include/asm/elf.h
+++ b/arch/parisc/include/asm/elf.h
@@ -348,4 +348,8 @@
 
 #define ELF_HWCAP	0
 
+struct mm_struct;
+extern unsigned long arch_randomize_brk(struct mm_struct *);
+#define arch_randomize_brk arch_randomize_brk
+
 #endif
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index c53fc63..60d5d17 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -29,18 +29,8 @@
 void clear_page_asm(void *page);
 void copy_page_asm(void *to, void *from);
 #define clear_user_page(vto, vaddr, page) clear_page_asm(vto)
-#define copy_user_page(vto, vfrom, vaddr, page) copy_page_asm(vto, vfrom)
-
-/* #define CONFIG_PARISC_TMPALIAS */
-
-#ifdef CONFIG_PARISC_TMPALIAS
-void clear_user_highpage(struct page *page, unsigned long vaddr);
-#define clear_user_highpage clear_user_highpage
-struct vm_area_struct;
-void copy_user_highpage(struct page *to, struct page *from,
-	unsigned long vaddr, struct vm_area_struct *vma);
-#define __HAVE_ARCH_COPY_USER_HIGHPAGE
-#endif
+void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
+			struct page *pg);
 
 /*
  * These are used to make use of C type-checking..
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 34899b5..22b89d1 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -511,6 +511,7 @@
 /* We provide our own get_unmapped_area to provide cache coherency */
 
 #define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index cc2290a..198a86f 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -30,6 +30,8 @@
 #endif
 #define current_text_addr() ({ void *pc; current_ia(pc); pc; })
 
+#define HAVE_ARCH_PICK_MMAP_LAYOUT
+
 #define TASK_SIZE_OF(tsk)       ((tsk)->thread.task_size)
 #define TASK_SIZE	        TASK_SIZE_OF(current)
 #define TASK_UNMAPPED_BASE      (current->thread.map_base)
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index 3516e0b..64f2992 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -191,8 +191,4 @@
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
 
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* __ASM_SPINLOCK_H */
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index d5f97ea..4b9b10c 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -76,6 +76,16 @@
 #define _TIF_SYSCALL_TRACE_MASK (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP |	\
 				 _TIF_BLOCKSTEP | _TIF_SYSCALL_AUDIT)
 
+#ifdef CONFIG_64BIT
+# ifdef CONFIG_COMPAT
+#  define is_32bit_task()	(test_thread_flag(TIF_32BIT))
+# else
+#  define is_32bit_task()	(0)
+# endif
+#else
+# define is_32bit_task()	(1)
+#endif
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_PARISC_THREAD_INFO_H */
diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h
index f3a8aa5..c0ae625 100644
--- a/arch/parisc/include/uapi/asm/errno.h
+++ b/arch/parisc/include/uapi/asm/errno.h
@@ -106,7 +106,7 @@
 
 #define	EALREADY	244	/* Operation already in progress */
 #define	EINPROGRESS	245	/* Operation now in progress */
-#define	EWOULDBLOCK	246	/* Operation would block (Linux returns EAGAIN) */
+#define	EWOULDBLOCK	EAGAIN	/* Operation would block (Not HPUX compliant) */
 #define	ENOTEMPTY	247	/* Directory not empty */
 #define	ENAMETOOLONG	248	/* File name too long */
 #define	ELOOP		249	/* Too many symbolic links encountered */
diff --git a/arch/parisc/include/uapi/asm/stat.h b/arch/parisc/include/uapi/asm/stat.h
index d76fbda..b606b36 100644
--- a/arch/parisc/include/uapi/asm/stat.h
+++ b/arch/parisc/include/uapi/asm/stat.h
@@ -5,67 +5,65 @@
 
 struct stat {
 	unsigned int	st_dev;		/* dev_t is 32 bits on parisc */
-	ino_t		st_ino;		/* 32 bits */
-	mode_t		st_mode;	/* 16 bits */
+	unsigned int	st_ino;		/* 32 bits */
+	unsigned short	st_mode;	/* 16 bits */
 	unsigned short	st_nlink;	/* 16 bits */
 	unsigned short	st_reserved1;	/* old st_uid */
 	unsigned short	st_reserved2;	/* old st_gid */
 	unsigned int	st_rdev;
-	off_t		st_size;
-	time_t		st_atime;
+	signed int	st_size;
+	signed int	st_atime;
 	unsigned int	st_atime_nsec;
-	time_t		st_mtime;
+	signed int	st_mtime;
 	unsigned int	st_mtime_nsec;
-	time_t		st_ctime;
+	signed int	st_ctime;
 	unsigned int	st_ctime_nsec;
 	int		st_blksize;
 	int		st_blocks;
 	unsigned int	__unused1;	/* ACL stuff */
 	unsigned int	__unused2;	/* network */
-	ino_t		__unused3;	/* network */
+	unsigned int	__unused3;	/* network */
 	unsigned int	__unused4;	/* cnodes */
 	unsigned short	__unused5;	/* netsite */
 	short		st_fstype;
 	unsigned int	st_realdev;
 	unsigned short	st_basemode;
 	unsigned short	st_spareshort;
-	uid_t		st_uid;
-	gid_t		st_gid;
+	unsigned int	st_uid;
+	unsigned int	st_gid;
 	unsigned int	st_spare4[3];
 };
 
 #define STAT_HAVE_NSEC
 
-typedef __kernel_off64_t	off64_t;
-
 struct hpux_stat64 {
 	unsigned int	st_dev;		/* dev_t is 32 bits on parisc */
-	ino_t           st_ino;         /* 32 bits */
-	mode_t		st_mode;	/* 16 bits */
+	unsigned int	st_ino;         /* 32 bits */
+	unsigned short	st_mode;	/* 16 bits */
 	unsigned short	st_nlink;	/* 16 bits */
 	unsigned short	st_reserved1;	/* old st_uid */
 	unsigned short	st_reserved2;	/* old st_gid */
 	unsigned int	st_rdev;
-	off64_t		st_size;
-	time_t		st_atime;
+	signed long long st_size;
+	signed int	st_atime;
 	unsigned int	st_spare1;
-	time_t		st_mtime;
+	signed int	st_mtime;
 	unsigned int	st_spare2;
-	time_t		st_ctime;
+	signed int	st_ctime;
 	unsigned int	st_spare3;
 	int		st_blksize;
-	__u64		st_blocks;
+	unsigned long long st_blocks;
 	unsigned int	__unused1;	/* ACL stuff */
 	unsigned int	__unused2;	/* network */
-	ino_t           __unused3;      /* network */
+	unsigned int	__unused3;      /* network */
 	unsigned int	__unused4;	/* cnodes */
 	unsigned short	__unused5;	/* netsite */
 	short		st_fstype;
 	unsigned int	st_realdev;
 	unsigned short	st_basemode;
 	unsigned short	st_spareshort;
-	uid_t		st_uid;
-	gid_t		st_gid;
+	unsigned int	st_uid;
+	unsigned int	st_gid;
 	unsigned int	st_spare4[3];
 };
 
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 2c8b9bd..265ae51 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -826,13 +826,15 @@
 #define __NR_process_vm_writev	(__NR_Linux + 331)
 #define __NR_kcmp		(__NR_Linux + 332)
 #define __NR_finit_module	(__NR_Linux + 333)
+#define __NR_sched_setattr	(__NR_Linux + 334)
+#define __NR_sched_getattr	(__NR_Linux + 335)
+#define __NR_utimes		(__NR_Linux + 336)
 
-#define __NR_Linux_syscalls	(__NR_finit_module + 1)
+#define __NR_Linux_syscalls	(__NR_utimes + 1)
 
 
 #define __IGNORE_select		/* newselect */
 #define __IGNORE_fadvise64	/* fadvise64_64 */
-#define __IGNORE_utimes		/* utime */
 
 
 #define HPUX_GATEWAY_ADDR       0xC0000004
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index a725455..a6ffc77 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -388,6 +388,20 @@
 }
 EXPORT_SYMBOL(flush_kernel_dcache_page_addr);
 
+void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
+	struct page *pg)
+{
+       /* Copy using kernel mapping.  No coherency is needed (all in
+	  kunmap) for the `to' page.  However, the `from' page needs to
+	  be flushed through a mapping equivalent to the user mapping
+	  before it can be accessed through the kernel mapping. */
+	preempt_disable();
+	flush_dcache_page_asm(__pa(vfrom), vaddr);
+	preempt_enable();
+	copy_page_asm(vto, vfrom);
+}
+EXPORT_SYMBOL(copy_user_page);
+
 void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 {
 	unsigned long flags;
@@ -567,67 +581,3 @@
 		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 	}
 }
-
-#ifdef CONFIG_PARISC_TMPALIAS
-
-void clear_user_highpage(struct page *page, unsigned long vaddr)
-{
-	void *vto;
-	unsigned long flags;
-
-	/* Clear using TMPALIAS region.  The page doesn't need to
-	   be flushed but the kernel mapping needs to be purged.  */
-
-	vto = kmap_atomic(page);
-
-	/* The PA-RISC 2.0 Architecture book states on page F-6:
-	   "Before a write-capable translation is enabled, *all*
-	   non-equivalently-aliased translations must be removed
-	   from the page table and purged from the TLB.  (Note
-	   that the caches are not required to be flushed at this
-	   time.)  Before any non-equivalent aliased translation
-	   is re-enabled, the virtual address range for the writeable
-	   page (the entire page) must be flushed from the cache,
-	   and the write-capable translation removed from the page
-	   table and purged from the TLB."  */
-
-	purge_kernel_dcache_page_asm((unsigned long)vto);
-	purge_tlb_start(flags);
-	pdtlb_kernel(vto);
-	purge_tlb_end(flags);
-	preempt_disable();
-	clear_user_page_asm(vto, vaddr);
-	preempt_enable();
-
-	pagefault_enable();		/* kunmap_atomic(addr, KM_USER0); */
-}
-
-void copy_user_highpage(struct page *to, struct page *from,
-	unsigned long vaddr, struct vm_area_struct *vma)
-{
-	void *vfrom, *vto;
-	unsigned long flags;
-
-	/* Copy using TMPALIAS region.  This has the advantage
-	   that the `from' page doesn't need to be flushed.  However,
-	   the `to' page must be flushed in copy_user_page_asm since
-	   it can be used to bring in executable code.  */
-
-	vfrom = kmap_atomic(from);
-	vto = kmap_atomic(to);
-
-	purge_kernel_dcache_page_asm((unsigned long)vto);
-	purge_tlb_start(flags);
-	pdtlb_kernel(vto);
-	pdtlb_kernel(vfrom);
-	purge_tlb_end(flags);
-	preempt_disable();
-	copy_user_page_asm(vto, vfrom, vaddr);
-	flush_dcache_page_asm(__pa(vto), vaddr);
-	preempt_enable();
-
-	pagefault_enable();		/* kunmap_atomic(addr, KM_USER1); */
-	pagefault_enable();		/* kunmap_atomic(addr, KM_USER0); */
-}
-
-#endif /* CONFIG_PARISC_TMPALIAS */
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 55f92b6..0bbbf0d 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -13,7 +13,7 @@
  *    Copyright (C) 2000 Grant Grundler <grundler with parisc-linux.org>
  *    Copyright (C) 2001 Alan Modra <amodra at parisc-linux.org>
  *    Copyright (C) 2001-2002 Ryan Bradetich <rbrad at parisc-linux.org>
- *    Copyright (C) 2001-2007 Helge Deller <deller at parisc-linux.org>
+ *    Copyright (C) 2001-2014 Helge Deller <deller@gmx.de>
  *    Copyright (C) 2002 Randolph Chung <tausq with parisc-linux.org>
  *
  *
@@ -49,6 +49,7 @@
 #include <linux/kallsyms.h>
 #include <linux/uaccess.h>
 #include <linux/rcupdate.h>
+#include <linux/random.h>
 
 #include <asm/io.h>
 #include <asm/asm-offsets.h>
@@ -286,3 +287,21 @@
 	return ptr;
 }
 #endif
+
+static inline unsigned long brk_rnd(void)
+{
+	/* 8MB for 32bit, 1GB for 64bit */
+	if (is_32bit_task())
+		return (get_random_int() & 0x7ffUL) << PAGE_SHIFT;
+	else
+		return (get_random_int() & 0x3ffffUL) << PAGE_SHIFT;
+}
+
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+	unsigned long ret = PAGE_ALIGN(mm->brk + brk_rnd());
+
+	if (ret < mm->brk)
+		return mm->brk;
+	return ret;
+}
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index 0d3a9d4..b7cadc4 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -5,6 +5,7 @@
  *    Copyright (C) 1999-2003 Matthew Wilcox <willy at parisc-linux.org>
  *    Copyright (C) 2000-2003 Paul Bame <bame at parisc-linux.org>
  *    Copyright (C) 2001 Thomas Bogendoerfer <tsbogend at parisc-linux.org>
+ *    Copyright (C) 1999-2014 Helge Deller <deller@gmx.de>
  *
  *
  *    This program is free software; you can redistribute it and/or modify
@@ -23,6 +24,7 @@
  */
 
 #include <asm/uaccess.h>
+#include <asm/elf.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/linkage.h>
@@ -32,78 +34,230 @@
 #include <linux/syscalls.h>
 #include <linux/utsname.h>
 #include <linux/personality.h>
+#include <linux/random.h>
 
-static unsigned long get_unshared_area(unsigned long addr, unsigned long len)
+/* we construct an artificial offset for the mapping based on the physical
+ * address of the kernel mapping variable */
+#define GET_LAST_MMAP(filp)		\
+	(filp ? ((unsigned long) filp->f_mapping) >> 8 : 0UL)
+#define SET_LAST_MMAP(filp, val)	\
+	 { /* nothing */ }
+
+static int get_offset(unsigned int last_mmap)
 {
-	struct vm_unmapped_area_info info;
+	return (last_mmap & (SHMLBA-1)) >> PAGE_SHIFT;
+}
 
-	info.flags = 0;
-	info.length = len;
-	info.low_limit = PAGE_ALIGN(addr);
-	info.high_limit = TASK_SIZE;
-	info.align_mask = 0;
-	info.align_offset = 0;
-	return vm_unmapped_area(&info);
+static unsigned long shared_align_offset(unsigned int last_mmap,
+					 unsigned long pgoff)
+{
+	return (get_offset(last_mmap) + pgoff) << PAGE_SHIFT;
+}
+
+static inline unsigned long COLOR_ALIGN(unsigned long addr,
+			 unsigned int last_mmap, unsigned long pgoff)
+{
+	unsigned long base = (addr+SHMLBA-1) & ~(SHMLBA-1);
+	unsigned long off  = (SHMLBA-1) &
+		(shared_align_offset(last_mmap, pgoff) << PAGE_SHIFT);
+
+	return base + off;
 }
 
 /*
- * We need to know the offset to use.  Old scheme was to look for
- * existing mapping and use the same offset.  New scheme is to use the
- * address of the kernel data structure as the seed for the offset.
- * We'll see how that works...
- *
- * The mapping is cacheline aligned, so there's no information in the bottom
- * few bits of the address.  We're looking for 10 bits (4MB / 4k), so let's
- * drop the bottom 8 bits and use bits 8-17.  
+ * Top of mmap area (just below the process stack).
  */
-static int get_offset(struct address_space *mapping)
+
+static unsigned long mmap_upper_limit(void)
 {
-	return (unsigned long) mapping >> 8;
+	unsigned long stack_base;
+
+	/* Limit stack size to 1GB - see setup_arg_pages() in fs/exec.c */
+	stack_base = rlimit_max(RLIMIT_STACK);
+	if (stack_base > (1 << 30))
+		stack_base = 1 << 30;
+
+	return PAGE_ALIGN(STACK_TOP - stack_base);
 }
 
-static unsigned long shared_align_offset(struct file *filp, unsigned long pgoff)
-{
-	struct address_space *mapping = filp ? filp->f_mapping : NULL;
-
-	return (get_offset(mapping) + pgoff) << PAGE_SHIFT;
-}
-
-static unsigned long get_shared_area(struct file *filp, unsigned long addr,
-		unsigned long len, unsigned long pgoff)
-{
-	struct vm_unmapped_area_info info;
-
-	info.flags = 0;
-	info.length = len;
-	info.low_limit = PAGE_ALIGN(addr);
-	info.high_limit = TASK_SIZE;
-	info.align_mask = PAGE_MASK & (SHMLBA - 1);
-	info.align_offset = shared_align_offset(filp, pgoff);
-	return vm_unmapped_area(&info);
-}
 
 unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
-	if (len > TASK_SIZE)
-		return -ENOMEM;
-	if (flags & MAP_FIXED) {
-		if ((flags & MAP_SHARED) &&
-		    (addr - shared_align_offset(filp, pgoff)) & (SHMLBA - 1))
-			return -EINVAL;
-		return addr;
-	}
-	if (!addr)
-		addr = TASK_UNMAPPED_BASE;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long task_size = TASK_SIZE;
+	int do_color_align, last_mmap;
+	struct vm_unmapped_area_info info;
 
+	if (len > task_size)
+		return -ENOMEM;
+
+	do_color_align = 0;
 	if (filp || (flags & MAP_SHARED))
-		addr = get_shared_area(filp, addr, len, pgoff);
-	else
-		addr = get_unshared_area(addr, len);
+		do_color_align = 1;
+	last_mmap = GET_LAST_MMAP(filp);
+
+	if (flags & MAP_FIXED) {
+		if ((flags & MAP_SHARED) && last_mmap &&
+		    (addr - shared_align_offset(last_mmap, pgoff))
+				& (SHMLBA - 1))
+			return -EINVAL;
+		goto found_addr;
+	}
+
+	if (addr) {
+		if (do_color_align && last_mmap)
+			addr = COLOR_ALIGN(addr, last_mmap, pgoff);
+		else
+			addr = PAGE_ALIGN(addr);
+
+		vma = find_vma(mm, addr);
+		if (task_size - len >= addr &&
+		    (!vma || addr + len <= vma->vm_start))
+			goto found_addr;
+	}
+
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = mm->mmap_legacy_base;
+	info.high_limit = mmap_upper_limit();
+	info.align_mask = last_mmap ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_offset = shared_align_offset(last_mmap, pgoff);
+	addr = vm_unmapped_area(&info);
+
+found_addr:
+	if (do_color_align && !last_mmap && !(addr & ~PAGE_MASK))
+		SET_LAST_MMAP(filp, addr - (pgoff << PAGE_SHIFT));
 
 	return addr;
 }
 
+unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
+			  const unsigned long len, const unsigned long pgoff,
+			  const unsigned long flags)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *mm = current->mm;
+	unsigned long addr = addr0;
+	int do_color_align, last_mmap;
+	struct vm_unmapped_area_info info;
+
+#ifdef CONFIG_64BIT
+	/* This should only ever run for 32-bit processes.  */
+	BUG_ON(!test_thread_flag(TIF_32BIT));
+#endif
+
+	/* requested length too big for entire address space */
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	do_color_align = 0;
+	if (filp || (flags & MAP_SHARED))
+		do_color_align = 1;
+	last_mmap = GET_LAST_MMAP(filp);
+
+	if (flags & MAP_FIXED) {
+		if ((flags & MAP_SHARED) && last_mmap &&
+		    (addr - shared_align_offset(last_mmap, pgoff))
+			& (SHMLBA - 1))
+			return -EINVAL;
+		goto found_addr;
+	}
+
+	/* requesting a specific address */
+	if (addr) {
+		if (do_color_align && last_mmap)
+			addr = COLOR_ALIGN(addr, last_mmap, pgoff);
+		else
+			addr = PAGE_ALIGN(addr);
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+		    (!vma || addr + len <= vma->vm_start))
+			goto found_addr;
+	}
+
+	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+	info.length = len;
+	info.low_limit = PAGE_SIZE;
+	info.high_limit = mm->mmap_base;
+	info.align_mask = last_mmap ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_offset = shared_align_offset(last_mmap, pgoff);
+	addr = vm_unmapped_area(&info);
+	if (!(addr & ~PAGE_MASK))
+		goto found_addr;
+	VM_BUG_ON(addr != -ENOMEM);
+
+	/*
+	 * A failed mmap() very likely causes application failure,
+	 * so fall back to the bottom-up function here. This scenario
+	 * can happen with large stack limits and large mmap()
+	 * allocations.
+	 */
+	return arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
+
+found_addr:
+	if (do_color_align && !last_mmap && !(addr & ~PAGE_MASK))
+		SET_LAST_MMAP(filp, addr - (pgoff << PAGE_SHIFT));
+
+	return addr;
+}
+
+static int mmap_is_legacy(void)
+{
+	if (current->personality & ADDR_COMPAT_LAYOUT)
+		return 1;
+
+	/* parisc stack always grows up - so a unlimited stack should
+	 * not be an indicator to use the legacy memory layout.
+	 * if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
+	 *	return 1;
+	 */
+
+	return sysctl_legacy_va_layout;
+}
+
+static unsigned long mmap_rnd(void)
+{
+	unsigned long rnd = 0;
+
+	/*
+	*  8 bits of randomness in 32bit mmaps, 20 address space bits
+	* 28 bits of randomness in 64bit mmaps, 40 address space bits
+	*/
+	if (current->flags & PF_RANDOMIZE) {
+		if (is_32bit_task())
+			rnd = get_random_int() % (1<<8);
+		else
+			rnd = get_random_int() % (1<<28);
+	}
+	return rnd << PAGE_SHIFT;
+}
+
+static unsigned long mmap_legacy_base(void)
+{
+	return TASK_UNMAPPED_BASE + mmap_rnd();
+}
+
+/*
+ * This function, called very early during the creation of a new
+ * process VM image, sets up which VM layout function to use:
+ */
+void arch_pick_mmap_layout(struct mm_struct *mm)
+{
+	mm->mmap_legacy_base = mmap_legacy_base();
+	mm->mmap_base = mmap_upper_limit();
+
+	if (mmap_is_legacy()) {
+		mm->mmap_base = mm->mmap_legacy_base;
+		mm->get_unmapped_area = arch_get_unmapped_area;
+	} else {
+		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+	}
+}
+
+
 asmlinkage unsigned long sys_mmap2(unsigned long addr, unsigned long len,
 	unsigned long prot, unsigned long flags, unsigned long fd,
 	unsigned long pgoff)
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 0c91072..80e5dd2 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -429,6 +429,9 @@
 	ENTRY_COMP(process_vm_writev)
 	ENTRY_SAME(kcmp)
 	ENTRY_SAME(finit_module)
+	ENTRY_SAME(sched_setattr)
+	ENTRY_SAME(sched_getattr)	/* 335 */
+	ENTRY_COMP(utimes)
 
 	/* Nothing yet */
 
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 84fdf68..a613d2c 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -200,10 +200,11 @@
 
 	/*
 	 * We can't access below the stack pointer in the 32bit ABI and
-	 * can access 288 bytes in the 64bit ABI
+	 * can access 288 bytes in the 64bit big-endian ABI,
+	 * or 512 bytes with the new ELFv2 little-endian ABI.
 	 */
 	if (!is_32bit_task())
-		usp -= 288;
+		usp -= USER_REDZONE_SIZE;
 
 	return (void __user *) (usp - len);
 }
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index e27e9ad..150866b 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -134,6 +134,7 @@
 }
 
 extern int dma_set_mask(struct device *dev, u64 dma_mask);
+extern int __dma_set_mask(struct device *dev, u64 dma_mask);
 
 #define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
 
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 9e39ceb..d4dd41f 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -172,10 +172,20 @@
 };
 
 extern struct eeh_ops *eeh_ops;
-extern int eeh_subsystem_enabled;
+extern bool eeh_subsystem_enabled;
 extern raw_spinlock_t confirm_error_lock;
 extern int eeh_probe_mode;
 
+static inline bool eeh_enabled(void)
+{
+	return eeh_subsystem_enabled;
+}
+
+static inline void eeh_set_enable(bool mode)
+{
+	eeh_subsystem_enabled = mode;
+}
+
 #define EEH_PROBE_MODE_DEV	(1<<0)	/* From PCI device	*/
 #define EEH_PROBE_MODE_DEVTREE	(1<<1)	/* From device tree	*/
 
@@ -246,7 +256,7 @@
  * If this macro yields TRUE, the caller relays to eeh_check_failure()
  * which does further tests out of line.
  */
-#define EEH_POSSIBLE_ERROR(val, type)	((val) == (type)~0 && eeh_subsystem_enabled)
+#define EEH_POSSIBLE_ERROR(val, type)	((val) == (type)~0 && eeh_enabled())
 
 /*
  * Reads from a device which has been isolated by EEH will return
@@ -257,6 +267,13 @@
 
 #else /* !CONFIG_EEH */
 
+static inline bool eeh_enabled(void)
+{
+        return false;
+}
+
+static inline void eeh_set_enable(bool mode) { }
+
 static inline int eeh_init(void)
 {
 	return 0;
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index d750336..623f297 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -127,7 +127,7 @@
 					    unsigned long addr, pte_t *ptep)
 {
 #ifdef CONFIG_PPC64
-	return __pte(pte_update(mm, addr, ptep, ~0UL, 1));
+	return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
 #else
 	return __pte(pte_update(ptep, ~0UL, 0));
 #endif
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index f7a8036..42632c7 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -77,6 +77,7 @@
 #ifdef CONFIG_IOMMU_API
 	struct iommu_group *it_group;
 #endif
+	void (*set_bypass)(struct iommu_table *tbl, bool enable);
 };
 
 /* Pure 2^n version of get_order */
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 40157e2..ed82142 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -816,8 +816,8 @@
 int64_t opal_pci_poll(uint64_t phb_id);
 int64_t opal_return_cpu(void);
 
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
-int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
+int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val);
+int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val);
 
 int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
 		       uint32_t addr, uint32_t data, uint32_t sz);
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index bc141c9..eb92610 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -195,6 +195,7 @@
 static inline unsigned long pte_update(struct mm_struct *mm,
 				       unsigned long addr,
 				       pte_t *ptep, unsigned long clr,
+				       unsigned long set,
 				       int huge)
 {
 #ifdef PTE_ATOMIC_UPDATES
@@ -205,14 +206,15 @@
 	andi.	%1,%0,%6\n\
 	bne-	1b \n\
 	andc	%1,%0,%4 \n\
+	or	%1,%1,%7\n\
 	stdcx.	%1,0,%3 \n\
 	bne-	1b"
 	: "=&r" (old), "=&r" (tmp), "=m" (*ptep)
-	: "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY)
+	: "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set)
 	: "cc" );
 #else
 	unsigned long old = pte_val(*ptep);
-	*ptep = __pte(old & ~clr);
+	*ptep = __pte((old & ~clr) | set);
 #endif
 	/* huge pages use the old page table lock */
 	if (!huge)
@@ -231,9 +233,9 @@
 {
 	unsigned long old;
 
-       	if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+	if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
 		return 0;
-	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0);
+	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
 	return (old & _PAGE_ACCESSED) != 0;
 }
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
@@ -252,7 +254,7 @@
 	if ((pte_val(*ptep) & _PAGE_RW) == 0)
 		return;
 
-	pte_update(mm, addr, ptep, _PAGE_RW, 0);
+	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
 }
 
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
@@ -261,7 +263,7 @@
 	if ((pte_val(*ptep) & _PAGE_RW) == 0)
 		return;
 
-	pte_update(mm, addr, ptep, _PAGE_RW, 1);
+	pte_update(mm, addr, ptep, _PAGE_RW, 0, 1);
 }
 
 /*
@@ -284,14 +286,14 @@
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long addr, pte_t *ptep)
 {
-	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0);
+	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0);
 	return __pte(old);
 }
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
 			     pte_t * ptep)
 {
-	pte_update(mm, addr, ptep, ~0UL, 0);
+	pte_update(mm, addr, ptep, ~0UL, 0, 0);
 }
 
 
@@ -506,7 +508,9 @@
 
 extern unsigned long pmd_hugepage_update(struct mm_struct *mm,
 					 unsigned long addr,
-					 pmd_t *pmdp, unsigned long clr);
+					 pmd_t *pmdp,
+					 unsigned long clr,
+					 unsigned long set);
 
 static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 					      unsigned long addr, pmd_t *pmdp)
@@ -515,7 +519,7 @@
 
 	if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
 		return 0;
-	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED);
+	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
 	return ((old & _PAGE_ACCESSED) != 0);
 }
 
@@ -542,7 +546,7 @@
 	if ((pmd_val(*pmdp) & _PAGE_RW) == 0)
 		return;
 
-	pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW);
+	pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0);
 }
 
 #define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index f83b6f3..3ebb188 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -75,12 +75,34 @@
 	return pte;
 }
 
+#define ptep_set_numa ptep_set_numa
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pte_t *ptep)
+{
+	if ((pte_val(*ptep) & _PAGE_PRESENT) == 0)
+		VM_BUG_ON(1);
+
+	pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0);
+	return;
+}
+
 #define pmd_numa pmd_numa
 static inline int pmd_numa(pmd_t pmd)
 {
 	return pte_numa(pmd_pte(pmd));
 }
 
+#define pmdp_set_numa pmdp_set_numa
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pmd_t *pmdp)
+{
+	if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0)
+		VM_BUG_ON(1);
+
+	pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA);
+	return;
+}
+
 #define pmd_mknonnuma pmd_mknonnuma
 static inline pmd_t pmd_mknonnuma(pmd_t pmd)
 {
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index becc08e..279b80f 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -28,11 +28,23 @@
 
 #ifdef __powerpc64__
 
+/*
+ * Size of redzone that userspace is allowed to use below the stack
+ * pointer.  This is 288 in the 64-bit big-endian ELF ABI, and 512 in
+ * the new ELFv2 little-endian ABI, so we allow the larger amount.
+ *
+ * For kernel code we allow a 288-byte redzone, in order to conserve
+ * kernel stack space; gcc currently only uses 288 bytes, and will
+ * hopefully allow explicit control of the redzone size in future.
+ */
+#define USER_REDZONE_SIZE	512
+#define KERNEL_REDZONE_SIZE	288
+
 #define STACK_FRAME_OVERHEAD	112	/* size of minimum stack frame */
 #define STACK_FRAME_LR_SAVE	2	/* Location of LR in stack frame */
 #define STACK_FRAME_REGS_MARKER	ASM_CONST(0x7265677368657265)
 #define STACK_INT_FRAME_SIZE	(sizeof(struct pt_regs) + \
-					STACK_FRAME_OVERHEAD + 288)
+				 STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
 #define STACK_FRAME_MARKER	12
 
 /* Size of dummy stack frame allocated when calling signal handler. */
@@ -41,6 +53,8 @@
 
 #else /* __powerpc64__ */
 
+#define USER_REDZONE_SIZE	0
+#define KERNEL_REDZONE_SIZE	0
 #define STACK_FRAME_OVERHEAD	16	/* size of minimum stack frame */
 #define STACK_FRAME_LR_SAVE	1	/* Location of LR in stack frame */
 #define STACK_FRAME_REGS_MARKER	ASM_CONST(0x72656773)
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 4ee06fe..d0e784e 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -8,6 +8,7 @@
 
 #ifdef __powerpc64__
 
+extern char __start_interrupts[];
 extern char __end_interrupts[];
 
 extern char __prom_init_toc_start[];
@@ -21,6 +22,17 @@
 	return 0;
 }
 
+static inline int overlaps_interrupt_vector_text(unsigned long start,
+							unsigned long end)
+{
+	unsigned long real_start, real_end;
+	real_start = __start_interrupts - _stext;
+	real_end = __end_interrupts - _stext;
+
+	return start < (unsigned long)__va(real_end) &&
+		(unsigned long)__va(real_start) < end;
+}
+
 static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
 {
 	return start < (unsigned long)__init_end &&
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index d0b5fca..c920215 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -99,7 +99,6 @@
 
 #ifdef CONFIG_SMP
 #include <asm/cputable.h>
-#define smt_capable()		(cpu_has_feature(CPU_FTR_SMT))
 
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index 0d9cecd..c53f5f6 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -4,11 +4,11 @@
 #ifdef __KERNEL__
 
 /* Default link addresses for the vDSOs */
-#define VDSO32_LBASE	0x100000
-#define VDSO64_LBASE	0x100000
+#define VDSO32_LBASE	0x0
+#define VDSO64_LBASE	0x0
 
 /* Default map addresses for 32bit vDSO */
-#define VDSO32_MBASE	VDSO32_LBASE
+#define VDSO32_MBASE	0x100000
 
 #define VDSO_VERSION_STRING	LINUX_2.6.15
 
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 11c1d06..7a13f37 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -98,17 +98,19 @@
 			size_t csize, unsigned long offset, int userbuf)
 {
 	void  *vaddr;
+	phys_addr_t paddr;
 
 	if (!csize)
 		return 0;
 
 	csize = min_t(size_t, csize, PAGE_SIZE);
+	paddr = pfn << PAGE_SHIFT;
 
-	if ((min_low_pfn < pfn) && (pfn < max_pfn)) {
-		vaddr = __va(pfn << PAGE_SHIFT);
+	if (memblock_is_region_memory(paddr, csize)) {
+		vaddr = __va(paddr);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 	} else {
-		vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0);
+		vaddr = __ioremap(paddr, PAGE_SIZE, 0);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 		iounmap(vaddr);
 	}
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 8032b97..ee78f6e 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -191,12 +191,10 @@
 
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
 
-int dma_set_mask(struct device *dev, u64 dma_mask)
+int __dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	if (ppc_md.dma_set_mask)
-		return ppc_md.dma_set_mask(dev, dma_mask);
 	if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL))
 		return dma_ops->set_dma_mask(dev, dma_mask);
 	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
@@ -204,6 +202,12 @@
 	*dev->dma_mask = dma_mask;
 	return 0;
 }
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (ppc_md.dma_set_mask)
+		return ppc_md.dma_set_mask(dev, dma_mask);
+	return __dma_set_mask(dev, dma_mask);
+}
 EXPORT_SYMBOL(dma_set_mask);
 
 u64 dma_get_required_mask(struct device *dev)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 148db72..e7b76a6 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -28,6 +28,7 @@
 #include <linux/pci.h>
 #include <linux/proc_fs.h>
 #include <linux/rbtree.h>
+#include <linux/reboot.h>
 #include <linux/seq_file.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
@@ -89,7 +90,7 @@
 /* Platform dependent EEH operations */
 struct eeh_ops *eeh_ops = NULL;
 
-int eeh_subsystem_enabled;
+bool eeh_subsystem_enabled = false;
 EXPORT_SYMBOL(eeh_subsystem_enabled);
 
 /*
@@ -364,7 +365,7 @@
 
 	eeh_stats.total_mmio_ffs++;
 
-	if (!eeh_subsystem_enabled)
+	if (!eeh_enabled())
 		return 0;
 
 	if (!edev) {
@@ -747,6 +748,17 @@
 	return -EEXIST;
 }
 
+static int eeh_reboot_notifier(struct notifier_block *nb,
+			       unsigned long action, void *unused)
+{
+	eeh_set_enable(false);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block eeh_reboot_nb = {
+	.notifier_call = eeh_reboot_notifier,
+};
+
 /**
  * eeh_init - EEH initialization
  *
@@ -778,6 +790,14 @@
 	if (machine_is(powernv) && cnt++ <= 0)
 		return ret;
 
+	/* Register reboot notifier */
+	ret = register_reboot_notifier(&eeh_reboot_nb);
+	if (ret) {
+		pr_warn("%s: Failed to register notifier (%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
 	/* call platform initialization function */
 	if (!eeh_ops) {
 		pr_warning("%s: Platform EEH operation not found\n",
@@ -822,7 +842,7 @@
 			return ret;
 	}
 
-	if (eeh_subsystem_enabled)
+	if (eeh_enabled())
 		pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
 	else
 		pr_warning("EEH: No capable adapters found\n");
@@ -897,7 +917,7 @@
 	struct device_node *dn;
 	struct eeh_dev *edev;
 
-	if (!dev || !eeh_subsystem_enabled)
+	if (!dev || !eeh_enabled())
 		return;
 
 	pr_debug("EEH: Adding device %s\n", pci_name(dev));
@@ -1005,7 +1025,7 @@
 {
 	struct eeh_dev *edev;
 
-	if (!dev || !eeh_subsystem_enabled)
+	if (!dev || !eeh_enabled())
 		return;
 	edev = pci_dev_to_eeh_dev(dev);
 
@@ -1045,7 +1065,7 @@
 
 static int proc_eeh_show(struct seq_file *m, void *v)
 {
-	if (0 == eeh_subsystem_enabled) {
+	if (!eeh_enabled()) {
 		seq_printf(m, "EEH Subsystem is globally disabled\n");
 		seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs);
 	} else {
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 7bb30dc..fdc679d 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -362,9 +362,13 @@
 	 */
 	if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
 		return NULL;
+
 	driver = eeh_pcid_get(dev);
-	if (driver && driver->err_handler)
-		return NULL;
+	if (driver) {
+		eeh_pcid_put(dev);
+		if (driver->err_handler)
+			return NULL;
+	}
 
 	/* Remove it from PCI subsystem */
 	pr_debug("EEH: Removing %s without EEH sensitive driver\n",
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 9b27b29..b0ded97 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -74,6 +74,7 @@
  */
 static int test_24bit_addr(unsigned long ip, unsigned long addr)
 {
+	addr = ppc_function_entry((void *)addr);
 
 	/* use the create_branch to verify that this offset can be branched */
 	return create_branch((unsigned int *)ip, addr, 0);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index d773dd4..88e3ec6 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1088,6 +1088,14 @@
 	memset(tbl->it_map, 0xff, sz);
 	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
 
+	/*
+	 * Disable iommu bypass, otherwise the user can DMA to all of
+	 * our physical memory via the bypass window instead of just
+	 * the pages that has been explicitly mapped into the iommu
+	 */
+	if (tbl->set_bypass)
+		tbl->set_bypass(tbl, false);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_take_ownership);
@@ -1102,6 +1110,10 @@
 	/* Restore bit#0 set by iommu_init_table() */
 	if (tbl->it_offset == 0)
 		set_bit(0, tbl->it_map);
+
+	/* The kernel owns the device now, we can restore the iommu bypass */
+	if (tbl->set_bypass)
+		tbl->set_bypass(tbl, true);
 }
 EXPORT_SYMBOL_GPL(iommu_release_ownership);
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 9729b23..1d0848b 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -559,8 +559,13 @@
 #ifdef CONFIG_PPC64
 		cpu_nr = i;
 #else
+#ifdef CONFIG_SMP
 		cpu_nr = get_hard_smp_processor_id(i);
+#else
+		cpu_nr = 0;
 #endif
+#endif
+
 		memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
 		tp = critirq_ctx[cpu_nr];
 		tp->cpu = cpu_nr;
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 75d4f73..015ae55 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -196,7 +196,9 @@
 
 /* Values we need to export to the second kernel via the device tree. */
 static phys_addr_t kernel_end;
+static phys_addr_t crashk_base;
 static phys_addr_t crashk_size;
+static unsigned long long mem_limit;
 
 static struct property kernel_end_prop = {
 	.name = "linux,kernel-end",
@@ -207,7 +209,7 @@
 static struct property crashk_base_prop = {
 	.name = "linux,crashkernel-base",
 	.length = sizeof(phys_addr_t),
-	.value = &crashk_res.start,
+	.value = &crashk_base
 };
 
 static struct property crashk_size_prop = {
@@ -219,9 +221,11 @@
 static struct property memory_limit_prop = {
 	.name = "linux,memory-limit",
 	.length = sizeof(unsigned long long),
-	.value = &memory_limit,
+	.value = &mem_limit,
 };
 
+#define cpu_to_be_ulong	__PASTE(cpu_to_be, BITS_PER_LONG)
+
 static void __init export_crashk_values(struct device_node *node)
 {
 	struct property *prop;
@@ -237,8 +241,9 @@
 		of_remove_property(node, prop);
 
 	if (crashk_res.start != 0) {
+		crashk_base = cpu_to_be_ulong(crashk_res.start),
 		of_add_property(node, &crashk_base_prop);
-		crashk_size = resource_size(&crashk_res);
+		crashk_size = cpu_to_be_ulong(resource_size(&crashk_res));
 		of_add_property(node, &crashk_size_prop);
 	}
 
@@ -246,6 +251,7 @@
 	 * memory_limit is required by the kexec-tools to limit the
 	 * crash regions to the actual memory used.
 	 */
+	mem_limit = cpu_to_be_ulong(memory_limit);
 	of_update_property(node, &memory_limit_prop);
 }
 
@@ -264,7 +270,7 @@
 		of_remove_property(node, prop);
 
 	/* information needed by userspace when using default_machine_kexec */
-	kernel_end = __pa(_end);
+	kernel_end = cpu_to_be_ulong(__pa(_end));
 	of_add_property(node, &kernel_end_prop);
 
 	export_crashk_values(node);
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index be4e6d6..59d229a 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -369,6 +369,7 @@
 
 /* Values we need to export to the second kernel via the device tree. */
 static unsigned long htab_base;
+static unsigned long htab_size;
 
 static struct property htab_base_prop = {
 	.name = "linux,htab-base",
@@ -379,7 +380,7 @@
 static struct property htab_size_prop = {
 	.name = "linux,htab-size",
 	.length = sizeof(unsigned long),
-	.value = &htab_size_bytes,
+	.value = &htab_size,
 };
 
 static int __init export_htab_values(void)
@@ -403,8 +404,9 @@
 	if (prop)
 		of_remove_property(node, prop);
 
-	htab_base = __pa(htab_address);
+	htab_base = cpu_to_be64(__pa(htab_address));
 	of_add_property(node, &htab_base_prop);
+	htab_size = cpu_to_be64(htab_size_bytes);
 	of_add_property(node, &htab_size_prop);
 
 	of_node_put(node);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 879f096..7c6bb4b 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -57,11 +57,14 @@
 	mtlr	r0
 	blr
 
+/*
+ * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
+ */
 _GLOBAL(call_do_irq)
 	mflr	r0
 	stw	r0,4(r1)
 	lwz	r10,THREAD+KSP_LIMIT(r2)
-	addi	r11,r3,THREAD_INFO_GAP
+	addi	r11,r4,THREAD_INFO_GAP
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
 	mr	r1,r4
 	stw	r10,8(r1)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8d4c247f1..af064d2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1048,6 +1048,15 @@
 	flush_altivec_to_thread(src);
 	flush_vsx_to_thread(src);
 	flush_spe_to_thread(src);
+	/*
+	 * Flush TM state out so we can copy it.  __switch_to_tm() does this
+	 * flush but it removes the checkpointed state from the current CPU and
+	 * transitions the CPU out of TM mode.  Hence we need to call
+	 * tm_recheckpoint_new_task() (on the same task) to restore the
+	 * checkpointed state back and the TM mode.
+	 */
+	__switch_to_tm(src);
+	tm_recheckpoint_new_task(src);
 
 	*dst = *src;
 
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index b47a0e1..d88736f 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -69,8 +69,8 @@
 	 * R_PPC64_RELATIVE ones.
 	 */
 	mtctr	r8
-5:	lwz	r0,12(9)	/* ELF64_R_TYPE(reloc->r_info) */
-	cmpwi	r0,R_PPC64_RELATIVE
+5:	ld	r0,8(9)		/* ELF64_R_TYPE(reloc->r_info) */
+	cmpdi	r0,R_PPC64_RELATIVE
 	bne	6f
 	ld	r6,0(r9)	/* reloc->r_offset */
 	ld	r0,16(r9)	/* reloc->r_addend */
@@ -81,6 +81,7 @@
 
 6:	blr
 
+.balign 8
 p_dyn:	.llong	__dynamic_start - 0b
 p_rela:	.llong	__rela_dyn_start - 0b
 p_st:	.llong	_stext - 0b
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 2b0da27..04cc4fc 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -247,7 +247,12 @@
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
 	 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
 	for_each_possible_cpu(i) {
+#ifdef CONFIG_SMP
 		hw_cpu = get_hard_smp_processor_id(i);
+#else
+		hw_cpu = 0;
+#endif
+
 		critirq_ctx[hw_cpu] = (struct thread_info *)
 			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 #ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index e35bf77..8d253c2 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -65,8 +65,8 @@
 	struct siginfo __user *pinfo;
 	void __user *puc;
 	struct siginfo info;
-	/* 64 bit ABI allows for 288 bytes below sp before decrementing it. */
-	char abigap[288];
+	/* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */
+	char abigap[USER_REDZONE_SIZE];
 } __attribute__ ((aligned (16)));
 
 static const char fmt32[] = KERN_INFO \
diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
index 79683d0..6ac107a 100644
--- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
+++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
@@ -6,7 +6,7 @@
 	.globl vdso32_start, vdso32_end
 	.balign PAGE_SIZE
 vdso32_start:
-	.incbin "arch/powerpc/kernel/vdso32/vdso32.so"
+	.incbin "arch/powerpc/kernel/vdso32/vdso32.so.dbg"
 	.balign PAGE_SIZE
 vdso32_end:
 
diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
index 8df9e24..df60fca 100644
--- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
+++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
@@ -6,7 +6,7 @@
 	.globl vdso64_start, vdso64_end
 	.balign PAGE_SIZE
 vdso64_start:
-	.incbin "arch/powerpc/kernel/vdso64/vdso64.so"
+	.incbin "arch/powerpc/kernel/vdso64/vdso64.so.dbg"
 	.balign PAGE_SIZE
 vdso64_end:
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e66d4ec..818dce3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1504,73 +1504,6 @@
 1:	addi	r8,r8,16
 	.endr
 
-	/* Save DEC */
-	mfspr	r5,SPRN_DEC
-	mftb	r6
-	extsw	r5,r5
-	add	r5,r5,r6
-	std	r5,VCPU_DEC_EXPIRES(r9)
-
-BEGIN_FTR_SECTION
-	b	8f
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
-	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
-	/* Save POWER8-specific registers */
-	mfspr	r5, SPRN_IAMR
-	mfspr	r6, SPRN_PSPB
-	mfspr	r7, SPRN_FSCR
-	std	r5, VCPU_IAMR(r9)
-	stw	r6, VCPU_PSPB(r9)
-	std	r7, VCPU_FSCR(r9)
-	mfspr	r5, SPRN_IC
-	mfspr	r6, SPRN_VTB
-	mfspr	r7, SPRN_TAR
-	std	r5, VCPU_IC(r9)
-	std	r6, VCPU_VTB(r9)
-	std	r7, VCPU_TAR(r9)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	mfspr	r5, SPRN_TFHAR
-	mfspr	r6, SPRN_TFIAR
-	mfspr	r7, SPRN_TEXASR
-	std	r5, VCPU_TFHAR(r9)
-	std	r6, VCPU_TFIAR(r9)
-	std	r7, VCPU_TEXASR(r9)
-#endif
-	mfspr	r8, SPRN_EBBHR
-	std	r8, VCPU_EBBHR(r9)
-	mfspr	r5, SPRN_EBBRR
-	mfspr	r6, SPRN_BESCR
-	mfspr	r7, SPRN_CSIGR
-	mfspr	r8, SPRN_TACR
-	std	r5, VCPU_EBBRR(r9)
-	std	r6, VCPU_BESCR(r9)
-	std	r7, VCPU_CSIGR(r9)
-	std	r8, VCPU_TACR(r9)
-	mfspr	r5, SPRN_TCSCR
-	mfspr	r6, SPRN_ACOP
-	mfspr	r7, SPRN_PID
-	mfspr	r8, SPRN_WORT
-	std	r5, VCPU_TCSCR(r9)
-	std	r6, VCPU_ACOP(r9)
-	stw	r7, VCPU_GUEST_PID(r9)
-	std	r8, VCPU_WORT(r9)
-8:
-
-	/* Save and reset AMR and UAMOR before turning on the MMU */
-BEGIN_FTR_SECTION
-	mfspr	r5,SPRN_AMR
-	mfspr	r6,SPRN_UAMOR
-	std	r5,VCPU_AMR(r9)
-	std	r6,VCPU_UAMOR(r9)
-	li	r6,0
-	mtspr	SPRN_AMR,r6
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
 	/* Unset guest mode */
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
@@ -2203,7 +2136,7 @@
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
 	mfspr	r6,SPRN_VRSAVE
-	stw	r6,VCPU_VRSAVE(r3)
+	stw	r6,VCPU_VRSAVE(r31)
 	mtlr	r30
 	mtmsrd	r5
 	isync
@@ -2240,7 +2173,7 @@
 	bl	.load_vr_state
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
-	lwz	r7,VCPU_VRSAVE(r4)
+	lwz	r7,VCPU_VRSAVE(r31)
 	mtspr	SPRN_VRSAVE,r7
 	mtlr	r30
 	mr	r4,r31
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index de68812..d766d6e 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -207,6 +207,20 @@
 		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
 
+		/*
+		 * If relocatable, check if it overlaps interrupt vectors that
+		 * are copied down to real 0. For relocatable kernel
+		 * (e.g. kdump case) we copy interrupt vectors down to real
+		 * address 0. Mark that region as executable. This is
+		 * because on p8 system with relocation on exception feature
+		 * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence
+		 * in order to execute the interrupt handlers in virtual
+		 * mode the vector region need to be marked as executable.
+		 */
+		if ((PHYSICAL_START > MEMORY_START) &&
+			overlaps_interrupt_vector_text(vaddr, vaddr + step))
+				tprot &= ~HPTE_R_N;
+
 		hash = hpt_hash(vpn, shift, ssize);
 		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 65b7b65..62bf5e8 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -510,7 +510,8 @@
 }
 
 unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
-				  pmd_t *pmdp, unsigned long clr)
+				  pmd_t *pmdp, unsigned long clr,
+				  unsigned long set)
 {
 
 	unsigned long old, tmp;
@@ -526,14 +527,15 @@
 		andi.	%1,%0,%6\n\
 		bne-	1b \n\
 		andc	%1,%0,%4 \n\
+		or	%1,%1,%7\n\
 		stdcx.	%1,0,%3 \n\
 		bne-	1b"
 	: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
-	: "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY)
+	: "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY), "r" (set)
 	: "cc" );
 #else
 	old = pmd_val(*pmdp);
-	*pmdp = __pmd(old & ~clr);
+	*pmdp = __pmd((old & ~clr) | set);
 #endif
 	if (old & _PAGE_HASHPTE)
 		hpte_do_hugepage_flush(mm, addr, pmdp);
@@ -708,7 +710,7 @@
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
-	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT);
+	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
 }
 
 /*
@@ -835,7 +837,7 @@
 	unsigned long old;
 	pgtable_t *pgtable_slot;
 
-	old = pmd_hugepage_update(mm, addr, pmdp, ~0UL);
+	old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0);
 	old_pmd = __pmd(old);
 	/*
 	 * We have pmd == none and we are holding page_table_lock.
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index a770df2d..6c0b1f5 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -78,7 +78,7 @@
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	arch_enter_lazy_mmu_mode();
 	for (; npages > 0; --npages) {
-		pte_update(mm, addr, pte, 0, 0);
+		pte_update(mm, addr, pte, 0, 0, 0);
 		addr += PAGE_SIZE;
 		++pte;
 	}
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 29b89e8..67cf220 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1147,6 +1147,9 @@
 	mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
 
 	mb();
+	if (cpuhw->bhrb_users)
+		ppmu->config_bhrb(cpuhw->bhrb_filter);
+
 	write_mmcr0(cpuhw, mmcr0);
 
 	/*
@@ -1158,8 +1161,6 @@
 	}
 
  out:
-	if (cpuhw->bhrb_users)
-		ppmu->config_bhrb(cpuhw->bhrb_filter);
 
 	local_irq_restore(flags);
 }
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index a3f7abd..96cee20 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -25,6 +25,37 @@
 #define PM_BRU_FIN			0x10068
 #define PM_BR_MPRED_CMPL		0x400f6
 
+/* All L1 D cache load references counted at finish, gated by reject */
+#define PM_LD_REF_L1			0x100ee
+/* Load Missed L1 */
+#define PM_LD_MISS_L1			0x3e054
+/* Store Missed L1 */
+#define PM_ST_MISS_L1			0x300f0
+/* L1 cache data prefetches */
+#define PM_L1_PREF			0x0d8b8
+/* Instruction fetches from L1 */
+#define PM_INST_FROM_L1			0x04080
+/* Demand iCache Miss */
+#define PM_L1_ICACHE_MISS		0x200fd
+/* Instruction Demand sectors wriittent into IL1 */
+#define PM_L1_DEMAND_WRITE		0x0408c
+/* Instruction prefetch written into IL1 */
+#define PM_IC_PREF_WRITE		0x0408e
+/* The data cache was reloaded from local core's L3 due to a demand load */
+#define PM_DATA_FROM_L3			0x4c042
+/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */
+#define PM_DATA_FROM_L3MISS		0x300fe
+/* All successful D-side store dispatches for this thread */
+#define PM_L2_ST			0x17080
+/* All successful D-side store dispatches for this thread that were L2 Miss */
+#define PM_L2_ST_MISS			0x17082
+/* Total HW L3 prefetches(Load+store) */
+#define PM_L3_PREF_ALL			0x4e052
+/* Data PTEG reload */
+#define PM_DTLB_MISS			0x300fc
+/* ITLB Reloaded */
+#define PM_ITLB_MISS			0x400fc
+
 
 /*
  * Raw event encoding for POWER8:
@@ -557,6 +588,8 @@
 	[PERF_COUNT_HW_INSTRUCTIONS] =			PM_INST_CMPL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PM_BRU_FIN,
 	[PERF_COUNT_HW_BRANCH_MISSES] =			PM_BR_MPRED_CMPL,
+	[PERF_COUNT_HW_CACHE_REFERENCES] =		PM_LD_REF_L1,
+	[PERF_COUNT_HW_CACHE_MISSES] =			PM_LD_MISS_L1,
 };
 
 static u64 power8_bhrb_filter_map(u64 branch_sample_type)
@@ -596,6 +629,116 @@
 	mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
 }
 
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[ C(L1D) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
+			[ C(RESULT_MISS)   ] = PM_LD_MISS_L1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ST_MISS_L1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_PREF,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(L1I) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_INST_FROM_L1,
+			[ C(RESULT_MISS)   ] = PM_L1_ICACHE_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(LL) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3,
+			[ C(RESULT_MISS)   ] = PM_DATA_FROM_L3MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L2_ST,
+			[ C(RESULT_MISS)   ] = PM_L2_ST_MISS,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(DTLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_DTLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(ITLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ITLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(BPU) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_BRU_FIN,
+			[ C(RESULT_MISS)   ] = PM_BR_MPRED_CMPL,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(NODE) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+};
+
+#undef C
+
 static struct power_pmu power8_pmu = {
 	.name			= "POWER8",
 	.n_counter		= 6,
@@ -611,6 +754,7 @@
 	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
+	.cache_events		= &power8_cache_events,
 	.attr_groups		= power8_pmu_attr_groups,
 	.bhrb_nr		= 32,
 };
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 5ec1e47..e865d74 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -123,7 +123,8 @@
 
 	area->nid = nid;
 	area->order = order;
-	area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE,
+	area->pages = alloc_pages_exact_node(area->nid,
+						GFP_KERNEL|__GFP_THISNODE,
 						area->order);
 
 	if (!area->pages) {
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 4931838..4a0a64f 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -83,7 +83,6 @@
 #define MIN_SPU_TIMESLICE	max(5 * HZ / (1000 * SPUSCHED_TICK), 1)
 #define DEF_SPU_TIMESLICE	(100 * HZ / (1000 * SPUSCHED_TICK))
 
-#define MAX_USER_PRIO		(MAX_PRIO - MAX_RT_PRIO)
 #define SCALE_PRIO(x, prio) \
 	max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_SPU_TIMESLICE)
 
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index e1e7161..253fefe 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -44,7 +44,8 @@
 
 	/* We simply send special EEH event */
 	if ((changed_evts & OPAL_EVENT_PCI_ERROR) &&
-	    (events & OPAL_EVENT_PCI_ERROR))
+	    (events & OPAL_EVENT_PCI_ERROR) &&
+	    eeh_enabled())
 		eeh_send_failure_event(NULL);
 
 	return 0;
@@ -113,6 +114,7 @@
 			ioda_eeh_inbB_dbgfs_set, "0x%llx\n");
 #endif /* CONFIG_DEBUG_FS */
 
+
 /**
  * ioda_eeh_post_init - Chip dependent post initialization
  * @hose: PCI controller
@@ -220,6 +222,22 @@
 	return ret;
 }
 
+static void ioda_eeh_phb_diag(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+	long rc;
+
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+					 PNV_PCI_DIAG_BUF_SIZE);
+	if (rc != OPAL_SUCCESS) {
+		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
+			    __func__, hose->global_number, rc);
+		return;
+	}
+
+	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
+}
+
 /**
  * ioda_eeh_get_state - Retrieve the state of PE
  * @pe: EEH PE
@@ -271,6 +289,9 @@
 			result |= EEH_STATE_DMA_ACTIVE;
 			result |= EEH_STATE_MMIO_ENABLED;
 			result |= EEH_STATE_DMA_ENABLED;
+		} else if (!(pe->state & EEH_PE_ISOLATED)) {
+			eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+			ioda_eeh_phb_diag(hose);
 		}
 
 		return result;
@@ -314,6 +335,15 @@
 			   __func__, fstate, hose->global_number, pe_no);
 	}
 
+	/* Dump PHB diag-data for frozen PE */
+	if (result != EEH_STATE_NOT_SUPPORT &&
+	    (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) !=
+	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) &&
+	    !(pe->state & EEH_PE_ISOLATED)) {
+		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+		ioda_eeh_phb_diag(hose);
+	}
+
 	return result;
 }
 
@@ -489,8 +519,7 @@
 static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 {
 	struct pci_controller *hose = pe->phb;
-	struct eeh_dev *edev;
-	struct pci_dev *dev;
+	struct pci_bus *bus;
 	int ret;
 
 	/*
@@ -519,73 +548,17 @@
 	if (pe->type & EEH_PE_PHB) {
 		ret = ioda_eeh_phb_reset(hose, option);
 	} else {
-		if (pe->type & EEH_PE_DEVICE) {
-			/*
-			 * If it's device PE, we didn't refer to the parent
-			 * PCI bus yet. So we have to figure it out indirectly.
-			 */
-			edev = list_first_entry(&pe->edevs,
-					struct eeh_dev, list);
-			dev = eeh_dev_to_pci_dev(edev);
-			dev = dev->bus->self;
-		} else {
-			/*
-			 * If it's bus PE, the parent PCI bus is already there
-			 * and just pick it up.
-			 */
-			dev = pe->bus->self;
-		}
-
-		/*
-		 * Do reset based on the fact that the direct upstream bridge
-		 * is root bridge (port) or not.
-		 */
-		if (dev->bus->number == 0)
+		bus = eeh_pe_bus_get(pe);
+		if (pci_is_root_bus(bus))
 			ret = ioda_eeh_root_reset(hose, option);
 		else
-			ret = ioda_eeh_bridge_reset(hose, dev, option);
+			ret = ioda_eeh_bridge_reset(hose, bus->self, option);
 	}
 
 	return ret;
 }
 
 /**
- * ioda_eeh_get_log - Retrieve error log
- * @pe: EEH PE
- * @severity: Severity level of the log
- * @drv_log: buffer to store the log
- * @len: space of the log buffer
- *
- * The function is used to retrieve error log from P7IOC.
- */
-static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
-			    char *drv_log, unsigned long len)
-{
-	s64 ret;
-	unsigned long flags;
-	struct pci_controller *hose = pe->phb;
-	struct pnv_phb *phb = hose->private_data;
-
-	spin_lock_irqsave(&phb->lock, flags);
-
-	ret = opal_pci_get_phb_diag_data2(phb->opal_id,
-			phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
-	if (ret) {
-		spin_unlock_irqrestore(&phb->lock, flags);
-		pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n",
-			   __func__, hose->global_number, pe->addr, ret);
-		return -EIO;
-	}
-
-	/* The PHB diag-data is always indicative */
-	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-
-	spin_unlock_irqrestore(&phb->lock, flags);
-
-	return 0;
-}
-
-/**
  * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
  * @pe: EEH PE
  *
@@ -666,22 +639,6 @@
 	}
 }
 
-static void ioda_eeh_phb_diag(struct pci_controller *hose)
-{
-	struct pnv_phb *phb = hose->private_data;
-	long rc;
-
-	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
-					 PNV_PCI_DIAG_BUF_SIZE);
-	if (rc != OPAL_SUCCESS) {
-		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
-			    __func__, hose->global_number, rc);
-		return;
-	}
-
-	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-}
-
 static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
 			       struct eeh_pe **pe)
 {
@@ -855,6 +812,20 @@
 		}
 
 		/*
+		 * EEH core will try recover from fenced PHB or
+		 * frozen PE. In the time for frozen PE, EEH core
+		 * enable IO path for that before collecting logs,
+		 * but it ruins the site. So we have to dump the
+		 * log in advance here.
+		 */
+		if ((ret == EEH_NEXT_ERR_FROZEN_PE  ||
+		    ret == EEH_NEXT_ERR_FENCED_PHB) &&
+		    !((*pe)->state & EEH_PE_ISOLATED)) {
+			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+			ioda_eeh_phb_diag(hose);
+		}
+
+		/*
 		 * If we have no errors on the specific PHB or only
 		 * informative error there, we continue poking it.
 		 * Otherwise, we need actions to be taken by upper
@@ -872,7 +843,6 @@
 	.set_option		= ioda_eeh_set_option,
 	.get_state		= ioda_eeh_get_state,
 	.reset			= ioda_eeh_reset,
-	.get_log		= ioda_eeh_get_log,
 	.configure_bridge	= ioda_eeh_configure_bridge,
 	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index a79fddc..a59788e 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -145,7 +145,7 @@
 	 * Enable EEH explicitly so that we will do EEH check
 	 * while accessing I/O stuff
 	 */
-	eeh_subsystem_enabled = 1;
+	eeh_set_enable(true);
 
 	/* Save memory bars */
 	eeh_save_bars(edev);
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4fbf276..4cd2ea6 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -71,11 +71,11 @@
 	}
 }
 
-static u64 opal_scom_unmangle(u64 reg)
+static u64 opal_scom_unmangle(u64 addr)
 {
 	/*
 	 * XSCOM indirect addresses have the top bit set. Additionally
-	 * the reset of the top 3 nibbles is always 0.
+	 * the rest of the top 3 nibbles is always 0.
 	 *
 	 * Because the debugfs interface uses signed offsets and shifts
 	 * the address left by 3, we basically cannot use the top 4 bits
@@ -86,10 +86,13 @@
 	 * conversion here. To leave room for further xscom address
 	 * expansion, we only clear out the top byte
 	 *
+	 * For in-kernel use, we also support the real indirect bit, so
+	 * we test for any of the top 5 bits
+	 *
 	 */
-	if (reg & (1ull << 59))
-		reg = (reg & ~(0xffull << 56)) | (1ull << 63);
-	return reg;
+	if (addr & (0x1full << 59))
+		addr = (addr & ~(0xffull << 56)) | (1ull << 63);
+	return addr;
 }
 
 static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
@@ -98,8 +101,8 @@
 	int64_t rc;
 	__be64 v;
 
-	reg = opal_scom_unmangle(reg);
-	rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+	reg = opal_scom_unmangle(m->addr + reg);
+	rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v));
 	*value = be64_to_cpu(v);
 	return opal_xscom_err_xlate(rc);
 }
@@ -109,8 +112,8 @@
 	struct opal_scom_map *m = map;
 	int64_t rc;
 
-	reg = opal_scom_unmangle(reg);
-	rc = opal_xscom_write(m->chip, m->addr + reg, value);
+	reg = opal_scom_unmangle(m->addr + reg);
+	rc = opal_xscom_write(m->chip, reg, value);
 	return opal_xscom_err_xlate(rc);
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 7d6dcc6..3b2b4fb 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -21,6 +21,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
+#include <linux/memblock.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -460,9 +461,39 @@
 		return;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
+	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
 	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
 }
 
+static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
+				     struct pci_dev *pdev, u64 dma_mask)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	struct pnv_ioda_pe *pe;
+	uint64_t top;
+	bool bypass = false;
+
+	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
+		return -ENODEV;;
+
+	pe = &phb->ioda.pe_array[pdn->pe_number];
+	if (pe->tce_bypass_enabled) {
+		top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
+		bypass = (dma_mask >= top);
+	}
+
+	if (bypass) {
+		dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
+		set_dma_ops(&pdev->dev, &dma_direct_ops);
+		set_dma_offset(&pdev->dev, pe->tce_bypass_base);
+	} else {
+		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
+		set_dma_ops(&pdev->dev, &dma_iommu_ops);
+		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+	}
+	return 0;
+}
+
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 {
 	struct pci_dev *dev;
@@ -657,6 +688,56 @@
 		__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
 }
 
+static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
+{
+	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
+					      tce32_table);
+	uint16_t window_id = (pe->pe_number << 1 ) + 1;
+	int64_t rc;
+
+	pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis");
+	if (enable) {
+		phys_addr_t top = memblock_end_of_DRAM();
+
+		top = roundup_pow_of_two(top);
+		rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+						     pe->pe_number,
+						     window_id,
+						     pe->tce_bypass_base,
+						     top);
+	} else {
+		rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+						     pe->pe_number,
+						     window_id,
+						     pe->tce_bypass_base,
+						     0);
+
+		/*
+		 * We might want to reset the DMA ops of all devices on
+		 * this PE. However in theory, that shouldn't be necessary
+		 * as this is used for VFIO/KVM pass-through and the device
+		 * hasn't yet been returned to its kernel driver
+		 */
+	}
+	if (rc)
+		pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
+	else
+		pe->tce_bypass_enabled = enable;
+}
+
+static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
+					  struct pnv_ioda_pe *pe)
+{
+	/* TVE #1 is selected by PCI address bit 59 */
+	pe->tce_bypass_base = 1ull << 59;
+
+	/* Install set_bypass callback for VFIO */
+	pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
+
+	/* Enable bypass by default */
+	pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
+}
+
 static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 				       struct pnv_ioda_pe *pe)
 {
@@ -727,6 +808,8 @@
 	else
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
+	/* Also create a bypass window */
+	pnv_pci_ioda2_setup_bypass_pe(phb, pe);
 	return;
 fail:
 	if (pe->tce32_seg >= 0)
@@ -1286,6 +1369,7 @@
 
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
+	phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
 
 	/* Setup shutdown function for kexec */
 	phb->shutdown = pnv_pci_ioda_shutdown;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b555ebc..8518817 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -134,57 +134,72 @@
 	pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n",
 		hose->global_number, common->version);
 
-	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-	pr_info("  slotStatus:           %08x\n", data->slotStatus);
-	pr_info("  linkStatus:           %08x\n", data->linkStatus);
-	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-	pr_info("  sourceId:             %08x\n", data->sourceId);
-	pr_info("  errorClass:           %016llx\n", data->errorClass);
-	pr_info("  correlator:           %016llx\n", data->correlator);
-	pr_info("  p7iocPlssr:           %016llx\n", data->p7iocPlssr);
-	pr_info("  p7iocCsr:             %016llx\n", data->p7iocCsr);
-	pr_info("  lemFir:               %016llx\n", data->lemFir);
-	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+	if (data->brdgCtl)
+		pr_info("  brdgCtl:     %08x\n",
+			data->brdgCtl);
+	if (data->portStatusReg || data->rootCmplxStatus ||
+	    data->busAgentStatus)
+		pr_info("  UtlSts:      %08x %08x %08x\n",
+			data->portStatusReg, data->rootCmplxStatus,
+			data->busAgentStatus);
+	if (data->deviceStatus || data->slotStatus   ||
+	    data->linkStatus   || data->devCmdStatus ||
+	    data->devSecStatus)
+		pr_info("  RootSts:     %08x %08x %08x %08x %08x\n",
+			data->deviceStatus, data->slotStatus,
+			data->linkStatus, data->devCmdStatus,
+			data->devSecStatus);
+	if (data->rootErrorStatus   || data->uncorrErrorStatus ||
+	    data->corrErrorStatus)
+		pr_info("  RootErrSts:  %08x %08x %08x\n",
+			data->rootErrorStatus, data->uncorrErrorStatus,
+			data->corrErrorStatus);
+	if (data->tlpHdr1 || data->tlpHdr2 ||
+	    data->tlpHdr3 || data->tlpHdr4)
+		pr_info("  RootErrLog:  %08x %08x %08x %08x\n",
+			data->tlpHdr1, data->tlpHdr2,
+			data->tlpHdr3, data->tlpHdr4);
+	if (data->sourceId || data->errorClass ||
+	    data->correlator)
+		pr_info("  RootErrLog1: %08x %016llx %016llx\n",
+			data->sourceId, data->errorClass,
+			data->correlator);
+	if (data->p7iocPlssr || data->p7iocCsr)
+		pr_info("  PhbSts:      %016llx %016llx\n",
+			data->p7iocPlssr, data->p7iocCsr);
+	if (data->lemFir || data->lemErrorMask ||
+	    data->lemWOF)
+		pr_info("  Lem:         %016llx %016llx %016llx\n",
+			data->lemFir, data->lemErrorMask,
+			data->lemWOF);
+	if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+	    data->phbErrorLog0   || data->phbErrorLog1)
+		pr_info("  PhbErr:      %016llx %016llx %016llx %016llx\n",
+			data->phbErrorStatus, data->phbFirstErrorStatus,
+			data->phbErrorLog0, data->phbErrorLog1);
+	if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+	    data->mmioErrorLog0   || data->mmioErrorLog1)
+		pr_info("  OutErr:      %016llx %016llx %016llx %016llx\n",
+			data->mmioErrorStatus, data->mmioFirstErrorStatus,
+			data->mmioErrorLog0, data->mmioErrorLog1);
+	if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+	    data->dma0ErrorLog0   || data->dma0ErrorLog1)
+		pr_info("  InAErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+			data->dma0ErrorLog0, data->dma0ErrorLog1);
+	if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+	    data->dma1ErrorLog0   || data->dma1ErrorLog1)
+		pr_info("  InBErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+			data->dma1ErrorLog0, data->dma1ErrorLog1);
 
 	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
 		if ((data->pestA[i] >> 63) == 0 &&
 		    (data->pestB[i] >> 63) == 0)
 			continue;
 
-		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+		pr_info("  PE[%3d] A/B: %016llx %016llx\n",
+			i, data->pestA[i], data->pestB[i]);
 	}
 }
 
@@ -197,62 +212,77 @@
 	data = (struct OpalIoPhb3ErrorData*)common;
 	pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n",
 		hose->global_number, common->version);
-
-	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-	pr_info("  slotStatus:           %08x\n", data->slotStatus);
-	pr_info("  linkStatus:           %08x\n", data->linkStatus);
-	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-	pr_info("  sourceId:             %08x\n", data->sourceId);
-	pr_info("  errorClass:           %016llx\n", data->errorClass);
-	pr_info("  correlator:           %016llx\n", data->correlator);
-
-	pr_info("  nFir:                 %016llx\n", data->nFir);
-	pr_info("  nFirMask:             %016llx\n", data->nFirMask);
-	pr_info("  nFirWOF:              %016llx\n", data->nFirWOF);
-	pr_info("  PhbPlssr:             %016llx\n", data->phbPlssr);
-	pr_info("  PhbCsr:               %016llx\n", data->phbCsr);
-	pr_info("  lemFir:               %016llx\n", data->lemFir);
-	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+	if (data->brdgCtl)
+		pr_info("  brdgCtl:     %08x\n",
+			data->brdgCtl);
+	if (data->portStatusReg || data->rootCmplxStatus ||
+	    data->busAgentStatus)
+		pr_info("  UtlSts:      %08x %08x %08x\n",
+			data->portStatusReg, data->rootCmplxStatus,
+			data->busAgentStatus);
+	if (data->deviceStatus || data->slotStatus   ||
+	    data->linkStatus   || data->devCmdStatus ||
+	    data->devSecStatus)
+		pr_info("  RootSts:     %08x %08x %08x %08x %08x\n",
+			data->deviceStatus, data->slotStatus,
+			data->linkStatus, data->devCmdStatus,
+			data->devSecStatus);
+	if (data->rootErrorStatus || data->uncorrErrorStatus ||
+	    data->corrErrorStatus)
+		pr_info("  RootErrSts:  %08x %08x %08x\n",
+			data->rootErrorStatus, data->uncorrErrorStatus,
+			data->corrErrorStatus);
+	if (data->tlpHdr1 || data->tlpHdr2 ||
+	    data->tlpHdr3 || data->tlpHdr4)
+		pr_info("  RootErrLog:  %08x %08x %08x %08x\n",
+			data->tlpHdr1, data->tlpHdr2,
+			data->tlpHdr3, data->tlpHdr4);
+	if (data->sourceId || data->errorClass ||
+	    data->correlator)
+		pr_info("  RootErrLog1: %08x %016llx %016llx\n",
+			data->sourceId, data->errorClass,
+			data->correlator);
+	if (data->nFir || data->nFirMask ||
+	    data->nFirWOF)
+		pr_info("  nFir:        %016llx %016llx %016llx\n",
+			data->nFir, data->nFirMask,
+			data->nFirWOF);
+	if (data->phbPlssr || data->phbCsr)
+		pr_info("  PhbSts:      %016llx %016llx\n",
+			data->phbPlssr, data->phbCsr);
+	if (data->lemFir || data->lemErrorMask ||
+	    data->lemWOF)
+		pr_info("  Lem:         %016llx %016llx %016llx\n",
+			data->lemFir, data->lemErrorMask,
+			data->lemWOF);
+	if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+	    data->phbErrorLog0   || data->phbErrorLog1)
+		pr_info("  PhbErr:      %016llx %016llx %016llx %016llx\n",
+			data->phbErrorStatus, data->phbFirstErrorStatus,
+			data->phbErrorLog0, data->phbErrorLog1);
+	if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+	    data->mmioErrorLog0   || data->mmioErrorLog1)
+		pr_info("  OutErr:      %016llx %016llx %016llx %016llx\n",
+			data->mmioErrorStatus, data->mmioFirstErrorStatus,
+			data->mmioErrorLog0, data->mmioErrorLog1);
+	if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+	    data->dma0ErrorLog0   || data->dma0ErrorLog1)
+		pr_info("  InAErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+			data->dma0ErrorLog0, data->dma0ErrorLog1);
+	if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+	    data->dma1ErrorLog0   || data->dma1ErrorLog1)
+		pr_info("  InBErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+			data->dma1ErrorLog0, data->dma1ErrorLog1);
 
 	for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
 		if ((data->pestA[i] >> 63) == 0 &&
 		    (data->pestB[i] >> 63) == 0)
 			continue;
 
-		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+		pr_info("  PE[%3d] A/B: %016llx %016llx\n",
+			i, data->pestA[i], data->pestB[i]);
 	}
 }
 
@@ -634,6 +664,16 @@
 		pnv_pci_dma_fallback_setup(hose, pdev);
 }
 
+int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	if (phb && phb->dma_set_mask)
+		return phb->dma_set_mask(phb, pdev, dma_mask);
+	return __dma_set_mask(&pdev->dev, dma_mask);
+}
+
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 13f1942..cde1694 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -54,7 +54,9 @@
 	struct iommu_table	tce32_table;
 	phys_addr_t		tce_inval_reg_phys;
 
-	/* XXX TODO: Add support for additional 64-bit iommus */
+	/* 64-bit TCE bypass region */
+	bool			tce_bypass_enabled;
+	uint64_t		tce_bypass_base;
 
 	/* MSIs. MVE index is identical for for 32 and 64 bit MSI
 	 * and -1 if not supported. (It's actually identical to the
@@ -113,6 +115,8 @@
 			 unsigned int hwirq, unsigned int virq,
 			 unsigned int is_64, struct msi_msg *msg);
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
+	int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev,
+			    u64 dma_mask);
 	void (*fixup_phb)(struct pci_controller *hose);
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
 	void (*shutdown)(struct pnv_phb *phb);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index de6819b..0051e10 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -7,12 +7,20 @@
 static inline void pnv_smp_init(void) { }
 #endif
 
+struct pci_dev;
+
 #ifdef CONFIG_PCI
 extern void pnv_pci_init(void);
 extern void pnv_pci_shutdown(void);
+extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask);
 #else
 static inline void pnv_pci_init(void) { }
 static inline void pnv_pci_shutdown(void) { }
+
+static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+	return -ENODEV;
+}
 #endif
 
 extern void pnv_lpc_init(void);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 21166f6..81a7a0a 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -26,7 +26,7 @@
 #include <linux/of_fdt.h>
 #include <linux/interrupt.h>
 #include <linux/bug.h>
-#include <linux/cpuidle.h>
+#include <linux/pci.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
@@ -141,6 +141,13 @@
 {
 }
 
+static int pnv_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (dev_is_pci(dev))
+		return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask);
+	return __dma_set_mask(dev, dma_mask);
+}
+
 static void pnv_shutdown(void)
 {
 	/* Let the PCI code clear up IODA tables */
@@ -217,16 +224,6 @@
 	return 1;
 }
 
-void powernv_idle(void)
-{
-	/* Hook to cpuidle framework if available, else
-	 * call on default platform idle code
-	 */
-	if (cpuidle_idle_call()) {
-		power7_idle();
-	}
-}
-
 define_machine(powernv) {
 	.name			= "PowerNV",
 	.probe			= pnv_probe,
@@ -236,8 +233,9 @@
 	.show_cpuinfo		= pnv_show_cpuinfo,
 	.progress		= pnv_progress,
 	.machine_shutdown	= pnv_shutdown,
-	.power_save             = powernv_idle,
+	.power_save             = power7_idle,
 	.calibrate_decr		= generic_calibrate_decr,
+	.dma_set_mask		= pnv_dma_set_mask,
 #ifdef CONFIG_KEXEC
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
 #endif
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 37300f6..80b1d57 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -20,6 +20,7 @@
 	select PPC_DOORBELL
 	select HAVE_CONTEXT_TRACKING
 	select HOTPLUG_CPU if SMP
+	select ARCH_RANDOM
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 9ef3cc8..8a8f047 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -265,7 +265,7 @@
 			enable = 1;
 
 		if (enable) {
-			eeh_subsystem_enabled = 1;
+			eeh_set_enable(true);
 			eeh_add_to_parent_pe(edev);
 
 			pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n",
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 82789e7..0ea99e3 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -35,12 +35,7 @@
 #include "offline_states.h"
 
 /* This version can't take the spinlock, because it never returns */
-static struct rtas_args rtas_stop_self_args = {
-	.token = RTAS_UNKNOWN_SERVICE,
-	.nargs = 0,
-	.nret = 1,
-	.rets = &rtas_stop_self_args.args[0],
-};
+static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE;
 
 static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
 							CPU_STATE_OFFLINE;
@@ -93,15 +88,20 @@
 
 static void rtas_stop_self(void)
 {
-	struct rtas_args *args = &rtas_stop_self_args;
+	struct rtas_args args = {
+		.token = cpu_to_be32(rtas_stop_self_token),
+		.nargs = 0,
+		.nret = 1,
+		.rets = &args.args[0],
+	};
 
 	local_irq_disable();
 
-	BUG_ON(args->token == RTAS_UNKNOWN_SERVICE);
+	BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
 
 	printk("cpu %u (hwid %u) Ready to die...\n",
 	       smp_processor_id(), hard_smp_processor_id());
-	enter_rtas(__pa(args));
+	enter_rtas(__pa(&args));
 
 	panic("Alas, I survived.\n");
 }
@@ -392,10 +392,10 @@
 		}
 	}
 
-	rtas_stop_self_args.token = rtas_token("stop-self");
+	rtas_stop_self_token = rtas_token("stop-self");
 	qcss_tok = rtas_token("query-cpu-stopped-state");
 
-	if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE ||
+	if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE ||
 			qcss_tok == RTAS_UNKNOWN_SERVICE) {
 		printk(KERN_INFO "CPU Hotplug not supported by firmware "
 				"- disabling.\n");
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 70670a2..c413ec1 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -113,7 +113,8 @@
 {
 	struct device_node *dn, *pdn;
 	struct pci_bus *bus;
-	const __be32 *pcie_link_speed_stats;
+	u32 pcie_link_speed_stats[2];
+	int rc;
 
 	bus = bridge->bus;
 
@@ -122,38 +123,45 @@
 		return 0;
 
 	for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) {
-		pcie_link_speed_stats = of_get_property(pdn,
-			"ibm,pcie-link-speed-stats", NULL);
-		if (pcie_link_speed_stats)
+		rc = of_property_read_u32_array(pdn,
+				"ibm,pcie-link-speed-stats",
+				&pcie_link_speed_stats[0], 2);
+		if (!rc)
 			break;
 	}
 
 	of_node_put(pdn);
 
-	if (!pcie_link_speed_stats) {
+	if (rc) {
 		pr_err("no ibm,pcie-link-speed-stats property\n");
 		return 0;
 	}
 
-	switch (be32_to_cpup(pcie_link_speed_stats)) {
+	switch (pcie_link_speed_stats[0]) {
 	case 0x01:
 		bus->max_bus_speed = PCIE_SPEED_2_5GT;
 		break;
 	case 0x02:
 		bus->max_bus_speed = PCIE_SPEED_5_0GT;
 		break;
+	case 0x04:
+		bus->max_bus_speed = PCIE_SPEED_8_0GT;
+		break;
 	default:
 		bus->max_bus_speed = PCI_SPEED_UNKNOWN;
 		break;
 	}
 
-	switch (be32_to_cpup(pcie_link_speed_stats)) {
+	switch (pcie_link_speed_stats[1]) {
 	case 0x01:
 		bus->cur_bus_speed = PCIE_SPEED_2_5GT;
 		break;
 	case 0x02:
 		bus->cur_bus_speed = PCIE_SPEED_5_0GT;
 		break;
+	case 0x04:
+		bus->cur_bus_speed = PCIE_SPEED_8_0GT;
+		break;
 	default:
 		bus->cur_bus_speed = PCI_SPEED_UNKNOWN;
 		break;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 8e639d7..2db8cc6 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -39,7 +39,6 @@
 #include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
-#include <linux/cpuidle.h>
 #include <linux/of.h>
 #include <linux/kexec.h>
 
@@ -356,29 +355,24 @@
 
 static void pseries_lpar_idle(void)
 {
-	/* This would call on the cpuidle framework, and the back-end pseries
-	 * driver to  go to idle states
+	/*
+	 * Default handler to go into low thread priority and possibly
+	 * low power mode by cedeing processor to hypervisor
 	 */
-	if (cpuidle_idle_call()) {
-		/* On error, execute default handler
-		 * to go into low thread priority and possibly
-		 * low power mode by cedeing processor to hypervisor
-		 */
 
-		/* Indicate to hypervisor that we are idle. */
-		get_lppaca()->idle = 1;
+	/* Indicate to hypervisor that we are idle. */
+	get_lppaca()->idle = 1;
 
-		/*
-		 * Yield the processor to the hypervisor.  We return if
-		 * an external interrupt occurs (which are driven prior
-		 * to returning here) or if a prod occurs from another
-		 * processor. When returning here, external interrupts
-		 * are enabled.
-		 */
-		cede_processor();
+	/*
+	 * Yield the processor to the hypervisor.  We return if
+	 * an external interrupt occurs (which are driven prior
+	 * to returning here) or if a prod occurs from another
+	 * processor. When returning here, external interrupts
+	 * are enabled.
+	 */
+	cede_processor();
 
-		get_lppaca()->idle = 0;
-	}
+	get_lppaca()->idle = 0;
 }
 
 /*
@@ -430,8 +424,7 @@
 {
 	long rc;
 
-	if (firmware_has_feature(FW_FEATURE_SET_MODE) &&
-	    (image->type != KEXEC_TYPE_CRASH)) {
+	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
 		rc = pSeries_disable_reloc_on_exc();
 		if (rc != H_SUCCESS)
 			pr_warning("Warning: Failed to disable relocation on "
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 0e166ed..8209744 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -886,25 +886,25 @@
 
 	/* Default: read HW settings */
 	if (flow_type == IRQ_TYPE_DEFAULT) {
-		switch(vold & (MPIC_INFO(VECPRI_POLARITY_MASK) |
-			       MPIC_INFO(VECPRI_SENSE_MASK))) {
-			case MPIC_INFO(VECPRI_SENSE_EDGE) |
-			     MPIC_INFO(VECPRI_POLARITY_POSITIVE):
-				flow_type = IRQ_TYPE_EDGE_RISING;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_EDGE) |
-			     MPIC_INFO(VECPRI_POLARITY_NEGATIVE):
-				flow_type = IRQ_TYPE_EDGE_FALLING;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_LEVEL) |
-			     MPIC_INFO(VECPRI_POLARITY_POSITIVE):
-				flow_type = IRQ_TYPE_LEVEL_HIGH;
-				break;
-			case MPIC_INFO(VECPRI_SENSE_LEVEL) |
-			     MPIC_INFO(VECPRI_POLARITY_NEGATIVE):
-				flow_type = IRQ_TYPE_LEVEL_LOW;
-				break;
-		}
+		int vold_ps;
+
+		vold_ps = vold & (MPIC_INFO(VECPRI_POLARITY_MASK) |
+				  MPIC_INFO(VECPRI_SENSE_MASK));
+
+		if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) |
+				MPIC_INFO(VECPRI_POLARITY_POSITIVE)))
+			flow_type = IRQ_TYPE_EDGE_RISING;
+		else if	(vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) |
+				     MPIC_INFO(VECPRI_POLARITY_NEGATIVE)))
+			flow_type = IRQ_TYPE_EDGE_FALLING;
+		else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) |
+				     MPIC_INFO(VECPRI_POLARITY_POSITIVE)))
+			flow_type = IRQ_TYPE_LEVEL_HIGH;
+		else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) |
+				     MPIC_INFO(VECPRI_POLARITY_NEGATIVE)))
+			flow_type = IRQ_TYPE_LEVEL_LOW;
+		else
+			WARN_ONCE(1, "mpic: unknown IRQ type %d\n", vold);
 	}
 
 	/* Apply to irq desc */
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index a90731b..b079098 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -309,16 +309,23 @@
 
 	if (xmon_speaker == me)
 		return;
+
 	for (;;) {
-		if (xmon_speaker == 0) {
-			last_speaker = cmpxchg(&xmon_speaker, 0, me);
-			if (last_speaker == 0)
-				return;
-		}
-		timeout = 10000000;
+		last_speaker = cmpxchg(&xmon_speaker, 0, me);
+		if (last_speaker == 0)
+			return;
+
+		/*
+		 * Wait a full second for the lock, we might be on a slow
+		 * console, but check every 100us.
+		 */
+		timeout = 10000;
 		while (xmon_speaker == last_speaker) {
-			if (--timeout > 0)
+			if (--timeout > 0) {
+				udelay(100);
 				continue;
+			}
+
 			/* hostile takeover */
 			prev = cmpxchg(&xmon_speaker, last_speaker, me);
 			if (prev == last_speaker)
@@ -397,7 +404,6 @@
 	}
 
 	xmon_fault_jmp[cpu] = recurse_jmp;
-	cpumask_set_cpu(cpu, &cpus_in_xmon);
 
 	bp = NULL;
 	if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT))
@@ -419,6 +425,8 @@
 		release_output_lock();
 	}
 
+	cpumask_set_cpu(cpu, &cpus_in_xmon);
+
  waiting:
 	secondary = 1;
 	while (secondary && !xmon_gate) {
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index bb74b21..953f17c 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -141,6 +141,7 @@
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
 	select SYSCTL_EXCEPTION_TRACE
+	select TTY
 	select VIRT_CPU_ACCOUNTING
 	select VIRT_TO_BUS
 
@@ -416,6 +417,10 @@
 config ARCH_ENABLE_MEMORY_HOTREMOVE
 	def_bool y
 
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+	def_bool y
+	depends on 64BIT
+
 config FORCE_MAX_ZONEORDER
 	int
 	default "9"
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 4c4a1ce..47c8630 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -529,6 +529,7 @@
 {
 	int rc;
 
+	init_virt_timer(&appldata_timer);
 	appldata_timer.function = appldata_timer_function;
 	appldata_timer.data = (unsigned long) &appldata_work;
 
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index de8e2b3..69b23b2 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -171,7 +171,7 @@
 	int rc, max_size;
 
 	max_size = sizeof(struct appldata_os_data) +
-		   (NR_CPUS * sizeof(struct appldata_os_per_cpu));
+		   (num_possible_cpus() * sizeof(struct appldata_os_per_cpu));
 	if (max_size > APPLDATA_MAX_REC_SIZE) {
 		pr_err("Maximum OS record size %i exceeds the maximum "
 		       "record size %i\n", max_size, APPLDATA_MAX_REC_SIZE);
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index e0af2ee..ddaae2f 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -46,6 +46,7 @@
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_MARCH_Z9_109=y
+CONFIG_NR_CPUS=256
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
@@ -58,7 +59,6 @@
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
 CONFIG_CRASH_DUMP=y
-CONFIG_ZFCPDUMP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
@@ -101,7 +101,6 @@
 CONFIG_TCP_CONG_YEAH=m
 CONFIG_TCP_CONG_ILLINOIS=m
 CONFIG_IPV6=y
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
@@ -111,6 +110,7 @@
 CONFIG_INET6_XFRM_MODE_TUNNEL=m
 CONFIG_INET6_XFRM_MODE_BEET=m
 CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_SIT=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
@@ -135,7 +135,17 @@
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
-CONFIG_NETFILTER_TPROXY=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_AUDIT=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -204,7 +214,9 @@
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
@@ -227,6 +239,11 @@
 CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -249,6 +266,9 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -268,6 +288,7 @@
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_NET_SCTPPROBE=m
 CONFIG_RDS=m
 CONFIG_RDS_RDMA=m
@@ -314,6 +335,7 @@
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_FLOW=m
 CONFIG_NET_CLS_CGROUP=y
+CONFIG_NET_CLS_BPF=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
@@ -381,8 +403,8 @@
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
-CONFIG_DM_RAID=m
 CONFIG_DM_LOG_USERSPACE=m
+CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
@@ -434,7 +456,6 @@
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
-CONFIG_ZVM_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
@@ -534,13 +555,23 @@
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_SELFTEST=y
+CONFIG_DEBUG_OBJECTS_FREE=y
+CONFIG_DEBUG_OBJECTS_TIMERS=y
+CONFIG_DEBUG_OBJECTS_WORK=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
 CONFIG_SLUB_DEBUG_ON=y
 CONFIG_SLUB_STATS=y
+CONFIG_DEBUG_KMEMLEAK=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_VM=y
 CONFIG_DEBUG_VM_RB=y
 CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
 CONFIG_DEBUG_PER_CPU_MAPS=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_DETECT_HUNG_TASK=y
 CONFIG_TIMER_STATS=y
 CONFIG_DEBUG_RT_MUTEXES=y
 CONFIG_RT_MUTEX_TESTER=y
@@ -573,9 +604,11 @@
 CONFIG_BLK_DEV_IO_TRACE=y
 # CONFIG_KPROBE_EVENT is not set
 CONFIG_LKDTM=m
+CONFIG_TEST_LIST_SORT=y
 CONFIG_KPROBES_SANITY_TEST=y
-CONFIG_RBTREE_TEST=m
+CONFIG_RBTREE_TEST=y
 CONFIG_INTERVAL_TREE_TEST=m
+CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_DMA_API_DEBUG=y
 # CONFIG_STRICT_DEVMEM is not set
@@ -638,7 +671,6 @@
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_ASYMMETRIC_KEY_TYPE=m
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
-CONFIG_PUBLIC_KEY_ALGO_RSA=m
 CONFIG_X509_CERTIFICATE_PARSER=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index b9f6b4c..c81a74e 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -46,6 +46,7 @@
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_MARCH_Z9_109=y
+CONFIG_NR_CPUS=256
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
@@ -56,7 +57,6 @@
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
 CONFIG_CRASH_DUMP=y
-CONFIG_ZFCPDUMP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
@@ -99,7 +99,6 @@
 CONFIG_TCP_CONG_YEAH=m
 CONFIG_TCP_CONG_ILLINOIS=m
 CONFIG_IPV6=y
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
@@ -109,6 +108,7 @@
 CONFIG_INET6_XFRM_MODE_TUNNEL=m
 CONFIG_INET6_XFRM_MODE_BEET=m
 CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_SIT=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
@@ -133,7 +133,17 @@
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
-CONFIG_NETFILTER_TPROXY=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_AUDIT=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -202,7 +212,9 @@
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
@@ -225,6 +237,11 @@
 CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -247,6 +264,9 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -266,6 +286,7 @@
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_NET_SCTPPROBE=m
 CONFIG_RDS=m
 CONFIG_RDS_RDMA=m
@@ -311,6 +332,7 @@
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_FLOW=m
 CONFIG_NET_CLS_CGROUP=y
+CONFIG_NET_CLS_BPF=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
@@ -378,8 +400,8 @@
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
-CONFIG_DM_RAID=m
 CONFIG_DM_LOG_USERSPACE=m
+CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
@@ -431,7 +453,6 @@
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
-CONFIG_ZVM_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
@@ -540,6 +561,7 @@
 CONFIG_LKDTM=m
 CONFIG_RBTREE_TEST=m
 CONFIG_INTERVAL_TREE_TEST=m
+CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 # CONFIG_STRICT_DEVMEM is not set
 CONFIG_S390_PTDUMP=y
@@ -601,7 +623,6 @@
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_ASYMMETRIC_KEY_TYPE=m
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
-CONFIG_PUBLIC_KEY_ALGO_RSA=m
 CONFIG_X509_CERTIFICATE_PARSER=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 91087b4..b5ba8fe 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -44,6 +44,7 @@
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_MARCH_Z9_109=y
+CONFIG_NR_CPUS=256
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
@@ -54,7 +55,6 @@
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
 CONFIG_CRASH_DUMP=y
-CONFIG_ZFCPDUMP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
@@ -97,7 +97,6 @@
 CONFIG_TCP_CONG_YEAH=m
 CONFIG_TCP_CONG_ILLINOIS=m
 CONFIG_IPV6=y
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
@@ -107,6 +106,7 @@
 CONFIG_INET6_XFRM_MODE_TUNNEL=m
 CONFIG_INET6_XFRM_MODE_BEET=m
 CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_SIT=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
@@ -131,7 +131,17 @@
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
-CONFIG_NETFILTER_TPROXY=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_AUDIT=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -200,7 +210,9 @@
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
@@ -223,6 +235,11 @@
 CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -245,6 +262,9 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -264,6 +284,7 @@
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_NET_SCTPPROBE=m
 CONFIG_RDS=m
 CONFIG_RDS_RDMA=m
@@ -309,6 +330,7 @@
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_FLOW=m
 CONFIG_NET_CLS_CGROUP=y
+CONFIG_NET_CLS_BPF=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
@@ -376,8 +398,8 @@
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
-CONFIG_DM_RAID=m
 CONFIG_DM_LOG_USERSPACE=m
+CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
@@ -429,7 +451,6 @@
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
-CONFIG_ZVM_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
@@ -532,6 +553,7 @@
 CONFIG_BLK_DEV_IO_TRACE=y
 # CONFIG_KPROBE_EVENT is not set
 CONFIG_LKDTM=m
+CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 # CONFIG_STRICT_DEVMEM is not set
 CONFIG_S390_PTDUMP=y
@@ -593,7 +615,6 @@
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_ASYMMETRIC_KEY_TYPE=m
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
-CONFIG_PUBLIC_KEY_ALGO_RSA=m
 CONFIG_X509_CERTIFICATE_PARSER=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index d725c4d..cef073c 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -19,7 +19,6 @@
 # CONFIG_CHSC_SCH is not set
 # CONFIG_SCM_BUS is not set
 CONFIG_CRASH_DUMP=y
-CONFIG_ZFCPDUMP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_SECCOMP is not set
 # CONFIG_IUCV is not set
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index b3feabd..cf3c008 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/spinlock.h>
 #include "crypt_s390.h"
 
 #define AES_KEYLEN_128		1
@@ -32,6 +33,7 @@
 #define AES_KEYLEN_256		4
 
 static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
 static char keylen_flag;
 
 struct s390_aes_ctx {
@@ -758,43 +760,67 @@
 	return aes_set_key(tfm, in_key, key_len);
 }
 
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+	unsigned int i, n;
+
+	/* only use complete blocks, max. PAGE_SIZE */
+	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1);
+	for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
+		memcpy(ctrptr + i, ctrptr + i - AES_BLOCK_SIZE,
+		       AES_BLOCK_SIZE);
+		crypto_inc(ctrptr + i, AES_BLOCK_SIZE);
+	}
+	return n;
+}
+
 static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 			 struct s390_aes_ctx *sctx, struct blkcipher_walk *walk)
 {
 	int ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE);
-	unsigned int i, n, nbytes;
-	u8 buf[AES_BLOCK_SIZE];
-	u8 *out, *in;
+	unsigned int n, nbytes;
+	u8 buf[AES_BLOCK_SIZE], ctrbuf[AES_BLOCK_SIZE];
+	u8 *out, *in, *ctrptr = ctrbuf;
 
 	if (!walk->nbytes)
 		return ret;
 
-	memcpy(ctrblk, walk->iv, AES_BLOCK_SIZE);
+	if (spin_trylock(&ctrblk_lock))
+		ctrptr = ctrblk;
+
+	memcpy(ctrptr, walk->iv, AES_BLOCK_SIZE);
 	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		while (nbytes >= AES_BLOCK_SIZE) {
-			/* only use complete blocks, max. PAGE_SIZE */
-			n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
-						 nbytes & ~(AES_BLOCK_SIZE - 1);
-			for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
-				memcpy(ctrblk + i, ctrblk + i - AES_BLOCK_SIZE,
-				       AES_BLOCK_SIZE);
-				crypto_inc(ctrblk + i, AES_BLOCK_SIZE);
-			}
-			ret = crypt_s390_kmctr(func, sctx->key, out, in, n, ctrblk);
-			if (ret < 0 || ret != n)
+			if (ctrptr == ctrblk)
+				n = __ctrblk_init(ctrptr, nbytes);
+			else
+				n = AES_BLOCK_SIZE;
+			ret = crypt_s390_kmctr(func, sctx->key, out, in,
+					       n, ctrptr);
+			if (ret < 0 || ret != n) {
+				if (ctrptr == ctrblk)
+					spin_unlock(&ctrblk_lock);
 				return -EIO;
+			}
 			if (n > AES_BLOCK_SIZE)
-				memcpy(ctrblk, ctrblk + n - AES_BLOCK_SIZE,
+				memcpy(ctrptr, ctrptr + n - AES_BLOCK_SIZE,
 				       AES_BLOCK_SIZE);
-			crypto_inc(ctrblk, AES_BLOCK_SIZE);
+			crypto_inc(ctrptr, AES_BLOCK_SIZE);
 			out += n;
 			in += n;
 			nbytes -= n;
 		}
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	}
+	if (ctrptr == ctrblk) {
+		if (nbytes)
+			memcpy(ctrbuf, ctrptr, AES_BLOCK_SIZE);
+		else
+			memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
+		spin_unlock(&ctrblk_lock);
+	}
 	/*
 	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
 	 */
@@ -802,14 +828,15 @@
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		ret = crypt_s390_kmctr(func, sctx->key, buf, in,
-				       AES_BLOCK_SIZE, ctrblk);
+				       AES_BLOCK_SIZE, ctrbuf);
 		if (ret < 0 || ret != AES_BLOCK_SIZE)
 			return -EIO;
 		memcpy(out, buf, nbytes);
-		crypto_inc(ctrblk, AES_BLOCK_SIZE);
+		crypto_inc(ctrbuf, AES_BLOCK_SIZE);
 		ret = blkcipher_walk_done(desc, walk, 0);
+		memcpy(walk->iv, ctrbuf, AES_BLOCK_SIZE);
 	}
-	memcpy(walk->iv, ctrblk, AES_BLOCK_SIZE);
+
 	return ret;
 }
 
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 200f2a1..0a5aac8 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -25,6 +25,7 @@
 #define DES3_KEY_SIZE	(3 * DES_KEY_SIZE)
 
 static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
 
 struct s390_des_ctx {
 	u8 iv[DES_BLOCK_SIZE];
@@ -105,29 +106,35 @@
 }
 
 static int cbc_desall_crypt(struct blkcipher_desc *desc, long func,
-			    u8 *iv, struct blkcipher_walk *walk)
+			    struct blkcipher_walk *walk)
 {
+	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	int ret = blkcipher_walk_virt(desc, walk);
 	unsigned int nbytes = walk->nbytes;
+	struct {
+		u8 iv[DES_BLOCK_SIZE];
+		u8 key[DES3_KEY_SIZE];
+	} param;
 
 	if (!nbytes)
 		goto out;
 
-	memcpy(iv, walk->iv, DES_BLOCK_SIZE);
+	memcpy(param.iv, walk->iv, DES_BLOCK_SIZE);
+	memcpy(param.key, ctx->key, DES3_KEY_SIZE);
 	do {
 		/* only use complete blocks */
 		unsigned int n = nbytes & ~(DES_BLOCK_SIZE - 1);
 		u8 *out = walk->dst.virt.addr;
 		u8 *in = walk->src.virt.addr;
 
-		ret = crypt_s390_kmc(func, iv, out, in, n);
+		ret = crypt_s390_kmc(func, &param, out, in, n);
 		if (ret < 0 || ret != n)
 			return -EIO;
 
 		nbytes &= DES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	} while ((nbytes = walk->nbytes));
-	memcpy(walk->iv, iv, DES_BLOCK_SIZE);
+	memcpy(walk->iv, param.iv, DES_BLOCK_SIZE);
 
 out:
 	return ret;
@@ -179,22 +186,20 @@
 			   struct scatterlist *dst, struct scatterlist *src,
 			   unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, &walk);
 }
 
 static int cbc_des_decrypt(struct blkcipher_desc *desc,
 			   struct scatterlist *dst, struct scatterlist *src,
 			   unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, &walk);
 }
 
 static struct crypto_alg cbc_des_alg = {
@@ -327,22 +332,20 @@
 			    struct scatterlist *dst, struct scatterlist *src,
 			    unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, &walk);
 }
 
 static int cbc_des3_decrypt(struct blkcipher_desc *desc,
 			    struct scatterlist *dst, struct scatterlist *src,
 			    unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, &walk);
 }
 
 static struct crypto_alg cbc_des3_alg = {
@@ -366,54 +369,80 @@
 	}
 };
 
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+	unsigned int i, n;
+
+	/* align to block size, max. PAGE_SIZE */
+	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(DES_BLOCK_SIZE - 1);
+	for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
+		memcpy(ctrptr + i, ctrptr + i - DES_BLOCK_SIZE, DES_BLOCK_SIZE);
+		crypto_inc(ctrptr + i, DES_BLOCK_SIZE);
+	}
+	return n;
+}
+
 static int ctr_desall_crypt(struct blkcipher_desc *desc, long func,
-			    struct s390_des_ctx *ctx, struct blkcipher_walk *walk)
+			    struct s390_des_ctx *ctx,
+			    struct blkcipher_walk *walk)
 {
 	int ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE);
-	unsigned int i, n, nbytes;
-	u8 buf[DES_BLOCK_SIZE];
-	u8 *out, *in;
+	unsigned int n, nbytes;
+	u8 buf[DES_BLOCK_SIZE], ctrbuf[DES_BLOCK_SIZE];
+	u8 *out, *in, *ctrptr = ctrbuf;
 
-	memcpy(ctrblk, walk->iv, DES_BLOCK_SIZE);
+	if (!walk->nbytes)
+		return ret;
+
+	if (spin_trylock(&ctrblk_lock))
+		ctrptr = ctrblk;
+
+	memcpy(ctrptr, walk->iv, DES_BLOCK_SIZE);
 	while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		while (nbytes >= DES_BLOCK_SIZE) {
-			/* align to block size, max. PAGE_SIZE */
-			n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
-				nbytes & ~(DES_BLOCK_SIZE - 1);
-			for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
-				memcpy(ctrblk + i, ctrblk + i - DES_BLOCK_SIZE,
-				       DES_BLOCK_SIZE);
-				crypto_inc(ctrblk + i, DES_BLOCK_SIZE);
-			}
-			ret = crypt_s390_kmctr(func, ctx->key, out, in, n, ctrblk);
-			if (ret < 0 || ret != n)
+			if (ctrptr == ctrblk)
+				n = __ctrblk_init(ctrptr, nbytes);
+			else
+				n = DES_BLOCK_SIZE;
+			ret = crypt_s390_kmctr(func, ctx->key, out, in,
+					       n, ctrptr);
+			if (ret < 0 || ret != n) {
+				if (ctrptr == ctrblk)
+					spin_unlock(&ctrblk_lock);
 				return -EIO;
+			}
 			if (n > DES_BLOCK_SIZE)
-				memcpy(ctrblk, ctrblk + n - DES_BLOCK_SIZE,
+				memcpy(ctrptr, ctrptr + n - DES_BLOCK_SIZE,
 				       DES_BLOCK_SIZE);
-			crypto_inc(ctrblk, DES_BLOCK_SIZE);
+			crypto_inc(ctrptr, DES_BLOCK_SIZE);
 			out += n;
 			in += n;
 			nbytes -= n;
 		}
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	}
-
+	if (ctrptr == ctrblk) {
+		if (nbytes)
+			memcpy(ctrbuf, ctrptr, DES_BLOCK_SIZE);
+		else
+			memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
+		spin_unlock(&ctrblk_lock);
+	}
 	/* final block may be < DES_BLOCK_SIZE, copy only nbytes */
 	if (nbytes) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		ret = crypt_s390_kmctr(func, ctx->key, buf, in,
-				       DES_BLOCK_SIZE, ctrblk);
+				       DES_BLOCK_SIZE, ctrbuf);
 		if (ret < 0 || ret != DES_BLOCK_SIZE)
 			return -EIO;
 		memcpy(out, buf, nbytes);
-		crypto_inc(ctrblk, DES_BLOCK_SIZE);
+		crypto_inc(ctrbuf, DES_BLOCK_SIZE);
 		ret = blkcipher_walk_done(desc, walk, 0);
+		memcpy(walk->iv, ctrbuf, DES_BLOCK_SIZE);
 	}
-	memcpy(walk->iv, ctrblk, DES_BLOCK_SIZE);
 	return ret;
 }
 
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 33f5751..4557cb7 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -40,6 +40,7 @@
 CONFIG_IBM_PARTITION=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_MARCH_Z196=y
+CONFIG_NR_CPUS=256
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
@@ -122,22 +123,31 @@
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_DETECT_HUNG_TASK=y
 CONFIG_TIMER_STATS=y
+CONFIG_DEBUG_RT_MUTEXES=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_LIST=y
+CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_RCU_TRACE=y
 CONFIG_LATENCYTOP=y
+CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_KPROBES_SANITY_TEST=y
 # CONFIG_STRICT_DEVMEM is not set
+CONFIG_S390_PTDUMP=y
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_AUTHENC=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index 24908ce..32040ac 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -32,7 +32,7 @@
 	__u32 pcpus;
 	__u32 lcpus;
 	__u32 vcpus;
-	__u32 cpu_min;
+	__u32 ocpus;
 	__u32 cpu_max;
 	__u32 cpu_shares;
 	__u32 cpu_use_samp;
@@ -142,7 +142,12 @@
 	ATTRIBUTE(cpus_dir, "capped", capped_value);
 	ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag);
 	ATTRIBUTE(cpus_dir, "count", data->vcpus);
-	ATTRIBUTE(cpus_dir, "weight_min", data->cpu_min);
+	/*
+	 * Note: The "weight_min" attribute got the wrong name.
+	 * The value represents the number of non-stopped (operating)
+	 * CPUS.
+	 */
+	ATTRIBUTE(cpus_dir, "weight_min", data->ocpus);
 	ATTRIBUTE(cpus_dir, "weight_max", data->cpu_max);
 	ATTRIBUTE(cpus_dir, "weight_cur", data->cpu_shares);
 
diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index 4bbb595..bd93ff6 100644
--- a/arch/s390/include/asm/airq.h
+++ b/arch/s390/include/asm/airq.h
@@ -44,11 +44,21 @@
 
 struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
 void airq_iv_release(struct airq_iv *iv);
-unsigned long airq_iv_alloc_bit(struct airq_iv *iv);
-void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit);
+unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num);
+void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num);
 unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start,
 			   unsigned long end);
 
+static inline unsigned long airq_iv_alloc_bit(struct airq_iv *iv)
+{
+	return airq_iv_alloc(iv, 1);
+}
+
+static inline void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit)
+{
+	airq_iv_free(iv, bit, 1);
+}
+
 static inline unsigned long airq_iv_end(struct airq_iv *iv)
 {
 	return iv->end;
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 6e6ad06..ec5ef89 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -13,9 +13,9 @@
  *
  * The bitop functions are defined to work on unsigned longs, so for an
  * s390x system the bits end up numbered:
- *   |63..............0|127............64|191...........128|255...........196|
+ *   |63..............0|127............64|191...........128|255...........192|
  * and on s390:
- *   |31.....0|63....31|95....64|127...96|159..128|191..160|223..192|255..224|
+ *   |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224|
  *
  * There are a few little-endian macros used mostly for filesystem
  * bitmaps, these work on similar bit arrays layouts, but
@@ -30,7 +30,7 @@
  * on an s390x system the bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
  * and on s390:
- *   |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ *   |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
  *
  * The main difference is that bit 0-63 (64b) or 0-31 (32b) in the bit
  * number field needs to be reversed compared to the LSB0 encoded bit
@@ -304,7 +304,7 @@
  * On an s390x system the bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
  * and on s390:
- *   |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ *   |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
  */
 unsigned long find_first_bit_inv(const unsigned long *addr, unsigned long size);
 unsigned long find_next_bit_inv(const unsigned long *addr, unsigned long size,
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index f201af8..a9c2c06 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -219,7 +219,9 @@
 #define to_ccwdev(n) container_of(n, struct ccw_device, dev)
 #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver)
 
-extern struct ccw_device *ccw_device_probe_console(void);
+extern struct ccw_device *ccw_device_create_console(struct ccw_driver *);
+extern void ccw_device_destroy_console(struct ccw_device *);
+extern int ccw_device_enable_console(struct ccw_device *);
 extern void ccw_device_wait_idle(struct ccw_device *);
 extern int ccw_device_force_console(struct ccw_device *);
 
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index 4f57a4f..7403648 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -44,22 +44,15 @@
  * here even more important to align src and dst on a 32-bit (or even
  * better 64-bit) boundary
  *
- * Copy from userspace and compute checksum.  If we catch an exception
- * then zero the rest of the buffer.
+ * Copy from userspace and compute checksum.
  */
 static inline __wsum
 csum_partial_copy_from_user(const void __user *src, void *dst,
                                           int len, __wsum sum,
                                           int *err_ptr)
 {
-	int missing;
-
-	missing = copy_from_user(dst, src, len);
-	if (missing) {
-		memset(dst + len - missing, 0, missing);
+	if (unlikely(copy_from_user(dst, src, len)))
 		*err_ptr = -EFAULT;
-	}
-		
 	return csum_partial(dst, len, sum);
 }
 
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 5d7e8cf..d350ed9 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -8,7 +8,11 @@
 #include <linux/thread_info.h>
 
 #define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p(typeof(0?(t)0:0ULL), u64))
-#define __SC_DELOUSE(t,v) (t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v))
+
+#define __SC_DELOUSE(t,v) ({ \
+	BUILD_BUG_ON(sizeof(t) > 4 && !__TYPE_IS_PTR(t)); \
+	(t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v)); \
+})
 
 #define PSW32_MASK_PER		0x40000000UL
 #define PSW32_MASK_DAT		0x04000000UL
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 51bcaa0..fda46bd 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -5,7 +5,10 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
-static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval);
+int __futex_atomic_op_inuser(int op, u32 __user *uaddr, int oparg, int *old);
+
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -17,7 +20,7 @@
 		oparg = 1 << oparg;
 
 	pagefault_disable();
-	ret = uaccess.futex_atomic_op(op, uaddr, oparg, &oldval);
+	ret = __futex_atomic_op_inuser(op, uaddr, oparg, &oldval);
 	pagefault_enable();
 
 	if (!ret) {
@@ -34,10 +37,4 @@
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
-						u32 oldval, u32 newval)
-{
-	return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval);
-}
-
 #endif /* _ASM_S390_FUTEX_H */
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index eef3dd3..9bf95bb 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -106,7 +106,9 @@
 	__u64	gbea;			/* 0x0180 */
 	__u8	reserved188[24];	/* 0x0188 */
 	__u32	fac;			/* 0x01a0 */
-	__u8	reserved1a4[68];	/* 0x01a4 */
+	__u8	reserved1a4[20];	/* 0x01a4 */
+	__u64	cbrlo;			/* 0x01b8 */
+	__u8	reserved1c0[40];	/* 0x01c0 */
 	__u64	itdba;			/* 0x01e8 */
 	__u8	reserved1f0[16];	/* 0x01f0 */
 } __attribute__((packed));
@@ -155,6 +157,7 @@
 	u32 instruction_stsi;
 	u32 instruction_stfl;
 	u32 instruction_tprot;
+	u32 instruction_essa;
 	u32 instruction_sigp_sense;
 	u32 instruction_sigp_sense_running;
 	u32 instruction_sigp_external_call;
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 5d1f950..38149b6 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -48,13 +48,42 @@
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			     struct task_struct *tsk)
 {
-	cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
-	update_mm(next, tsk);
+	int cpu = smp_processor_id();
+
+	if (prev == next)
+		return;
+	if (atomic_inc_return(&next->context.attach_count) >> 16) {
+		/* Delay update_mm until all TLB flushes are done. */
+		set_tsk_thread_flag(tsk, TIF_TLB_WAIT);
+	} else {
+		cpumask_set_cpu(cpu, mm_cpumask(next));
+		update_mm(next, tsk);
+		if (next->context.flush_mm)
+			/* Flush pending TLBs */
+			__tlb_flush_mm(next);
+	}
 	atomic_dec(&prev->context.attach_count);
 	WARN_ON(atomic_read(&prev->context.attach_count) < 0);
-	atomic_inc(&next->context.attach_count);
-	/* Check for TLBs not flushed yet */
-	__tlb_flush_mm_lazy(next);
+}
+
+#define finish_arch_post_lock_switch finish_arch_post_lock_switch
+static inline void finish_arch_post_lock_switch(void)
+{
+	struct task_struct *tsk = current;
+	struct mm_struct *mm = tsk->mm;
+
+	if (!test_tsk_thread_flag(tsk, TIF_TLB_WAIT))
+		return;
+	preempt_disable();
+	clear_tsk_thread_flag(tsk, TIF_TLB_WAIT);
+	while (atomic_read(&mm->context.attach_count) >> 16)
+		cpu_relax();
+
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+	update_mm(mm, tsk);
+	if (mm->context.flush_mm)
+		__tlb_flush_mm(mm);
+	preempt_enable();
 }
 
 #define enter_lazy_tlb(mm,tsk)	do { } while (0)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index e1408dd..884017c 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -22,6 +22,7 @@
 void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mmu_gather *, unsigned long *);
 
+void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned long key, bool nq);
 
@@ -91,11 +92,22 @@
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 {
 	unsigned long *table = crst_table_alloc(mm);
-	if (table)
-		crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
+
+	if (!table)
+		return NULL;
+	crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
+	if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
+		crst_table_free(mm, table);
+		return NULL;
+	}
 	return (pmd_t *) table;
 }
-#define pmd_free(mm, pmd) crst_table_free(mm, (unsigned long *) pmd)
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	pgtable_pmd_page_dtor(virt_to_page(pmd));
+	crst_table_free(mm, (unsigned long *) pmd);
+}
 
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 2204400..1ab75ea 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -229,6 +229,7 @@
 #define _PAGE_READ	0x010		/* SW pte read bit */
 #define _PAGE_WRITE	0x020		/* SW pte write bit */
 #define _PAGE_SPECIAL	0x040		/* SW associated with special page */
+#define _PAGE_UNUSED	0x080		/* SW bit for pgste usage state */
 #define __HAVE_ARCH_PTE_SPECIAL
 
 /* Set of bits not changed in pte_modify */
@@ -394,6 +395,12 @@
 
 #endif /* CONFIG_64BIT */
 
+/* Guest Page State used for virtualization */
+#define _PGSTE_GPS_ZERO		0x0000000080000000UL
+#define _PGSTE_GPS_USAGE_MASK	0x0000000003000000UL
+#define _PGSTE_GPS_USAGE_STABLE 0x0000000000000000UL
+#define _PGSTE_GPS_USAGE_UNUSED 0x0000000001000000UL
+
 /*
  * A user page table pointer has the space-switch-event bit, the
  * private-space-control bit and the storage-alteration-event-control
@@ -617,6 +624,14 @@
 	return pte_val(pte) == _PAGE_INVALID;
 }
 
+static inline int pte_swap(pte_t pte)
+{
+	/* Bit pattern: (pte & 0x603) == 0x402 */
+	return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT |
+				_PAGE_TYPE | _PAGE_PRESENT))
+		== (_PAGE_INVALID | _PAGE_TYPE);
+}
+
 static inline int pte_file(pte_t pte)
 {
 	/* Bit pattern: (pte & 0x601) == 0x600 */
@@ -821,20 +836,20 @@
 unsigned long __gmap_fault(unsigned long address, struct gmap *);
 unsigned long gmap_fault(unsigned long address, struct gmap *);
 void gmap_discard(unsigned long from, unsigned long to, struct gmap *);
+void __gmap_zap(unsigned long address, struct gmap *);
 
 void gmap_register_ipte_notifier(struct gmap_notifier *);
 void gmap_unregister_ipte_notifier(struct gmap_notifier *);
 int gmap_ipte_notify(struct gmap *, unsigned long start, unsigned long len);
-void gmap_do_ipte_notify(struct mm_struct *, unsigned long addr, pte_t *);
+void gmap_do_ipte_notify(struct mm_struct *, pte_t *);
 
 static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,
-					unsigned long addr,
 					pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
 	if (pgste_val(pgste) & PGSTE_IN_BIT) {
 		pgste_val(pgste) &= ~PGSTE_IN_BIT;
-		gmap_do_ipte_notify(mm, addr, ptep);
+		gmap_do_ipte_notify(mm, ptep);
 	}
 #endif
 	return pgste;
@@ -852,6 +867,7 @@
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
+		pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
 		pgste_set_key(ptep, pgste, entry);
 		pgste_set_pte(ptep, entry);
 		pgste_set_unlock(ptep, pgste);
@@ -881,6 +897,12 @@
 	return (pte_val(pte) & _PAGE_YOUNG) != 0;
 }
 
+#define __HAVE_ARCH_PTE_UNUSED
+static inline int pte_unused(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_UNUSED;
+}
+
 /*
  * pgd/pmd/pte modification functions
  */
@@ -1034,30 +1056,41 @@
 
 static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
 {
-	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
+	unsigned long pto = (unsigned long) ptep;
+
 #ifndef CONFIG_64BIT
-		/* pto must point to the start of the segment table */
-		pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00);
-#else
-		/* ipte in zarch mode can do the math */
-		pte_t *pto = ptep;
+	/* pto in ESA mode must point to the start of the segment table */
+	pto &= 0x7ffffc00;
 #endif
-		asm volatile(
-			"	ipte	%2,%3"
-			: "=m" (*ptep) : "m" (*ptep),
-			  "a" (pto), "a" (address));
-	}
+	/* Invalidation + global TLB flush for the pte */
+	asm volatile(
+		"	ipte	%2,%3"
+		: "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address));
+}
+
+static inline void ptep_flush_direct(struct mm_struct *mm,
+				     unsigned long address, pte_t *ptep)
+{
+	if (pte_val(*ptep) & _PAGE_INVALID)
+		return;
+	__ptep_ipte(address, ptep);
 }
 
 static inline void ptep_flush_lazy(struct mm_struct *mm,
 				   unsigned long address, pte_t *ptep)
 {
-	int active = (mm == current->active_mm) ? 1 : 0;
+	int active, count;
 
-	if (atomic_read(&mm->context.attach_count) > active)
-		__ptep_ipte(address, ptep);
-	else
+	if (pte_val(*ptep) & _PAGE_INVALID)
+		return;
+	active = (mm == current->active_mm) ? 1 : 0;
+	count = atomic_add_return(0x10000, &mm->context.attach_count);
+	if ((count & 0xffff) <= active) {
+		pte_val(*ptep) |= _PAGE_INVALID;
 		mm->context.flush_mm = 1;
+	} else
+		__ptep_ipte(address, ptep);
+	atomic_sub(0x10000, &mm->context.attach_count);
 }
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
@@ -1070,11 +1103,11 @@
 
 	if (mm_has_pgste(vma->vm_mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste);
+		pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
 	}
 
 	pte = *ptep;
-	__ptep_ipte(addr, ptep);
+	ptep_flush_direct(vma->vm_mm, addr, ptep);
 	young = pte_young(pte);
 	pte = pte_mkold(pte);
 
@@ -1116,7 +1149,7 @@
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+		pgste = pgste_ipte_notify(mm, ptep, pgste);
 	}
 
 	pte = *ptep;
@@ -1140,12 +1173,11 @@
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste_ipte_notify(mm, address, ptep, pgste);
+		pgste_ipte_notify(mm, ptep, pgste);
 	}
 
 	pte = *ptep;
 	ptep_flush_lazy(mm, address, ptep);
-	pte_val(*ptep) |= _PAGE_INVALID;
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_update_all(&pte, pgste);
@@ -1178,14 +1210,17 @@
 
 	if (mm_has_pgste(vma->vm_mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);
+		pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
 	}
 
 	pte = *ptep;
-	__ptep_ipte(address, ptep);
+	ptep_flush_direct(vma->vm_mm, address, ptep);
 	pte_val(*ptep) = _PAGE_INVALID;
 
 	if (mm_has_pgste(vma->vm_mm)) {
+		if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) ==
+		    _PGSTE_GPS_USAGE_UNUSED)
+			pte_val(pte) |= _PAGE_UNUSED;
 		pgste = pgste_update_all(&pte, pgste);
 		pgste_set_unlock(ptep, pgste);
 	}
@@ -1209,7 +1244,7 @@
 
 	if (!full && mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+		pgste = pgste_ipte_notify(mm, ptep, pgste);
 	}
 
 	pte = *ptep;
@@ -1234,7 +1269,7 @@
 	if (pte_write(pte)) {
 		if (mm_has_pgste(mm)) {
 			pgste = pgste_get_lock(ptep);
-			pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+			pgste = pgste_ipte_notify(mm, ptep, pgste);
 		}
 
 		ptep_flush_lazy(mm, address, ptep);
@@ -1260,10 +1295,10 @@
 		return 0;
 	if (mm_has_pgste(vma->vm_mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);
+		pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
 	}
 
-	__ptep_ipte(address, ptep);
+	ptep_flush_direct(vma->vm_mm, address, ptep);
 
 	if (mm_has_pgste(vma->vm_mm)) {
 		pgste_set_pte(ptep, entry);
@@ -1447,12 +1482,16 @@
 static inline void pmdp_flush_lazy(struct mm_struct *mm,
 				   unsigned long address, pmd_t *pmdp)
 {
-	int active = (mm == current->active_mm) ? 1 : 0;
+	int active, count;
 
-	if ((atomic_read(&mm->context.attach_count) & 0xffff) > active)
-		__pmd_idte(address, pmdp);
-	else
+	active = (mm == current->active_mm) ? 1 : 0;
+	count = atomic_add_return(0x10000, &mm->context.attach_count);
+	if ((count & 0xffff) <= active) {
+		pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
 		mm->context.flush_mm = 1;
+	} else
+		__pmd_idte(address, pmdp);
+	atomic_sub(0x10000, &mm->context.attach_count);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 9c82ceb..f4783c0 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -83,6 +83,7 @@
  * These are defined as per linux/ptrace.h, which see.
  */
 #define arch_has_single_step()	(1)
+#define arch_has_block_step()	(1)
 
 #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0)
 #define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN)
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index abaca22..2f5e993 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -46,6 +46,7 @@
 int sclp_cpu_deconfigure(u8 cpu);
 unsigned long long sclp_get_rnmax(void);
 unsigned long long sclp_get_rzm(void);
+unsigned int sclp_get_max_cpu(void);
 int sclp_sdias_blk_count(void);
 int sclp_sdias_copy(void *dest, int blk_num, int nr_blks);
 int sclp_chp_configure(struct chp_id chpid);
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 94cfbe4..406f3a1 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -59,7 +59,6 @@
 #define MACHINE_FLAG_DIAG44	(1UL << 4)
 #define MACHINE_FLAG_IDTE	(1UL << 5)
 #define MACHINE_FLAG_DIAG9C	(1UL << 6)
-#define MACHINE_FLAG_MVCOS	(1UL << 7)
 #define MACHINE_FLAG_KVM	(1UL << 8)
 #define MACHINE_FLAG_ESOP	(1UL << 9)
 #define MACHINE_FLAG_EDAT1	(1UL << 10)
@@ -85,7 +84,6 @@
 #define MACHINE_HAS_IDTE	(0)
 #define MACHINE_HAS_DIAG44	(1)
 #define MACHINE_HAS_MVPG	(S390_lowcore.machine_flags & MACHINE_FLAG_MVPG)
-#define MACHINE_HAS_MVCOS	(0)
 #define MACHINE_HAS_EDAT1	(0)
 #define MACHINE_HAS_EDAT2	(0)
 #define MACHINE_HAS_LPP		(0)
@@ -98,7 +96,6 @@
 #define MACHINE_HAS_IDTE	(S390_lowcore.machine_flags & MACHINE_FLAG_IDTE)
 #define MACHINE_HAS_DIAG44	(S390_lowcore.machine_flags & MACHINE_FLAG_DIAG44)
 #define MACHINE_HAS_MVPG	(1)
-#define MACHINE_HAS_MVCOS	(S390_lowcore.machine_flags & MACHINE_FLAG_MVCOS)
 #define MACHINE_HAS_EDAT1	(S390_lowcore.machine_flags & MACHINE_FLAG_EDAT1)
 #define MACHINE_HAS_EDAT2	(S390_lowcore.machine_flags & MACHINE_FLAG_EDAT2)
 #define MACHINE_HAS_LPP		(S390_lowcore.machine_flags & MACHINE_FLAG_LPP)
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 10e0fcd..3ccd71b 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -81,6 +81,7 @@
 #define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
 #define TIF_SIGPENDING		2	/* signal pending */
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
+#define TIF_TLB_WAIT		4	/* wait for TLB flush completion */
 #define TIF_PER_TRAP		6	/* deliver sigtrap on return to user */
 #define TIF_MCCK_PENDING	7	/* machine check handling is pending */
 #define TIF_SYSCALL_TRACE	8	/* syscall trace active */
@@ -91,11 +92,13 @@
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	19	/* restore signal mask in do_signal() */
 #define TIF_SINGLE_STEP		20	/* This task is single stepped */
+#define TIF_BLOCK_STEP		21	/* This task is block stepped */
 
 #define _TIF_SYSCALL		(1<<TIF_SYSCALL)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
+#define _TIF_TLB_WAIT		(1<<TIF_TLB_WAIT)
 #define _TIF_PER_TRAP		(1<<TIF_PER_TRAP)
 #define _TIF_MCCK_PENDING	(1<<TIF_MCCK_PENDING)
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 79330af..4133b3f 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -92,33 +92,58 @@
 #define ARCH_HAS_SORT_EXTABLE
 #define ARCH_HAS_SEARCH_EXTABLE
 
-struct uaccess_ops {
-	size_t (*copy_from_user)(size_t, const void __user *, void *);
-	size_t (*copy_to_user)(size_t, void __user *, const void *);
-	size_t (*copy_in_user)(size_t, void __user *, const void __user *);
-	size_t (*clear_user)(size_t, void __user *);
-	size_t (*strnlen_user)(size_t, const char __user *);
-	size_t (*strncpy_from_user)(size_t, const char __user *, char *);
-	int (*futex_atomic_op)(int op, u32 __user *, int oparg, int *old);
-	int (*futex_atomic_cmpxchg)(u32 *, u32 __user *, u32 old, u32 new);
-};
+int __handle_fault(unsigned long, unsigned long, int);
 
-extern struct uaccess_ops uaccess;
-extern struct uaccess_ops uaccess_mvcos;
-extern struct uaccess_ops uaccess_pt;
+/**
+ * __copy_from_user: - Copy a block of data from user space, with less checking.
+ * @to:   Destination address, in kernel space.
+ * @from: Source address, in user space.
+ * @n:	  Number of bytes to copy.
+ *
+ * Context: User context only.	This function may sleep.
+ *
+ * Copy data from user space to kernel space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ *
+ * If some data could not be copied, this function will pad the copied
+ * data to the requested size using zero bytes.
+ */
+unsigned long __must_check __copy_from_user(void *to, const void __user *from,
+					    unsigned long n);
 
-extern int __handle_fault(unsigned long, unsigned long, int);
+/**
+ * __copy_to_user: - Copy a block of data into user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n:	  Number of bytes to copy.
+ *
+ * Context: User context only.	This function may sleep.
+ *
+ * Copy data from kernel space to user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ */
+unsigned long __must_check __copy_to_user(void __user *to, const void *from,
+					  unsigned long n);
 
-static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
+
+static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 {
-	size = uaccess.copy_to_user(size, ptr, x);
-	return size ? -EFAULT : size;
+	size = __copy_to_user(ptr, x, size);
+	return size ? -EFAULT : 0;
 }
 
-static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
+static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
 {
-	size = uaccess.copy_from_user(size, ptr, x);
-	return size ? -EFAULT : size;
+	size = __copy_from_user(x, ptr, size);
+	return size ? -EFAULT : 0;
 }
 
 /*
@@ -135,8 +160,8 @@
 	case 2:							\
 	case 4:							\
 	case 8:							\
-		__pu_err = __put_user_fn(sizeof (*(ptr)),	\
-					 ptr, &__x);		\
+		__pu_err = __put_user_fn(&__x, ptr,		\
+					 sizeof(*(ptr)));	\
 		break;						\
 	default:						\
 		__put_user_bad();				\
@@ -152,7 +177,7 @@
 })
 
 
-extern int __put_user_bad(void) __attribute__((noreturn));
+int __put_user_bad(void) __attribute__((noreturn));
 
 #define __get_user(x, ptr)					\
 ({								\
@@ -161,29 +186,29 @@
 	switch (sizeof(*(ptr))) {				\
 	case 1: {						\
 		unsigned char __x;				\
-		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
-					 ptr, &__x);		\
+		__gu_err = __get_user_fn(&__x, ptr,		\
+					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 2: {						\
 		unsigned short __x;				\
-		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
-					 ptr, &__x);		\
+		__gu_err = __get_user_fn(&__x, ptr,		\
+					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 4: {						\
 		unsigned int __x;				\
-		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
-					 ptr, &__x);		\
+		__gu_err = __get_user_fn(&__x, ptr,		\
+					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 8: {						\
 		unsigned long long __x;				\
-		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
-					 ptr, &__x);		\
+		__gu_err = __get_user_fn(&__x, ptr,		\
+					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
@@ -200,35 +225,12 @@
 	__get_user(x, ptr);					\
 })
 
-extern int __get_user_bad(void) __attribute__((noreturn));
+int __get_user_bad(void) __attribute__((noreturn));
 
 #define __put_user_unaligned __put_user
 #define __get_user_unaligned __get_user
 
 /**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only.  This function may sleep.
- *
- * Copy data from kernel space to user space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	return uaccess.copy_to_user(n, to, from);
-}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-/**
  * copy_to_user: - Copy a block of data into user space.
  * @to:   Destination address, in user space.
  * @from: Source address, in kernel space.
@@ -248,30 +250,7 @@
 	return __copy_to_user(to, from, n);
 }
 
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only.  This function may sleep.
- *
- * Copy data from user space to kernel space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	return uaccess.copy_from_user(n, from, to);
-}
-
-extern void copy_from_user_overflow(void)
+void copy_from_user_overflow(void)
 #ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
 __compiletime_warning("copy_from_user() buffer size is not provably correct")
 #endif
@@ -306,11 +285,8 @@
 	return __copy_from_user(to, from, n);
 }
 
-static inline unsigned long __must_check
-__copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
-	return uaccess.copy_in_user(n, to, from);
-}
+unsigned long __must_check
+__copy_in_user(void __user *to, const void __user *from, unsigned long n);
 
 static inline unsigned long __must_check
 copy_in_user(void __user *to, const void __user *from, unsigned long n)
@@ -322,18 +298,22 @@
 /*
  * Copy a null terminated string from userspace.
  */
+
+long __strncpy_from_user(char *dst, const char __user *src, long count);
+
 static inline long __must_check
 strncpy_from_user(char *dst, const char __user *src, long count)
 {
 	might_fault();
-	return uaccess.strncpy_from_user(count, src, dst);
+	return __strncpy_from_user(dst, src, count);
 }
 
-static inline unsigned long
-strnlen_user(const char __user * src, unsigned long n)
+unsigned long __must_check __strnlen_user(const char __user *src, unsigned long count);
+
+static inline unsigned long strnlen_user(const char __user *src, unsigned long n)
 {
 	might_fault();
-	return uaccess.strnlen_user(n, src);
+	return __strnlen_user(src, n);
 }
 
 /**
@@ -355,21 +335,14 @@
 /*
  * Zero Userspace
  */
+unsigned long __must_check __clear_user(void __user *to, unsigned long size);
 
-static inline unsigned long __must_check
-__clear_user(void __user *to, unsigned long n)
-{
-	return uaccess.clear_user(n, to);
-}
-
-static inline unsigned long __must_check
-clear_user(void __user *to, unsigned long n)
+static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
 {
 	might_fault();
-	return uaccess.clear_user(n, to);
+	return __clear_user(to, n);
 }
 
-extern int copy_to_user_real(void __user *dest, void *src, size_t count);
-extern int copy_from_user_real(void *dest, void __user *src, size_t count);
+int copy_to_user_real(void __user *dest, void *src, unsigned long count);
 
 #endif /* __S390_UACCESS_H */
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index 7e0b498..a150f4f 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -403,6 +403,12 @@
 #define PTRACE_TE_ABORT_RAND	      0x5011
 
 /*
+ * The numbers chosen here are somewhat arbitrary but absolutely MUST
+ * not overlap with any of the number assigned in <linux/ptrace.h>.
+ */
+#define PTRACE_SINGLEBLOCK	12	/* resume execution until next branch */
+
+/*
  * PT_PROT definition is loosely based on hppa bsd definition in
  * gdb/hppab-nat.c
  */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 1b3ac09..a95c4ca 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -47,9 +47,8 @@
 obj-$(CONFIG_HIBERNATION)	+= suspend.o swsusp_asm64.o
 obj-$(CONFIG_AUDIT)		+= audit.o
 compat-obj-$(CONFIG_AUDIT)	+= compat_audit.o
-obj-$(CONFIG_COMPAT)		+= compat_linux.o compat_signal.o \
-					compat_wrapper.o compat_exec_domain.o \
-					$(compat-obj-y)
+obj-$(CONFIG_COMPAT)		+= compat_linux.o compat_signal.o
+obj-$(CONFIG_COMPAT)		+= compat_wrapper.o $(compat-obj-y)
 
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
diff --git a/arch/s390/kernel/compat_exec_domain.c b/arch/s390/kernel/compat_exec_domain.c
deleted file mode 100644
index 765fabd..0000000
--- a/arch/s390/kernel/compat_exec_domain.c
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Support for 32-bit Linux for S390 personality.
- *
- * Copyright IBM Corp. 2000
- * Author(s): Gerhard Tonn (ton@de.ibm.com)
- *
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/personality.h>
-#include <linux/sched.h>
-
-static struct exec_domain s390_exec_domain;
-
-static int __init s390_init (void)
-{
-	s390_exec_domain.name = "Linux/s390";
-	s390_exec_domain.handler = NULL;
-	s390_exec_domain.pers_low = PER_LINUX32;
-	s390_exec_domain.pers_high = PER_LINUX32;
-	s390_exec_domain.signal_map = default_exec_domain.signal_map;
-	s390_exec_domain.signal_invmap = default_exec_domain.signal_invmap;
-	register_exec_domain(&s390_exec_domain);
-	return 0;
-}
-
-__initcall(s390_init);
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index db02052..ca38139 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -86,48 +86,51 @@
 #define SET_STAT_UID(stat, uid)		(stat).st_uid = high2lowuid(uid)
 #define SET_STAT_GID(stat, gid)		(stat).st_gid = high2lowgid(gid)
 
-asmlinkage long sys32_chown16(const char __user * filename, u16 user, u16 group)
+COMPAT_SYSCALL_DEFINE3(s390_chown16, const char __user *, filename,
+		       u16, user, u16, group)
 {
 	return sys_chown(filename, low2highuid(user), low2highgid(group));
 }
 
-asmlinkage long sys32_lchown16(const char __user * filename, u16 user, u16 group)
+COMPAT_SYSCALL_DEFINE3(s390_lchown16, const char __user *,
+		       filename, u16, user, u16, group)
 {
 	return sys_lchown(filename, low2highuid(user), low2highgid(group));
 }
 
-asmlinkage long sys32_fchown16(unsigned int fd, u16 user, u16 group)
+COMPAT_SYSCALL_DEFINE3(s390_fchown16, unsigned int, fd, u16, user, u16, group)
 {
 	return sys_fchown(fd, low2highuid(user), low2highgid(group));
 }
 
-asmlinkage long sys32_setregid16(u16 rgid, u16 egid)
+COMPAT_SYSCALL_DEFINE2(s390_setregid16, u16, rgid, u16, egid)
 {
 	return sys_setregid(low2highgid(rgid), low2highgid(egid));
 }
 
-asmlinkage long sys32_setgid16(u16 gid)
+COMPAT_SYSCALL_DEFINE1(s390_setgid16, u16, gid)
 {
 	return sys_setgid((gid_t)gid);
 }
 
-asmlinkage long sys32_setreuid16(u16 ruid, u16 euid)
+COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid)
 {
 	return sys_setreuid(low2highuid(ruid), low2highuid(euid));
 }
 
-asmlinkage long sys32_setuid16(u16 uid)
+COMPAT_SYSCALL_DEFINE1(s390_setuid16, u16, uid)
 {
 	return sys_setuid((uid_t)uid);
 }
 
-asmlinkage long sys32_setresuid16(u16 ruid, u16 euid, u16 suid)
+COMPAT_SYSCALL_DEFINE3(s390_setresuid16, u16, ruid, u16, euid, u16, suid)
 {
 	return sys_setresuid(low2highuid(ruid), low2highuid(euid),
-		low2highuid(suid));
+			     low2highuid(suid));
 }
 
-asmlinkage long sys32_getresuid16(u16 __user *ruidp, u16 __user *euidp, u16 __user *suidp)
+COMPAT_SYSCALL_DEFINE3(s390_getresuid16, u16 __user *, ruidp,
+		       u16 __user *, euidp, u16 __user *, suidp)
 {
 	const struct cred *cred = current_cred();
 	int retval;
@@ -144,13 +147,14 @@
 	return retval;
 }
 
-asmlinkage long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid)
+COMPAT_SYSCALL_DEFINE3(s390_setresgid16, u16, rgid, u16, egid, u16, sgid)
 {
 	return sys_setresgid(low2highgid(rgid), low2highgid(egid),
-		low2highgid(sgid));
+			     low2highgid(sgid));
 }
 
-asmlinkage long sys32_getresgid16(u16 __user *rgidp, u16 __user *egidp, u16 __user *sgidp)
+COMPAT_SYSCALL_DEFINE3(s390_getresgid16, u16 __user *, rgidp,
+		       u16 __user *, egidp, u16 __user *, sgidp)
 {
 	const struct cred *cred = current_cred();
 	int retval;
@@ -167,12 +171,12 @@
 	return retval;
 }
 
-asmlinkage long sys32_setfsuid16(u16 uid)
+COMPAT_SYSCALL_DEFINE1(s390_setfsuid16, u16, uid)
 {
 	return sys_setfsuid((uid_t)uid);
 }
 
-asmlinkage long sys32_setfsgid16(u16 gid)
+COMPAT_SYSCALL_DEFINE1(s390_setfsgid16, u16, gid)
 {
 	return sys_setfsgid((gid_t)gid);
 }
@@ -215,7 +219,7 @@
 	return 0;
 }
 
-asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist)
+COMPAT_SYSCALL_DEFINE2(s390_getgroups16, int, gidsetsize, u16 __user *, grouplist)
 {
 	const struct cred *cred = current_cred();
 	int i;
@@ -240,7 +244,7 @@
 	return i;
 }
 
-asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
+COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplist)
 {
 	struct group_info *group_info;
 	int retval;
@@ -265,22 +269,22 @@
 	return retval;
 }
 
-asmlinkage long sys32_getuid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_getuid16)
 {
 	return high2lowuid(from_kuid_munged(current_user_ns(), current_uid()));
 }
 
-asmlinkage long sys32_geteuid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_geteuid16)
 {
 	return high2lowuid(from_kuid_munged(current_user_ns(), current_euid()));
 }
 
-asmlinkage long sys32_getgid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_getgid16)
 {
 	return high2lowgid(from_kgid_munged(current_user_ns(), current_gid()));
 }
 
-asmlinkage long sys32_getegid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_getegid16)
 {
 	return high2lowgid(from_kgid_munged(current_user_ns(), current_egid()));
 }
@@ -295,41 +299,35 @@
 }
 #endif
 
-asmlinkage long sys32_truncate64(const char __user * path, unsigned long high, unsigned long low)
+COMPAT_SYSCALL_DEFINE3(s390_truncate64, const char __user *, path, u32, high, u32, low)
 {
-	if ((int)high < 0)
-		return -EINVAL;
-	else
-		return sys_truncate(path, (high << 32) | low);
+	return sys_truncate(path, (unsigned long)high << 32 | low);
 }
 
-asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low)
+COMPAT_SYSCALL_DEFINE3(s390_ftruncate64, unsigned int, fd, u32, high, u32, low)
 {
-	if ((int)high < 0)
-		return -EINVAL;
-	else
-		return sys_ftruncate(fd, (high << 32) | low);
+	return sys_ftruncate(fd, (unsigned long)high << 32 | low);
 }
 
-asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf,
-				size_t count, u32 poshi, u32 poslo)
+COMPAT_SYSCALL_DEFINE5(s390_pread64, unsigned int, fd, char __user *, ubuf,
+		       compat_size_t, count, u32, high, u32, low)
 {
 	if ((compat_ssize_t) count < 0)
 		return -EINVAL;
-	return sys_pread64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo));
+	return sys_pread64(fd, ubuf, count, (unsigned long)high << 32 | low);
 }
 
-asmlinkage long sys32_pwrite64(unsigned int fd, const char __user *ubuf,
-				size_t count, u32 poshi, u32 poslo)
+COMPAT_SYSCALL_DEFINE5(s390_pwrite64, unsigned int, fd, const char __user *, ubuf,
+		       compat_size_t, count, u32, high, u32, low)
 {
 	if ((compat_ssize_t) count < 0)
 		return -EINVAL;
-	return sys_pwrite64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo));
+	return sys_pwrite64(fd, ubuf, count, (unsigned long)high << 32 | low);
 }
 
-asmlinkage compat_ssize_t sys32_readahead(int fd, u32 offhi, u32 offlo, s32 count)
+COMPAT_SYSCALL_DEFINE4(s390_readahead, int, fd, u32, high, u32, low, s32, count)
 {
-	return sys_readahead(fd, ((loff_t)AA(offhi) << 32) | AA(offlo), count);
+	return sys_readahead(fd, (unsigned long)high << 32 | low, count);
 }
 
 struct stat64_emu31 {
@@ -381,7 +379,7 @@
 	return copy_to_user(ubuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; 
 }
 
-asmlinkage long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(s390_stat64, const char __user *, filename, struct stat64_emu31 __user *, statbuf)
 {
 	struct kstat stat;
 	int ret = vfs_stat(filename, &stat);
@@ -390,7 +388,7 @@
 	return ret;
 }
 
-asmlinkage long sys32_lstat64(const char __user * filename, struct stat64_emu31 __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(s390_lstat64, const char __user *, filename, struct stat64_emu31 __user *, statbuf)
 {
 	struct kstat stat;
 	int ret = vfs_lstat(filename, &stat);
@@ -399,7 +397,7 @@
 	return ret;
 }
 
-asmlinkage long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(s390_fstat64, unsigned int, fd, struct stat64_emu31 __user *, statbuf)
 {
 	struct kstat stat;
 	int ret = vfs_fstat(fd, &stat);
@@ -408,8 +406,8 @@
 	return ret;
 }
 
-asmlinkage long sys32_fstatat64(unsigned int dfd, const char __user *filename,
-				struct stat64_emu31 __user* statbuf, int flag)
+COMPAT_SYSCALL_DEFINE4(s390_fstatat64, unsigned int, dfd, const char __user *, filename,
+		       struct stat64_emu31 __user *, statbuf, int, flag)
 {
 	struct kstat stat;
 	int error;
@@ -435,7 +433,7 @@
 	compat_ulong_t offset;
 };
 
-asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg)
+COMPAT_SYSCALL_DEFINE1(s390_old_mmap, struct mmap_arg_struct_emu31 __user *, arg)
 {
 	struct mmap_arg_struct_emu31 a;
 
@@ -447,7 +445,7 @@
 			      a.offset >> PAGE_SHIFT);
 }
 
-asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg)
+COMPAT_SYSCALL_DEFINE1(s390_mmap2, struct mmap_arg_struct_emu31 __user *, arg)
 {
 	struct mmap_arg_struct_emu31 a;
 
@@ -456,7 +454,7 @@
 	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset);
 }
 
-asmlinkage long sys32_read(unsigned int fd, char __user * buf, size_t count)
+COMPAT_SYSCALL_DEFINE3(s390_read, unsigned int, fd, char __user *, buf, compat_size_t, count)
 {
 	if ((compat_ssize_t) count < 0)
 		return -EINVAL; 
@@ -464,7 +462,7 @@
 	return sys_read(fd, buf, count);
 }
 
-asmlinkage long sys32_write(unsigned int fd, const char __user * buf, size_t count)
+COMPAT_SYSCALL_DEFINE3(s390_write, unsigned int, fd, const char __user *, buf, compat_size_t, count)
 {
 	if ((compat_ssize_t) count < 0)
 		return -EINVAL; 
@@ -478,14 +476,13 @@
  * because the 31 bit values differ from the 64 bit values.
  */
 
-asmlinkage long
-sys32_fadvise64(int fd, loff_t offset, size_t len, int advise)
+COMPAT_SYSCALL_DEFINE5(s390_fadvise64, int, fd, u32, high, u32, low, compat_size_t, len, int, advise)
 {
 	if (advise == 4)
 		advise = POSIX_FADV_DONTNEED;
 	else if (advise == 5)
 		advise = POSIX_FADV_NOREUSE;
-	return sys_fadvise64(fd, offset, len, advise);
+	return sys_fadvise64(fd, (unsigned long)high << 32 | low, len, advise);
 }
 
 struct fadvise64_64_args {
@@ -495,8 +492,7 @@
 	int advice;
 };
 
-asmlinkage long
-sys32_fadvise64_64(struct fadvise64_64_args __user *args)
+COMPAT_SYSCALL_DEFINE1(s390_fadvise64_64, struct fadvise64_64_args __user *, args)
 {
 	struct fadvise64_64_args a;
 
@@ -508,3 +504,17 @@
 		a.advice = POSIX_FADV_NOREUSE;
 	return sys_fadvise64_64(a.fd, a.offset, a.len, a.advice);
 }
+
+COMPAT_SYSCALL_DEFINE6(s390_sync_file_range, int, fd, u32, offhigh, u32, offlow,
+		       u32, nhigh, u32, nlow, unsigned int, flags)
+{
+	return sys_sync_file_range(fd, ((loff_t)offhigh << 32) + offlow,
+				   ((u64)nhigh << 32) + nlow, flags);
+}
+
+COMPAT_SYSCALL_DEFINE6(s390_fallocate, int, fd, int, mode, u32, offhigh, u32, offlow,
+		       u32, lenhigh, u32, lenlow)
+{
+	return sys_fallocate(fd, mode, ((loff_t)offhigh << 32) + offlow,
+			     ((u64)lenhigh << 32) + lenlow);
+}
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
index 1bfda3e..39ddfdb 100644
--- a/arch/s390/kernel/compat_linux.h
+++ b/arch/s390/kernel/compat_linux.h
@@ -76,46 +76,43 @@
 struct mmap_arg_struct_emu31;
 struct fadvise64_64_args;
 
-long sys32_chown16(const char __user * filename, u16 user, u16 group);
-long sys32_lchown16(const char __user * filename, u16 user, u16 group);
-long sys32_fchown16(unsigned int fd, u16 user, u16 group);
-long sys32_setregid16(u16 rgid, u16 egid);
-long sys32_setgid16(u16 gid);
-long sys32_setreuid16(u16 ruid, u16 euid);
-long sys32_setuid16(u16 uid);
-long sys32_setresuid16(u16 ruid, u16 euid, u16 suid);
-long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid);
-long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid);
-long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid);
-long sys32_setfsuid16(u16 uid);
-long sys32_setfsgid16(u16 gid);
-long sys32_getgroups16(int gidsetsize, u16 __user *grouplist);
-long sys32_setgroups16(int gidsetsize, u16 __user *grouplist);
-long sys32_getuid16(void);
-long sys32_geteuid16(void);
-long sys32_getgid16(void);
-long sys32_getegid16(void);
-long sys32_truncate64(const char __user * path, unsigned long high,
-		      unsigned long low);
-long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low);
-long sys32_init_module(void __user *umod, unsigned long len,
-		       const char __user *uargs);
-long sys32_delete_module(const char __user *name_user, unsigned int flags);
-long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count,
-		   u32 poshi, u32 poslo);
-long sys32_pwrite64(unsigned int fd, const char __user *ubuf,
-		    size_t count, u32 poshi, u32 poslo);
-compat_ssize_t sys32_readahead(int fd, u32 offhi, u32 offlo, s32 count);
-long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf);
-long sys32_lstat64(const char __user * filename,
-		   struct stat64_emu31 __user * statbuf);
-long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf);
-long sys32_fstatat64(unsigned int dfd, const char __user *filename,
-		     struct stat64_emu31 __user* statbuf, int flag);
-unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg);
-long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg);
-long sys32_read(unsigned int fd, char __user * buf, size_t count);
-long sys32_write(unsigned int fd, const char __user * buf, size_t count);
-long sys32_fadvise64(int fd, loff_t offset, size_t len, int advise);
-long sys32_fadvise64_64(struct fadvise64_64_args __user *args);
+long compat_sys_s390_chown16(const char __user *filename, u16 user, u16 group);
+long compat_sys_s390_lchown16(const char __user *filename, u16 user, u16 group);
+long compat_sys_s390_fchown16(unsigned int fd, u16 user, u16 group);
+long compat_sys_s390_setregid16(u16 rgid, u16 egid);
+long compat_sys_s390_setgid16(u16 gid);
+long compat_sys_s390_setreuid16(u16 ruid, u16 euid);
+long compat_sys_s390_setuid16(u16 uid);
+long compat_sys_s390_setresuid16(u16 ruid, u16 euid, u16 suid);
+long compat_sys_s390_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid);
+long compat_sys_s390_setresgid16(u16 rgid, u16 egid, u16 sgid);
+long compat_sys_s390_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid);
+long compat_sys_s390_setfsuid16(u16 uid);
+long compat_sys_s390_setfsgid16(u16 gid);
+long compat_sys_s390_getgroups16(int gidsetsize, u16 __user *grouplist);
+long compat_sys_s390_setgroups16(int gidsetsize, u16 __user *grouplist);
+long compat_sys_s390_getuid16(void);
+long compat_sys_s390_geteuid16(void);
+long compat_sys_s390_getgid16(void);
+long compat_sys_s390_getegid16(void);
+long compat_sys_s390_truncate64(const char __user *path, u32 high, u32 low);
+long compat_sys_s390_ftruncate64(unsigned int fd, u32 high, u32 low);
+long compat_sys_s390_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, u32 high, u32 low);
+long compat_sys_s390_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count, u32 high, u32 low);
+long compat_sys_s390_readahead(int fd, u32 high, u32 low, s32 count);
+long compat_sys_s390_stat64(const char __user *filename, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_lstat64(const char __user *filename, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_fstat64(unsigned int fd, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_fstatat64(unsigned int dfd, const char __user *filename, struct stat64_emu31 __user *statbuf, int flag);
+long compat_sys_s390_old_mmap(struct mmap_arg_struct_emu31 __user *arg);
+long compat_sys_s390_mmap2(struct mmap_arg_struct_emu31 __user *arg);
+long compat_sys_s390_read(unsigned int fd, char __user * buf, compat_size_t count);
+long compat_sys_s390_write(unsigned int fd, const char __user * buf, compat_size_t count);
+long compat_sys_s390_fadvise64(int fd, u32 high, u32 low, compat_size_t len, int advise);
+long compat_sys_s390_fadvise64_64(struct fadvise64_64_args __user *args);
+long compat_sys_s390_sync_file_range(int fd, u32 offhigh, u32 offlow, u32 nhigh, u32 nlow, unsigned int flags);
+long compat_sys_s390_fallocate(int fd, int mode, u32 offhigh, u32 offlow, u32 lenhigh, u32 lenlow);
+long compat_sys_sigreturn(void);
+long compat_sys_rt_sigreturn(void);
+
 #endif /* _ASM_S390X_S390_H */
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 8b84bc3..7df5ed9 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -241,7 +241,7 @@
 	return 0;
 }
 
-asmlinkage long sys32_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
 	sigframe32 __user *frame = (sigframe32 __user *)regs->gprs[15];
@@ -260,7 +260,7 @@
 	return 0;
 }
 
-asmlinkage long sys32_rt_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
 	rt_sigframe32 __user *frame = (rt_sigframe32 __user *)regs->gprs[15];
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
deleted file mode 100644
index 59c8efc..0000000
--- a/arch/s390/kernel/compat_wrapper.S
+++ /dev/null
@@ -1,1425 +0,0 @@
-/*
-*    wrapper for 31 bit compatible system calls.
-*
-*    Copyright IBM Corp. 2000, 2006
-*    Author(s): Gerhard Tonn (ton@de.ibm.com),
-*		Thomas Spatzier (tspat@de.ibm.com)
-*/
-
-#include <linux/linkage.h>
-
-ENTRY(sys32_exit_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_exit		# branch to sys_exit
-
-ENTRY(sys32_read_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# char *
-	llgfr	%r4,%r4			# size_t
-	jg	sys32_read		# branch to sys_read
-
-ENTRY(sys32_write_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# const char *
-	llgfr	%r4,%r4			# size_t
-	jg	sys32_write		# branch to system call
-
-ENTRY(sys32_close_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	jg	sys_close		# branch to system call
-
-ENTRY(sys32_creat_wrapper)
-	llgtr	%r2,%r2			# const char *
-	lgfr	%r3,%r3			# int
-	jg	sys_creat		# branch to system call
-
-ENTRY(sys32_link_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgtr	%r3,%r3			# const char *
-	jg	sys_link		# branch to system call
-
-ENTRY(sys32_unlink_wrapper)
-	llgtr	%r2,%r2			# const char *
-	jg	sys_unlink		# branch to system call
-
-ENTRY(sys32_chdir_wrapper)
-	llgtr	%r2,%r2			# const char *
-	jg	sys_chdir		# branch to system call
-
-ENTRY(sys32_time_wrapper)
-	llgtr	%r2,%r2			# int *
-	jg	compat_sys_time		# branch to system call
-
-ENTRY(sys32_mknod_wrapper)
-	llgtr	%r2,%r2			# const char *
-	lgfr	%r3,%r3			# int
-	llgfr	%r4,%r4			# dev
-	jg	sys_mknod		# branch to system call
-
-ENTRY(sys32_chmod_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgfr	%r3,%r3			# mode_t
-	jg	sys_chmod		# branch to system call
-
-ENTRY(sys32_lchown16_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgfr	%r3,%r3			# __kernel_old_uid_emu31_t
-	llgfr	%r4,%r4			# __kernel_old_uid_emu31_t
-	jg	sys32_lchown16		# branch to system call
-
-#sys32_getpid_wrapper				# void
-
-ENTRY(sys32_mount_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# char *
-	llgtr	%r4,%r4			# char *
-	llgfr	%r5,%r5			# unsigned long
-	llgtr	%r6,%r6			# void *
-	jg	compat_sys_mount	# branch to system call
-
-ENTRY(sys32_oldumount_wrapper)
-	llgtr	%r2,%r2			# char *
-	jg	sys_oldumount		# branch to system call
-
-ENTRY(sys32_setuid16_wrapper)
-	llgfr	%r2,%r2			# __kernel_old_uid_emu31_t
-	jg	sys32_setuid16		# branch to system call
-
-#sys32_getuid16_wrapper			# void
-
-ENTRY(sys32_ptrace_wrapper)
-	lgfr	%r2,%r2			# long
-	lgfr	%r3,%r3			# long
-	llgtr	%r4,%r4			# long
-	llgfr	%r5,%r5			# long
-	jg	compat_sys_ptrace	# branch to system call
-
-ENTRY(sys32_alarm_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	jg	sys_alarm		# branch to system call
-
-ENTRY(compat_sys_utime_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# struct compat_utimbuf *
-	jg	compat_sys_utime	# branch to system call
-
-ENTRY(sys32_access_wrapper)
-	llgtr	%r2,%r2			# const char *
-	lgfr	%r3,%r3			# int
-	jg	sys_access		# branch to system call
-
-ENTRY(sys32_nice_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_nice		# branch to system call
-
-#sys32_sync_wrapper			# void
-
-ENTRY(sys32_kill_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	jg	sys_kill		# branch to system call
-
-ENTRY(sys32_rename_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgtr	%r3,%r3			# const char *
-	jg	sys_rename		# branch to system call
-
-ENTRY(sys32_mkdir_wrapper)
-	llgtr	%r2,%r2			# const char *
-	lgfr	%r3,%r3			# int
-	jg	sys_mkdir		# branch to system call
-
-ENTRY(sys32_rmdir_wrapper)
-	llgtr	%r2,%r2			# const char *
-	jg	sys_rmdir		# branch to system call
-
-ENTRY(sys32_dup_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	jg	sys_dup			# branch to system call
-
-ENTRY(sys32_pipe_wrapper)
-	llgtr	%r2,%r2			# u32 *
-	jg	sys_pipe		# branch to system call
-
-ENTRY(compat_sys_times_wrapper)
-	llgtr	%r2,%r2			# struct compat_tms *
-	jg	compat_sys_times	# branch to system call
-
-ENTRY(sys32_brk_wrapper)
-	llgtr	%r2,%r2			# unsigned long
-	jg	sys_brk			# branch to system call
-
-ENTRY(sys32_setgid16_wrapper)
-	llgfr	%r2,%r2			# __kernel_old_gid_emu31_t
-	jg	sys32_setgid16		# branch to system call
-
-#sys32_getgid16_wrapper			# void
-
-ENTRY(sys32_signal_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# __sighandler_t
-	jg	sys_signal
-
-#sys32_geteuid16_wrapper		# void
-
-#sys32_getegid16_wrapper		# void
-
-ENTRY(sys32_acct_wrapper)
-	llgtr	%r2,%r2			# char *
-	jg	sys_acct		# branch to system call
-
-ENTRY(sys32_umount_wrapper)
-	llgtr	%r2,%r2			# char *
-	lgfr	%r3,%r3			# int
-	jg	sys_umount		# branch to system call
-
-ENTRY(compat_sys_ioctl_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# unsigned int
-	llgfr	%r4,%r4			# unsigned int
-	jg	compat_sys_ioctl	# branch to system call
-
-ENTRY(compat_sys_fcntl_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# unsigned int
-	llgfr	%r4,%r4			# unsigned long
-	jg	compat_sys_fcntl	# branch to system call
-
-ENTRY(sys32_setpgid_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	lgfr	%r3,%r3			# pid_t
-	jg	sys_setpgid		# branch to system call
-
-ENTRY(sys32_umask_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_umask		# branch to system call
-
-ENTRY(sys32_chroot_wrapper)
-	llgtr	%r2,%r2			# char *
-	jg	sys_chroot		# branch to system call
-
-ENTRY(sys32_ustat_wrapper)
-	llgfr	%r2,%r2			# dev_t
-	llgtr	%r3,%r3			# struct ustat *
-	jg	compat_sys_ustat
-
-ENTRY(sys32_dup2_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# unsigned int
-	jg	sys_dup2		# branch to system call
-
-#sys32_getppid_wrapper			# void
-
-#sys32_getpgrp_wrapper			# void
-
-#sys32_setsid_wrapper			# void
-
-ENTRY(sys32_setreuid16_wrapper)
-	llgfr	%r2,%r2			# __kernel_old_uid_emu31_t
-	llgfr	%r3,%r3			# __kernel_old_uid_emu31_t
-	jg	sys32_setreuid16	# branch to system call
-
-ENTRY(sys32_setregid16_wrapper)
-	llgfr	%r2,%r2			# __kernel_old_gid_emu31_t
-	llgfr	%r3,%r3			# __kernel_old_gid_emu31_t
-	jg	sys32_setregid16	# branch to system call
-
-ENTRY(sys_sigsuspend_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	llgfr	%r4,%r4			# old_sigset_t
-	jg	sys_sigsuspend
-
-ENTRY(compat_sys_sigpending_wrapper)
-	llgtr	%r2,%r2			# compat_old_sigset_t *
-	jg	compat_sys_sigpending	# branch to system call
-
-ENTRY(sys32_sethostname_wrapper)
-	llgtr	%r2,%r2			# char *
-	lgfr	%r3,%r3			# int
-	jg	sys_sethostname		# branch to system call
-
-ENTRY(compat_sys_setrlimit_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# struct rlimit_emu31 *
-	jg	compat_sys_setrlimit	# branch to system call
-
-ENTRY(compat_sys_old_getrlimit_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# struct rlimit_emu31 *
-	jg	compat_sys_old_getrlimit # branch to system call
-
-ENTRY(compat_sys_getrlimit_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# struct rlimit_emu31 *
-	jg	compat_sys_getrlimit	# branch to system call
-
-ENTRY(sys32_mmap2_wrapper)
-	llgtr	%r2,%r2			# struct mmap_arg_struct_emu31 *
-	jg	sys32_mmap2			# branch to system call
-
-ENTRY(compat_sys_gettimeofday_wrapper)
-	llgtr	%r2,%r2			# struct timeval_emu31 *
-	llgtr	%r3,%r3			# struct timezone *
-	jg	compat_sys_gettimeofday	# branch to system call
-
-ENTRY(compat_sys_settimeofday_wrapper)
-	llgtr	%r2,%r2			# struct timeval_emu31 *
-	llgtr	%r3,%r3			# struct timezone *
-	jg	compat_sys_settimeofday	# branch to system call
-
-ENTRY(sys32_getgroups16_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# __kernel_old_gid_emu31_t *
-	jg	sys32_getgroups16	# branch to system call
-
-ENTRY(sys32_setgroups16_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# __kernel_old_gid_emu31_t *
-	jg	sys32_setgroups16	# branch to system call
-
-ENTRY(sys32_symlink_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgtr	%r3,%r3			# const char *
-	jg	sys_symlink		# branch to system call
-
-ENTRY(sys32_readlink_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgtr	%r3,%r3			# char *
-	lgfr	%r4,%r4			# int
-	jg	sys_readlink		# branch to system call
-
-ENTRY(sys32_uselib_wrapper)
-	llgtr	%r2,%r2			# const char *
-	jg	sys_uselib		# branch to system call
-
-ENTRY(sys32_swapon_wrapper)
-	llgtr	%r2,%r2			# const char *
-	lgfr	%r3,%r3			# int
-	jg	sys_swapon		# branch to system call
-
-ENTRY(sys32_reboot_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	llgfr	%r4,%r4			# unsigned int
-	llgtr	%r5,%r5			# void *
-	jg	sys_reboot		# branch to system call
-
-ENTRY(old32_readdir_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# void *
-	llgfr	%r4,%r4			# unsigned int
-	jg	compat_sys_old_readdir	# branch to system call
-
-ENTRY(old32_mmap_wrapper)
-	llgtr	%r2,%r2			# struct mmap_arg_struct_emu31 *
-	jg	old32_mmap		# branch to system call
-
-ENTRY(sys32_munmap_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgfr	%r3,%r3			# size_t
-	jg	sys_munmap		# branch to system call
-
-ENTRY(sys32_fchmod_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# mode_t
-	jg	sys_fchmod		# branch to system call
-
-ENTRY(sys32_fchown16_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# compat_uid_t
-	llgfr	%r4,%r4			# compat_uid_t
-	jg	sys32_fchown16		# branch to system call
-
-ENTRY(sys32_getpriority_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	jg	sys_getpriority		# branch to system call
-
-ENTRY(sys32_setpriority_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	lgfr	%r4,%r4			# int
-	jg	sys_setpriority		# branch to system call
-
-ENTRY(compat_sys_statfs_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# struct compat_statfs *
-	jg	compat_sys_statfs	# branch to system call
-
-ENTRY(compat_sys_fstatfs_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# struct compat_statfs *
-	jg	compat_sys_fstatfs	# branch to system call
-
-ENTRY(compat_sys_socketcall_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# u32 *
-	jg	compat_sys_socketcall	# branch to system call
-
-ENTRY(sys32_syslog_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# char *
-	lgfr	%r4,%r4			# int
-	jg	sys_syslog		# branch to system call
-
-ENTRY(compat_sys_newstat_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# struct stat_emu31 *
-	jg	compat_sys_newstat	# branch to system call
-
-ENTRY(compat_sys_newlstat_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# struct stat_emu31 *
-	jg	compat_sys_newlstat	# branch to system call
-
-ENTRY(compat_sys_newfstat_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# struct stat_emu31 *
-	jg	compat_sys_newfstat	# branch to system call
-
-#sys32_vhangup_wrapper			# void
-
-ENTRY(sys32_swapoff_wrapper)
-	llgtr	%r2,%r2			# const char *
-	jg	sys_swapoff		# branch to system call
-
-ENTRY(compat_sys_sysinfo_wrapper)
-	llgtr	%r2,%r2			# struct sysinfo_emu31 *
-	jg	compat_sys_sysinfo	# branch to system call
-
-ENTRY(sys32_fsync_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	jg	sys_fsync		# branch to system call
-
-#sys32_sigreturn_wrapper		# done in sigreturn_glue
-
-#sys32_clone_wrapper			# done in clone_glue
-
-ENTRY(sys32_setdomainname_wrapper)
-	llgtr	%r2,%r2			# char *
-	lgfr	%r3,%r3			# int
-	jg	sys_setdomainname	# branch to system call
-
-ENTRY(sys32_newuname_wrapper)
-	llgtr	%r2,%r2			# struct new_utsname *
-	jg	sys_newuname		# branch to system call
-
-ENTRY(compat_sys_adjtimex_wrapper)
-	llgtr	%r2,%r2			# struct compat_timex *
-	jg	compat_sys_adjtimex	# branch to system call
-
-ENTRY(sys32_mprotect_wrapper)
-	llgtr	%r2,%r2			# unsigned long (actually pointer
-	llgfr	%r3,%r3			# size_t
-	llgfr	%r4,%r4			# unsigned long
-	jg	sys_mprotect		# branch to system call
-
-ENTRY(sys_init_module_wrapper)
-	llgtr	%r2,%r2			# void *
-	llgfr	%r3,%r3			# unsigned long
-	llgtr	%r4,%r4			# char *
-	jg	sys_init_module		# branch to system call
-
-ENTRY(sys_delete_module_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgfr	%r3,%r3			# unsigned int
-	jg	sys_delete_module	# branch to system call
-
-ENTRY(sys32_quotactl_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# const char *
-	llgfr	%r4,%r4			# qid_t
-	llgtr	%r5,%r5			# caddr_t
-	jg	sys_quotactl		# branch to system call
-
-ENTRY(sys32_getpgid_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	jg	sys_getpgid		# branch to system call
-
-ENTRY(sys32_fchdir_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	jg	sys_fchdir		# branch to system call
-
-ENTRY(sys32_bdflush_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# long
-	jg	sys_bdflush		# branch to system call
-
-ENTRY(sys32_sysfs_wrapper)
-	lgfr	%r2,%r2			# int
-	llgfr	%r3,%r3			# unsigned long
-	llgfr	%r4,%r4			# unsigned long
-	jg	sys_sysfs		# branch to system call
-
-ENTRY(sys32_personality_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	jg	sys_s390_personality	# branch to system call
-
-ENTRY(sys32_setfsuid16_wrapper)
-	llgfr	%r2,%r2			# __kernel_old_uid_emu31_t
-	jg	sys32_setfsuid16	# branch to system call
-
-ENTRY(sys32_setfsgid16_wrapper)
-	llgfr	%r2,%r2			# __kernel_old_gid_emu31_t
-	jg	sys32_setfsgid16	# branch to system call
-
-ENTRY(sys32_llseek_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# unsigned long
-	llgfr	%r4,%r4			# unsigned long
-	llgtr	%r5,%r5			# loff_t *
-	llgfr	%r6,%r6			# unsigned int
-	jg	sys_llseek		# branch to system call
-
-ENTRY(sys32_getdents_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# void *
-	llgfr	%r4,%r4			# unsigned int
-	jg	compat_sys_getdents	# branch to system call
-
-ENTRY(compat_sys_select_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# compat_fd_set *
-	llgtr	%r4,%r4			# compat_fd_set *
-	llgtr	%r5,%r5			# compat_fd_set *
-	llgtr	%r6,%r6			# struct compat_timeval *
-	jg	compat_sys_select	# branch to system call
-
-ENTRY(sys32_flock_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# unsigned int
-	jg	sys_flock		# branch to system call
-
-ENTRY(sys32_msync_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgfr	%r3,%r3			# size_t
-	lgfr	%r4,%r4			# int
-	jg	sys_msync		# branch to system call
-
-ENTRY(compat_sys_readv_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const struct compat_iovec *
-	llgfr	%r4,%r4			# unsigned long
-	jg	compat_sys_readv	# branch to system call
-
-ENTRY(compat_sys_writev_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const struct compat_iovec *
-	llgfr	%r4,%r4			# unsigned long
-	jg	compat_sys_writev	# branch to system call
-
-ENTRY(sys32_getsid_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	jg	sys_getsid		# branch to system call
-
-ENTRY(sys32_fdatasync_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	jg	sys_fdatasync		# branch to system call
-
-ENTRY(sys32_mlock_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgfr	%r3,%r3			# size_t
-	jg	sys_mlock		# branch to system call
-
-ENTRY(sys32_munlock_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgfr	%r3,%r3			# size_t
-	jg	sys_munlock		# branch to system call
-
-ENTRY(sys32_mlockall_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_mlockall		# branch to system call
-
-#sys32_munlockall_wrapper		# void
-
-ENTRY(sys32_sched_setparam_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	llgtr	%r3,%r3			# struct sched_param *
-	jg	sys_sched_setparam	# branch to system call
-
-ENTRY(sys32_sched_getparam_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	llgtr	%r3,%r3			# struct sched_param *
-	jg	sys_sched_getparam	# branch to system call
-
-ENTRY(sys32_sched_setscheduler_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	lgfr	%r3,%r3			# int
-	llgtr	%r4,%r4			# struct sched_param *
-	jg	sys_sched_setscheduler	# branch to system call
-
-ENTRY(sys32_sched_getscheduler_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	jg	sys_sched_getscheduler	# branch to system call
-
-#sys32_sched_yield_wrapper		# void
-
-ENTRY(sys32_sched_get_priority_max_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_sched_get_priority_max	# branch to system call
-
-ENTRY(sys32_sched_get_priority_min_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_sched_get_priority_min	# branch to system call
-
-ENTRY(compat_sys_nanosleep_wrapper)
-	llgtr	%r2,%r2			# struct compat_timespec *
-	llgtr	%r3,%r3			# struct compat_timespec *
-	jg	compat_sys_nanosleep		# branch to system call
-
-ENTRY(sys32_mremap_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgfr	%r3,%r3			# unsigned long
-	llgfr	%r4,%r4			# unsigned long
-	llgfr	%r5,%r5			# unsigned long
-	llgfr	%r6,%r6			# unsigned long
-	jg	sys_mremap		# branch to system call
-
-ENTRY(sys32_setresuid16_wrapper)
-	llgfr	%r2,%r2			# __kernel_old_uid_emu31_t
-	llgfr	%r3,%r3			# __kernel_old_uid_emu31_t
-	llgfr	%r4,%r4			# __kernel_old_uid_emu31_t
-	jg	sys32_setresuid16	# branch to system call
-
-ENTRY(sys32_getresuid16_wrapper)
-	llgtr	%r2,%r2			# __kernel_old_uid_emu31_t *
-	llgtr	%r3,%r3			# __kernel_old_uid_emu31_t *
-	llgtr	%r4,%r4			# __kernel_old_uid_emu31_t *
-	jg	sys32_getresuid16	# branch to system call
-
-ENTRY(sys32_poll_wrapper)
-	llgtr	%r2,%r2			# struct pollfd *
-	llgfr	%r3,%r3			# unsigned int
-	lgfr	%r4,%r4			# int
-	jg	sys_poll		# branch to system call
-
-ENTRY(sys32_setresgid16_wrapper)
-	llgfr	%r2,%r2			# __kernel_old_gid_emu31_t
-	llgfr	%r3,%r3			# __kernel_old_gid_emu31_t
-	llgfr	%r4,%r4			# __kernel_old_gid_emu31_t
-	jg	sys32_setresgid16	# branch to system call
-
-ENTRY(sys32_getresgid16_wrapper)
-	llgtr	%r2,%r2			# __kernel_old_gid_emu31_t *
-	llgtr	%r3,%r3			# __kernel_old_gid_emu31_t *
-	llgtr	%r4,%r4			# __kernel_old_gid_emu31_t *
-	jg	sys32_getresgid16	# branch to system call
-
-ENTRY(sys32_prctl_wrapper)
-	lgfr	%r2,%r2			# int
-	llgfr	%r3,%r3			# unsigned long
-	llgfr	%r4,%r4			# unsigned long
-	llgfr	%r5,%r5			# unsigned long
-	llgfr	%r6,%r6			# unsigned long
-	jg	sys_prctl		# branch to system call
-
-#sys32_rt_sigreturn_wrapper		# done in rt_sigreturn_glue
-
-ENTRY(sys32_pread64_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# char *
-	llgfr	%r4,%r4			# size_t
-	llgfr	%r5,%r5			# u32
-	llgfr	%r6,%r6			# u32
-	jg	sys32_pread64		# branch to system call
-
-ENTRY(sys32_pwrite64_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# const char *
-	llgfr	%r4,%r4			# size_t
-	llgfr	%r5,%r5			# u32
-	llgfr	%r6,%r6			# u32
-	jg	sys32_pwrite64		# branch to system call
-
-ENTRY(sys32_chown16_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgfr	%r3,%r3			# __kernel_old_uid_emu31_t
-	llgfr	%r4,%r4			# __kernel_old_gid_emu31_t
-	jg	sys32_chown16		# branch to system call
-
-ENTRY(sys32_getcwd_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgfr	%r3,%r3			# unsigned long
-	jg	sys_getcwd		# branch to system call
-
-ENTRY(sys32_capget_wrapper)
-	llgtr	%r2,%r2			# cap_user_header_t
-	llgtr	%r3,%r3			# cap_user_data_t
-	jg	sys_capget		# branch to system call
-
-ENTRY(sys32_capset_wrapper)
-	llgtr	%r2,%r2			# cap_user_header_t
-	llgtr	%r3,%r3			# const cap_user_data_t
-	jg	sys_capset		# branch to system call
-
-#sys32_vfork_wrapper			# done in vfork_glue
-
-ENTRY(sys32_truncate64_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgfr	%r3,%r3			# unsigned long
-	llgfr	%r4,%r4			# unsigned long
-	jg	sys32_truncate64	# branch to system call
-
-ENTRY(sys32_ftruncate64_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# unsigned long
-	llgfr	%r4,%r4			# unsigned long
-	jg	sys32_ftruncate64	# branch to system call
-
-ENTRY(sys32_lchown_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgfr	%r3,%r3			# uid_t
-	llgfr	%r4,%r4			# gid_t
-	jg	sys_lchown		# branch to system call
-
-#sys32_getuid_wrapper			# void
-#sys32_getgid_wrapper			# void
-#sys32_geteuid_wrapper			# void
-#sys32_getegid_wrapper			# void
-
-ENTRY(sys32_setreuid_wrapper)
-	llgfr	%r2,%r2			# uid_t
-	llgfr	%r3,%r3			# uid_t
-	jg	sys_setreuid		# branch to system call
-
-ENTRY(sys32_setregid_wrapper)
-	llgfr	%r2,%r2			# gid_t
-	llgfr	%r3,%r3			# gid_t
-	jg	sys_setregid		# branch to system call
-
-ENTRY(sys32_getgroups_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# gid_t *
-	jg	sys_getgroups		# branch to system call
-
-ENTRY(sys32_setgroups_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# gid_t *
-	jg	sys_setgroups		# branch to system call
-
-ENTRY(sys32_fchown_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# uid_t
-	llgfr	%r4,%r4			# gid_t
-	jg	sys_fchown		# branch to system call
-
-ENTRY(sys32_setresuid_wrapper)
-	llgfr	%r2,%r2			# uid_t
-	llgfr	%r3,%r3			# uid_t
-	llgfr	%r4,%r4			# uid_t
-	jg	sys_setresuid		# branch to system call
-
-ENTRY(sys32_getresuid_wrapper)
-	llgtr	%r2,%r2			# uid_t *
-	llgtr	%r3,%r3			# uid_t *
-	llgtr	%r4,%r4			# uid_t *
-	jg	sys_getresuid		# branch to system call
-
-ENTRY(sys32_setresgid_wrapper)
-	llgfr	%r2,%r2			# gid_t
-	llgfr	%r3,%r3			# gid_t
-	llgfr	%r4,%r4			# gid_t
-	jg	sys_setresgid		# branch to system call
-
-ENTRY(sys32_getresgid_wrapper)
-	llgtr	%r2,%r2			# gid_t *
-	llgtr	%r3,%r3			# gid_t *
-	llgtr	%r4,%r4			# gid_t *
-	jg	sys_getresgid		# branch to system call
-
-ENTRY(sys32_chown_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgfr	%r3,%r3			# uid_t
-	llgfr	%r4,%r4			# gid_t
-	jg	sys_chown		# branch to system call
-
-ENTRY(sys32_setuid_wrapper)
-	llgfr	%r2,%r2			# uid_t
-	jg	sys_setuid		# branch to system call
-
-ENTRY(sys32_setgid_wrapper)
-	llgfr	%r2,%r2			# gid_t
-	jg	sys_setgid		# branch to system call
-
-ENTRY(sys32_setfsuid_wrapper)
-	llgfr	%r2,%r2			# uid_t
-	jg	sys_setfsuid		# branch to system call
-
-ENTRY(sys32_setfsgid_wrapper)
-	llgfr	%r2,%r2			# gid_t
-	jg	sys_setfsgid		# branch to system call
-
-ENTRY(sys32_pivot_root_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgtr	%r3,%r3			# const char *
-	jg	sys_pivot_root		# branch to system call
-
-ENTRY(sys32_mincore_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgfr	%r3,%r3			# size_t
-	llgtr	%r4,%r4			# unsigned char *
-	jg	sys_mincore		# branch to system call
-
-ENTRY(sys32_madvise_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgfr	%r3,%r3			# size_t
-	lgfr	%r4,%r4			# int
-	jg	sys_madvise		# branch to system call
-
-ENTRY(sys32_getdents64_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# void *
-	llgfr	%r4,%r4			# unsigned int
-	jg	sys_getdents64		# branch to system call
-
-ENTRY(compat_sys_fcntl64_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# unsigned int
-	llgfr	%r4,%r4			# unsigned long
-	jg	compat_sys_fcntl64	# branch to system call
-
-ENTRY(sys32_stat64_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# struct stat64 *
-	jg	sys32_stat64		# branch to system call
-
-ENTRY(sys32_lstat64_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# struct stat64 *
-	jg	sys32_lstat64		# branch to system call
-
-ENTRY(sys32_stime_wrapper)
-	llgtr	%r2,%r2			# long *
-	jg	compat_sys_stime	# branch to system call
-
-ENTRY(sys32_fstat64_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgtr	%r3,%r3			# struct stat64 *
-	jg	sys32_fstat64		# branch to system call
-
-ENTRY(sys32_setxattr_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# char *
-	llgtr	%r4,%r4			# void *
-	llgfr	%r5,%r5			# size_t
-	lgfr	%r6,%r6			# int
-	jg	sys_setxattr
-
-ENTRY(sys32_lsetxattr_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# char *
-	llgtr	%r4,%r4			# void *
-	llgfr	%r5,%r5			# size_t
-	lgfr	%r6,%r6			# int
-	jg	sys_lsetxattr
-
-ENTRY(sys32_fsetxattr_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# char *
-	llgtr	%r4,%r4			# void *
-	llgfr	%r5,%r5			# size_t
-	lgfr	%r6,%r6			# int
-	jg	sys_fsetxattr
-
-ENTRY(sys32_getxattr_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# char *
-	llgtr	%r4,%r4			# void *
-	llgfr	%r5,%r5			# size_t
-	jg	sys_getxattr
-
-ENTRY(sys32_lgetxattr_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# char *
-	llgtr	%r4,%r4			# void *
-	llgfr	%r5,%r5			# size_t
-	jg	sys_lgetxattr
-
-ENTRY(sys32_fgetxattr_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# char *
-	llgtr	%r4,%r4			# void *
-	llgfr	%r5,%r5			# size_t
-	jg	sys_fgetxattr
-
-ENTRY(sys32_listxattr_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# char *
-	llgfr	%r4,%r4			# size_t
-	jg	sys_listxattr
-
-ENTRY(sys32_llistxattr_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# char *
-	llgfr	%r4,%r4			# size_t
-	jg	sys_llistxattr
-
-ENTRY(sys32_flistxattr_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# char *
-	llgfr	%r4,%r4			# size_t
-	jg	sys_flistxattr
-
-ENTRY(sys32_removexattr_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# char *
-	jg	sys_removexattr
-
-ENTRY(sys32_lremovexattr_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# char *
-	jg	sys_lremovexattr
-
-ENTRY(sys32_fremovexattr_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# char *
-	jg	sys_fremovexattr
-
-ENTRY(sys32_sched_setaffinity_wrapper)
-	lgfr	%r2,%r2			# int
-	llgfr	%r3,%r3			# unsigned int
-	llgtr	%r4,%r4			# unsigned long *
-	jg	compat_sys_sched_setaffinity
-
-ENTRY(sys32_sched_getaffinity_wrapper)
-	lgfr	%r2,%r2			# int
-	llgfr	%r3,%r3			# unsigned int
-	llgtr	%r4,%r4			# unsigned long *
-	jg	compat_sys_sched_getaffinity
-
-ENTRY(sys32_exit_group_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_exit_group		# branch to system call
-
-ENTRY(sys32_set_tid_address_wrapper)
-	llgtr	%r2,%r2			# int *
-	jg	sys_set_tid_address	# branch to system call
-
-ENTRY(sys_epoll_create_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_epoll_create	# branch to system call
-
-ENTRY(sys_epoll_ctl_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	lgfr	%r4,%r4			# int
-	llgtr	%r5,%r5			# struct epoll_event *
-	jg	sys_epoll_ctl		# branch to system call
-
-ENTRY(sys_epoll_wait_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# struct epoll_event *
-	lgfr	%r4,%r4			# int
-	lgfr	%r5,%r5			# int
-	jg	sys_epoll_wait		# branch to system call
-
-ENTRY(sys32_fadvise64_wrapper)
-	lgfr	%r2,%r2			# int
-	sllg	%r3,%r3,32		# get high word of 64bit loff_t
-	or	%r3,%r4			# get low word of 64bit loff_t
-	llgfr	%r4,%r5			# size_t (unsigned long)
-	lgfr	%r5,%r6			# int
-	jg	sys32_fadvise64
-
-ENTRY(sys32_fadvise64_64_wrapper)
-	llgtr	%r2,%r2			# struct fadvise64_64_args *
-	jg	sys32_fadvise64_64
-
-ENTRY(sys32_clock_settime_wrapper)
-	lgfr	%r2,%r2			# clockid_t (int)
-	llgtr	%r3,%r3			# struct compat_timespec *
-	jg	compat_sys_clock_settime
-
-ENTRY(sys32_clock_gettime_wrapper)
-	lgfr	%r2,%r2			# clockid_t (int)
-	llgtr	%r3,%r3			# struct compat_timespec *
-	jg	compat_sys_clock_gettime
-
-ENTRY(sys32_clock_getres_wrapper)
-	lgfr	%r2,%r2			# clockid_t (int)
-	llgtr	%r3,%r3			# struct compat_timespec *
-	jg	compat_sys_clock_getres
-
-ENTRY(sys32_clock_nanosleep_wrapper)
-	lgfr	%r2,%r2			# clockid_t (int)
-	lgfr	%r3,%r3			# int
-	llgtr	%r4,%r4			# struct compat_timespec *
-	llgtr	%r5,%r5			# struct compat_timespec *
-	jg	compat_sys_clock_nanosleep
-
-ENTRY(sys32_timer_create_wrapper)
-	lgfr	%r2,%r2			# timer_t (int)
-	llgtr	%r3,%r3			# struct compat_sigevent *
-	llgtr	%r4,%r4			# timer_t *
-	jg	compat_sys_timer_create
-
-ENTRY(sys32_timer_settime_wrapper)
-	lgfr	%r2,%r2			# timer_t (int)
-	lgfr	%r3,%r3			# int
-	llgtr	%r4,%r4			# struct compat_itimerspec *
-	llgtr	%r5,%r5			# struct compat_itimerspec *
-	jg	compat_sys_timer_settime
-
-ENTRY(sys32_timer_gettime_wrapper)
-	lgfr	%r2,%r2			# timer_t (int)
-	llgtr	%r3,%r3			# struct compat_itimerspec *
-	jg	compat_sys_timer_gettime
-
-ENTRY(sys32_timer_getoverrun_wrapper)
-	lgfr	%r2,%r2			# timer_t (int)
-	jg	sys_timer_getoverrun
-
-ENTRY(sys32_timer_delete_wrapper)
-	lgfr	%r2,%r2			# timer_t (int)
-	jg	sys_timer_delete
-
-ENTRY(sys32_io_setup_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# u32 *
-	jg	compat_sys_io_setup
-
-ENTRY(sys32_io_destroy_wrapper)
-	llgfr	%r2,%r2			# (aio_context_t) u32
-	jg	sys_io_destroy
-
-ENTRY(sys32_io_getevents_wrapper)
-	llgfr	%r2,%r2			# (aio_context_t) u32
-	lgfr	%r3,%r3			# long
-	lgfr	%r4,%r4			# long
-	llgtr	%r5,%r5			# struct io_event *
-	llgtr	%r6,%r6			# struct compat_timespec *
-	jg	compat_sys_io_getevents
-
-ENTRY(sys32_io_submit_wrapper)
-	llgfr	%r2,%r2			# (aio_context_t) u32
-	lgfr	%r3,%r3			# long
-	llgtr	%r4,%r4			# struct iocb **
-	jg	compat_sys_io_submit
-
-ENTRY(sys32_io_cancel_wrapper)
-	llgfr	%r2,%r2			# (aio_context_t) u32
-	llgtr	%r3,%r3			# struct iocb *
-	llgtr	%r4,%r4			# struct io_event *
-	jg	sys_io_cancel
-
-ENTRY(compat_sys_statfs64_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgfr	%r3,%r3			# compat_size_t
-	llgtr	%r4,%r4			# struct compat_statfs64 *
-	jg	compat_sys_statfs64
-
-ENTRY(compat_sys_fstatfs64_wrapper)
-	llgfr	%r2,%r2			# unsigned int fd
-	llgfr	%r3,%r3			# compat_size_t
-	llgtr	%r4,%r4			# struct compat_statfs64 *
-	jg	compat_sys_fstatfs64
-
-ENTRY(compat_sys_mq_open_wrapper)
-	llgtr	%r2,%r2			# const char *
-	lgfr	%r3,%r3			# int
-	llgfr	%r4,%r4			# mode_t
-	llgtr	%r5,%r5			# struct compat_mq_attr *
-	jg	compat_sys_mq_open
-
-ENTRY(sys32_mq_unlink_wrapper)
-	llgtr	%r2,%r2			# const char *
-	jg	sys_mq_unlink
-
-ENTRY(compat_sys_mq_timedsend_wrapper)
-	lgfr	%r2,%r2			# mqd_t
-	llgtr	%r3,%r3			# const char *
-	llgfr	%r4,%r4			# size_t
-	llgfr	%r5,%r5			# unsigned int
-	llgtr	%r6,%r6			# const struct compat_timespec *
-	jg	compat_sys_mq_timedsend
-
-ENTRY(compat_sys_mq_timedreceive_wrapper)
-	lgfr	%r2,%r2			# mqd_t
-	llgtr	%r3,%r3			# char *
-	llgfr	%r4,%r4			# size_t
-	llgtr	%r5,%r5			# unsigned int *
-	llgtr	%r6,%r6			# const struct compat_timespec *
-	jg	compat_sys_mq_timedreceive
-
-ENTRY(compat_sys_mq_notify_wrapper)
-	lgfr	%r2,%r2			# mqd_t
-	llgtr	%r3,%r3			# struct compat_sigevent *
-	jg	compat_sys_mq_notify
-
-ENTRY(compat_sys_mq_getsetattr_wrapper)
-	lgfr	%r2,%r2			# mqd_t
-	llgtr	%r3,%r3			# struct compat_mq_attr *
-	llgtr	%r4,%r4			# struct compat_mq_attr *
-	jg	compat_sys_mq_getsetattr
-
-ENTRY(compat_sys_add_key_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgtr	%r3,%r3			# const char *
-	llgtr	%r4,%r4			# const void *
-	llgfr	%r5,%r5			# size_t
-	llgfr	%r6,%r6			# (key_serial_t) u32
-	jg	sys_add_key
-
-ENTRY(compat_sys_request_key_wrapper)
-	llgtr	%r2,%r2			# const char *
-	llgtr	%r3,%r3			# const char *
-	llgtr	%r4,%r4			# const void *
-	llgfr	%r5,%r5			# (key_serial_t) u32
-	jg	sys_request_key
-
-ENTRY(sys32_remap_file_pages_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgfr	%r3,%r3			# unsigned long
-	llgfr	%r4,%r4			# unsigned long
-	llgfr	%r5,%r5			# unsigned long
-	llgfr	%r6,%r6			# unsigned long
-	jg	sys_remap_file_pages
-
-ENTRY(compat_sys_kexec_load_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgfr	%r3,%r3			# unsigned long
-	llgtr	%r4,%r4			# struct kexec_segment *
-	llgfr	%r5,%r5			# unsigned long
-	jg	compat_sys_kexec_load
-
-ENTRY(sys_ioprio_set_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	lgfr	%r4,%r4			# int
-	jg	sys_ioprio_set
-
-ENTRY(sys_ioprio_get_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	jg	sys_ioprio_get
-
-ENTRY(sys_inotify_add_watch_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char *
-	llgfr	%r4,%r4			# u32
-	jg	sys_inotify_add_watch
-
-ENTRY(sys_inotify_rm_watch_wrapper)
-	lgfr	%r2,%r2			# int
-	llgfr	%r3,%r3			# u32
-	jg	sys_inotify_rm_watch
-
-ENTRY(sys_mkdirat_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char *
-	lgfr	%r4,%r4			# int
-	jg	sys_mkdirat
-
-ENTRY(sys_mknodat_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char *
-	lgfr	%r4,%r4			# int
-	llgfr	%r5,%r5			# unsigned int
-	jg	sys_mknodat
-
-ENTRY(sys_fchownat_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char *
-	llgfr	%r4,%r4			# uid_t
-	llgfr	%r5,%r5			# gid_t
-	lgfr	%r6,%r6			# int
-	jg	sys_fchownat
-
-ENTRY(compat_sys_futimesat_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# char *
-	llgtr	%r4,%r4			# struct timeval *
-	jg	compat_sys_futimesat
-
-ENTRY(sys32_fstatat64_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# char *
-	llgtr	%r4,%r4			# struct stat64 *
-	lgfr	%r5,%r5			# int
-	jg	sys32_fstatat64
-
-ENTRY(sys_unlinkat_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char *
-	lgfr	%r4,%r4			# int
-	jg	sys_unlinkat
-
-ENTRY(sys_renameat_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char *
-	lgfr	%r4,%r4			# int
-	llgtr	%r5,%r5			# const char *
-	jg	sys_renameat
-
-ENTRY(sys_linkat_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char *
-	lgfr	%r4,%r4			# int
-	llgtr	%r5,%r5			# const char *
-	lgfr	%r6,%r6			# int
-	jg	sys_linkat
-
-ENTRY(sys_symlinkat_wrapper)
-	llgtr	%r2,%r2			# const char *
-	lgfr	%r3,%r3			# int
-	llgtr	%r4,%r4			# const char *
-	jg	sys_symlinkat
-
-ENTRY(sys_readlinkat_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char *
-	llgtr	%r4,%r4			# char *
-	lgfr	%r5,%r5			# int
-	jg	sys_readlinkat
-
-ENTRY(sys_fchmodat_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char *
-	llgfr	%r4,%r4			# mode_t
-	jg	sys_fchmodat
-
-ENTRY(sys_faccessat_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char *
-	lgfr	%r4,%r4			# int
-	jg	sys_faccessat
-
-ENTRY(compat_sys_pselect6_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# fd_set *
-	llgtr	%r4,%r4			# fd_set *
-	llgtr	%r5,%r5			# fd_set *
-	llgtr	%r6,%r6			# struct timespec *
-	llgt	%r0,164(%r15)		# void *
-	stg	%r0,160(%r15)
-	jg	compat_sys_pselect6
-
-ENTRY(compat_sys_ppoll_wrapper)
-	llgtr	%r2,%r2			# struct pollfd *
-	llgfr	%r3,%r3			# unsigned int
-	llgtr	%r4,%r4			# struct timespec *
-	llgtr	%r5,%r5			# const sigset_t *
-	llgfr	%r6,%r6			# size_t
-	jg	compat_sys_ppoll
-
-ENTRY(sys_unshare_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	jg	sys_unshare
-
-ENTRY(sys_splice_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# loff_t *
-	lgfr	%r4,%r4			# int
-	llgtr	%r5,%r5			# loff_t *
-	llgfr	%r6,%r6			# size_t
-	llgf	%r0,164(%r15)		# unsigned int
-	stg	%r0,160(%r15)
-	jg	sys_splice
-
-ENTRY(sys_sync_file_range_wrapper)
-	lgfr	%r2,%r2			# int
-	sllg	%r3,%r3,32		# get high word of 64bit loff_t
-	or	%r3,%r4			# get low word of 64bit loff_t
-	sllg	%r4,%r5,32		# get high word of 64bit loff_t
-	or	%r4,%r6			# get low word of 64bit loff_t
-	llgf	%r5,164(%r15)		# unsigned int
-	jg	sys_sync_file_range
-
-ENTRY(sys_tee_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	llgfr	%r4,%r4			# size_t
-	llgfr	%r5,%r5			# unsigned int
-	jg	sys_tee
-
-ENTRY(sys_getcpu_wrapper)
-	llgtr	%r2,%r2			# unsigned *
-	llgtr	%r3,%r3			# unsigned *
-	llgtr	%r4,%r4			# struct getcpu_cache *
-	jg	sys_getcpu
-
-ENTRY(compat_sys_utimes_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# struct compat_timeval *
-	jg	compat_sys_utimes
-
-ENTRY(compat_sys_utimensat_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgtr	%r3,%r3			# char *
-	llgtr	%r4,%r4			# struct compat_timespec *
-	lgfr	%r5,%r5			# int
-	jg	compat_sys_utimensat
-
-ENTRY(sys_eventfd_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	jg	sys_eventfd
-
-ENTRY(sys_fallocate_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	sllg	%r4,%r4,32		# get high word of 64bit loff_t
-	lr	%r4,%r5			# get low word of 64bit loff_t
-	sllg	%r5,%r6,32		# get high word of 64bit loff_t
-	l	%r5,164(%r15)		# get low word of 64bit loff_t
-	jg	sys_fallocate
-
-ENTRY(sys_timerfd_create_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	jg	sys_timerfd_create
-
-ENTRY(sys_eventfd2_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	lgfr	%r3,%r3			# int
-	jg	sys_eventfd2
-
-ENTRY(sys_inotify_init1_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_inotify_init1
-
-ENTRY(sys_pipe2_wrapper)
-	llgtr	%r2,%r2			# u32 *
-	lgfr	%r3,%r3			# int
-	jg	sys_pipe2		# branch to system call
-
-ENTRY(sys_dup3_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# unsigned int
-	lgfr	%r4,%r4			# int
-	jg	sys_dup3		# branch to system call
-
-ENTRY(sys_epoll_create1_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_epoll_create1	# branch to system call
-
-ENTRY(sys32_readahead_wrapper)
-	lgfr	%r2,%r2			# int
-	llgfr	%r3,%r3			# u32
-	llgfr	%r4,%r4			# u32
-	lgfr	%r5,%r5			# s32
-	jg	sys32_readahead		# branch to system call
-
-ENTRY(sys_tkill_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	lgfr	%r3,%r3			# int
-	jg	sys_tkill		# branch to system call
-
-ENTRY(sys_tgkill_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	lgfr	%r3,%r3			# pid_t
-	lgfr	%r4,%r4			# int
-	jg	sys_tgkill		# branch to system call
-
-ENTRY(compat_sys_keyctl_wrapper)
-	llgfr	%r2,%r2			# u32
-	llgfr	%r3,%r3			# u32
-	llgfr	%r4,%r4			# u32
-	llgfr	%r5,%r5			# u32
-	llgfr	%r6,%r6			# u32
-	jg	compat_sys_keyctl	# branch to system call
-
-ENTRY(sys_perf_event_open_wrapper)
-	llgtr	%r2,%r2			# const struct perf_event_attr *
-	lgfr	%r3,%r3			# pid_t
-	lgfr	%r4,%r4			# int
-	lgfr	%r5,%r5			# int
-	llgfr	%r6,%r6			# unsigned long
-	jg	sys_perf_event_open	# branch to system call
-
-ENTRY(sys_clone_wrapper)
-	llgfr	%r2,%r2			# unsigned long
-	llgfr	%r3,%r3			# unsigned long
-	llgtr	%r4,%r4			# int *
-	llgtr	%r5,%r5			# int *
-	jg	sys_clone		# branch to system call
-
-ENTRY(sys32_execve_wrapper)
-	llgtr	%r2,%r2			# char *
-	llgtr	%r3,%r3			# compat_uptr_t *
-	llgtr	%r4,%r4			# compat_uptr_t *
-	jg	compat_sys_execve	# branch to system call
-
-ENTRY(sys_fanotify_init_wrapper)
-	llgfr	%r2,%r2			# unsigned int
-	llgfr	%r3,%r3			# unsigned int
-	jg	sys_fanotify_init	# branch to system call
-
-ENTRY(sys_prlimit64_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	llgfr	%r3,%r3			# unsigned int
-	llgtr	%r4,%r4			# const struct rlimit64 __user *
-	llgtr	%r5,%r5			# struct rlimit64 __user *
-	jg	sys_prlimit64		# branch to system call
-
-ENTRY(sys_name_to_handle_at_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char __user *
-	llgtr	%r4,%r4			# struct file_handle __user *
-	llgtr	%r5,%r5			# int __user *
-	lgfr	%r6,%r6			# int
-	jg	sys_name_to_handle_at
-
-ENTRY(compat_sys_clock_adjtime_wrapper)
-	lgfr	%r2,%r2			# clockid_t (int)
-	llgtr	%r3,%r3			# struct compat_timex __user *
-	jg	compat_sys_clock_adjtime
-
-ENTRY(sys_syncfs_wrapper)
-	lgfr	%r2,%r2			# int
-	jg	sys_syncfs
-
-ENTRY(sys_setns_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	jg	sys_setns
-
-ENTRY(compat_sys_process_vm_readv_wrapper)
-	lgfr	%r2,%r2			# compat_pid_t
-	llgtr	%r3,%r3			# struct compat_iovec __user *
-	llgfr	%r4,%r4			# unsigned long
-	llgtr	%r5,%r5			# struct compat_iovec __user *
-	llgfr	%r6,%r6			# unsigned long
-	llgf	%r0,164(%r15)		# unsigned long
-	stg	%r0,160(%r15)
-	jg	compat_sys_process_vm_readv
-
-ENTRY(compat_sys_process_vm_writev_wrapper)
-	lgfr	%r2,%r2			# compat_pid_t
-	llgtr	%r3,%r3			# struct compat_iovec __user *
-	llgfr	%r4,%r4			# unsigned long
-	llgtr	%r5,%r5			# struct compat_iovec __user *
-	llgfr	%r6,%r6			# unsigned long
-	llgf	%r0,164(%r15)		# unsigned long
-	stg	%r0,160(%r15)
-	jg	compat_sys_process_vm_writev
-
-ENTRY(sys_s390_runtime_instr_wrapper)
-	lgfr	%r2,%r2			# int
-	lgfr	%r3,%r3			# int
-	jg	sys_s390_runtime_instr
-
-ENTRY(sys_kcmp_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	lgfr	%r3,%r3			# pid_t
-	lgfr	%r4,%r4			# int
-	llgfr	%r5,%r5			# unsigned long
-	llgfr	%r6,%r6			# unsigned long
-	jg	sys_kcmp
-
-ENTRY(sys_finit_module_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# const char __user *
-	lgfr	%r4,%r4			# int
-	jg	sys_finit_module
-
-ENTRY(sys_sched_setattr_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	llgtr	%r3,%r3			# struct sched_attr __user *
-	jg	sys_sched_setattr
-
-ENTRY(sys_sched_getattr_wrapper)
-	lgfr	%r2,%r2			# pid_t
-	llgtr	%r3,%r3			# const char __user *
-	llgfr	%r3,%r3			# unsigned int
-	jg	sys_sched_getattr
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
new file mode 100644
index 0000000..824c39d
--- /dev/null
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -0,0 +1,215 @@
+/*
+ *  Compat sytem call wrappers.
+ *
+ *    Copyright IBM Corp. 2014
+ */
+
+#include <linux/syscalls.h>
+#include <linux/compat.h>
+#include "entry.h"
+
+#define COMPAT_SYSCALL_WRAP1(name, ...) \
+	COMPAT_SYSCALL_WRAPx(1, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP2(name, ...) \
+	COMPAT_SYSCALL_WRAPx(2, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP3(name, ...) \
+	COMPAT_SYSCALL_WRAPx(3, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP4(name, ...) \
+	COMPAT_SYSCALL_WRAPx(4, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP5(name, ...) \
+	COMPAT_SYSCALL_WRAPx(5, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP6(name, ...) \
+	COMPAT_SYSCALL_WRAPx(6, _##name, __VA_ARGS__)
+
+#define __SC_COMPAT_TYPE(t, a) \
+	__typeof(__builtin_choose_expr(sizeof(t) > 4, 0L, (t)0)) a
+
+#define __SC_COMPAT_CAST(t, a)						\
+({									\
+	long __ReS = a;							\
+									\
+	BUILD_BUG_ON((sizeof(t) > 4) && !__TYPE_IS_L(t) &&		\
+		     !__TYPE_IS_UL(t) && !__TYPE_IS_PTR(t));		\
+	if (__TYPE_IS_L(t))						\
+		__ReS = (s32)a;						\
+	if (__TYPE_IS_UL(t))						\
+		__ReS = (u32)a;						\
+	if (__TYPE_IS_PTR(t))						\
+		__ReS = a & 0x7fffffff;					\
+	(t)__ReS;							\
+})
+
+/*
+ * The COMPAT_SYSCALL_WRAP macro generates system call wrappers to be used by
+ * compat tasks. These wrappers will only be used for system calls where only
+ * the system call arguments need sign or zero extension or zeroing of the upper
+ * 33 bits of pointers.
+ * Note: since the wrapper function will afterwards call a system call which
+ * again performs zero and sign extension for all system call arguments with
+ * a size of less than eight bytes, these compat wrappers only touch those
+ * system call arguments with a size of eight bytes ((unsigned) long and
+ * pointers). Zero and sign extension for e.g. int parameters will be done by
+ * the regular system call wrappers.
+ */
+#define COMPAT_SYSCALL_WRAPx(x, name, ...)					\
+	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));		\
+	asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__));\
+	asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__))	\
+	{									\
+		return sys##name(__MAP(x,__SC_COMPAT_CAST,__VA_ARGS__));	\
+	}
+
+COMPAT_SYSCALL_WRAP1(exit, int, error_code);
+COMPAT_SYSCALL_WRAP1(close, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(creat, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP2(link, const char __user *, oldname, const char __user *, newname);
+COMPAT_SYSCALL_WRAP1(unlink, const char __user *, pathname);
+COMPAT_SYSCALL_WRAP1(chdir, const char __user *, filename);
+COMPAT_SYSCALL_WRAP3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev);
+COMPAT_SYSCALL_WRAP2(chmod, const char __user *, filename, umode_t, mode);
+COMPAT_SYSCALL_WRAP1(oldumount, char __user *, name);
+COMPAT_SYSCALL_WRAP1(alarm, unsigned int, seconds);
+COMPAT_SYSCALL_WRAP2(access, const char __user *, filename, int, mode);
+COMPAT_SYSCALL_WRAP1(nice, int, increment);
+COMPAT_SYSCALL_WRAP2(kill, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP2(rename, const char __user *, oldname, const char __user *, newname);
+COMPAT_SYSCALL_WRAP2(mkdir, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP1(rmdir, const char __user *, pathname);
+COMPAT_SYSCALL_WRAP1(dup, unsigned int, fildes);
+COMPAT_SYSCALL_WRAP1(pipe, int __user *, fildes);
+COMPAT_SYSCALL_WRAP1(brk, unsigned long, brk);
+COMPAT_SYSCALL_WRAP2(signal, int, sig, __sighandler_t, handler);
+COMPAT_SYSCALL_WRAP1(acct, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(umount, char __user *, name, int, flags);
+COMPAT_SYSCALL_WRAP2(setpgid, pid_t, pid, pid_t, pgid);
+COMPAT_SYSCALL_WRAP1(umask, int, mask);
+COMPAT_SYSCALL_WRAP1(chroot, const char __user *, filename);
+COMPAT_SYSCALL_WRAP2(dup2, unsigned int, oldfd, unsigned int, newfd);
+COMPAT_SYSCALL_WRAP3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask);
+COMPAT_SYSCALL_WRAP2(sethostname, char __user *, name, int, len);
+COMPAT_SYSCALL_WRAP2(symlink, const char __user *, old, const char __user *, new);
+COMPAT_SYSCALL_WRAP3(readlink, const char __user *, path, char __user *, buf, int, bufsiz);
+COMPAT_SYSCALL_WRAP1(uselib, const char __user *, library);
+COMPAT_SYSCALL_WRAP2(swapon, const char __user *, specialfile, int, swap_flags);
+COMPAT_SYSCALL_WRAP4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg);
+COMPAT_SYSCALL_WRAP2(munmap, unsigned long, addr, size_t, len);
+COMPAT_SYSCALL_WRAP2(fchmod, unsigned int, fd, umode_t, mode);
+COMPAT_SYSCALL_WRAP2(getpriority, int, which, int, who);
+COMPAT_SYSCALL_WRAP3(setpriority, int, which, int, who, int, niceval);
+COMPAT_SYSCALL_WRAP3(syslog, int, type, char __user *, buf, int, len);
+COMPAT_SYSCALL_WRAP1(swapoff, const char __user *, specialfile);
+COMPAT_SYSCALL_WRAP1(fsync, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(setdomainname, char __user *, name, int, len);
+COMPAT_SYSCALL_WRAP1(newuname, struct new_utsname __user *, name);
+COMPAT_SYSCALL_WRAP3(mprotect, unsigned long, start, size_t, len, unsigned long, prot);
+COMPAT_SYSCALL_WRAP3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs);
+COMPAT_SYSCALL_WRAP2(delete_module, const char __user *, name_user, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(quotactl, unsigned int, cmd, const char __user *, special, qid_t, id, void __user *, addr);
+COMPAT_SYSCALL_WRAP1(getpgid, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(fchdir, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(bdflush, int, func, long, data);
+COMPAT_SYSCALL_WRAP3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2);
+COMPAT_SYSCALL_WRAP1(s390_personality, unsigned int, personality);
+COMPAT_SYSCALL_WRAP5(llseek, unsigned int, fd, unsigned long, high, unsigned long, low, loff_t __user *, result, unsigned int, whence);
+COMPAT_SYSCALL_WRAP2(flock, unsigned int, fd, unsigned int, cmd);
+COMPAT_SYSCALL_WRAP3(msync, unsigned long, start, size_t, len, int, flags);
+COMPAT_SYSCALL_WRAP1(getsid, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(fdatasync, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(mlock, unsigned long, start, size_t, len);
+COMPAT_SYSCALL_WRAP2(munlock, unsigned long, start, size_t, len);
+COMPAT_SYSCALL_WRAP1(mlockall, int, flags);
+COMPAT_SYSCALL_WRAP2(sched_setparam, pid_t, pid, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP2(sched_getparam, pid_t, pid, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP1(sched_getscheduler, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(sched_get_priority_max, int, policy);
+COMPAT_SYSCALL_WRAP1(sched_get_priority_min, int, policy);
+COMPAT_SYSCALL_WRAP5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long, new_len, unsigned long, flags, unsigned long, new_addr);
+COMPAT_SYSCALL_WRAP3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout);
+COMPAT_SYSCALL_WRAP5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5);
+COMPAT_SYSCALL_WRAP2(getcwd, char __user *, buf, unsigned long, size);
+COMPAT_SYSCALL_WRAP2(capget, cap_user_header_t, header, cap_user_data_t, dataptr);
+COMPAT_SYSCALL_WRAP2(capset, cap_user_header_t, header, const cap_user_data_t, data);
+COMPAT_SYSCALL_WRAP3(lchown, const char __user *, filename, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP2(setreuid, uid_t, ruid, uid_t, euid);
+COMPAT_SYSCALL_WRAP2(setregid, gid_t, rgid, gid_t, egid);
+COMPAT_SYSCALL_WRAP2(getgroups, int, gidsetsize, gid_t __user *, grouplist);
+COMPAT_SYSCALL_WRAP2(setgroups, int, gidsetsize, gid_t __user *, grouplist);
+COMPAT_SYSCALL_WRAP3(fchown, unsigned int, fd, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid);
+COMPAT_SYSCALL_WRAP3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid);
+COMPAT_SYSCALL_WRAP3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid);
+COMPAT_SYSCALL_WRAP3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid);
+COMPAT_SYSCALL_WRAP3(chown, const char __user *, filename, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP1(setuid, uid_t, uid);
+COMPAT_SYSCALL_WRAP1(setgid, gid_t, gid);
+COMPAT_SYSCALL_WRAP1(setfsuid, uid_t, uid);
+COMPAT_SYSCALL_WRAP1(setfsgid, gid_t, gid);
+COMPAT_SYSCALL_WRAP2(pivot_root, const char __user *, new_root, const char __user *, put_old);
+COMPAT_SYSCALL_WRAP3(mincore, unsigned long, start, size_t, len, unsigned char __user *, vec);
+COMPAT_SYSCALL_WRAP3(madvise, unsigned long, start, size_t, len, int, behavior);
+COMPAT_SYSCALL_WRAP5(setxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP5(lsetxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP5(fsetxattr, int, fd, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP3(getdents64, unsigned int, fd, struct linux_dirent64 __user *, dirent, unsigned int, count);
+COMPAT_SYSCALL_WRAP4(getxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP4(lgetxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP3(listxattr, const char __user *, path, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP3(llistxattr, const char __user *, path, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP3(flistxattr, int, fd, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP2(removexattr, const char __user *, path, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(lremovexattr, const char __user *, path, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(fremovexattr, int, fd, const char __user *, name);
+COMPAT_SYSCALL_WRAP1(exit_group, int, error_code);
+COMPAT_SYSCALL_WRAP1(set_tid_address, int __user *, tidptr);
+COMPAT_SYSCALL_WRAP1(epoll_create, int, size);
+COMPAT_SYSCALL_WRAP4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event);
+COMPAT_SYSCALL_WRAP4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout);
+COMPAT_SYSCALL_WRAP1(timer_getoverrun, timer_t, timer_id);
+COMPAT_SYSCALL_WRAP1(timer_delete, compat_timer_t, compat_timer_id);
+COMPAT_SYSCALL_WRAP1(io_destroy, aio_context_t, ctx);
+COMPAT_SYSCALL_WRAP3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result);
+COMPAT_SYSCALL_WRAP1(mq_unlink, const char __user *, name);
+COMPAT_SYSCALL_WRAP5(add_key, const char __user *, tp, const char __user *, dsc, const void __user *, pld, size_t, len, key_serial_t, id);
+COMPAT_SYSCALL_WRAP4(request_key, const char __user *, tp, const char __user *, dsc, const char __user *, info, key_serial_t, id);
+COMPAT_SYSCALL_WRAP5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags);
+COMPAT_SYSCALL_WRAP3(ioprio_set, int, which, int, who, int, ioprio);
+COMPAT_SYSCALL_WRAP2(ioprio_get, int, which, int, who);
+COMPAT_SYSCALL_WRAP3(inotify_add_watch, int, fd, const char __user *, path, u32, mask);
+COMPAT_SYSCALL_WRAP2(inotify_rm_watch, int, fd, __s32, wd);
+COMPAT_SYSCALL_WRAP3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned, dev);
+COMPAT_SYSCALL_WRAP5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag);
+COMPAT_SYSCALL_WRAP3(unlinkat, int, dfd, const char __user *, pathname, int, flag);
+COMPAT_SYSCALL_WRAP4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname);
+COMPAT_SYSCALL_WRAP5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags);
+COMPAT_SYSCALL_WRAP3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname);
+COMPAT_SYSCALL_WRAP4(readlinkat, int, dfd, const char __user *, path, char __user *, buf, int, bufsiz);
+COMPAT_SYSCALL_WRAP3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode);
+COMPAT_SYSCALL_WRAP3(faccessat, int, dfd, const char __user *, filename, int, mode);
+COMPAT_SYSCALL_WRAP1(unshare, unsigned long, unshare_flags);
+COMPAT_SYSCALL_WRAP6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP3(getcpu, unsigned __user *, cpu, unsigned __user *, node, struct getcpu_cache __user *, cache);
+COMPAT_SYSCALL_WRAP1(eventfd, unsigned int, count);
+COMPAT_SYSCALL_WRAP2(timerfd_create, int, clockid, int, flags);
+COMPAT_SYSCALL_WRAP2(eventfd2, unsigned int, count, int, flags);
+COMPAT_SYSCALL_WRAP1(inotify_init1, int, flags);
+COMPAT_SYSCALL_WRAP2(pipe2, int __user *, fildes, int, flags);
+COMPAT_SYSCALL_WRAP3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags);
+COMPAT_SYSCALL_WRAP1(epoll_create1, int, flags);
+COMPAT_SYSCALL_WRAP2(tkill, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP3(tgkill, int, tgid, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP5(perf_event_open, struct perf_event_attr __user *, attr_uptr, pid_t, pid, int, cpu, int, group_fd, unsigned long, flags);
+COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, int, tls_val);
+COMPAT_SYSCALL_WRAP2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags);
+COMPAT_SYSCALL_WRAP4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim);
+COMPAT_SYSCALL_WRAP5(name_to_handle_at, int, dfd, const char __user *, name, struct file_handle __user *, handle, int __user *, mnt_id, int, flag);
+COMPAT_SYSCALL_WRAP1(syncfs, int, fd);
+COMPAT_SYSCALL_WRAP2(setns, int, fd, int, nstype);
+COMPAT_SYSCALL_WRAP2(s390_runtime_instr, int, command, int, signum);
+COMPAT_SYSCALL_WRAP5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, idx1, unsigned long, idx2);
+COMPAT_SYSCALL_WRAP3(finit_module, int, fd, const char __user *, uargs, int, flags);
+COMPAT_SYSCALL_WRAP3(sched_setattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(sched_getattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, size, unsigned int, flags);
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index fca20b5..6b59443 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -380,8 +380,6 @@
 		S390_lowcore.machine_flags |= MACHINE_FLAG_EDAT2;
 	if (test_facility(3))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE;
-	if (test_facility(27))
-		S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS;
 	if (test_facility(40))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_LPP;
 	if (test_facility(50) && test_facility(73))
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 0dc2b6d..526d373 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -43,6 +43,7 @@
 		 _TIF_MCCK_PENDING)
 _TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		 _TIF_SYSCALL_TRACEPOINT)
+_TIF_TRANSFER = (_TIF_MCCK_PENDING | _TIF_TLB_WAIT)
 
 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
 STACK_SIZE  = 1 << STACK_SHIFT
@@ -159,10 +160,12 @@
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	mvc	__LC_CURRENT_PID(4,%r0),__TASK_pid(%r3)	# store pid of next
 	l	%r15,__THREAD_ksp(%r3)		# load kernel stack of next
-	tm	__TI_flags+3(%r4),_TIF_MCCK_PENDING # machine check pending?
+	lhi	%r6,_TIF_TRANSFER		# transfer TIF bits
+	n	%r6,__TI_flags(%r4)		# isolate TIF bits
 	jz	0f
-	ni	__TI_flags+3(%r4),255-_TIF_MCCK_PENDING	# clear flag in prev
-	oi	__TI_flags+3(%r5),_TIF_MCCK_PENDING	# set it in next
+	o	%r6,__TI_flags(%r5)		# set TIF bits of next
+	st	%r6,__TI_flags(%r5)
+	ni	__TI_flags+3(%r4),255-_TIF_TRANSFER # clear TIF bits of prev
 0:	lm	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	br	%r14
 
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index cb533f7..6ac7819 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -67,9 +67,7 @@
 struct fadvise64_64_args;
 struct old_sigaction;
 
-long sys_sigreturn(void);
-long sys_rt_sigreturn(void);
-long sys32_sigreturn(void);
-long sys32_rt_sigreturn(void);
+long sys_s390_personality(unsigned int personality);
+long sys_s390_runtime_instr(int command, int signum);
 
 #endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 384e609..e09dbe5 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -48,6 +48,7 @@
 		 _TIF_MCCK_PENDING)
 _TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		 _TIF_SYSCALL_TRACEPOINT)
+_TIF_TRANSFER = (_TIF_MCCK_PENDING | _TIF_TLB_WAIT)
 
 #define BASED(name) name-system_call(%r13)
 
@@ -189,10 +190,12 @@
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	mvc	__LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next
 	lg	%r15,__THREAD_ksp(%r3)		# load kernel stack of next
-	tm	__TI_flags+7(%r4),_TIF_MCCK_PENDING # machine check pending?
+	llill	%r6,_TIF_TRANSFER		# transfer TIF bits
+	ng	%r6,__TI_flags(%r4)		# isolate TIF bits
 	jz	0f
-	ni	__TI_flags+7(%r4),255-_TIF_MCCK_PENDING	# clear flag in prev
-	oi	__TI_flags+7(%r5),_TIF_MCCK_PENDING	# set it in next
+	og	%r6,__TI_flags(%r5)		# set TIF bits of next
+	stg	%r6,__TI_flags(%r5)
+	ni	__TI_flags+7(%r4),255-_TIF_TRANSFER # clear TIF bits of prev
 0:	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	br	%r14
 
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index b9e25ae..d7c0050 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -59,7 +59,7 @@
 	.quad	0			# cr12: tracing off
 	.quad	0			# cr13: home space segment table
 	.quad	0xc0000000		# cr14: machine check handling off
-	.quad	0			# cr15: linkage stack operations
+	.quad	.Llinkage_stack		# cr15: linkage stack operations
 .Lpcmsk:.quad	0x0000000180000000
 .L4malign:.quad 0xffffffffffc00000
 .Lscan2g:.quad	0x80000000 + 0x20000 - 8	# 2GB + 128K - 8
@@ -67,12 +67,15 @@
 .Lparmaddr:
 	.quad	PARMAREA
 	.align	64
-.Lduct: .long	0,0,0,0,.Lduald,0,0,0
+.Lduct: .long	0,.Laste,.Laste,0,.Lduald,0,0,0
 	.long	0,0,0,0,0,0,0,0
+.Laste:	.quad	0,0xffffffffffffffff,0,0,0,0,0,0
 	.align	128
 .Lduald:.rept	8
 	.long	0x80000000,0,0,0	# invalid access-list entries
 	.endr
+.Llinkage_stack:
+	.long	0,0,0x89000000,0,0,0,0x8a000000,0
 
 ENTRY(_ehead)
 
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 5d2dfa3..61595c1 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -121,7 +121,7 @@
 			       : PERF_RECORD_MISC_KERNEL;
 }
 
-void print_debug_cf(void)
+static void print_debug_cf(void)
 {
 	struct cpumf_ctr_info cf_info;
 	int cpu = smp_processor_id();
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index f6be608..4ac8faf 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -85,7 +85,10 @@
 
 	/* merge TIF_SINGLE_STEP into user specified PER registers. */
 	if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) {
-		new.control |= PER_EVENT_IFETCH;
+		if (test_tsk_thread_flag(task, TIF_BLOCK_STEP))
+			new.control |= PER_EVENT_BRANCH;
+		else
+			new.control |= PER_EVENT_IFETCH;
 #ifdef CONFIG_64BIT
 		new.control |= PER_CONTROL_SUSPENSION;
 		new.control |= PER_EVENT_TRANSACTION_END;
@@ -107,14 +110,22 @@
 
 void user_enable_single_step(struct task_struct *task)
 {
+	clear_tsk_thread_flag(task, TIF_BLOCK_STEP);
 	set_tsk_thread_flag(task, TIF_SINGLE_STEP);
 }
 
 void user_disable_single_step(struct task_struct *task)
 {
+	clear_tsk_thread_flag(task, TIF_BLOCK_STEP);
 	clear_tsk_thread_flag(task, TIF_SINGLE_STEP);
 }
 
+void user_enable_block_step(struct task_struct *task)
+{
+	set_tsk_thread_flag(task, TIF_SINGLE_STEP);
+	set_tsk_thread_flag(task, TIF_BLOCK_STEP);
+}
+
 /*
  * Called by kernel/ptrace.c when detaching..
  *
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 09e2f46..f70f248 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -47,7 +47,6 @@
 #include <linux/compat.h>
 
 #include <asm/ipl.h>
-#include <asm/uaccess.h>
 #include <asm/facility.h>
 #include <asm/smp.h>
 #include <asm/mmu_context.h>
@@ -65,12 +64,6 @@
 #include "entry.h"
 
 /*
- * User copy operations.
- */
-struct uaccess_ops uaccess;
-EXPORT_SYMBOL(uaccess);
-
-/*
  * Machine setup..
  */
 unsigned int console_mode = 0;
@@ -294,14 +287,6 @@
 }
 early_param("vmalloc", parse_vmalloc);
 
-static int __init early_parse_user_mode(char *p)
-{
-	if (!p || strcmp(p, "primary") == 0)
-		return 0;
-	return 1;
-}
-early_param("user_mode", early_parse_user_mode);
-
 void *restart_stack __attribute__((__section__(".data")));
 
 static void __init setup_lowcore(void)
@@ -1009,8 +994,6 @@
 	init_mm.end_data = (unsigned long) &_edata;
 	init_mm.brk = (unsigned long) &_end;
 
-	uaccess = MACHINE_HAS_MVCOS ? uaccess_mvcos : uaccess_pt;
-
 	parse_early_param();
 	detect_memory_layout(memory_chunk, memory_end);
 	os_info_init();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index a7125b6..8827883 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -773,11 +773,11 @@
 
 void __init smp_fill_possible_mask(void)
 {
-	unsigned int possible, cpu;
+	unsigned int possible, sclp, cpu;
 
-	possible = setup_possible_cpus;
-	if (!possible)
-		possible = MACHINE_IS_VM ? 64 : nr_cpu_ids;
+	sclp = sclp_get_max_cpu() ?: nr_cpu_ids;
+	possible = setup_possible_cpus ?: nr_cpu_ids;
+	possible = min(possible, sclp);
 	for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++)
 		set_cpu_possible(cpu, true);
 }
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 1439921..542ef48 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -9,349 +9,349 @@
 #define NI_SYSCALL SYSCALL(sys_ni_syscall,sys_ni_syscall,sys_ni_syscall)
 
 NI_SYSCALL							/* 0 */
-SYSCALL(sys_exit,sys_exit,sys32_exit_wrapper)
+SYSCALL(sys_exit,sys_exit,compat_sys_exit)
 SYSCALL(sys_fork,sys_fork,sys_fork)
-SYSCALL(sys_read,sys_read,sys32_read_wrapper)
-SYSCALL(sys_write,sys_write,sys32_write_wrapper)
+SYSCALL(sys_read,sys_read,compat_sys_s390_read)
+SYSCALL(sys_write,sys_write,compat_sys_s390_write)
 SYSCALL(sys_open,sys_open,compat_sys_open)			/* 5 */
-SYSCALL(sys_close,sys_close,sys32_close_wrapper)
+SYSCALL(sys_close,sys_close,compat_sys_close)
 SYSCALL(sys_restart_syscall,sys_restart_syscall,sys_restart_syscall)
-SYSCALL(sys_creat,sys_creat,sys32_creat_wrapper)
-SYSCALL(sys_link,sys_link,sys32_link_wrapper)
-SYSCALL(sys_unlink,sys_unlink,sys32_unlink_wrapper)		/* 10 */
-SYSCALL(sys_execve,sys_execve,sys32_execve_wrapper)
-SYSCALL(sys_chdir,sys_chdir,sys32_chdir_wrapper)
-SYSCALL(sys_time,sys_ni_syscall,sys32_time_wrapper)		/* old time syscall */
-SYSCALL(sys_mknod,sys_mknod,sys32_mknod_wrapper)
-SYSCALL(sys_chmod,sys_chmod,sys32_chmod_wrapper)		/* 15 */
-SYSCALL(sys_lchown16,sys_ni_syscall,sys32_lchown16_wrapper)	/* old lchown16 syscall*/
+SYSCALL(sys_creat,sys_creat,compat_sys_creat)
+SYSCALL(sys_link,sys_link,compat_sys_link)
+SYSCALL(sys_unlink,sys_unlink,compat_sys_unlink)		/* 10 */
+SYSCALL(sys_execve,sys_execve,compat_sys_execve)
+SYSCALL(sys_chdir,sys_chdir,compat_sys_chdir)
+SYSCALL(sys_time,sys_ni_syscall,compat_sys_time)		/* old time syscall */
+SYSCALL(sys_mknod,sys_mknod,compat_sys_mknod)
+SYSCALL(sys_chmod,sys_chmod,compat_sys_chmod)			/* 15 */
+SYSCALL(sys_lchown16,sys_ni_syscall,compat_sys_s390_lchown16)	/* old lchown16 syscall*/
 NI_SYSCALL							/* old break syscall holder */
 NI_SYSCALL							/* old stat syscall holder */
 SYSCALL(sys_lseek,sys_lseek,compat_sys_lseek)
 SYSCALL(sys_getpid,sys_getpid,sys_getpid)			/* 20 */
-SYSCALL(sys_mount,sys_mount,sys32_mount_wrapper)
-SYSCALL(sys_oldumount,sys_oldumount,sys32_oldumount_wrapper)
-SYSCALL(sys_setuid16,sys_ni_syscall,sys32_setuid16_wrapper)	/* old setuid16 syscall*/
-SYSCALL(sys_getuid16,sys_ni_syscall,sys32_getuid16)		/* old getuid16 syscall*/
-SYSCALL(sys_stime,sys_ni_syscall,sys32_stime_wrapper)		/* 25 old stime syscall */
-SYSCALL(sys_ptrace,sys_ptrace,sys32_ptrace_wrapper)
-SYSCALL(sys_alarm,sys_alarm,sys32_alarm_wrapper)
+SYSCALL(sys_mount,sys_mount,compat_sys_mount)
+SYSCALL(sys_oldumount,sys_oldumount,compat_sys_oldumount)
+SYSCALL(sys_setuid16,sys_ni_syscall,compat_sys_s390_setuid16)	/* old setuid16 syscall*/
+SYSCALL(sys_getuid16,sys_ni_syscall,compat_sys_s390_getuid16)	/* old getuid16 syscall*/
+SYSCALL(sys_stime,sys_ni_syscall,compat_sys_stime)		/* 25 old stime syscall */
+SYSCALL(sys_ptrace,sys_ptrace,compat_sys_ptrace)
+SYSCALL(sys_alarm,sys_alarm,compat_sys_alarm)
 NI_SYSCALL							/* old fstat syscall */
 SYSCALL(sys_pause,sys_pause,sys_pause)
-SYSCALL(sys_utime,sys_utime,compat_sys_utime_wrapper)		/* 30 */
+SYSCALL(sys_utime,sys_utime,compat_sys_utime)		/* 30 */
 NI_SYSCALL							/* old stty syscall */
 NI_SYSCALL							/* old gtty syscall */
-SYSCALL(sys_access,sys_access,sys32_access_wrapper)
-SYSCALL(sys_nice,sys_nice,sys32_nice_wrapper)
+SYSCALL(sys_access,sys_access,compat_sys_access)
+SYSCALL(sys_nice,sys_nice,compat_sys_nice)
 NI_SYSCALL							/* 35 old ftime syscall */
 SYSCALL(sys_sync,sys_sync,sys_sync)
-SYSCALL(sys_kill,sys_kill,sys32_kill_wrapper)
-SYSCALL(sys_rename,sys_rename,sys32_rename_wrapper)
-SYSCALL(sys_mkdir,sys_mkdir,sys32_mkdir_wrapper)
-SYSCALL(sys_rmdir,sys_rmdir,sys32_rmdir_wrapper)		/* 40 */
-SYSCALL(sys_dup,sys_dup,sys32_dup_wrapper)
-SYSCALL(sys_pipe,sys_pipe,sys32_pipe_wrapper)
-SYSCALL(sys_times,sys_times,compat_sys_times_wrapper)
+SYSCALL(sys_kill,sys_kill,compat_sys_kill)
+SYSCALL(sys_rename,sys_rename,compat_sys_rename)
+SYSCALL(sys_mkdir,sys_mkdir,compat_sys_mkdir)
+SYSCALL(sys_rmdir,sys_rmdir,compat_sys_rmdir)		/* 40 */
+SYSCALL(sys_dup,sys_dup,compat_sys_dup)
+SYSCALL(sys_pipe,sys_pipe,compat_sys_pipe)
+SYSCALL(sys_times,sys_times,compat_sys_times)
 NI_SYSCALL							/* old prof syscall */
-SYSCALL(sys_brk,sys_brk,sys32_brk_wrapper)			/* 45 */
-SYSCALL(sys_setgid16,sys_ni_syscall,sys32_setgid16_wrapper)	/* old setgid16 syscall*/
-SYSCALL(sys_getgid16,sys_ni_syscall,sys32_getgid16)		/* old getgid16 syscall*/
-SYSCALL(sys_signal,sys_signal,sys32_signal_wrapper)
-SYSCALL(sys_geteuid16,sys_ni_syscall,sys32_geteuid16)		/* old geteuid16 syscall */
-SYSCALL(sys_getegid16,sys_ni_syscall,sys32_getegid16)		/* 50 old getegid16 syscall */
-SYSCALL(sys_acct,sys_acct,sys32_acct_wrapper)
-SYSCALL(sys_umount,sys_umount,sys32_umount_wrapper)
+SYSCALL(sys_brk,sys_brk,compat_sys_brk)				/* 45 */
+SYSCALL(sys_setgid16,sys_ni_syscall,compat_sys_s390_setgid16)	/* old setgid16 syscall*/
+SYSCALL(sys_getgid16,sys_ni_syscall,compat_sys_s390_getgid16)	/* old getgid16 syscall*/
+SYSCALL(sys_signal,sys_signal,compat_sys_signal)
+SYSCALL(sys_geteuid16,sys_ni_syscall,compat_sys_s390_geteuid16)	/* old geteuid16 syscall */
+SYSCALL(sys_getegid16,sys_ni_syscall,compat_sys_s390_getegid16)	/* 50 old getegid16 syscall */
+SYSCALL(sys_acct,sys_acct,compat_sys_acct)
+SYSCALL(sys_umount,sys_umount,compat_sys_umount)
 NI_SYSCALL							/* old lock syscall */
-SYSCALL(sys_ioctl,sys_ioctl,compat_sys_ioctl_wrapper)
-SYSCALL(sys_fcntl,sys_fcntl,compat_sys_fcntl_wrapper)		/* 55 */
+SYSCALL(sys_ioctl,sys_ioctl,compat_sys_ioctl)
+SYSCALL(sys_fcntl,sys_fcntl,compat_sys_fcntl)		/* 55 */
 NI_SYSCALL							/* intel mpx syscall */
-SYSCALL(sys_setpgid,sys_setpgid,sys32_setpgid_wrapper)
+SYSCALL(sys_setpgid,sys_setpgid,compat_sys_setpgid)
 NI_SYSCALL							/* old ulimit syscall */
 NI_SYSCALL							/* old uname syscall */
-SYSCALL(sys_umask,sys_umask,sys32_umask_wrapper)		/* 60 */
-SYSCALL(sys_chroot,sys_chroot,sys32_chroot_wrapper)
-SYSCALL(sys_ustat,sys_ustat,sys32_ustat_wrapper)
-SYSCALL(sys_dup2,sys_dup2,sys32_dup2_wrapper)
+SYSCALL(sys_umask,sys_umask,compat_sys_umask)			/* 60 */
+SYSCALL(sys_chroot,sys_chroot,compat_sys_chroot)
+SYSCALL(sys_ustat,sys_ustat,compat_sys_ustat)
+SYSCALL(sys_dup2,sys_dup2,compat_sys_dup2)
 SYSCALL(sys_getppid,sys_getppid,sys_getppid)
 SYSCALL(sys_getpgrp,sys_getpgrp,sys_getpgrp)			/* 65 */
 SYSCALL(sys_setsid,sys_setsid,sys_setsid)
 SYSCALL(sys_sigaction,sys_sigaction,compat_sys_sigaction)
 NI_SYSCALL							/* old sgetmask syscall*/
 NI_SYSCALL							/* old ssetmask syscall*/
-SYSCALL(sys_setreuid16,sys_ni_syscall,sys32_setreuid16_wrapper)	/* old setreuid16 syscall */
-SYSCALL(sys_setregid16,sys_ni_syscall,sys32_setregid16_wrapper)	/* old setregid16 syscall */
-SYSCALL(sys_sigsuspend,sys_sigsuspend,sys_sigsuspend_wrapper)
-SYSCALL(sys_sigpending,sys_sigpending,compat_sys_sigpending_wrapper)
-SYSCALL(sys_sethostname,sys_sethostname,sys32_sethostname_wrapper)
-SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit_wrapper)	/* 75 */
-SYSCALL(sys_old_getrlimit,sys_getrlimit,compat_sys_old_getrlimit_wrapper)
+SYSCALL(sys_setreuid16,sys_ni_syscall,compat_sys_s390_setreuid16) /* old setreuid16 syscall */
+SYSCALL(sys_setregid16,sys_ni_syscall,compat_sys_s390_setregid16) /* old setregid16 syscall */
+SYSCALL(sys_sigsuspend,sys_sigsuspend,compat_sys_sigsuspend)
+SYSCALL(sys_sigpending,sys_sigpending,compat_sys_sigpending)
+SYSCALL(sys_sethostname,sys_sethostname,compat_sys_sethostname)
+SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit)	/* 75 */
+SYSCALL(sys_old_getrlimit,sys_getrlimit,compat_sys_old_getrlimit)
 SYSCALL(sys_getrusage,sys_getrusage,compat_sys_getrusage)
-SYSCALL(sys_gettimeofday,sys_gettimeofday,compat_sys_gettimeofday_wrapper)
-SYSCALL(sys_settimeofday,sys_settimeofday,compat_sys_settimeofday_wrapper)
-SYSCALL(sys_getgroups16,sys_ni_syscall,sys32_getgroups16_wrapper)	/* 80 old getgroups16 syscall */
-SYSCALL(sys_setgroups16,sys_ni_syscall,sys32_setgroups16_wrapper)	/* old setgroups16 syscall */
+SYSCALL(sys_gettimeofday,sys_gettimeofday,compat_sys_gettimeofday)
+SYSCALL(sys_settimeofday,sys_settimeofday,compat_sys_settimeofday)
+SYSCALL(sys_getgroups16,sys_ni_syscall,compat_sys_s390_getgroups16)	/* 80 old getgroups16 syscall */
+SYSCALL(sys_setgroups16,sys_ni_syscall,compat_sys_s390_setgroups16)	/* old setgroups16 syscall */
 NI_SYSCALL							/* old select syscall */
-SYSCALL(sys_symlink,sys_symlink,sys32_symlink_wrapper)
+SYSCALL(sys_symlink,sys_symlink,compat_sys_symlink)
 NI_SYSCALL							/* old lstat syscall */
-SYSCALL(sys_readlink,sys_readlink,sys32_readlink_wrapper)	/* 85 */
-SYSCALL(sys_uselib,sys_uselib,sys32_uselib_wrapper)
-SYSCALL(sys_swapon,sys_swapon,sys32_swapon_wrapper)
-SYSCALL(sys_reboot,sys_reboot,sys32_reboot_wrapper)
-SYSCALL(sys_ni_syscall,sys_ni_syscall,old32_readdir_wrapper)	/* old readdir syscall */
-SYSCALL(sys_old_mmap,sys_old_mmap,old32_mmap_wrapper)		/* 90 */
-SYSCALL(sys_munmap,sys_munmap,sys32_munmap_wrapper)
+SYSCALL(sys_readlink,sys_readlink,compat_sys_readlink)		/* 85 */
+SYSCALL(sys_uselib,sys_uselib,compat_sys_uselib)
+SYSCALL(sys_swapon,sys_swapon,compat_sys_swapon)
+SYSCALL(sys_reboot,sys_reboot,compat_sys_reboot)
+SYSCALL(sys_ni_syscall,sys_ni_syscall,compat_sys_old_readdir)	/* old readdir syscall */
+SYSCALL(sys_old_mmap,sys_old_mmap,compat_sys_s390_old_mmap)	/* 90 */
+SYSCALL(sys_munmap,sys_munmap,compat_sys_munmap)
 SYSCALL(sys_truncate,sys_truncate,compat_sys_truncate)
 SYSCALL(sys_ftruncate,sys_ftruncate,compat_sys_ftruncate)
-SYSCALL(sys_fchmod,sys_fchmod,sys32_fchmod_wrapper)
-SYSCALL(sys_fchown16,sys_ni_syscall,sys32_fchown16_wrapper)	/* 95 old fchown16 syscall*/
-SYSCALL(sys_getpriority,sys_getpriority,sys32_getpriority_wrapper)
-SYSCALL(sys_setpriority,sys_setpriority,sys32_setpriority_wrapper)
+SYSCALL(sys_fchmod,sys_fchmod,compat_sys_fchmod)
+SYSCALL(sys_fchown16,sys_ni_syscall,compat_sys_s390_fchown16)	/* 95 old fchown16 syscall*/
+SYSCALL(sys_getpriority,sys_getpriority,compat_sys_getpriority)
+SYSCALL(sys_setpriority,sys_setpriority,compat_sys_setpriority)
 NI_SYSCALL							/* old profil syscall */
-SYSCALL(sys_statfs,sys_statfs,compat_sys_statfs_wrapper)
-SYSCALL(sys_fstatfs,sys_fstatfs,compat_sys_fstatfs_wrapper)	/* 100 */
+SYSCALL(sys_statfs,sys_statfs,compat_sys_statfs)
+SYSCALL(sys_fstatfs,sys_fstatfs,compat_sys_fstatfs)	/* 100 */
 NI_SYSCALL							/* ioperm for i386 */
-SYSCALL(sys_socketcall,sys_socketcall,compat_sys_socketcall_wrapper)
-SYSCALL(sys_syslog,sys_syslog,sys32_syslog_wrapper)
+SYSCALL(sys_socketcall,sys_socketcall,compat_sys_socketcall)
+SYSCALL(sys_syslog,sys_syslog,compat_sys_syslog)
 SYSCALL(sys_setitimer,sys_setitimer,compat_sys_setitimer)
 SYSCALL(sys_getitimer,sys_getitimer,compat_sys_getitimer)	/* 105 */
-SYSCALL(sys_newstat,sys_newstat,compat_sys_newstat_wrapper)
-SYSCALL(sys_newlstat,sys_newlstat,compat_sys_newlstat_wrapper)
-SYSCALL(sys_newfstat,sys_newfstat,compat_sys_newfstat_wrapper)
+SYSCALL(sys_newstat,sys_newstat,compat_sys_newstat)
+SYSCALL(sys_newlstat,sys_newlstat,compat_sys_newlstat)
+SYSCALL(sys_newfstat,sys_newfstat,compat_sys_newfstat)
 NI_SYSCALL							/* old uname syscall */
 SYSCALL(sys_lookup_dcookie,sys_lookup_dcookie,compat_sys_lookup_dcookie)	/* 110 */
 SYSCALL(sys_vhangup,sys_vhangup,sys_vhangup)
 NI_SYSCALL							/* old "idle" system call */
 NI_SYSCALL							/* vm86old for i386 */
 SYSCALL(sys_wait4,sys_wait4,compat_sys_wait4)
-SYSCALL(sys_swapoff,sys_swapoff,sys32_swapoff_wrapper)		/* 115 */
-SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper)
+SYSCALL(sys_swapoff,sys_swapoff,compat_sys_swapoff)		/* 115 */
+SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo)
 SYSCALL(sys_s390_ipc,sys_s390_ipc,compat_sys_s390_ipc)
-SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper)
-SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn)
-SYSCALL(sys_clone,sys_clone,sys_clone_wrapper)			/* 120 */
-SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper)
-SYSCALL(sys_newuname,sys_newuname,sys32_newuname_wrapper)
+SYSCALL(sys_fsync,sys_fsync,compat_sys_fsync)
+SYSCALL(sys_sigreturn,sys_sigreturn,compat_sys_sigreturn)
+SYSCALL(sys_clone,sys_clone,compat_sys_clone)			/* 120 */
+SYSCALL(sys_setdomainname,sys_setdomainname,compat_sys_setdomainname)
+SYSCALL(sys_newuname,sys_newuname,compat_sys_newuname)
 NI_SYSCALL							/* modify_ldt for i386 */
-SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper)
-SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper)	/* 125 */
+SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex)
+SYSCALL(sys_mprotect,sys_mprotect,compat_sys_mprotect)		/* 125 */
 SYSCALL(sys_sigprocmask,sys_sigprocmask,compat_sys_sigprocmask)
 NI_SYSCALL							/* old "create module" */
-SYSCALL(sys_init_module,sys_init_module,sys_init_module_wrapper)
-SYSCALL(sys_delete_module,sys_delete_module,sys_delete_module_wrapper)
+SYSCALL(sys_init_module,sys_init_module,compat_sys_init_module)
+SYSCALL(sys_delete_module,sys_delete_module,compat_sys_delete_module)
 NI_SYSCALL							/* 130: old get_kernel_syms */
-SYSCALL(sys_quotactl,sys_quotactl,sys32_quotactl_wrapper)
-SYSCALL(sys_getpgid,sys_getpgid,sys32_getpgid_wrapper)
-SYSCALL(sys_fchdir,sys_fchdir,sys32_fchdir_wrapper)
-SYSCALL(sys_bdflush,sys_bdflush,sys32_bdflush_wrapper)
-SYSCALL(sys_sysfs,sys_sysfs,sys32_sysfs_wrapper)		/* 135 */
-SYSCALL(sys_personality,sys_s390_personality,sys32_personality_wrapper)
+SYSCALL(sys_quotactl,sys_quotactl,compat_sys_quotactl)
+SYSCALL(sys_getpgid,sys_getpgid,compat_sys_getpgid)
+SYSCALL(sys_fchdir,sys_fchdir,compat_sys_fchdir)
+SYSCALL(sys_bdflush,sys_bdflush,compat_sys_bdflush)
+SYSCALL(sys_sysfs,sys_sysfs,compat_sys_sysfs)		/* 135 */
+SYSCALL(sys_personality,sys_s390_personality,compat_sys_s390_personality)
 NI_SYSCALL							/* for afs_syscall */
-SYSCALL(sys_setfsuid16,sys_ni_syscall,sys32_setfsuid16_wrapper)	/* old setfsuid16 syscall */
-SYSCALL(sys_setfsgid16,sys_ni_syscall,sys32_setfsgid16_wrapper)	/* old setfsgid16 syscall */
-SYSCALL(sys_llseek,sys_llseek,sys32_llseek_wrapper)		/* 140 */
-SYSCALL(sys_getdents,sys_getdents,sys32_getdents_wrapper)
-SYSCALL(sys_select,sys_select,compat_sys_select_wrapper)
-SYSCALL(sys_flock,sys_flock,sys32_flock_wrapper)
-SYSCALL(sys_msync,sys_msync,sys32_msync_wrapper)
-SYSCALL(sys_readv,sys_readv,compat_sys_readv_wrapper)		/* 145 */
-SYSCALL(sys_writev,sys_writev,compat_sys_writev_wrapper)
-SYSCALL(sys_getsid,sys_getsid,sys32_getsid_wrapper)
-SYSCALL(sys_fdatasync,sys_fdatasync,sys32_fdatasync_wrapper)
+SYSCALL(sys_setfsuid16,sys_ni_syscall,compat_sys_s390_setfsuid16)	/* old setfsuid16 syscall */
+SYSCALL(sys_setfsgid16,sys_ni_syscall,compat_sys_s390_setfsgid16)	/* old setfsgid16 syscall */
+SYSCALL(sys_llseek,sys_llseek,compat_sys_llseek)		/* 140 */
+SYSCALL(sys_getdents,sys_getdents,compat_sys_getdents)
+SYSCALL(sys_select,sys_select,compat_sys_select)
+SYSCALL(sys_flock,sys_flock,compat_sys_flock)
+SYSCALL(sys_msync,sys_msync,compat_sys_msync)
+SYSCALL(sys_readv,sys_readv,compat_sys_readv)		/* 145 */
+SYSCALL(sys_writev,sys_writev,compat_sys_writev)
+SYSCALL(sys_getsid,sys_getsid,compat_sys_getsid)
+SYSCALL(sys_fdatasync,sys_fdatasync,compat_sys_fdatasync)
 SYSCALL(sys_sysctl,sys_sysctl,compat_sys_sysctl)
-SYSCALL(sys_mlock,sys_mlock,sys32_mlock_wrapper)		/* 150 */
-SYSCALL(sys_munlock,sys_munlock,sys32_munlock_wrapper)
-SYSCALL(sys_mlockall,sys_mlockall,sys32_mlockall_wrapper)
+SYSCALL(sys_mlock,sys_mlock,compat_sys_mlock)			/* 150 */
+SYSCALL(sys_munlock,sys_munlock,compat_sys_munlock)
+SYSCALL(sys_mlockall,sys_mlockall,compat_sys_mlockall)
 SYSCALL(sys_munlockall,sys_munlockall,sys_munlockall)
-SYSCALL(sys_sched_setparam,sys_sched_setparam,sys32_sched_setparam_wrapper)
-SYSCALL(sys_sched_getparam,sys_sched_getparam,sys32_sched_getparam_wrapper)	/* 155 */
-SYSCALL(sys_sched_setscheduler,sys_sched_setscheduler,sys32_sched_setscheduler_wrapper)
-SYSCALL(sys_sched_getscheduler,sys_sched_getscheduler,sys32_sched_getscheduler_wrapper)
+SYSCALL(sys_sched_setparam,sys_sched_setparam,compat_sys_sched_setparam)
+SYSCALL(sys_sched_getparam,sys_sched_getparam,compat_sys_sched_getparam)	/* 155 */
+SYSCALL(sys_sched_setscheduler,sys_sched_setscheduler,compat_sys_sched_setscheduler)
+SYSCALL(sys_sched_getscheduler,sys_sched_getscheduler,compat_sys_sched_getscheduler)
 SYSCALL(sys_sched_yield,sys_sched_yield,sys_sched_yield)
-SYSCALL(sys_sched_get_priority_max,sys_sched_get_priority_max,sys32_sched_get_priority_max_wrapper)
-SYSCALL(sys_sched_get_priority_min,sys_sched_get_priority_min,sys32_sched_get_priority_min_wrapper)	/* 160 */
+SYSCALL(sys_sched_get_priority_max,sys_sched_get_priority_max,compat_sys_sched_get_priority_max)
+SYSCALL(sys_sched_get_priority_min,sys_sched_get_priority_min,compat_sys_sched_get_priority_min)	/* 160 */
 SYSCALL(sys_sched_rr_get_interval,sys_sched_rr_get_interval,compat_sys_sched_rr_get_interval)
-SYSCALL(sys_nanosleep,sys_nanosleep,compat_sys_nanosleep_wrapper)
-SYSCALL(sys_mremap,sys_mremap,sys32_mremap_wrapper)
-SYSCALL(sys_setresuid16,sys_ni_syscall,sys32_setresuid16_wrapper)	/* old setresuid16 syscall */
-SYSCALL(sys_getresuid16,sys_ni_syscall,sys32_getresuid16_wrapper)	/* 165 old getresuid16 syscall */
+SYSCALL(sys_nanosleep,sys_nanosleep,compat_sys_nanosleep)
+SYSCALL(sys_mremap,sys_mremap,compat_sys_mremap)
+SYSCALL(sys_setresuid16,sys_ni_syscall,compat_sys_s390_setresuid16)	/* old setresuid16 syscall */
+SYSCALL(sys_getresuid16,sys_ni_syscall,compat_sys_s390_getresuid16)	/* 165 old getresuid16 syscall */
 NI_SYSCALL							/* for vm86 */
 NI_SYSCALL							/* old sys_query_module */
-SYSCALL(sys_poll,sys_poll,sys32_poll_wrapper)
+SYSCALL(sys_poll,sys_poll,compat_sys_poll)
 NI_SYSCALL							/* old nfsservctl */
-SYSCALL(sys_setresgid16,sys_ni_syscall,sys32_setresgid16_wrapper)	/* 170 old setresgid16 syscall */
-SYSCALL(sys_getresgid16,sys_ni_syscall,sys32_getresgid16_wrapper)	/* old getresgid16 syscall */
-SYSCALL(sys_prctl,sys_prctl,sys32_prctl_wrapper)
-SYSCALL(sys_rt_sigreturn,sys_rt_sigreturn,sys32_rt_sigreturn)
+SYSCALL(sys_setresgid16,sys_ni_syscall,compat_sys_s390_setresgid16)	/* 170 old setresgid16 syscall */
+SYSCALL(sys_getresgid16,sys_ni_syscall,compat_sys_s390_getresgid16)	/* old getresgid16 syscall */
+SYSCALL(sys_prctl,sys_prctl,compat_sys_prctl)
+SYSCALL(sys_rt_sigreturn,sys_rt_sigreturn,compat_sys_rt_sigreturn)
 SYSCALL(sys_rt_sigaction,sys_rt_sigaction,compat_sys_rt_sigaction)
 SYSCALL(sys_rt_sigprocmask,sys_rt_sigprocmask,compat_sys_rt_sigprocmask) /* 175 */
 SYSCALL(sys_rt_sigpending,sys_rt_sigpending,compat_sys_rt_sigpending)
 SYSCALL(sys_rt_sigtimedwait,sys_rt_sigtimedwait,compat_sys_rt_sigtimedwait)
 SYSCALL(sys_rt_sigqueueinfo,sys_rt_sigqueueinfo,compat_sys_rt_sigqueueinfo)
 SYSCALL(sys_rt_sigsuspend,sys_rt_sigsuspend,compat_sys_rt_sigsuspend)
-SYSCALL(sys_pread64,sys_pread64,sys32_pread64_wrapper)		/* 180 */
-SYSCALL(sys_pwrite64,sys_pwrite64,sys32_pwrite64_wrapper)
-SYSCALL(sys_chown16,sys_ni_syscall,sys32_chown16_wrapper)	/* old chown16 syscall */
-SYSCALL(sys_getcwd,sys_getcwd,sys32_getcwd_wrapper)
-SYSCALL(sys_capget,sys_capget,sys32_capget_wrapper)
-SYSCALL(sys_capset,sys_capset,sys32_capset_wrapper)		/* 185 */
+SYSCALL(sys_pread64,sys_pread64,compat_sys_s390_pread64)		/* 180 */
+SYSCALL(sys_pwrite64,sys_pwrite64,compat_sys_s390_pwrite64)
+SYSCALL(sys_chown16,sys_ni_syscall,compat_sys_s390_chown16)	/* old chown16 syscall */
+SYSCALL(sys_getcwd,sys_getcwd,compat_sys_getcwd)
+SYSCALL(sys_capget,sys_capget,compat_sys_capget)
+SYSCALL(sys_capset,sys_capset,compat_sys_capset)		/* 185 */
 SYSCALL(sys_sigaltstack,sys_sigaltstack,compat_sys_sigaltstack)
 SYSCALL(sys_sendfile,sys_sendfile64,compat_sys_sendfile)
 NI_SYSCALL							/* streams1 */
 NI_SYSCALL							/* streams2 */
 SYSCALL(sys_vfork,sys_vfork,sys_vfork)				/* 190 */
-SYSCALL(sys_getrlimit,sys_getrlimit,compat_sys_getrlimit_wrapper)
-SYSCALL(sys_mmap2,sys_mmap2,sys32_mmap2_wrapper)
-SYSCALL(sys_truncate64,sys_ni_syscall,sys32_truncate64_wrapper)
-SYSCALL(sys_ftruncate64,sys_ni_syscall,sys32_ftruncate64_wrapper)
-SYSCALL(sys_stat64,sys_ni_syscall,sys32_stat64_wrapper)		/* 195 */
-SYSCALL(sys_lstat64,sys_ni_syscall,sys32_lstat64_wrapper)
-SYSCALL(sys_fstat64,sys_ni_syscall,sys32_fstat64_wrapper)
-SYSCALL(sys_lchown,sys_lchown,sys32_lchown_wrapper)
+SYSCALL(sys_getrlimit,sys_getrlimit,compat_sys_getrlimit)
+SYSCALL(sys_mmap2,sys_mmap2,compat_sys_s390_mmap2)
+SYSCALL(sys_truncate64,sys_ni_syscall,compat_sys_s390_truncate64)
+SYSCALL(sys_ftruncate64,sys_ni_syscall,compat_sys_s390_ftruncate64)
+SYSCALL(sys_stat64,sys_ni_syscall,compat_sys_s390_stat64)		/* 195 */
+SYSCALL(sys_lstat64,sys_ni_syscall,compat_sys_s390_lstat64)
+SYSCALL(sys_fstat64,sys_ni_syscall,compat_sys_s390_fstat64)
+SYSCALL(sys_lchown,sys_lchown,compat_sys_lchown)
 SYSCALL(sys_getuid,sys_getuid,sys_getuid)
 SYSCALL(sys_getgid,sys_getgid,sys_getgid)			/* 200 */
 SYSCALL(sys_geteuid,sys_geteuid,sys_geteuid)
 SYSCALL(sys_getegid,sys_getegid,sys_getegid)
-SYSCALL(sys_setreuid,sys_setreuid,sys32_setreuid_wrapper)
-SYSCALL(sys_setregid,sys_setregid,sys32_setregid_wrapper)
-SYSCALL(sys_getgroups,sys_getgroups,sys32_getgroups_wrapper)	/* 205 */
-SYSCALL(sys_setgroups,sys_setgroups,sys32_setgroups_wrapper)
-SYSCALL(sys_fchown,sys_fchown,sys32_fchown_wrapper)
-SYSCALL(sys_setresuid,sys_setresuid,sys32_setresuid_wrapper)
-SYSCALL(sys_getresuid,sys_getresuid,sys32_getresuid_wrapper)
-SYSCALL(sys_setresgid,sys_setresgid,sys32_setresgid_wrapper)	/* 210 */
-SYSCALL(sys_getresgid,sys_getresgid,sys32_getresgid_wrapper)
-SYSCALL(sys_chown,sys_chown,sys32_chown_wrapper)
-SYSCALL(sys_setuid,sys_setuid,sys32_setuid_wrapper)
-SYSCALL(sys_setgid,sys_setgid,sys32_setgid_wrapper)
-SYSCALL(sys_setfsuid,sys_setfsuid,sys32_setfsuid_wrapper)	/* 215 */
-SYSCALL(sys_setfsgid,sys_setfsgid,sys32_setfsgid_wrapper)
-SYSCALL(sys_pivot_root,sys_pivot_root,sys32_pivot_root_wrapper)
-SYSCALL(sys_mincore,sys_mincore,sys32_mincore_wrapper)
-SYSCALL(sys_madvise,sys_madvise,sys32_madvise_wrapper)
-SYSCALL(sys_getdents64,sys_getdents64,sys32_getdents64_wrapper)	/* 220 */
-SYSCALL(sys_fcntl64,sys_ni_syscall,compat_sys_fcntl64_wrapper)
-SYSCALL(sys_readahead,sys_readahead,sys32_readahead_wrapper)
+SYSCALL(sys_setreuid,sys_setreuid,compat_sys_setreuid)
+SYSCALL(sys_setregid,sys_setregid,compat_sys_setregid)
+SYSCALL(sys_getgroups,sys_getgroups,compat_sys_getgroups)	/* 205 */
+SYSCALL(sys_setgroups,sys_setgroups,compat_sys_setgroups)
+SYSCALL(sys_fchown,sys_fchown,compat_sys_fchown)
+SYSCALL(sys_setresuid,sys_setresuid,compat_sys_setresuid)
+SYSCALL(sys_getresuid,sys_getresuid,compat_sys_getresuid)
+SYSCALL(sys_setresgid,sys_setresgid,compat_sys_setresgid)	/* 210 */
+SYSCALL(sys_getresgid,sys_getresgid,compat_sys_getresgid)
+SYSCALL(sys_chown,sys_chown,compat_sys_chown)
+SYSCALL(sys_setuid,sys_setuid,compat_sys_setuid)
+SYSCALL(sys_setgid,sys_setgid,compat_sys_setgid)
+SYSCALL(sys_setfsuid,sys_setfsuid,compat_sys_setfsuid)	/* 215 */
+SYSCALL(sys_setfsgid,sys_setfsgid,compat_sys_setfsgid)
+SYSCALL(sys_pivot_root,sys_pivot_root,compat_sys_pivot_root)
+SYSCALL(sys_mincore,sys_mincore,compat_sys_mincore)
+SYSCALL(sys_madvise,sys_madvise,compat_sys_madvise)
+SYSCALL(sys_getdents64,sys_getdents64,compat_sys_getdents64)	/* 220 */
+SYSCALL(sys_fcntl64,sys_ni_syscall,compat_sys_fcntl64)
+SYSCALL(sys_readahead,sys_readahead,compat_sys_s390_readahead)
 SYSCALL(sys_sendfile64,sys_ni_syscall,compat_sys_sendfile64)
-SYSCALL(sys_setxattr,sys_setxattr,sys32_setxattr_wrapper)
-SYSCALL(sys_lsetxattr,sys_lsetxattr,sys32_lsetxattr_wrapper)	/* 225 */
-SYSCALL(sys_fsetxattr,sys_fsetxattr,sys32_fsetxattr_wrapper)
-SYSCALL(sys_getxattr,sys_getxattr,sys32_getxattr_wrapper)
-SYSCALL(sys_lgetxattr,sys_lgetxattr,sys32_lgetxattr_wrapper)
-SYSCALL(sys_fgetxattr,sys_fgetxattr,sys32_fgetxattr_wrapper)
-SYSCALL(sys_listxattr,sys_listxattr,sys32_listxattr_wrapper)	/* 230 */
-SYSCALL(sys_llistxattr,sys_llistxattr,sys32_llistxattr_wrapper)
-SYSCALL(sys_flistxattr,sys_flistxattr,sys32_flistxattr_wrapper)
-SYSCALL(sys_removexattr,sys_removexattr,sys32_removexattr_wrapper)
-SYSCALL(sys_lremovexattr,sys_lremovexattr,sys32_lremovexattr_wrapper)
-SYSCALL(sys_fremovexattr,sys_fremovexattr,sys32_fremovexattr_wrapper)	/* 235 */
+SYSCALL(sys_setxattr,sys_setxattr,compat_sys_setxattr)
+SYSCALL(sys_lsetxattr,sys_lsetxattr,compat_sys_lsetxattr)	/* 225 */
+SYSCALL(sys_fsetxattr,sys_fsetxattr,compat_sys_fsetxattr)
+SYSCALL(sys_getxattr,sys_getxattr,compat_sys_getxattr)
+SYSCALL(sys_lgetxattr,sys_lgetxattr,compat_sys_lgetxattr)
+SYSCALL(sys_fgetxattr,sys_fgetxattr,compat_sys_fgetxattr)
+SYSCALL(sys_listxattr,sys_listxattr,compat_sys_listxattr)	/* 230 */
+SYSCALL(sys_llistxattr,sys_llistxattr,compat_sys_llistxattr)
+SYSCALL(sys_flistxattr,sys_flistxattr,compat_sys_flistxattr)
+SYSCALL(sys_removexattr,sys_removexattr,compat_sys_removexattr)
+SYSCALL(sys_lremovexattr,sys_lremovexattr,compat_sys_lremovexattr)
+SYSCALL(sys_fremovexattr,sys_fremovexattr,compat_sys_fremovexattr)	/* 235 */
 SYSCALL(sys_gettid,sys_gettid,sys_gettid)
-SYSCALL(sys_tkill,sys_tkill,sys_tkill_wrapper)
+SYSCALL(sys_tkill,sys_tkill,compat_sys_tkill)
 SYSCALL(sys_futex,sys_futex,compat_sys_futex)
-SYSCALL(sys_sched_setaffinity,sys_sched_setaffinity,sys32_sched_setaffinity_wrapper)
-SYSCALL(sys_sched_getaffinity,sys_sched_getaffinity,sys32_sched_getaffinity_wrapper)	/* 240 */
-SYSCALL(sys_tgkill,sys_tgkill,sys_tgkill_wrapper)
+SYSCALL(sys_sched_setaffinity,sys_sched_setaffinity,compat_sys_sched_setaffinity)
+SYSCALL(sys_sched_getaffinity,sys_sched_getaffinity,compat_sys_sched_getaffinity)	/* 240 */
+SYSCALL(sys_tgkill,sys_tgkill,compat_sys_tgkill)
 NI_SYSCALL							/* reserved for TUX */
-SYSCALL(sys_io_setup,sys_io_setup,sys32_io_setup_wrapper)
-SYSCALL(sys_io_destroy,sys_io_destroy,sys32_io_destroy_wrapper)
-SYSCALL(sys_io_getevents,sys_io_getevents,sys32_io_getevents_wrapper)	/* 245 */
-SYSCALL(sys_io_submit,sys_io_submit,sys32_io_submit_wrapper)
-SYSCALL(sys_io_cancel,sys_io_cancel,sys32_io_cancel_wrapper)
-SYSCALL(sys_exit_group,sys_exit_group,sys32_exit_group_wrapper)
-SYSCALL(sys_epoll_create,sys_epoll_create,sys_epoll_create_wrapper)
-SYSCALL(sys_epoll_ctl,sys_epoll_ctl,sys_epoll_ctl_wrapper)	/* 250 */
-SYSCALL(sys_epoll_wait,sys_epoll_wait,sys_epoll_wait_wrapper)
-SYSCALL(sys_set_tid_address,sys_set_tid_address,sys32_set_tid_address_wrapper)
-SYSCALL(sys_s390_fadvise64,sys_fadvise64_64,sys32_fadvise64_wrapper)
-SYSCALL(sys_timer_create,sys_timer_create,sys32_timer_create_wrapper)
-SYSCALL(sys_timer_settime,sys_timer_settime,sys32_timer_settime_wrapper)	/* 255 */
-SYSCALL(sys_timer_gettime,sys_timer_gettime,sys32_timer_gettime_wrapper)
-SYSCALL(sys_timer_getoverrun,sys_timer_getoverrun,sys32_timer_getoverrun_wrapper)
-SYSCALL(sys_timer_delete,sys_timer_delete,sys32_timer_delete_wrapper)
-SYSCALL(sys_clock_settime,sys_clock_settime,sys32_clock_settime_wrapper)
-SYSCALL(sys_clock_gettime,sys_clock_gettime,sys32_clock_gettime_wrapper)	/* 260 */
-SYSCALL(sys_clock_getres,sys_clock_getres,sys32_clock_getres_wrapper)
-SYSCALL(sys_clock_nanosleep,sys_clock_nanosleep,sys32_clock_nanosleep_wrapper)
+SYSCALL(sys_io_setup,sys_io_setup,compat_sys_io_setup)
+SYSCALL(sys_io_destroy,sys_io_destroy,compat_sys_io_destroy)
+SYSCALL(sys_io_getevents,sys_io_getevents,compat_sys_io_getevents)	/* 245 */
+SYSCALL(sys_io_submit,sys_io_submit,compat_sys_io_submit)
+SYSCALL(sys_io_cancel,sys_io_cancel,compat_sys_io_cancel)
+SYSCALL(sys_exit_group,sys_exit_group,compat_sys_exit_group)
+SYSCALL(sys_epoll_create,sys_epoll_create,compat_sys_epoll_create)
+SYSCALL(sys_epoll_ctl,sys_epoll_ctl,compat_sys_epoll_ctl)	/* 250 */
+SYSCALL(sys_epoll_wait,sys_epoll_wait,compat_sys_epoll_wait)
+SYSCALL(sys_set_tid_address,sys_set_tid_address,compat_sys_set_tid_address)
+SYSCALL(sys_s390_fadvise64,sys_fadvise64_64,compat_sys_s390_fadvise64)
+SYSCALL(sys_timer_create,sys_timer_create,compat_sys_timer_create)
+SYSCALL(sys_timer_settime,sys_timer_settime,compat_sys_timer_settime)	/* 255 */
+SYSCALL(sys_timer_gettime,sys_timer_gettime,compat_sys_timer_gettime)
+SYSCALL(sys_timer_getoverrun,sys_timer_getoverrun,compat_sys_timer_getoverrun)
+SYSCALL(sys_timer_delete,sys_timer_delete,compat_sys_timer_delete)
+SYSCALL(sys_clock_settime,sys_clock_settime,compat_sys_clock_settime)
+SYSCALL(sys_clock_gettime,sys_clock_gettime,compat_sys_clock_gettime)	/* 260 */
+SYSCALL(sys_clock_getres,sys_clock_getres,compat_sys_clock_getres)
+SYSCALL(sys_clock_nanosleep,sys_clock_nanosleep,compat_sys_clock_nanosleep)
 NI_SYSCALL							/* reserved for vserver */
-SYSCALL(sys_s390_fadvise64_64,sys_ni_syscall,sys32_fadvise64_64_wrapper)
-SYSCALL(sys_statfs64,sys_statfs64,compat_sys_statfs64_wrapper)
-SYSCALL(sys_fstatfs64,sys_fstatfs64,compat_sys_fstatfs64_wrapper)
-SYSCALL(sys_remap_file_pages,sys_remap_file_pages,sys32_remap_file_pages_wrapper)
+SYSCALL(sys_s390_fadvise64_64,sys_ni_syscall,compat_sys_s390_fadvise64_64)
+SYSCALL(sys_statfs64,sys_statfs64,compat_sys_statfs64)
+SYSCALL(sys_fstatfs64,sys_fstatfs64,compat_sys_fstatfs64)
+SYSCALL(sys_remap_file_pages,sys_remap_file_pages,compat_sys_remap_file_pages)
 NI_SYSCALL							/* 268 sys_mbind */
 NI_SYSCALL							/* 269 sys_get_mempolicy */
 NI_SYSCALL							/* 270 sys_set_mempolicy */
-SYSCALL(sys_mq_open,sys_mq_open,compat_sys_mq_open_wrapper)
-SYSCALL(sys_mq_unlink,sys_mq_unlink,sys32_mq_unlink_wrapper)
-SYSCALL(sys_mq_timedsend,sys_mq_timedsend,compat_sys_mq_timedsend_wrapper)
-SYSCALL(sys_mq_timedreceive,sys_mq_timedreceive,compat_sys_mq_timedreceive_wrapper)
-SYSCALL(sys_mq_notify,sys_mq_notify,compat_sys_mq_notify_wrapper) /* 275 */
-SYSCALL(sys_mq_getsetattr,sys_mq_getsetattr,compat_sys_mq_getsetattr_wrapper)
-SYSCALL(sys_kexec_load,sys_kexec_load,compat_sys_kexec_load_wrapper)
-SYSCALL(sys_add_key,sys_add_key,compat_sys_add_key_wrapper)
-SYSCALL(sys_request_key,sys_request_key,compat_sys_request_key_wrapper)
-SYSCALL(sys_keyctl,sys_keyctl,compat_sys_keyctl_wrapper)		/* 280 */
+SYSCALL(sys_mq_open,sys_mq_open,compat_sys_mq_open)
+SYSCALL(sys_mq_unlink,sys_mq_unlink,compat_sys_mq_unlink)
+SYSCALL(sys_mq_timedsend,sys_mq_timedsend,compat_sys_mq_timedsend)
+SYSCALL(sys_mq_timedreceive,sys_mq_timedreceive,compat_sys_mq_timedreceive)
+SYSCALL(sys_mq_notify,sys_mq_notify,compat_sys_mq_notify) /* 275 */
+SYSCALL(sys_mq_getsetattr,sys_mq_getsetattr,compat_sys_mq_getsetattr)
+SYSCALL(sys_kexec_load,sys_kexec_load,compat_sys_kexec_load)
+SYSCALL(sys_add_key,sys_add_key,compat_sys_add_key)
+SYSCALL(sys_request_key,sys_request_key,compat_sys_request_key)
+SYSCALL(sys_keyctl,sys_keyctl,compat_sys_keyctl)		/* 280 */
 SYSCALL(sys_waitid,sys_waitid,compat_sys_waitid)
-SYSCALL(sys_ioprio_set,sys_ioprio_set,sys_ioprio_set_wrapper)
-SYSCALL(sys_ioprio_get,sys_ioprio_get,sys_ioprio_get_wrapper)
+SYSCALL(sys_ioprio_set,sys_ioprio_set,compat_sys_ioprio_set)
+SYSCALL(sys_ioprio_get,sys_ioprio_get,compat_sys_ioprio_get)
 SYSCALL(sys_inotify_init,sys_inotify_init,sys_inotify_init)
-SYSCALL(sys_inotify_add_watch,sys_inotify_add_watch,sys_inotify_add_watch_wrapper)	/* 285 */
-SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch,sys_inotify_rm_watch_wrapper)
+SYSCALL(sys_inotify_add_watch,sys_inotify_add_watch,compat_sys_inotify_add_watch)	/* 285 */
+SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch,compat_sys_inotify_rm_watch)
 NI_SYSCALL							/* 287 sys_migrate_pages */
 SYSCALL(sys_openat,sys_openat,compat_sys_openat)
-SYSCALL(sys_mkdirat,sys_mkdirat,sys_mkdirat_wrapper)
-SYSCALL(sys_mknodat,sys_mknodat,sys_mknodat_wrapper)	/* 290 */
-SYSCALL(sys_fchownat,sys_fchownat,sys_fchownat_wrapper)
-SYSCALL(sys_futimesat,sys_futimesat,compat_sys_futimesat_wrapper)
-SYSCALL(sys_fstatat64,sys_newfstatat,sys32_fstatat64_wrapper)
-SYSCALL(sys_unlinkat,sys_unlinkat,sys_unlinkat_wrapper)
-SYSCALL(sys_renameat,sys_renameat,sys_renameat_wrapper)	/* 295 */
-SYSCALL(sys_linkat,sys_linkat,sys_linkat_wrapper)
-SYSCALL(sys_symlinkat,sys_symlinkat,sys_symlinkat_wrapper)
-SYSCALL(sys_readlinkat,sys_readlinkat,sys_readlinkat_wrapper)
-SYSCALL(sys_fchmodat,sys_fchmodat,sys_fchmodat_wrapper)
-SYSCALL(sys_faccessat,sys_faccessat,sys_faccessat_wrapper)	/* 300 */
-SYSCALL(sys_pselect6,sys_pselect6,compat_sys_pselect6_wrapper)
-SYSCALL(sys_ppoll,sys_ppoll,compat_sys_ppoll_wrapper)
-SYSCALL(sys_unshare,sys_unshare,sys_unshare_wrapper)
+SYSCALL(sys_mkdirat,sys_mkdirat,compat_sys_mkdirat)
+SYSCALL(sys_mknodat,sys_mknodat,compat_sys_mknodat)	/* 290 */
+SYSCALL(sys_fchownat,sys_fchownat,compat_sys_fchownat)
+SYSCALL(sys_futimesat,sys_futimesat,compat_sys_futimesat)
+SYSCALL(sys_fstatat64,sys_newfstatat,compat_sys_s390_fstatat64)
+SYSCALL(sys_unlinkat,sys_unlinkat,compat_sys_unlinkat)
+SYSCALL(sys_renameat,sys_renameat,compat_sys_renameat)	/* 295 */
+SYSCALL(sys_linkat,sys_linkat,compat_sys_linkat)
+SYSCALL(sys_symlinkat,sys_symlinkat,compat_sys_symlinkat)
+SYSCALL(sys_readlinkat,sys_readlinkat,compat_sys_readlinkat)
+SYSCALL(sys_fchmodat,sys_fchmodat,compat_sys_fchmodat)
+SYSCALL(sys_faccessat,sys_faccessat,compat_sys_faccessat)	/* 300 */
+SYSCALL(sys_pselect6,sys_pselect6,compat_sys_pselect6)
+SYSCALL(sys_ppoll,sys_ppoll,compat_sys_ppoll)
+SYSCALL(sys_unshare,sys_unshare,compat_sys_unshare)
 SYSCALL(sys_set_robust_list,sys_set_robust_list,compat_sys_set_robust_list)
 SYSCALL(sys_get_robust_list,sys_get_robust_list,compat_sys_get_robust_list)
-SYSCALL(sys_splice,sys_splice,sys_splice_wrapper)
-SYSCALL(sys_sync_file_range,sys_sync_file_range,sys_sync_file_range_wrapper)
-SYSCALL(sys_tee,sys_tee,sys_tee_wrapper)
+SYSCALL(sys_splice,sys_splice,compat_sys_splice)
+SYSCALL(sys_sync_file_range,sys_sync_file_range,compat_sys_s390_sync_file_range)
+SYSCALL(sys_tee,sys_tee,compat_sys_tee)
 SYSCALL(sys_vmsplice,sys_vmsplice,compat_sys_vmsplice)
 NI_SYSCALL							/* 310 sys_move_pages */
-SYSCALL(sys_getcpu,sys_getcpu,sys_getcpu_wrapper)
+SYSCALL(sys_getcpu,sys_getcpu,compat_sys_getcpu)
 SYSCALL(sys_epoll_pwait,sys_epoll_pwait,compat_sys_epoll_pwait)
-SYSCALL(sys_utimes,sys_utimes,compat_sys_utimes_wrapper)
-SYSCALL(sys_s390_fallocate,sys_fallocate,sys_fallocate_wrapper)
-SYSCALL(sys_utimensat,sys_utimensat,compat_sys_utimensat_wrapper)	/* 315 */
+SYSCALL(sys_utimes,sys_utimes,compat_sys_utimes)
+SYSCALL(sys_s390_fallocate,sys_fallocate,compat_sys_s390_fallocate)
+SYSCALL(sys_utimensat,sys_utimensat,compat_sys_utimensat)	/* 315 */
 SYSCALL(sys_signalfd,sys_signalfd,compat_sys_signalfd)
 NI_SYSCALL						/* 317 old sys_timer_fd */
-SYSCALL(sys_eventfd,sys_eventfd,sys_eventfd_wrapper)
-SYSCALL(sys_timerfd_create,sys_timerfd_create,sys_timerfd_create_wrapper)
+SYSCALL(sys_eventfd,sys_eventfd,compat_sys_eventfd)
+SYSCALL(sys_timerfd_create,sys_timerfd_create,compat_sys_timerfd_create)
 SYSCALL(sys_timerfd_settime,sys_timerfd_settime,compat_sys_timerfd_settime) /* 320 */
 SYSCALL(sys_timerfd_gettime,sys_timerfd_gettime,compat_sys_timerfd_gettime)
 SYSCALL(sys_signalfd4,sys_signalfd4,compat_sys_signalfd4)
-SYSCALL(sys_eventfd2,sys_eventfd2,sys_eventfd2_wrapper)
-SYSCALL(sys_inotify_init1,sys_inotify_init1,sys_inotify_init1_wrapper)
-SYSCALL(sys_pipe2,sys_pipe2,sys_pipe2_wrapper) /* 325 */
-SYSCALL(sys_dup3,sys_dup3,sys_dup3_wrapper)
-SYSCALL(sys_epoll_create1,sys_epoll_create1,sys_epoll_create1_wrapper)
+SYSCALL(sys_eventfd2,sys_eventfd2,compat_sys_eventfd2)
+SYSCALL(sys_inotify_init1,sys_inotify_init1,compat_sys_inotify_init1)
+SYSCALL(sys_pipe2,sys_pipe2,compat_sys_pipe2) /* 325 */
+SYSCALL(sys_dup3,sys_dup3,compat_sys_dup3)
+SYSCALL(sys_epoll_create1,sys_epoll_create1,compat_sys_epoll_create1)
 SYSCALL(sys_preadv,sys_preadv,compat_sys_preadv)
 SYSCALL(sys_pwritev,sys_pwritev,compat_sys_pwritev)
 SYSCALL(sys_rt_tgsigqueueinfo,sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo) /* 330 */
-SYSCALL(sys_perf_event_open,sys_perf_event_open,sys_perf_event_open_wrapper)
-SYSCALL(sys_fanotify_init,sys_fanotify_init,sys_fanotify_init_wrapper)
+SYSCALL(sys_perf_event_open,sys_perf_event_open,compat_sys_perf_event_open)
+SYSCALL(sys_fanotify_init,sys_fanotify_init,compat_sys_fanotify_init)
 SYSCALL(sys_fanotify_mark,sys_fanotify_mark,compat_sys_fanotify_mark)
-SYSCALL(sys_prlimit64,sys_prlimit64,sys_prlimit64_wrapper)
-SYSCALL(sys_name_to_handle_at,sys_name_to_handle_at,sys_name_to_handle_at_wrapper) /* 335 */
+SYSCALL(sys_prlimit64,sys_prlimit64,compat_sys_prlimit64)
+SYSCALL(sys_name_to_handle_at,sys_name_to_handle_at,compat_sys_name_to_handle_at) /* 335 */
 SYSCALL(sys_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at)
-SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime_wrapper)
-SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper)
-SYSCALL(sys_setns,sys_setns,sys_setns_wrapper)
-SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv_wrapper) /* 340 */
-SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev_wrapper)
-SYSCALL(sys_ni_syscall,sys_s390_runtime_instr,sys_s390_runtime_instr_wrapper)
-SYSCALL(sys_kcmp,sys_kcmp,sys_kcmp_wrapper)
-SYSCALL(sys_finit_module,sys_finit_module,sys_finit_module_wrapper)
-SYSCALL(sys_sched_setattr,sys_sched_setattr,sys_sched_setattr_wrapper) /* 345 */
-SYSCALL(sys_sched_getattr,sys_sched_getattr,sys_sched_getattr_wrapper)
+SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime)
+SYSCALL(sys_syncfs,sys_syncfs,compat_sys_syncfs)
+SYSCALL(sys_setns,sys_setns,compat_sys_setns)
+SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv) /* 340 */
+SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev)
+SYSCALL(sys_ni_syscall,sys_s390_runtime_instr,compat_sys_s390_runtime_instr)
+SYSCALL(sys_kcmp,sys_kcmp,compat_sys_kcmp)
+SYSCALL(sys_finit_module,sys_finit_module,compat_sys_finit_module)
+SYSCALL(sys_sched_setattr,sys_sched_setattr,compat_sys_sched_setattr) /* 345 */
+SYSCALL(sys_sched_getattr,sys_sched_getattr,compat_sys_sched_getattr)
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 4b2e3e3..6298fed 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -451,7 +451,6 @@
 	}
 	set_topology_timer();
 out:
-	update_cpu_masks();
 	return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
 }
 device_initcall(topology_init);
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 8216c0e..6f9cfa5 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -13,6 +13,7 @@
 
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <asm/pgalloc.h>
 #include <asm/virtio-ccw.h>
 #include "kvm-s390.h"
 #include "trace.h"
@@ -86,9 +87,11 @@
 	switch (subcode) {
 	case 3:
 		vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
+		page_table_reset_pgste(current->mm, 0, TASK_SIZE);
 		break;
 	case 4:
 		vcpu->run->s390_reset_flags = 0;
+		page_table_reset_pgste(current->mm, 0, TASK_SIZE);
 		break;
 	default:
 		return -EOPNOTSUPP;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index e0676f3..10b5db3 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -68,6 +68,7 @@
 	{ "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
 	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
 	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
+	{ "instruction_essa", VCPU_STAT(instruction_essa) },
 	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
 	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
 	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
@@ -283,7 +284,11 @@
 	if (kvm_is_ucontrol(vcpu->kvm))
 		gmap_free(vcpu->arch.gmap);
 
+	if (vcpu->arch.sie_block->cbrlo)
+		__free_page(__pfn_to_page(
+				vcpu->arch.sie_block->cbrlo >> PAGE_SHIFT));
 	free_page((unsigned long)(vcpu->arch.sie_block));
+
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
@@ -390,6 +395,8 @@
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
+	struct page *cbrl;
+
 	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
 						    CPUSTAT_SM |
 						    CPUSTAT_STOPPED |
@@ -401,6 +408,14 @@
 	vcpu->arch.sie_block->ecb2  = 8;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
 	vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
+	if (kvm_enabled_cmma()) {
+		cbrl = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (cbrl) {
+			vcpu->arch.sie_block->ecb2 |= 0x80;
+			vcpu->arch.sie_block->ecb2 &= ~0x08;
+			vcpu->arch.sie_block->cbrlo = page_to_phys(cbrl);
+		}
+	}
 	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
 	tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
 		     (unsigned long) vcpu);
@@ -761,6 +776,16 @@
 	return rc;
 }
 
+bool kvm_enabled_cmma(void)
+{
+	if (!MACHINE_IS_LPAR)
+		return false;
+	/* only enable for z10 and later */
+	if (!MACHINE_HAS_EDAT1)
+		return false;
+	return true;
+}
+
 static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
 	int rc, exit_reason;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index f9559b0..564514f 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -156,6 +156,8 @@
 void s390_vcpu_unblock(struct kvm_vcpu *vcpu);
 void exit_sie(struct kvm_vcpu *vcpu);
 void exit_sie_sync(struct kvm_vcpu *vcpu);
+/* are we going to support cmma? */
+bool kvm_enabled_cmma(void);
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
 
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 75beea6..aacb6b1 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -636,8 +636,49 @@
 	return 0;
 }
 
+static int handle_essa(struct kvm_vcpu *vcpu)
+{
+	/* entries expected to be 1FF */
+	int entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3;
+	unsigned long *cbrlo, cbrle;
+	struct gmap *gmap;
+	int i;
+
+	VCPU_EVENT(vcpu, 5, "cmma release %d pages", entries);
+	gmap = vcpu->arch.gmap;
+	vcpu->stat.instruction_essa++;
+	if (!kvm_enabled_cmma() || !vcpu->arch.sie_block->cbrlo)
+		return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
+
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+	if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	/* Rewind PSW to repeat the ESSA instruction */
+	vcpu->arch.sie_block->gpsw.addr =
+		__rewind_psw(vcpu->arch.sie_block->gpsw, 4);
+	vcpu->arch.sie_block->cbrlo &= PAGE_MASK;	/* reset nceo */
+	cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
+	down_read(&gmap->mm->mmap_sem);
+	for (i = 0; i < entries; ++i) {
+		cbrle = cbrlo[i];
+		if (unlikely(cbrle & ~PAGE_MASK || cbrle < 2 * PAGE_SIZE))
+			/* invalid entry */
+			break;
+		/* try to free backing */
+		__gmap_zap(cbrle, gmap);
+	}
+	up_read(&gmap->mm->mmap_sem);
+	if (i < entries)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+	return 0;
+}
+
 static const intercept_handler_t b9_handlers[256] = {
 	[0x8d] = handle_epsw,
+	[0xab] = handle_essa,
 	[0xaf] = handle_pfmf,
 };
 
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index b068729..e3fffe1 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -2,8 +2,7 @@
 # Makefile for s390-specific library files..
 #
 
-lib-y += delay.o string.o uaccess_pt.o find.o
+lib-y += delay.o string.o uaccess_pt.o uaccess_mvcos.o find.o
 obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o mem32.o
 obj-$(CONFIG_64BIT) += mem64.o
-lib-$(CONFIG_64BIT) += uaccess_mvcos.o
 lib-$(CONFIG_SMP) += spinlock.o
diff --git a/arch/s390/lib/find.c b/arch/s390/lib/find.c
index 620d34d..922003c 100644
--- a/arch/s390/lib/find.c
+++ b/arch/s390/lib/find.c
@@ -4,7 +4,7 @@
  * On s390x the bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
  * and on s390:
- *   |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ *   |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
  *
  * The reason for this bit numbering is the fact that the hardware sets bits
  * in a bitmap starting at bit 0 (MSB) and we don't want to scan the bitmap
diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h
index b1a2217..c7e0e81f 100644
--- a/arch/s390/lib/uaccess.h
+++ b/arch/s390/lib/uaccess.h
@@ -6,7 +6,11 @@
 #ifndef __ARCH_S390_LIB_UACCESS_H
 #define __ARCH_S390_LIB_UACCESS_H
 
-extern int futex_atomic_op_pt(int, u32 __user *, int, int *);
-extern int futex_atomic_cmpxchg_pt(u32 *, u32 __user *, u32, u32);
+unsigned long copy_from_user_pt(void *to, const void __user *from, unsigned long n);
+unsigned long copy_to_user_pt(void __user *to, const void *from, unsigned long n);
+unsigned long copy_in_user_pt(void __user *to, const void __user *from, unsigned long n);
+unsigned long clear_user_pt(void __user *to, unsigned long n);
+unsigned long strnlen_user_pt(const char __user *src, unsigned long count);
+long strncpy_from_user_pt(char *dst, const char __user *src, long count);
 
 #endif /* __ARCH_S390_LIB_UACCESS_H */
diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c
index 4b7993b..ae97b8d 100644
--- a/arch/s390/lib/uaccess_mvcos.c
+++ b/arch/s390/lib/uaccess_mvcos.c
@@ -6,8 +6,11 @@
  *		 Gerald Schaefer (gerald.schaefer@de.ibm.com)
  */
 
+#include <linux/jump_label.h>
 #include <linux/errno.h>
+#include <linux/init.h>
 #include <linux/mm.h>
+#include <asm/facility.h>
 #include <asm/uaccess.h>
 #include <asm/futex.h>
 #include "uaccess.h"
@@ -26,7 +29,10 @@
 #define SLR	"slgr"
 #endif
 
-static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x)
+static struct static_key have_mvcos = STATIC_KEY_INIT_TRUE;
+
+static inline unsigned long copy_from_user_mvcos(void *x, const void __user *ptr,
+						 unsigned long size)
 {
 	register unsigned long reg0 asm("0") = 0x81UL;
 	unsigned long tmp1, tmp2;
@@ -65,7 +71,16 @@
 	return size;
 }
 
-static size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x)
+unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	if (static_key_true(&have_mvcos))
+		return copy_from_user_mvcos(to, from, n);
+	return copy_from_user_pt(to, from, n);
+}
+EXPORT_SYMBOL(__copy_from_user);
+
+static inline unsigned long copy_to_user_mvcos(void __user *ptr, const void *x,
+					       unsigned long size)
 {
 	register unsigned long reg0 asm("0") = 0x810000UL;
 	unsigned long tmp1, tmp2;
@@ -94,8 +109,16 @@
 	return size;
 }
 
-static size_t copy_in_user_mvcos(size_t size, void __user *to,
-				 const void __user *from)
+unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	if (static_key_true(&have_mvcos))
+		return copy_to_user_mvcos(to, from, n);
+	return copy_to_user_pt(to, from, n);
+}
+EXPORT_SYMBOL(__copy_to_user);
+
+static inline unsigned long copy_in_user_mvcos(void __user *to, const void __user *from,
+					       unsigned long size)
 {
 	register unsigned long reg0 asm("0") = 0x810081UL;
 	unsigned long tmp1, tmp2;
@@ -117,7 +140,15 @@
 	return size;
 }
 
-static size_t clear_user_mvcos(size_t size, void __user *to)
+unsigned long __copy_in_user(void __user *to, const void __user *from, unsigned long n)
+{
+	if (static_key_true(&have_mvcos))
+		return copy_in_user_mvcos(to, from, n);
+	return copy_in_user_pt(to, from, n);
+}
+EXPORT_SYMBOL(__copy_in_user);
+
+static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size)
 {
 	register unsigned long reg0 asm("0") = 0x810000UL;
 	unsigned long tmp1, tmp2;
@@ -145,17 +176,26 @@
 	return size;
 }
 
-static size_t strnlen_user_mvcos(size_t count, const char __user *src)
+unsigned long __clear_user(void __user *to, unsigned long size)
 {
-	size_t done, len, offset, len_str;
+	if (static_key_true(&have_mvcos))
+		return clear_user_mvcos(to, size);
+	return clear_user_pt(to, size);
+}
+EXPORT_SYMBOL(__clear_user);
+
+static inline unsigned long strnlen_user_mvcos(const char __user *src,
+					       unsigned long count)
+{
+	unsigned long done, len, offset, len_str;
 	char buf[256];
 
 	done = 0;
 	do {
-		offset = (size_t)src & ~PAGE_MASK;
+		offset = (unsigned long)src & ~PAGE_MASK;
 		len = min(256UL, PAGE_SIZE - offset);
 		len = min(count - done, len);
-		if (copy_from_user_mvcos(len, src, buf))
+		if (copy_from_user_mvcos(buf, src, len))
 			return 0;
 		len_str = strnlen(buf, len);
 		done += len_str;
@@ -164,18 +204,26 @@
 	return done + 1;
 }
 
-static size_t strncpy_from_user_mvcos(size_t count, const char __user *src,
-				      char *dst)
+unsigned long __strnlen_user(const char __user *src, unsigned long count)
 {
-	size_t done, len, offset, len_str;
+	if (static_key_true(&have_mvcos))
+		return strnlen_user_mvcos(src, count);
+	return strnlen_user_pt(src, count);
+}
+EXPORT_SYMBOL(__strnlen_user);
 
-	if (unlikely(!count))
+static inline long strncpy_from_user_mvcos(char *dst, const char __user *src,
+					   long count)
+{
+	unsigned long done, len, offset, len_str;
+
+	if (unlikely(count <= 0))
 		return 0;
 	done = 0;
 	do {
-		offset = (size_t)src & ~PAGE_MASK;
+		offset = (unsigned long)src & ~PAGE_MASK;
 		len = min(count - done, PAGE_SIZE - offset);
-		if (copy_from_user_mvcos(len, src, dst))
+		if (copy_from_user_mvcos(dst, src, len))
 			return -EFAULT;
 		len_str = strnlen(dst, len);
 		done += len_str;
@@ -185,13 +233,31 @@
 	return done;
 }
 
-struct uaccess_ops uaccess_mvcos = {
-	.copy_from_user = copy_from_user_mvcos,
-	.copy_to_user = copy_to_user_mvcos,
-	.copy_in_user = copy_in_user_mvcos,
-	.clear_user = clear_user_mvcos,
-	.strnlen_user = strnlen_user_mvcos,
-	.strncpy_from_user = strncpy_from_user_mvcos,
-	.futex_atomic_op = futex_atomic_op_pt,
-	.futex_atomic_cmpxchg = futex_atomic_cmpxchg_pt,
-};
+long __strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	if (static_key_true(&have_mvcos))
+		return strncpy_from_user_mvcos(dst, src, count);
+	return strncpy_from_user_pt(dst, src, count);
+}
+EXPORT_SYMBOL(__strncpy_from_user);
+
+/*
+ * The uaccess page tabe walk variant can be enforced with the "uaccesspt"
+ * kernel parameter. This is mainly for debugging purposes.
+ */
+static int force_uaccess_pt __initdata;
+
+static int __init parse_uaccess_pt(char *__unused)
+{
+	force_uaccess_pt = 1;
+	return 0;
+}
+early_param("uaccesspt", parse_uaccess_pt);
+
+static int __init uaccess_init(void)
+{
+	if (IS_ENABLED(CONFIG_32BIT) || force_uaccess_pt || !test_facility(27))
+		static_key_slow_dec(&have_mvcos);
+	return 0;
+}
+early_initcall(uaccess_init);
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 61ebcc9..8d39760 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -22,7 +22,7 @@
 #define SLR	"slgr"
 #endif
 
-static size_t strnlen_kernel(size_t count, const char __user *src)
+static unsigned long strnlen_kernel(const char __user *src, unsigned long count)
 {
 	register unsigned long reg0 asm("0") = 0UL;
 	unsigned long tmp1, tmp2;
@@ -42,8 +42,8 @@
 	return count;
 }
 
-static size_t copy_in_kernel(size_t count, void __user *to,
-			     const void __user *from)
+static unsigned long copy_in_kernel(void __user *to, const void __user *from,
+				    unsigned long count)
 {
 	unsigned long tmp1;
 
@@ -146,8 +146,8 @@
 
 #endif /* CONFIG_64BIT */
 
-static __always_inline size_t __user_copy_pt(unsigned long uaddr, void *kptr,
-					     size_t n, int write_user)
+static inline unsigned long __user_copy_pt(unsigned long uaddr, void *kptr,
+					   unsigned long n, int write_user)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long offset, done, size, kaddr;
@@ -189,8 +189,7 @@
  * Do DAT for user address by page table walk, return kernel address.
  * This function needs to be called with current->mm->page_table_lock held.
  */
-static __always_inline unsigned long __dat_user_addr(unsigned long uaddr,
-						     int write)
+static inline unsigned long __dat_user_addr(unsigned long uaddr, int write)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long kaddr;
@@ -211,29 +210,29 @@
 	return 0;
 }
 
-static size_t copy_from_user_pt(size_t n, const void __user *from, void *to)
+unsigned long copy_from_user_pt(void *to, const void __user *from, unsigned long n)
 {
-	size_t rc;
+	unsigned long rc;
 
 	if (segment_eq(get_fs(), KERNEL_DS))
-		return copy_in_kernel(n, (void __user *) to, from);
+		return copy_in_kernel((void __user *) to, from, n);
 	rc = __user_copy_pt((unsigned long) from, to, n, 0);
 	if (unlikely(rc))
 		memset(to + n - rc, 0, rc);
 	return rc;
 }
 
-static size_t copy_to_user_pt(size_t n, void __user *to, const void *from)
+unsigned long copy_to_user_pt(void __user *to, const void *from, unsigned long n)
 {
 	if (segment_eq(get_fs(), KERNEL_DS))
-		return copy_in_kernel(n, to, (void __user *) from);
+		return copy_in_kernel(to, (void __user *) from, n);
 	return __user_copy_pt((unsigned long) to, (void *) from, n, 1);
 }
 
-static size_t clear_user_pt(size_t n, void __user *to)
+unsigned long clear_user_pt(void __user *to, unsigned long n)
 {
 	void *zpage = (void *) empty_zero_page;
-	long done, size, ret;
+	unsigned long done, size, ret;
 
 	done = 0;
 	do {
@@ -242,7 +241,7 @@
 		else
 			size = n - done;
 		if (segment_eq(get_fs(), KERNEL_DS))
-			ret = copy_in_kernel(n, to, (void __user *) zpage);
+			ret = copy_in_kernel(to, (void __user *) zpage, n);
 		else
 			ret = __user_copy_pt((unsigned long) to, zpage, size, 1);
 		done += size;
@@ -253,17 +252,17 @@
 	return 0;
 }
 
-static size_t strnlen_user_pt(size_t count, const char __user *src)
+unsigned long strnlen_user_pt(const char __user *src, unsigned long count)
 {
 	unsigned long uaddr = (unsigned long) src;
 	struct mm_struct *mm = current->mm;
 	unsigned long offset, done, len, kaddr;
-	size_t len_str;
+	unsigned long len_str;
 
 	if (unlikely(!count))
 		return 0;
 	if (segment_eq(get_fs(), KERNEL_DS))
-		return strnlen_kernel(count, src);
+		return strnlen_kernel(src, count);
 	if (!mm)
 		return 0;
 	done = 0;
@@ -289,19 +288,18 @@
 	goto retry;
 }
 
-static size_t strncpy_from_user_pt(size_t count, const char __user *src,
-				   char *dst)
+long strncpy_from_user_pt(char *dst, const char __user *src, long count)
 {
-	size_t done, len, offset, len_str;
+	unsigned long done, len, offset, len_str;
 
-	if (unlikely(!count))
+	if (unlikely(count <= 0))
 		return 0;
 	done = 0;
 	do {
-		offset = (size_t)src & ~PAGE_MASK;
+		offset = (unsigned long)src & ~PAGE_MASK;
 		len = min(count - done, PAGE_SIZE - offset);
 		if (segment_eq(get_fs(), KERNEL_DS)) {
-			if (copy_in_kernel(len, (void __user *) dst, src))
+			if (copy_in_kernel((void __user *) dst, src, len))
 				return -EFAULT;
 		} else {
 			if (__user_copy_pt((unsigned long) src, dst, len, 0))
@@ -315,8 +313,8 @@
 	return done;
 }
 
-static size_t copy_in_user_pt(size_t n, void __user *to,
-			      const void __user *from)
+unsigned long copy_in_user_pt(void __user *to, const void __user *from,
+			      unsigned long n)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long offset_max, uaddr, done, size, error_code;
@@ -326,7 +324,7 @@
 	int write_user;
 
 	if (segment_eq(get_fs(), KERNEL_DS))
-		return copy_in_kernel(n, to, from);
+		return copy_in_kernel(to, from, n);
 	if (!mm)
 		return n;
 	done = 0;
@@ -411,7 +409,7 @@
 	return ret;
 }
 
-int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
+int __futex_atomic_op_inuser(int op, u32 __user *uaddr, int oparg, int *old)
 {
 	int ret;
 
@@ -449,8 +447,8 @@
 	return ret;
 }
 
-int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
-			    u32 oldval, u32 newval)
+int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+				  u32 oldval, u32 newval)
 {
 	int ret;
 
@@ -471,14 +469,3 @@
 	put_page(virt_to_page(uaddr));
 	return ret;
 }
-
-struct uaccess_ops uaccess_pt = {
-	.copy_from_user		= copy_from_user_pt,
-	.copy_to_user		= copy_to_user_pt,
-	.copy_in_user		= copy_in_user_pt,
-	.clear_user		= clear_user_pt,
-	.strnlen_user		= strnlen_user_pt,
-	.strncpy_from_user	= strncpy_from_user_pt,
-	.futex_atomic_op	= futex_atomic_op_pt,
-	.futex_atomic_cmpxchg	= futex_atomic_cmpxchg_pt,
-};
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index d1e0e0c..2a2e354 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -128,7 +128,7 @@
 /*
  * Copy memory from kernel (real) to user (virtual)
  */
-int copy_to_user_real(void __user *dest, void *src, size_t count)
+int copy_to_user_real(void __user *dest, void *src, unsigned long count)
 {
 	int offs = 0, size, rc;
 	char *buf;
@@ -152,32 +152,6 @@
 }
 
 /*
- * Copy memory from user (virtual) to kernel (real)
- */
-int copy_from_user_real(void *dest, void __user *src, size_t count)
-{
-	int offs = 0, size, rc;
-	char *buf;
-
-	buf = (char *) __get_free_page(GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-	rc = -EFAULT;
-	while (offs < count) {
-		size = min(PAGE_SIZE, count - offs);
-		if (copy_from_user(buf, src + offs, size))
-			goto out;
-		if (memcpy_real(dest + offs, buf, size))
-			goto out;
-		offs += size;
-	}
-	rc = 0;
-out:
-	free_page((unsigned long) buf);
-	return rc;
-}
-
-/*
  * Check if physical address is within prefix or zero page
  */
 static int is_swapped(unsigned long addr)
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index a90d45e..27c50f4 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -12,6 +12,8 @@
 #include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/init.h>
+#include <asm/setup.h>
+#include <asm/ipl.h>
 
 #define ESSA_SET_STABLE		1
 #define ESSA_SET_UNUSED		2
@@ -41,6 +43,14 @@
 
 	if (!cmma_flag)
 		return;
+	/*
+	 * Disable CMM for dump, otherwise  the tprot based memory
+	 * detection can fail because of unstable pages.
+	 */
+	if (OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP) {
+		cmma_flag = 0;
+		return;
+	}
 	asm volatile(
 		"       .insn rrf,0xb9ab0000,%1,%1,0,0\n"
 		"0:     la      %0,0\n"
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 3584ed9..796c932 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -17,6 +17,7 @@
 #include <linux/quicklist.h>
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
+#include <linux/swapops.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -594,6 +595,82 @@
 }
 EXPORT_SYMBOL_GPL(gmap_fault);
 
+static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm)
+{
+	if (!non_swap_entry(entry))
+		dec_mm_counter(mm, MM_SWAPENTS);
+	else if (is_migration_entry(entry)) {
+		struct page *page = migration_entry_to_page(entry);
+
+		if (PageAnon(page))
+			dec_mm_counter(mm, MM_ANONPAGES);
+		else
+			dec_mm_counter(mm, MM_FILEPAGES);
+	}
+	free_swap_and_cache(entry);
+}
+
+/**
+ * The mm->mmap_sem lock must be held
+ */
+static void gmap_zap_unused(struct mm_struct *mm, unsigned long address)
+{
+	unsigned long ptev, pgstev;
+	spinlock_t *ptl;
+	pgste_t pgste;
+	pte_t *ptep, pte;
+
+	ptep = get_locked_pte(mm, address, &ptl);
+	if (unlikely(!ptep))
+		return;
+	pte = *ptep;
+	if (!pte_swap(pte))
+		goto out_pte;
+	/* Zap unused and logically-zero pages */
+	pgste = pgste_get_lock(ptep);
+	pgstev = pgste_val(pgste);
+	ptev = pte_val(pte);
+	if (((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED) ||
+	    ((pgstev & _PGSTE_GPS_ZERO) && (ptev & _PAGE_INVALID))) {
+		gmap_zap_swap_entry(pte_to_swp_entry(pte), mm);
+		pte_clear(mm, address, ptep);
+	}
+	pgste_set_unlock(ptep, pgste);
+out_pte:
+	pte_unmap_unlock(*ptep, ptl);
+}
+
+/*
+ * this function is assumed to be called with mmap_sem held
+ */
+void __gmap_zap(unsigned long address, struct gmap *gmap)
+{
+	unsigned long *table, *segment_ptr;
+	unsigned long segment, pgstev, ptev;
+	struct gmap_pgtable *mp;
+	struct page *page;
+
+	segment_ptr = gmap_table_walk(address, gmap);
+	if (IS_ERR(segment_ptr))
+		return;
+	segment = *segment_ptr;
+	if (segment & _SEGMENT_ENTRY_INVALID)
+		return;
+	page = pfn_to_page(segment >> PAGE_SHIFT);
+	mp = (struct gmap_pgtable *) page->index;
+	address = mp->vmaddr | (address & ~PMD_MASK);
+	/* Page table is present */
+	table = (unsigned long *)(segment & _SEGMENT_ENTRY_ORIGIN);
+	table = table + ((address >> 12) & 0xff);
+	pgstev = table[PTRS_PER_PTE];
+	ptev = table[0];
+	/* quick check, checked again with locks held */
+	if (((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED) ||
+	    ((pgstev & _PGSTE_GPS_ZERO) && (ptev & _PAGE_INVALID)))
+		gmap_zap_unused(gmap->mm, address);
+}
+EXPORT_SYMBOL_GPL(__gmap_zap);
+
 void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap)
 {
 
@@ -671,7 +748,7 @@
 /**
  * gmap_ipte_notify - mark a range of ptes for invalidation notification
  * @gmap: pointer to guest mapping meta data structure
- * @address: virtual address in the guest address space
+ * @start: virtual address in the guest address space
  * @len: size of area
  *
  * Returns 0 if for each page in the given range a gmap mapping exists and
@@ -725,13 +802,12 @@
 /**
  * gmap_do_ipte_notify - call all invalidation callbacks for a specific pte.
  * @mm: pointer to the process mm_struct
- * @addr: virtual address in the process address space
  * @pte: pointer to the page table entry
  *
  * This function is assumed to be called with the page table lock held
  * for the pte to notify.
  */
-void gmap_do_ipte_notify(struct mm_struct *mm, unsigned long addr, pte_t *pte)
+void gmap_do_ipte_notify(struct mm_struct *mm, pte_t *pte)
 {
 	unsigned long segment_offset;
 	struct gmap_notifier *nb;
@@ -802,6 +878,78 @@
 	__free_page(page);
 }
 
+static inline unsigned long page_table_reset_pte(struct mm_struct *mm,
+			pmd_t *pmd, unsigned long addr, unsigned long end)
+{
+	pte_t *start_pte, *pte;
+	spinlock_t *ptl;
+	pgste_t pgste;
+
+	start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	pte = start_pte;
+	do {
+		pgste = pgste_get_lock(pte);
+		pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
+		pgste_set_unlock(pte, pgste);
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	pte_unmap_unlock(start_pte, ptl);
+
+	return addr;
+}
+
+static inline unsigned long page_table_reset_pmd(struct mm_struct *mm,
+			pud_t *pud, unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	pmd_t *pmd;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none_or_clear_bad(pmd))
+			continue;
+		next = page_table_reset_pte(mm, pmd, addr, next);
+	} while (pmd++, addr = next, addr != end);
+
+	return addr;
+}
+
+static inline unsigned long page_table_reset_pud(struct mm_struct *mm,
+			pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	pud_t *pud;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(pud))
+			continue;
+		next = page_table_reset_pmd(mm, pud, addr, next);
+	} while (pud++, addr = next, addr != end);
+
+	return addr;
+}
+
+void page_table_reset_pgste(struct mm_struct *mm,
+			unsigned long start, unsigned long end)
+{
+	unsigned long addr, next;
+	pgd_t *pgd;
+
+	addr = start;
+	down_read(&mm->mmap_sem);
+	pgd = pgd_offset(mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(pgd))
+			continue;
+		next = page_table_reset_pud(mm, pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+	up_read(&mm->mmap_sem);
+}
+EXPORT_SYMBOL(page_table_reset_pgste);
+
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned long key, bool nq)
 {
@@ -1248,7 +1396,7 @@
 {
 	struct list_head *lh = (struct list_head *) pgtable;
 
-	assert_spin_locked(&mm->page_table_lock);
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
 	/* FIFO */
 	if (!pmd_huge_pte(mm, pmdp))
@@ -1264,7 +1412,7 @@
 	pgtable_t pgtable;
 	pte_t *ptep;
 
-	assert_spin_locked(&mm->page_table_lock);
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
 	/* FIFO */
 	pgtable = pmd_huge_pte(mm, pmdp);
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index 75c69b4..c5c6684 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -139,7 +139,7 @@
 int __init zpci_debug_init(void)
 {
 	/* event trace buffer */
-	pci_debug_msg_id = debug_register("pci_msg", 16, 1, 16 * sizeof(long));
+	pci_debug_msg_id = debug_register("pci_msg", 8, 1, 8 * sizeof(long));
 	if (!pci_debug_msg_id)
 		return -EINVAL;
 	debug_register_view(pci_debug_msg_id, &debug_sprintf_view);
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 60c11a6..f91c031 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -206,11 +206,13 @@
 	zdev->dma_table = NULL;
 }
 
-static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, unsigned long start,
-				   int size)
+static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev,
+				       unsigned long start, int size)
 {
-	unsigned long boundary_size = 0x1000000;
+	unsigned long boundary_size;
 
+	boundary_size = ALIGN(dma_get_seg_boundary(&zdev->pdev->dev) + 1,
+			      PAGE_SIZE) >> PAGE_SHIFT;
 	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
 				start, size, 0, boundary_size, 0);
 }
diff --git a/arch/sh/include/cpu-sh2/cpu/cache.h b/arch/sh/include/cpu-sh2/cpu/cache.h
index 673515b..aa1b2b9 100644
--- a/arch/sh/include/cpu-sh2/cpu/cache.h
+++ b/arch/sh/include/cpu-sh2/cpu/cache.h
@@ -18,7 +18,7 @@
 #define SH_CACHE_ASSOC		8
 
 #if defined(CONFIG_CPU_SUBTYPE_SH7619)
-#define CCR		0xffffffec
+#define SH_CCR		0xffffffec
 
 #define CCR_CACHE_CE	0x01	/* Cache enable */
 #define CCR_CACHE_WT	0x02    /* CCR[bit1=1,bit2=1] */
diff --git a/arch/sh/include/cpu-sh2a/cpu/cache.h b/arch/sh/include/cpu-sh2a/cpu/cache.h
index defb0ba..b27ce92 100644
--- a/arch/sh/include/cpu-sh2a/cpu/cache.h
+++ b/arch/sh/include/cpu-sh2a/cpu/cache.h
@@ -17,8 +17,8 @@
 #define SH_CACHE_COMBINED	4
 #define SH_CACHE_ASSOC		8
 
-#define CCR		0xfffc1000 /* CCR1 */
-#define CCR2		0xfffc1004
+#define SH_CCR		0xfffc1000 /* CCR1 */
+#define SH_CCR2		0xfffc1004
 
 /*
  * Most of the SH-2A CCR1 definitions resemble the SH-4 ones. All others not
diff --git a/arch/sh/include/cpu-sh3/cpu/cache.h b/arch/sh/include/cpu-sh3/cpu/cache.h
index bee2d81..29700fd 100644
--- a/arch/sh/include/cpu-sh3/cpu/cache.h
+++ b/arch/sh/include/cpu-sh3/cpu/cache.h
@@ -17,7 +17,7 @@
 #define SH_CACHE_COMBINED	4
 #define SH_CACHE_ASSOC		8
 
-#define CCR		0xffffffec	/* Address of Cache Control Register */
+#define SH_CCR		0xffffffec	/* Address of Cache Control Register */
 
 #define CCR_CACHE_CE	0x01	/* Cache Enable */
 #define CCR_CACHE_WT	0x02	/* Write-Through (for P0,U0,P3) (else writeback) */
diff --git a/arch/sh/include/cpu-sh4/cpu/cache.h b/arch/sh/include/cpu-sh4/cpu/cache.h
index 7bfb9e8..92c4cd1 100644
--- a/arch/sh/include/cpu-sh4/cpu/cache.h
+++ b/arch/sh/include/cpu-sh4/cpu/cache.h
@@ -17,7 +17,7 @@
 #define SH_CACHE_COMBINED	4
 #define SH_CACHE_ASSOC		8
 
-#define CCR		0xff00001c	/* Address of Cache Control Register */
+#define SH_CCR		0xff00001c	/* Address of Cache Control Register */
 #define CCR_CACHE_OCE	0x0001	/* Operand Cache Enable */
 #define CCR_CACHE_WT	0x0002	/* Write-Through (for P0,U0,P3) (else writeback)*/
 #define CCR_CACHE_CB	0x0004	/* Copy-Back (for P1) (else writethrough) */
diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c
index ecf83cd..0d7360d 100644
--- a/arch/sh/kernel/cpu/init.c
+++ b/arch/sh/kernel/cpu/init.c
@@ -112,7 +112,7 @@
 	unsigned long ccr, flags;
 
 	jump_to_uncached();
-	ccr = __raw_readl(CCR);
+	ccr = __raw_readl(SH_CCR);
 
 	/*
 	 * At this point we don't know whether the cache is enabled or not - a
@@ -189,7 +189,7 @@
 
 	l2_cache_init();
 
-	__raw_writel(flags, CCR);
+	__raw_writel(flags, SH_CCR);
 	back_to_cached();
 }
 #else
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index 2ea4483..be616ee 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -16,7 +16,6 @@
 #include <linux/thread_info.h>
 #include <linux/irqflags.h>
 #include <linux/smp.h>
-#include <linux/cpuidle.h>
 #include <linux/atomic.h>
 #include <asm/pgalloc.h>
 #include <asm/smp.h>
@@ -40,8 +39,7 @@
 
 void arch_cpu_idle(void)
 {
-	if (cpuidle_idle_call())
-		sh_idle();
+	sh_idle();
 }
 
 void __init select_idle_routine(void)
diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c
index 1157251..777e50f 100644
--- a/arch/sh/mm/cache-debugfs.c
+++ b/arch/sh/mm/cache-debugfs.c
@@ -36,7 +36,7 @@
 	 */
 	jump_to_uncached();
 
-	ccr = __raw_readl(CCR);
+	ccr = __raw_readl(SH_CCR);
 	if ((ccr & CCR_CACHE_ENABLE) == 0) {
 		back_to_cached();
 
diff --git a/arch/sh/mm/cache-sh2.c b/arch/sh/mm/cache-sh2.c
index defcf71..a74259f 100644
--- a/arch/sh/mm/cache-sh2.c
+++ b/arch/sh/mm/cache-sh2.c
@@ -63,9 +63,9 @@
 	local_irq_save(flags);
 	jump_to_uncached();
 
-	ccr = __raw_readl(CCR);
+	ccr = __raw_readl(SH_CCR);
 	ccr |= CCR_CACHE_INVALIDATE;
-	__raw_writel(ccr, CCR);
+	__raw_writel(ccr, SH_CCR);
 
 	back_to_cached();
 	local_irq_restore(flags);
diff --git a/arch/sh/mm/cache-sh2a.c b/arch/sh/mm/cache-sh2a.c
index 949e2d3..ee87d08 100644
--- a/arch/sh/mm/cache-sh2a.c
+++ b/arch/sh/mm/cache-sh2a.c
@@ -134,7 +134,8 @@
 
 	/* If there are too many pages then just blow the cache */
 	if (((end - begin) >> PAGE_SHIFT) >= MAX_OCACHE_PAGES) {
-		__raw_writel(__raw_readl(CCR) | CCR_OCACHE_INVALIDATE, CCR);
+		__raw_writel(__raw_readl(SH_CCR) | CCR_OCACHE_INVALIDATE,
+			     SH_CCR);
 	} else {
 		for (v = begin; v < end; v += L1_CACHE_BYTES)
 			sh2a_invalidate_line(CACHE_OC_ADDRESS_ARRAY, v);
@@ -167,7 +168,8 @@
 	/* I-Cache invalidate */
 	/* If there are too many pages then just blow the cache */
 	if (((end - start) >> PAGE_SHIFT) >= MAX_ICACHE_PAGES) {
-		__raw_writel(__raw_readl(CCR) | CCR_ICACHE_INVALIDATE, CCR);
+		__raw_writel(__raw_readl(SH_CCR) | CCR_ICACHE_INVALIDATE,
+			     SH_CCR);
 	} else {
 		for (v = start; v < end; v += L1_CACHE_BYTES)
 			sh2a_invalidate_line(CACHE_IC_ADDRESS_ARRAY, v);
diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c
index 0e52928..51d8f7f 100644
--- a/arch/sh/mm/cache-sh4.c
+++ b/arch/sh/mm/cache-sh4.c
@@ -133,9 +133,9 @@
 	jump_to_uncached();
 
 	/* Flush I-cache */
-	ccr = __raw_readl(CCR);
+	ccr = __raw_readl(SH_CCR);
 	ccr |= CCR_CACHE_ICI;
-	__raw_writel(ccr, CCR);
+	__raw_writel(ccr, SH_CCR);
 
 	/*
 	 * back_to_cached() will take care of the barrier for us, don't add
diff --git a/arch/sh/mm/cache-shx3.c b/arch/sh/mm/cache-shx3.c
index c0adbee..24c58b7 100644
--- a/arch/sh/mm/cache-shx3.c
+++ b/arch/sh/mm/cache-shx3.c
@@ -19,7 +19,7 @@
 {
 	unsigned int ccr;
 
-	ccr = __raw_readl(CCR);
+	ccr = __raw_readl(SH_CCR);
 
 	/*
 	 * If we've got cache aliases, resolve them in hardware.
@@ -40,5 +40,5 @@
 	ccr |= CCR_CACHE_IBE;
 #endif
 
-	writel_uncached(ccr, CCR);
+	writel_uncached(ccr, SH_CCR);
 }
diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c
index 616966a..097c2cd 100644
--- a/arch/sh/mm/cache.c
+++ b/arch/sh/mm/cache.c
@@ -285,8 +285,8 @@
 {
 	unsigned int cache_disabled = 0;
 
-#ifdef CCR
-	cache_disabled = !(__raw_readl(CCR) & CCR_CACHE_ENABLE);
+#ifdef SH_CCR
+	cache_disabled = !(__raw_readl(SH_CCR) & CCR_CACHE_ENABLE);
 #endif
 
 	compute_alias(&boot_cpu_data.icache);
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index c51efdc..7d8b7e9 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -27,7 +27,7 @@
 	select RTC_DRV_M48T59
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
-	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_JUMP_LABEL if SPARC64
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_PCI_IOMAP
diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h
index dd3bef4..0571039 100644
--- a/arch/sparc/include/asm/smp_64.h
+++ b/arch/sparc/include/asm/smp_64.h
@@ -32,7 +32,6 @@
 
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 extern cpumask_t cpu_core_map[NR_CPUS];
-extern int sparc64_multi_core;
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index 1754390..a2d10fc 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -42,8 +42,6 @@
 #define topology_core_id(cpu)			(cpu_data(cpu).core_id)
 #define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
 #define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
-#define mc_capable()				(sparc64_multi_core)
-#define smt_capable()				(sparc64_multi_core)
 #endif /* CONFIG_SMP */
 
 extern cpumask_t cpu_core_map[NR_CPUS];
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index b90bf23..a1a4400 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -896,10 +896,6 @@
 
 	mdesc_iterate_over_cpus(fill_in_one_cpu, NULL, mask);
 
-#ifdef CONFIG_SMP
-	sparc64_multi_core = 1;
-#endif
-
 	hp = mdesc_grab();
 
 	set_core_ids(hp);
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 32a280e..d7b4967 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -58,9 +58,12 @@
 {
 	if (tlb_type != hypervisor) {
 		touch_nmi_watchdog();
+		local_irq_enable();
 	} else {
 		unsigned long pstate;
 
+		local_irq_enable();
+
                 /* The sun4v sleeping code requires that we have PSTATE.IE cleared over
                  * the cpu sleep hypervisor call.
                  */
@@ -82,7 +85,6 @@
 			: "=&r" (pstate)
 			: "i" (PSTATE_IE));
 	}
-	local_irq_enable();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c
index 6b39125..9a690d3 100644
--- a/arch/sparc/kernel/prom_64.c
+++ b/arch/sparc/kernel/prom_64.c
@@ -555,9 +555,6 @@
 
 		cpu_data(cpuid).core_id = portid + 1;
 		cpu_data(cpuid).proc_id = portid;
-#ifdef CONFIG_SMP
-		sparc64_multi_core = 1;
-#endif
 	} else {
 		cpu_data(cpuid).dcache_size =
 			of_getintprop_default(dp, "dcache-size", 16 * 1024);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index b085311..9781048 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -53,8 +53,6 @@
 
 #include "cpumap.h"
 
-int sparc64_multi_core __read_mostly;
-
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
 	{ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index 87729ff..33a17e7 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -189,7 +189,8 @@
 	 mov	%i0, %l5				! IEU1
 5:	call	%l7					! CTI	Group brk forced
 	 srl	%i5, 0, %o5				! IEU1
-	ba,a,pt	%xcc, 3f
+	ba,pt	%xcc, 3f
+	 sra	%o0, 0, %o0
 
 	/* Linux native system calls enter here... */
 	.align	32
@@ -217,7 +218,6 @@
 3:	stx	%o0, [%sp + PTREGS_OFF + PT_V9_I0]
 ret_sys_call:
 	ldx	[%sp + PTREGS_OFF + PT_V9_TSTATE], %g3
-	sra	%o0, 0, %o0
 	mov	%ulo(TSTATE_XCARRY | TSTATE_ICARRY), %g2
 	sllx	%g2, 32, %g2
 
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 869023a..cfbe53c 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -14,6 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/vmalloc.h>
 #include <linux/kdebug.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/log2.h>
@@ -62,6 +63,7 @@
 static pgd_t *srmmu_swapper_pg_dir;
 
 const struct sparc32_cachetlb_ops *sparc32_cachetlb_ops;
+EXPORT_SYMBOL(sparc32_cachetlb_ops);
 
 #ifdef CONFIG_SMP
 const struct sparc32_cachetlb_ops *local_ops;
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 3b3a360..f5d506f 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -273,7 +273,7 @@
 		prom_halt();
 	}
 
-	for (i = 0; i < 8; i++) {
+	for (i = 0; i < ARRAY_SIZE(tsb_cache_names); i++) {
 		unsigned long size = 8192 << i;
 		const char *name = tsb_cache_names[i];
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 940e50e..8453fe1 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -444,6 +444,7 @@
 	bool "Intel MID platform support"
 	depends on X86_32
 	depends on X86_EXTENDED_PLATFORM
+	depends on X86_PLATFORM_DEVICES
 	depends on PCI
 	depends on PCI_GOANY
 	depends on X86_IO_APIC
@@ -1051,9 +1052,9 @@
 	  This options enables microcode patch loading support for Intel
 	  processors.
 
-	  For latest news and information on obtaining all the required
-	  Intel ingredients for this driver, check:
-	  <http://www.urbanmyth.org/microcode/>.
+	  For the current Intel microcode data package go to
+	  <https://downloadcenter.intel.com> and search for
+	  'Linux Processor Microcode Data File'.
 
 config MICROCODE_AMD
 	bool "AMD microcode loading support"
@@ -1584,6 +1585,20 @@
 
 	  See Documentation/efi-stub.txt for more information.
 
+config EFI_MIXED
+	bool "EFI mixed-mode support"
+	depends on EFI_STUB && X86_64
+	---help---
+	   Enabling this feature allows a 64-bit kernel to be booted
+	   on a 32-bit firmware, provided that your CPU supports 64-bit
+	   mode.
+
+	   Note that it is not possible to boot a mixed-mode enabled
+	   kernel via the EFI boot stub - a bootloader that supports
+	   the EFI handover protocol must be used.
+
+	   If unsure, say N.
+
 config SECCOMP
 	def_bool y
 	prompt "Enable seccomp to safely compute untrusted bytecode"
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index c026cca..f3aaf23 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -341,10 +341,6 @@
 	def_bool y
 	depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
 
-config X86_OOSTORE
-	def_bool y
-	depends on (MWINCHIP3D || MWINCHIPC6) && MTRR
-
 #
 # P6_NOPs are a relatively minor optimization that require a family >=
 # 6 processor, except that it is broken on certain VIA chips.
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 0f3621e..61bd2ad 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -81,6 +81,15 @@
 	  kernel.
 	  If in doubt, say "N"
 
+config EFI_PGT_DUMP
+	bool "Dump the EFI pagetable"
+	depends on EFI && X86_PTDUMP
+	---help---
+	  Enable this if you want to dump the EFI page table before
+	  enabling virtual mode. This can be used to debug miscellaneous
+	  issues with the mapping of the EFI runtime regions into that
+	  table.
+
 config DEBUG_RODATA
 	bool "Write protect kernel read-only data structures"
 	default y
@@ -184,6 +193,7 @@
 config X86_DECODER_SELFTEST
 	bool "x86 instruction decoder selftest"
 	depends on DEBUG_KERNEL && KPROBES
+	depends on !COMPILE_TEST
 	---help---
 	 Perform x86 instruction decoder selftests at build time.
 	 This option is useful for checking the sanity of x86 instruction
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index eeda43a..3b9348a 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -82,8 +82,8 @@
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
-        # Don't autogenerate MMX or SSE instructions
-        KBUILD_CFLAGS += -mno-mmx -mno-sse
+        # Don't autogenerate traditional x87, MMX or SSE instructions
+        KBUILD_CFLAGS += -mno-mmx -mno-sse -mno-80387 -mno-fp-ret-in-387
 
 	# Use -mpreferred-stack-boundary=3 if supported.
 	KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
@@ -152,6 +152,7 @@
 
 # does binutils support specific instructions?
 asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
+asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
 avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
 
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 878df7e..abb9eba 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -80,7 +80,7 @@
 $(obj)/voffset.h: vmlinux FORCE
 	$(call if_changed,voffset)
 
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi_pe_entry\|efi_stub_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 90a21f4..4dbf967 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -111,7 +111,7 @@
 };
 
 #define MEM_AVOID_MAX 5
-struct mem_vector mem_avoid[MEM_AVOID_MAX];
+static struct mem_vector mem_avoid[MEM_AVOID_MAX];
 
 static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
 {
@@ -180,7 +180,7 @@
 }
 
 /* Does this memory vector overlap a known avoided area? */
-bool mem_avoid_overlap(struct mem_vector *img)
+static bool mem_avoid_overlap(struct mem_vector *img)
 {
 	int i;
 
@@ -192,8 +192,9 @@
 	return false;
 }
 
-unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN];
-unsigned long slot_max = 0;
+static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+			   CONFIG_PHYSICAL_ALIGN];
+static unsigned long slot_max;
 
 static void slots_append(unsigned long addr)
 {
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index a7677ba..1e61461 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -19,11 +19,273 @@
 
 static efi_system_table_t *sys_table;
 
+static struct efi_config *efi_early;
+
+#define efi_call_early(f, ...)						\
+	efi_early->call(efi_early->f, __VA_ARGS__);
+
+#define BOOT_SERVICES(bits)						\
+static void setup_boot_services##bits(struct efi_config *c)		\
+{									\
+	efi_system_table_##bits##_t *table;				\
+	efi_boot_services_##bits##_t *bt;				\
+									\
+	table = (typeof(table))sys_table;				\
+									\
+	c->text_output = table->con_out;				\
+									\
+	bt = (typeof(bt))(unsigned long)(table->boottime);		\
+									\
+	c->allocate_pool = bt->allocate_pool;				\
+	c->allocate_pages = bt->allocate_pages;				\
+	c->get_memory_map = bt->get_memory_map;				\
+	c->free_pool = bt->free_pool;					\
+	c->free_pages = bt->free_pages;					\
+	c->locate_handle = bt->locate_handle;				\
+	c->handle_protocol = bt->handle_protocol;			\
+	c->exit_boot_services = bt->exit_boot_services;			\
+}
+BOOT_SERVICES(32);
+BOOT_SERVICES(64);
+
+static void efi_printk(efi_system_table_t *, char *);
+static void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
+
+static efi_status_t
+__file_size32(void *__fh, efi_char16_t *filename_16,
+	      void **handle, u64 *file_sz)
+{
+	efi_file_handle_32_t *h, *fh = __fh;
+	efi_file_info_t *info;
+	efi_status_t status;
+	efi_guid_t info_guid = EFI_FILE_INFO_ID;
+	u32 info_sz;
+
+	status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
+				 EFI_FILE_MODE_READ, (u64)0);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table, "Failed to open file: ");
+		efi_char16_printk(sys_table, filename_16);
+		efi_printk(sys_table, "\n");
+		return status;
+	}
+
+	*handle = h;
+
+	info_sz = 0;
+	status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+				 &info_sz, NULL);
+	if (status != EFI_BUFFER_TOO_SMALL) {
+		efi_printk(sys_table, "Failed to get file info size\n");
+		return status;
+	}
+
+grow:
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				info_sz, (void **)&info);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table, "Failed to alloc mem for file info\n");
+		return status;
+	}
+
+	status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+				 &info_sz, info);
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		efi_call_early(free_pool, info);
+		goto grow;
+	}
+
+	*file_sz = info->file_size;
+	efi_call_early(free_pool, info);
+
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table, "Failed to get initrd info\n");
+
+	return status;
+}
+
+static efi_status_t
+__file_size64(void *__fh, efi_char16_t *filename_16,
+	      void **handle, u64 *file_sz)
+{
+	efi_file_handle_64_t *h, *fh = __fh;
+	efi_file_info_t *info;
+	efi_status_t status;
+	efi_guid_t info_guid = EFI_FILE_INFO_ID;
+	u32 info_sz;
+
+	status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
+				 EFI_FILE_MODE_READ, (u64)0);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table, "Failed to open file: ");
+		efi_char16_printk(sys_table, filename_16);
+		efi_printk(sys_table, "\n");
+		return status;
+	}
+
+	*handle = h;
+
+	info_sz = 0;
+	status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+				 &info_sz, NULL);
+	if (status != EFI_BUFFER_TOO_SMALL) {
+		efi_printk(sys_table, "Failed to get file info size\n");
+		return status;
+	}
+
+grow:
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				info_sz, (void **)&info);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table, "Failed to alloc mem for file info\n");
+		return status;
+	}
+
+	status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+				 &info_sz, info);
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		efi_call_early(free_pool, info);
+		goto grow;
+	}
+
+	*file_sz = info->file_size;
+	efi_call_early(free_pool, info);
+
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table, "Failed to get initrd info\n");
+
+	return status;
+}
+static efi_status_t
+efi_file_size(efi_system_table_t *sys_table, void *__fh,
+	      efi_char16_t *filename_16, void **handle, u64 *file_sz)
+{
+	if (efi_early->is64)
+		return __file_size64(__fh, filename_16, handle, file_sz);
+
+	return __file_size32(__fh, filename_16, handle, file_sz);
+}
+
+static inline efi_status_t
+efi_file_read(void *__fh, void *handle, unsigned long *size, void *addr)
+{
+	unsigned long func;
+
+	if (efi_early->is64) {
+		efi_file_handle_64_t *fh = __fh;
+
+		func = (unsigned long)fh->read;
+		return efi_early->call(func, handle, size, addr);
+	} else {
+		efi_file_handle_32_t *fh = __fh;
+
+		func = (unsigned long)fh->read;
+		return efi_early->call(func, handle, size, addr);
+	}
+}
+
+static inline efi_status_t efi_file_close(void *__fh, void *handle)
+{
+	if (efi_early->is64) {
+		efi_file_handle_64_t *fh = __fh;
+
+		return efi_early->call((unsigned long)fh->close, handle);
+	} else {
+		efi_file_handle_32_t *fh = __fh;
+
+		return efi_early->call((unsigned long)fh->close, handle);
+	}
+}
+
+static inline efi_status_t __open_volume32(void *__image, void **__fh)
+{
+	efi_file_io_interface_t *io;
+	efi_loaded_image_32_t *image = __image;
+	efi_file_handle_32_t *fh;
+	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+	efi_status_t status;
+	void *handle = (void *)(unsigned long)image->device_handle;
+	unsigned long func;
+
+	status = efi_call_early(handle_protocol, handle,
+				&fs_proto, (void **)&io);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table, "Failed to handle fs_proto\n");
+		return status;
+	}
+
+	func = (unsigned long)io->open_volume;
+	status = efi_early->call(func, io, &fh);
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table, "Failed to open volume\n");
+
+	*__fh = fh;
+	return status;
+}
+
+static inline efi_status_t __open_volume64(void *__image, void **__fh)
+{
+	efi_file_io_interface_t *io;
+	efi_loaded_image_64_t *image = __image;
+	efi_file_handle_64_t *fh;
+	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+	efi_status_t status;
+	void *handle = (void *)(unsigned long)image->device_handle;
+	unsigned long func;
+
+	status = efi_call_early(handle_protocol, handle,
+				&fs_proto, (void **)&io);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table, "Failed to handle fs_proto\n");
+		return status;
+	}
+
+	func = (unsigned long)io->open_volume;
+	status = efi_early->call(func, io, &fh);
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table, "Failed to open volume\n");
+
+	*__fh = fh;
+	return status;
+}
+
+static inline efi_status_t
+efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
+{
+	if (efi_early->is64)
+		return __open_volume64(__image, __fh);
+
+	return __open_volume32(__image, __fh);
+}
+
+static void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
+{
+	unsigned long output_string;
+	size_t offset;
+
+	if (efi_early->is64) {
+		struct efi_simple_text_output_protocol_64 *out;
+		u64 *func;
+
+		offset = offsetof(typeof(*out), output_string);
+		output_string = efi_early->text_output + offset;
+		func = (u64 *)output_string;
+
+		efi_early->call(*func, efi_early->text_output, str);
+	} else {
+		struct efi_simple_text_output_protocol_32 *out;
+		u32 *func;
+
+		offset = offsetof(typeof(*out), output_string);
+		output_string = efi_early->text_output + offset;
+		func = (u32 *)output_string;
+
+		efi_early->call(*func, efi_early->text_output, str);
+	}
+}
 
 #include "../../../../drivers/firmware/efi/efi-stub-helper.c"
 
-
-
 static void find_bits(unsigned long mask, u8 *pos, u8 *size)
 {
 	u8 first, len;
@@ -47,48 +309,87 @@
 	*size = len;
 }
 
-static efi_status_t setup_efi_pci(struct boot_params *params)
+static efi_status_t
+__setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
 {
-	efi_pci_io_protocol *pci;
+	struct pci_setup_rom *rom = NULL;
 	efi_status_t status;
-	void **pci_handle;
+	unsigned long size;
+	uint64_t attributes;
+
+	status = efi_early->call(pci->attributes, pci,
+				 EfiPciIoAttributeOperationGet, 0, 0,
+				 &attributes);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	if (!pci->romimage || !pci->romsize)
+		return EFI_INVALID_PARAMETER;
+
+	size = pci->romsize + sizeof(*rom);
+
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	memset(rom, 0, sizeof(*rom));
+
+	rom->data.type = SETUP_PCI;
+	rom->data.len = size - sizeof(struct setup_data);
+	rom->data.next = 0;
+	rom->pcilen = pci->romsize;
+	*__rom = rom;
+
+	status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+				 PCI_VENDOR_ID, 1, &(rom->vendor));
+
+	if (status != EFI_SUCCESS)
+		goto free_struct;
+
+	status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+				 PCI_DEVICE_ID, 1, &(rom->devid));
+
+	if (status != EFI_SUCCESS)
+		goto free_struct;
+
+	status = efi_early->call(pci->get_location, pci, &(rom->segment),
+				 &(rom->bus), &(rom->device), &(rom->function));
+
+	if (status != EFI_SUCCESS)
+		goto free_struct;
+
+	memcpy(rom->romdata, pci->romimage, pci->romsize);
+	return status;
+
+free_struct:
+	efi_call_early(free_pool, rom);
+	return status;
+}
+
+static efi_status_t
+setup_efi_pci32(struct boot_params *params, void **pci_handle,
+		unsigned long size)
+{
+	efi_pci_io_protocol_32 *pci = NULL;
 	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
-	unsigned long nr_pci, size = 0;
-	int i;
+	u32 *handles = (u32 *)(unsigned long)pci_handle;
+	efi_status_t status;
+	unsigned long nr_pci;
 	struct setup_data *data;
+	int i;
 
 	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
 
 	while (data && data->next)
 		data = (struct setup_data *)(unsigned long)data->next;
 
-	status = efi_call_phys5(sys_table->boottime->locate_handle,
-				EFI_LOCATE_BY_PROTOCOL, &pci_proto,
-				NULL, &size, pci_handle);
-
-	if (status == EFI_BUFFER_TOO_SMALL) {
-		status = efi_call_phys3(sys_table->boottime->allocate_pool,
-					EFI_LOADER_DATA, size, &pci_handle);
-
-		if (status != EFI_SUCCESS)
-			return status;
-
-		status = efi_call_phys5(sys_table->boottime->locate_handle,
-					EFI_LOCATE_BY_PROTOCOL, &pci_proto,
-					NULL, &size, pci_handle);
-	}
-
-	if (status != EFI_SUCCESS)
-		goto free_handle;
-
-	nr_pci = size / sizeof(void *);
+	nr_pci = size / sizeof(u32);
 	for (i = 0; i < nr_pci; i++) {
-		void *h = pci_handle[i];
-		uint64_t attributes;
-		struct pci_setup_rom *rom;
+		struct pci_setup_rom *rom = NULL;
+		u32 h = handles[i];
 
-		status = efi_call_phys3(sys_table->boottime->handle_protocol,
-					h, &pci_proto, &pci);
+		status = efi_call_early(handle_protocol, h,
+					&pci_proto, (void **)&pci);
 
 		if (status != EFI_SUCCESS)
 			continue;
@@ -96,57 +397,10 @@
 		if (!pci)
 			continue;
 
-#ifdef CONFIG_X86_64
-		status = efi_call_phys4(pci->attributes, pci,
-					EfiPciIoAttributeOperationGet, 0,
-					&attributes);
-#else
-		status = efi_call_phys5(pci->attributes, pci,
-					EfiPciIoAttributeOperationGet, 0, 0,
-					&attributes);
-#endif
+		status = __setup_efi_pci32(pci, &rom);
 		if (status != EFI_SUCCESS)
 			continue;
 
-		if (!pci->romimage || !pci->romsize)
-			continue;
-
-		size = pci->romsize + sizeof(*rom);
-
-		status = efi_call_phys3(sys_table->boottime->allocate_pool,
-				EFI_LOADER_DATA, size, &rom);
-
-		if (status != EFI_SUCCESS)
-			continue;
-
-		rom->data.type = SETUP_PCI;
-		rom->data.len = size - sizeof(struct setup_data);
-		rom->data.next = 0;
-		rom->pcilen = pci->romsize;
-
-		status = efi_call_phys5(pci->pci.read, pci,
-					EfiPciIoWidthUint16, PCI_VENDOR_ID,
-					1, &(rom->vendor));
-
-		if (status != EFI_SUCCESS)
-			goto free_struct;
-
-		status = efi_call_phys5(pci->pci.read, pci,
-					EfiPciIoWidthUint16, PCI_DEVICE_ID,
-					1, &(rom->devid));
-
-		if (status != EFI_SUCCESS)
-			goto free_struct;
-
-		status = efi_call_phys5(pci->get_location, pci,
-					&(rom->segment), &(rom->bus),
-					&(rom->device), &(rom->function));
-
-		if (status != EFI_SUCCESS)
-			goto free_struct;
-
-		memcpy(rom->romdata, pci->romimage, pci->romsize);
-
 		if (data)
 			data->next = (unsigned long)rom;
 		else
@@ -154,105 +408,155 @@
 
 		data = (struct setup_data *)rom;
 
-		continue;
-	free_struct:
-		efi_call_phys1(sys_table->boottime->free_pool, rom);
 	}
 
-free_handle:
-	efi_call_phys1(sys_table->boottime->free_pool, pci_handle);
 	return status;
 }
 
-/*
- * See if we have Graphics Output Protocol
- */
-static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
-			      unsigned long size)
+static efi_status_t
+__setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom)
 {
-	struct efi_graphics_output_protocol *gop, *first_gop;
-	struct efi_pixel_bitmask pixel_info;
-	unsigned long nr_gops;
+	struct pci_setup_rom *rom;
 	efi_status_t status;
-	void **gop_handle;
-	u16 width, height;
-	u32 fb_base, fb_size;
-	u32 pixels_per_scan_line;
-	int pixel_format;
-	int i;
+	unsigned long size;
+	uint64_t attributes;
 
-	status = efi_call_phys3(sys_table->boottime->allocate_pool,
-				EFI_LOADER_DATA, size, &gop_handle);
+	status = efi_early->call(pci->attributes, pci,
+				 EfiPciIoAttributeOperationGet, 0,
+				 &attributes);
 	if (status != EFI_SUCCESS)
 		return status;
 
-	status = efi_call_phys5(sys_table->boottime->locate_handle,
-				EFI_LOCATE_BY_PROTOCOL, proto,
-				NULL, &size, gop_handle);
+	if (!pci->romimage || !pci->romsize)
+		return EFI_INVALID_PARAMETER;
+
+	size = pci->romsize + sizeof(*rom);
+
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
 	if (status != EFI_SUCCESS)
-		goto free_handle;
+		return status;
 
-	first_gop = NULL;
+	rom->data.type = SETUP_PCI;
+	rom->data.len = size - sizeof(struct setup_data);
+	rom->data.next = 0;
+	rom->pcilen = pci->romsize;
+	*__rom = rom;
 
-	nr_gops = size / sizeof(void *);
-	for (i = 0; i < nr_gops; i++) {
-		struct efi_graphics_output_mode_info *info;
-		efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
-		bool conout_found = false;
-		void *dummy;
-		void *h = gop_handle[i];
+	status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+				 PCI_VENDOR_ID, 1, &(rom->vendor));
 
-		status = efi_call_phys3(sys_table->boottime->handle_protocol,
-					h, proto, &gop);
+	if (status != EFI_SUCCESS)
+		goto free_struct;
+
+	status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+				 PCI_DEVICE_ID, 1, &(rom->devid));
+
+	if (status != EFI_SUCCESS)
+		goto free_struct;
+
+	status = efi_early->call(pci->get_location, pci, &(rom->segment),
+				 &(rom->bus), &(rom->device), &(rom->function));
+
+	if (status != EFI_SUCCESS)
+		goto free_struct;
+
+	memcpy(rom->romdata, pci->romimage, pci->romsize);
+	return status;
+
+free_struct:
+	efi_call_early(free_pool, rom);
+	return status;
+
+}
+
+static efi_status_t
+setup_efi_pci64(struct boot_params *params, void **pci_handle,
+		unsigned long size)
+{
+	efi_pci_io_protocol_64 *pci = NULL;
+	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+	u64 *handles = (u64 *)(unsigned long)pci_handle;
+	efi_status_t status;
+	unsigned long nr_pci;
+	struct setup_data *data;
+	int i;
+
+	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+	while (data && data->next)
+		data = (struct setup_data *)(unsigned long)data->next;
+
+	nr_pci = size / sizeof(u64);
+	for (i = 0; i < nr_pci; i++) {
+		struct pci_setup_rom *rom = NULL;
+		u64 h = handles[i];
+
+		status = efi_call_early(handle_protocol, h,
+					&pci_proto, (void **)&pci);
+
 		if (status != EFI_SUCCESS)
 			continue;
 
-		status = efi_call_phys3(sys_table->boottime->handle_protocol,
-					h, &conout_proto, &dummy);
+		if (!pci)
+			continue;
 
-		if (status == EFI_SUCCESS)
-			conout_found = true;
+		status = __setup_efi_pci64(pci, &rom);
+		if (status != EFI_SUCCESS)
+			continue;
 
-		status = efi_call_phys4(gop->query_mode, gop,
-					gop->mode->mode, &size, &info);
-		if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
-			/*
-			 * Systems that use the UEFI Console Splitter may
-			 * provide multiple GOP devices, not all of which are
-			 * backed by real hardware. The workaround is to search
-			 * for a GOP implementing the ConOut protocol, and if
-			 * one isn't found, to just fall back to the first GOP.
-			 */
-			width = info->horizontal_resolution;
-			height = info->vertical_resolution;
-			fb_base = gop->mode->frame_buffer_base;
-			fb_size = gop->mode->frame_buffer_size;
-			pixel_format = info->pixel_format;
-			pixel_info = info->pixel_information;
-			pixels_per_scan_line = info->pixels_per_scan_line;
+		if (data)
+			data->next = (unsigned long)rom;
+		else
+			params->hdr.setup_data = (unsigned long)rom;
 
-			/*
-			 * Once we've found a GOP supporting ConOut,
-			 * don't bother looking any further.
-			 */
-			first_gop = gop;
-			if (conout_found)
-				break;
-		}
+		data = (struct setup_data *)rom;
+
 	}
 
-	/* Did we find any GOPs? */
-	if (!first_gop)
+	return status;
+}
+
+static efi_status_t setup_efi_pci(struct boot_params *params)
+{
+	efi_status_t status;
+	void **pci_handle = NULL;
+	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+	unsigned long size = 0;
+
+	status = efi_call_early(locate_handle,
+				EFI_LOCATE_BY_PROTOCOL,
+				&pci_proto, NULL, &size, pci_handle);
+
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		status = efi_call_early(allocate_pool,
+					EFI_LOADER_DATA,
+					size, (void **)&pci_handle);
+
+		if (status != EFI_SUCCESS)
+			return status;
+
+		status = efi_call_early(locate_handle,
+					EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+					NULL, &size, pci_handle);
+	}
+
+	if (status != EFI_SUCCESS)
 		goto free_handle;
 
-	/* EFI framebuffer */
-	si->orig_video_isVGA = VIDEO_TYPE_EFI;
+	if (efi_early->is64)
+		status = setup_efi_pci64(params, pci_handle, size);
+	else
+		status = setup_efi_pci32(params, pci_handle, size);
 
-	si->lfb_width = width;
-	si->lfb_height = height;
-	si->lfb_base = fb_base;
-	si->pages = 1;
+free_handle:
+	efi_call_early(free_pool, pci_handle);
+	return status;
+}
 
+static void
+setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line,
+		 struct efi_pixel_bitmask pixel_info, int pixel_format)
+{
 	if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) {
 		si->lfb_depth = 32;
 		si->lfb_linelength = pixels_per_scan_line * 4;
@@ -297,62 +601,274 @@
 		si->rsvd_size = 0;
 		si->rsvd_pos = 0;
 	}
+}
+
+static efi_status_t
+__gop_query32(struct efi_graphics_output_protocol_32 *gop32,
+	      struct efi_graphics_output_mode_info **info,
+	      unsigned long *size, u32 *fb_base)
+{
+	struct efi_graphics_output_protocol_mode_32 *mode;
+	efi_status_t status;
+	unsigned long m;
+
+	m = gop32->mode;
+	mode = (struct efi_graphics_output_protocol_mode_32 *)m;
+
+	status = efi_early->call(gop32->query_mode, gop32,
+				 mode->mode, size, info);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	*fb_base = mode->frame_buffer_base;
+	return status;
+}
+
+static efi_status_t
+setup_gop32(struct screen_info *si, efi_guid_t *proto,
+	    unsigned long size, void **gop_handle)
+{
+	struct efi_graphics_output_protocol_32 *gop32, *first_gop;
+	unsigned long nr_gops;
+	u16 width, height;
+	u32 pixels_per_scan_line;
+	u32 fb_base;
+	struct efi_pixel_bitmask pixel_info;
+	int pixel_format;
+	efi_status_t status;
+	u32 *handles = (u32 *)(unsigned long)gop_handle;
+	int i;
+
+	first_gop = NULL;
+	gop32 = NULL;
+
+	nr_gops = size / sizeof(u32);
+	for (i = 0; i < nr_gops; i++) {
+		struct efi_graphics_output_mode_info *info = NULL;
+		efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
+		bool conout_found = false;
+		void *dummy = NULL;
+		u32 h = handles[i];
+
+		status = efi_call_early(handle_protocol, h,
+					proto, (void **)&gop32);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		status = efi_call_early(handle_protocol, h,
+					&conout_proto, &dummy);
+		if (status == EFI_SUCCESS)
+			conout_found = true;
+
+		status = __gop_query32(gop32, &info, &size, &fb_base);
+		if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+			/*
+			 * Systems that use the UEFI Console Splitter may
+			 * provide multiple GOP devices, not all of which are
+			 * backed by real hardware. The workaround is to search
+			 * for a GOP implementing the ConOut protocol, and if
+			 * one isn't found, to just fall back to the first GOP.
+			 */
+			width = info->horizontal_resolution;
+			height = info->vertical_resolution;
+			pixel_format = info->pixel_format;
+			pixel_info = info->pixel_information;
+			pixels_per_scan_line = info->pixels_per_scan_line;
+
+			/*
+			 * Once we've found a GOP supporting ConOut,
+			 * don't bother looking any further.
+			 */
+			first_gop = gop32;
+			if (conout_found)
+				break;
+		}
+	}
+
+	/* Did we find any GOPs? */
+	if (!first_gop)
+		goto out;
+
+	/* EFI framebuffer */
+	si->orig_video_isVGA = VIDEO_TYPE_EFI;
+
+	si->lfb_width = width;
+	si->lfb_height = height;
+	si->lfb_base = fb_base;
+	si->pages = 1;
+
+	setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format);
 
 	si->lfb_size = si->lfb_linelength * si->lfb_height;
 
 	si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
+out:
+	return status;
+}
 
-free_handle:
-	efi_call_phys1(sys_table->boottime->free_pool, gop_handle);
+static efi_status_t
+__gop_query64(struct efi_graphics_output_protocol_64 *gop64,
+	      struct efi_graphics_output_mode_info **info,
+	      unsigned long *size, u32 *fb_base)
+{
+	struct efi_graphics_output_protocol_mode_64 *mode;
+	efi_status_t status;
+	unsigned long m;
+
+	m = gop64->mode;
+	mode = (struct efi_graphics_output_protocol_mode_64 *)m;
+
+	status = efi_early->call(gop64->query_mode, gop64,
+				 mode->mode, size, info);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	*fb_base = mode->frame_buffer_base;
+	return status;
+}
+
+static efi_status_t
+setup_gop64(struct screen_info *si, efi_guid_t *proto,
+	    unsigned long size, void **gop_handle)
+{
+	struct efi_graphics_output_protocol_64 *gop64, *first_gop;
+	unsigned long nr_gops;
+	u16 width, height;
+	u32 pixels_per_scan_line;
+	u32 fb_base;
+	struct efi_pixel_bitmask pixel_info;
+	int pixel_format;
+	efi_status_t status;
+	u64 *handles = (u64 *)(unsigned long)gop_handle;
+	int i;
+
+	first_gop = NULL;
+	gop64 = NULL;
+
+	nr_gops = size / sizeof(u64);
+	for (i = 0; i < nr_gops; i++) {
+		struct efi_graphics_output_mode_info *info = NULL;
+		efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
+		bool conout_found = false;
+		void *dummy = NULL;
+		u64 h = handles[i];
+
+		status = efi_call_early(handle_protocol, h,
+					proto, (void **)&gop64);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		status = efi_call_early(handle_protocol, h,
+					&conout_proto, &dummy);
+		if (status == EFI_SUCCESS)
+			conout_found = true;
+
+		status = __gop_query64(gop64, &info, &size, &fb_base);
+		if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+			/*
+			 * Systems that use the UEFI Console Splitter may
+			 * provide multiple GOP devices, not all of which are
+			 * backed by real hardware. The workaround is to search
+			 * for a GOP implementing the ConOut protocol, and if
+			 * one isn't found, to just fall back to the first GOP.
+			 */
+			width = info->horizontal_resolution;
+			height = info->vertical_resolution;
+			pixel_format = info->pixel_format;
+			pixel_info = info->pixel_information;
+			pixels_per_scan_line = info->pixels_per_scan_line;
+
+			/*
+			 * Once we've found a GOP supporting ConOut,
+			 * don't bother looking any further.
+			 */
+			first_gop = gop64;
+			if (conout_found)
+				break;
+		}
+	}
+
+	/* Did we find any GOPs? */
+	if (!first_gop)
+		goto out;
+
+	/* EFI framebuffer */
+	si->orig_video_isVGA = VIDEO_TYPE_EFI;
+
+	si->lfb_width = width;
+	si->lfb_height = height;
+	si->lfb_base = fb_base;
+	si->pages = 1;
+
+	setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format);
+
+	si->lfb_size = si->lfb_linelength * si->lfb_height;
+
+	si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
+out:
 	return status;
 }
 
 /*
- * See if we have Universal Graphics Adapter (UGA) protocol
+ * See if we have Graphics Output Protocol
  */
-static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
+static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
 			      unsigned long size)
 {
-	struct efi_uga_draw_protocol *uga, *first_uga;
-	unsigned long nr_ugas;
 	efi_status_t status;
-	u32 width, height;
-	void **uga_handle = NULL;
-	int i;
+	void **gop_handle = NULL;
 
-	status = efi_call_phys3(sys_table->boottime->allocate_pool,
-				EFI_LOADER_DATA, size, &uga_handle);
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				size, (void **)&gop_handle);
 	if (status != EFI_SUCCESS)
 		return status;
 
-	status = efi_call_phys5(sys_table->boottime->locate_handle,
-				EFI_LOCATE_BY_PROTOCOL, uga_proto,
-				NULL, &size, uga_handle);
+	status = efi_call_early(locate_handle,
+				EFI_LOCATE_BY_PROTOCOL,
+				proto, NULL, &size, gop_handle);
 	if (status != EFI_SUCCESS)
 		goto free_handle;
 
-	first_uga = NULL;
+	if (efi_early->is64)
+		status = setup_gop64(si, proto, size, gop_handle);
+	else
+		status = setup_gop32(si, proto, size, gop_handle);
 
-	nr_ugas = size / sizeof(void *);
+free_handle:
+	efi_call_early(free_pool, gop_handle);
+	return status;
+}
+
+static efi_status_t
+setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
+{
+	struct efi_uga_draw_protocol *uga = NULL, *first_uga;
+	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+	unsigned long nr_ugas;
+	u32 *handles = (u32 *)uga_handle;;
+	efi_status_t status;
+	int i;
+
+	first_uga = NULL;
+	nr_ugas = size / sizeof(u32);
 	for (i = 0; i < nr_ugas; i++) {
 		efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
-		void *handle = uga_handle[i];
 		u32 w, h, depth, refresh;
 		void *pciio;
+		u32 handle = handles[i];
 
-		status = efi_call_phys3(sys_table->boottime->handle_protocol,
-					handle, uga_proto, &uga);
+		status = efi_call_early(handle_protocol, handle,
+					&uga_proto, (void **)&uga);
 		if (status != EFI_SUCCESS)
 			continue;
 
-		efi_call_phys3(sys_table->boottime->handle_protocol,
-			       handle, &pciio_proto, &pciio);
+		efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
 
-		status = efi_call_phys5(uga->get_mode, uga, &w, &h,
-					&depth, &refresh);
+		status = efi_early->call((unsigned long)uga->get_mode, uga,
+					 &w, &h, &depth, &refresh);
 		if (status == EFI_SUCCESS && (!first_uga || pciio)) {
-			width = w;
-			height = h;
+			*width = w;
+			*height = h;
 
 			/*
 			 * Once we've found a UGA supporting PCIIO,
@@ -365,7 +881,84 @@
 		}
 	}
 
-	if (!first_uga)
+	return status;
+}
+
+static efi_status_t
+setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
+{
+	struct efi_uga_draw_protocol *uga = NULL, *first_uga;
+	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+	unsigned long nr_ugas;
+	u64 *handles = (u64 *)uga_handle;;
+	efi_status_t status;
+	int i;
+
+	first_uga = NULL;
+	nr_ugas = size / sizeof(u64);
+	for (i = 0; i < nr_ugas; i++) {
+		efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
+		u32 w, h, depth, refresh;
+		void *pciio;
+		u64 handle = handles[i];
+
+		status = efi_call_early(handle_protocol, handle,
+					&uga_proto, (void **)&uga);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
+
+		status = efi_early->call((unsigned long)uga->get_mode, uga,
+					 &w, &h, &depth, &refresh);
+		if (status == EFI_SUCCESS && (!first_uga || pciio)) {
+			*width = w;
+			*height = h;
+
+			/*
+			 * Once we've found a UGA supporting PCIIO,
+			 * don't bother looking any further.
+			 */
+			if (pciio)
+				break;
+
+			first_uga = uga;
+		}
+	}
+
+	return status;
+}
+
+/*
+ * See if we have Universal Graphics Adapter (UGA) protocol
+ */
+static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
+			      unsigned long size)
+{
+	efi_status_t status;
+	u32 width, height;
+	void **uga_handle = NULL;
+
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				size, (void **)&uga_handle);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	status = efi_call_early(locate_handle,
+				EFI_LOCATE_BY_PROTOCOL,
+				uga_proto, NULL, &size, uga_handle);
+	if (status != EFI_SUCCESS)
+		goto free_handle;
+
+	height = 0;
+	width = 0;
+
+	if (efi_early->is64)
+		status = setup_uga64(uga_handle, size, &width, &height);
+	else
+		status = setup_uga32(uga_handle, size, &width, &height);
+
+	if (!width && !height)
 		goto free_handle;
 
 	/* EFI framebuffer */
@@ -384,9 +977,8 @@
 	si->rsvd_size = 8;
 	si->rsvd_pos = 24;
 
-
 free_handle:
-	efi_call_phys1(sys_table->boottime->free_pool, uga_handle);
+	efi_call_early(free_pool, uga_handle);
 	return status;
 }
 
@@ -404,29 +996,28 @@
 	memset(si, 0, sizeof(*si));
 
 	size = 0;
-	status = efi_call_phys5(sys_table->boottime->locate_handle,
-				EFI_LOCATE_BY_PROTOCOL, &graphics_proto,
-				NULL, &size, gop_handle);
+	status = efi_call_early(locate_handle,
+				EFI_LOCATE_BY_PROTOCOL,
+				&graphics_proto, NULL, &size, gop_handle);
 	if (status == EFI_BUFFER_TOO_SMALL)
 		status = setup_gop(si, &graphics_proto, size);
 
 	if (status != EFI_SUCCESS) {
 		size = 0;
-		status = efi_call_phys5(sys_table->boottime->locate_handle,
-					EFI_LOCATE_BY_PROTOCOL, &uga_proto,
-					NULL, &size, uga_handle);
+		status = efi_call_early(locate_handle,
+					EFI_LOCATE_BY_PROTOCOL,
+					&uga_proto, NULL, &size, uga_handle);
 		if (status == EFI_BUFFER_TOO_SMALL)
 			setup_uga(si, &uga_proto, size);
 	}
 }
 
-
 /*
  * Because the x86 boot code expects to be passed a boot_params we
  * need to create one ourselves (usually the bootloader would create
  * one for us).
  */
-struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
+struct boot_params *make_boot_params(struct efi_config *c)
 {
 	struct boot_params *boot_params;
 	struct sys_desc_table *sdt;
@@ -434,7 +1025,7 @@
 	struct setup_header *hdr;
 	struct efi_info *efi;
 	efi_loaded_image_t *image;
-	void *options;
+	void *options, *handle;
 	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
 	int options_size = 0;
 	efi_status_t status;
@@ -445,14 +1036,21 @@
 	unsigned long ramdisk_addr;
 	unsigned long ramdisk_size;
 
-	sys_table = _table;
+	efi_early = c;
+	sys_table = (efi_system_table_t *)(unsigned long)efi_early->table;
+	handle = (void *)(unsigned long)efi_early->image_handle;
 
 	/* Check if we were booted by the EFI firmware */
 	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		return NULL;
 
-	status = efi_call_phys3(sys_table->boottime->handle_protocol,
-				handle, &proto, (void *)&image);
+	if (efi_early->is64)
+		setup_boot_services64(efi_early);
+	else
+		setup_boot_services32(efi_early);
+
+	status = efi_call_early(handle_protocol, handle,
+				&proto, (void *)&image);
 	if (status != EFI_SUCCESS) {
 		efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
 		return NULL;
@@ -641,14 +1239,13 @@
 		sizeof(struct e820entry) * nr_desc;
 
 	if (*e820ext) {
-		efi_call_phys1(sys_table->boottime->free_pool, *e820ext);
+		efi_call_early(free_pool, *e820ext);
 		*e820ext = NULL;
 		*e820ext_size = 0;
 	}
 
-	status = efi_call_phys3(sys_table->boottime->allocate_pool,
-				EFI_LOADER_DATA, size, e820ext);
-
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				size, (void **)e820ext);
 	if (status == EFI_SUCCESS)
 		*e820ext_size = size;
 
@@ -656,12 +1253,13 @@
 }
 
 static efi_status_t exit_boot(struct boot_params *boot_params,
-			      void *handle)
+			      void *handle, bool is64)
 {
 	struct efi_info *efi = &boot_params->efi_info;
 	unsigned long map_sz, key, desc_size;
 	efi_memory_desc_t *mem_map;
 	struct setup_data *e820ext;
+	const char *signature;
 	__u32 e820ext_size;
 	__u32 nr_desc, prev_nr_desc;
 	efi_status_t status;
@@ -691,11 +1289,13 @@
 		if (status != EFI_SUCCESS)
 			goto free_mem_map;
 
-		efi_call_phys1(sys_table->boottime->free_pool, mem_map);
+		efi_call_early(free_pool, mem_map);
 		goto get_map; /* Allocated memory, get map again */
 	}
 
-	memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
+	signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+	memcpy(&efi->efi_loader_signature, signature, sizeof(__u32));
+
 	efi->efi_systab = (unsigned long)sys_table;
 	efi->efi_memdesc_size = desc_size;
 	efi->efi_memdesc_version = desc_version;
@@ -708,8 +1308,7 @@
 #endif
 
 	/* Might as well exit boot services now */
-	status = efi_call_phys2(sys_table->boottime->exit_boot_services,
-				handle, key);
+	status = efi_call_early(exit_boot_services, handle, key);
 	if (status != EFI_SUCCESS) {
 		/*
 		 * ExitBootServices() will fail if any of the event
@@ -722,7 +1321,7 @@
 			goto free_mem_map;
 
 		called_exit = true;
-		efi_call_phys1(sys_table->boottime->free_pool, mem_map);
+		efi_call_early(free_pool, mem_map);
 		goto get_map;
 	}
 
@@ -736,23 +1335,31 @@
 	return EFI_SUCCESS;
 
 free_mem_map:
-	efi_call_phys1(sys_table->boottime->free_pool, mem_map);
+	efi_call_early(free_pool, mem_map);
 	return status;
 }
 
-
 /*
  * On success we return a pointer to a boot_params structure, and NULL
  * on failure.
  */
-struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
+struct boot_params *efi_main(struct efi_config *c,
 			     struct boot_params *boot_params)
 {
-	struct desc_ptr *gdt;
+	struct desc_ptr *gdt = NULL;
 	efi_loaded_image_t *image;
 	struct setup_header *hdr = &boot_params->hdr;
 	efi_status_t status;
 	struct desc_struct *desc;
+	void *handle;
+	efi_system_table_t *_table;
+	bool is64;
+
+	efi_early = c;
+
+	_table = (efi_system_table_t *)(unsigned long)efi_early->table;
+	handle = (void *)(unsigned long)efi_early->image_handle;
+	is64 = efi_early->is64;
 
 	sys_table = _table;
 
@@ -760,13 +1367,17 @@
 	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		goto fail;
 
+	if (is64)
+		setup_boot_services64(efi_early);
+	else
+		setup_boot_services32(efi_early);
+
 	setup_graphics(boot_params);
 
 	setup_efi_pci(boot_params);
 
-	status = efi_call_phys3(sys_table->boottime->allocate_pool,
-				EFI_LOADER_DATA, sizeof(*gdt),
-				(void **)&gdt);
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				sizeof(*gdt), (void **)&gdt);
 	if (status != EFI_SUCCESS) {
 		efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
 		goto fail;
@@ -797,7 +1408,7 @@
 		hdr->code32_start = bzimage_addr;
 	}
 
-	status = exit_boot(boot_params, handle);
+	status = exit_boot(boot_params, handle, is64);
 	if (status != EFI_SUCCESS)
 		goto fail;
 
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index 81b6b65..c88c31e 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -37,6 +37,24 @@
 	u32 pixels_per_scan_line;
 } __packed;
 
+struct efi_graphics_output_protocol_mode_32 {
+	u32 max_mode;
+	u32 mode;
+	u32 info;
+	u32 size_of_info;
+	u64 frame_buffer_base;
+	u32 frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol_mode_64 {
+	u32 max_mode;
+	u32 mode;
+	u64 info;
+	u64 size_of_info;
+	u64 frame_buffer_base;
+	u64 frame_buffer_size;
+} __packed;
+
 struct efi_graphics_output_protocol_mode {
 	u32 max_mode;
 	u32 mode;
@@ -46,6 +64,20 @@
 	unsigned long frame_buffer_size;
 } __packed;
 
+struct efi_graphics_output_protocol_32 {
+	u32 query_mode;
+	u32 set_mode;
+	u32 blt;
+	u32 mode;
+};
+
+struct efi_graphics_output_protocol_64 {
+	u64 query_mode;
+	u64 set_mode;
+	u64 blt;
+	u64 mode;
+};
+
 struct efi_graphics_output_protocol {
 	void *query_mode;
 	unsigned long set_mode;
@@ -53,10 +85,38 @@
 	struct efi_graphics_output_protocol_mode *mode;
 };
 
+struct efi_uga_draw_protocol_32 {
+	u32 get_mode;
+	u32 set_mode;
+	u32 blt;
+};
+
+struct efi_uga_draw_protocol_64 {
+	u64 get_mode;
+	u64 set_mode;
+	u64 blt;
+};
+
 struct efi_uga_draw_protocol {
 	void *get_mode;
 	void *set_mode;
 	void *blt;
 };
 
+struct efi_config {
+	u64 image_handle;
+	u64 table;
+	u64 allocate_pool;
+	u64 allocate_pages;
+	u64 get_memory_map;
+	u64 free_pool;
+	u64 free_pages;
+	u64 locate_handle;
+	u64 handle_protocol;
+	u64 exit_boot_services;
+	u64 text_output;
+	efi_status_t (*call)(unsigned long, ...);
+	bool is64;
+} __packed;
+
 #endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S
index cedc60d..7ff3632 100644
--- a/arch/x86/boot/compressed/efi_stub_64.S
+++ b/arch/x86/boot/compressed/efi_stub_64.S
@@ -1 +1,30 @@
+#include <asm/segment.h>
+#include <asm/msr.h>
+#include <asm/processor-flags.h>
+
 #include "../../platform/efi/efi_stub_64.S"
+
+#ifdef CONFIG_EFI_MIXED
+	.code64
+	.text
+ENTRY(efi64_thunk)
+	push	%rbp
+	push	%rbx
+
+	subq	$16, %rsp
+	leaq	efi_exit32(%rip), %rax
+	movl	%eax, 8(%rsp)
+	leaq	efi_gdt64(%rip), %rax
+	movl	%eax, 4(%rsp)
+	movl	%eax, 2(%rax)		/* Fixup the gdt base address */
+	leaq	efi32_boot_gdt(%rip), %rax
+	movl	%eax, (%rsp)
+
+	call	__efi64_thunk
+
+	addq	$16, %rsp
+	pop	%rbx
+	pop	%rbp
+	ret
+ENDPROC(efi64_thunk)
+#endif /* CONFIG_EFI_MIXED */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 9116aac..de9d420 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -42,26 +42,53 @@
 ENTRY(efi_pe_entry)
 	add	$0x4, %esp
 
+	call	1f
+1:	popl	%esi
+	subl	$1b, %esi
+
+	popl	%ecx
+	movl	%ecx, efi32_config(%esi)	/* Handle */
+	popl	%ecx
+	movl	%ecx, efi32_config+8(%esi)	/* EFI System table pointer */
+
+	/* Relocate efi_config->call() */
+	leal	efi32_config(%esi), %eax
+	add	%esi, 88(%eax)
+	pushl	%eax
+
 	call	make_boot_params
 	cmpl	$0, %eax
-	je	1f
-	movl	0x4(%esp), %esi
-	movl	(%esp), %ecx
+	je	fail
+	popl	%ecx
 	pushl	%eax
-	pushl	%esi
 	pushl	%ecx
-	sub	$0x4, %esp
+	jmp	2f		/* Skip efi_config initialization */
 
-ENTRY(efi_stub_entry)
+ENTRY(efi32_stub_entry)
 	add	$0x4, %esp
+	popl	%ecx
+	popl	%edx
+
+	call	1f
+1:	popl	%esi
+	subl	$1b, %esi
+
+	movl	%ecx, efi32_config(%esi)	/* Handle */
+	movl	%edx, efi32_config+8(%esi)	/* EFI System table pointer */
+
+	/* Relocate efi_config->call() */
+	leal	efi32_config(%esi), %eax
+	add	%esi, 88(%eax)
+	pushl	%eax
+2:
 	call	efi_main
 	cmpl	$0, %eax
 	movl	%eax, %esi
 	jne	2f
-1:
+fail:
 	/* EFI init failed, so hang. */
 	hlt
-	jmp	1b
+	jmp	fail
 2:
 	call	3f
 3:
@@ -202,6 +229,15 @@
 	xorl	%ebx, %ebx
 	jmp	*%eax
 
+#ifdef CONFIG_EFI_STUB
+	.data
+efi32_config:
+	.fill 11,8,0
+	.long efi_call_phys
+	.long 0
+	.byte 0
+#endif
+
 /*
  * Stack and heap for uncompression
  */
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index c5c1ae0..57e58a5 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -113,7 +113,8 @@
 	lgdt	gdt(%ebp)
 
 	/* Enable PAE mode */
-	movl	$(X86_CR4_PAE), %eax
+	movl	%cr4, %eax
+	orl	$X86_CR4_PAE, %eax
 	movl	%eax, %cr4
 
  /*
@@ -178,6 +179,13 @@
 	 */
 	pushl	$__KERNEL_CS
 	leal	startup_64(%ebp), %eax
+#ifdef CONFIG_EFI_MIXED
+	movl	efi32_config(%ebp), %ebx
+	cmp	$0, %ebx
+	jz	1f
+	leal	handover_entry(%ebp), %eax
+1:
+#endif
 	pushl	%eax
 
 	/* Enter paged protected Mode, activating Long Mode */
@@ -188,6 +196,30 @@
 	lret
 ENDPROC(startup_32)
 
+#ifdef CONFIG_EFI_MIXED
+	.org 0x190
+ENTRY(efi32_stub_entry)
+	add	$0x4, %esp		/* Discard return address */
+	popl	%ecx
+	popl	%edx
+	popl	%esi
+
+	leal	(BP_scratch+4)(%esi), %esp
+	call	1f
+1:	pop	%ebp
+	subl	$1b, %ebp
+
+	movl	%ecx, efi32_config(%ebp)
+	movl	%edx, efi32_config+8(%ebp)
+	sgdtl	efi32_boot_gdt(%ebp)
+
+	leal	efi32_config(%ebp), %eax
+	movl	%eax, efi_config(%ebp)
+
+	jmp	startup_32
+ENDPROC(efi32_stub_entry)
+#endif
+
 	.code64
 	.org 0x200
 ENTRY(startup_64)
@@ -209,26 +241,48 @@
 	jmp	preferred_addr
 
 ENTRY(efi_pe_entry)
-	mov	%rcx, %rdi
-	mov	%rdx, %rsi
-	pushq	%rdi
-	pushq	%rsi
+	movq	%rcx, efi64_config(%rip)	/* Handle */
+	movq	%rdx, efi64_config+8(%rip) /* EFI System table pointer */
+
+	leaq	efi64_config(%rip), %rax
+	movq	%rax, efi_config(%rip)
+
+	call	1f
+1:	popq	%rbp
+	subq	$1b, %rbp
+
+	/*
+	 * Relocate efi_config->call().
+	 */
+	addq	%rbp, efi64_config+88(%rip)
+
+	movq	%rax, %rdi
 	call	make_boot_params
 	cmpq	$0,%rax
-	je	1f
-	mov	%rax, %rdx
-	popq	%rsi
-	popq	%rdi
+	je	fail
+	mov	%rax, %rsi
+	jmp	2f		/* Skip the relocation */
 
-ENTRY(efi_stub_entry)
+handover_entry:
+	call	1f
+1:	popq	%rbp
+	subq	$1b, %rbp
+
+	/*
+	 * Relocate efi_config->call().
+	 */
+	movq	efi_config(%rip), %rax
+	addq	%rbp, 88(%rax)
+2:
+	movq	efi_config(%rip), %rdi
 	call	efi_main
 	movq	%rax,%rsi
 	cmpq	$0,%rax
 	jne	2f
-1:
+fail:
 	/* EFI init failed, so hang. */
 	hlt
-	jmp	1b
+	jmp	fail
 2:
 	call	3f
 3:
@@ -307,6 +361,20 @@
 	leaq	relocated(%rbx), %rax
 	jmp	*%rax
 
+#ifdef CONFIG_EFI_STUB
+	.org 0x390
+ENTRY(efi64_stub_entry)
+	movq	%rdi, efi64_config(%rip)	/* Handle */
+	movq	%rsi, efi64_config+8(%rip) /* EFI System table pointer */
+
+	leaq	efi64_config(%rip), %rax
+	movq	%rax, efi_config(%rip)
+
+	movq	%rdx, %rsi
+	jmp	handover_entry
+ENDPROC(efi64_stub_entry)
+#endif
+
 	.text
 relocated:
 
@@ -372,6 +440,25 @@
 	.quad   0x0000000000000000	/* TS continued */
 gdt_end:
 
+#ifdef CONFIG_EFI_STUB
+efi_config:
+	.quad	0
+
+#ifdef CONFIG_EFI_MIXED
+	.global efi32_config
+efi32_config:
+	.fill	11,8,0
+	.quad	efi64_thunk
+	.byte	0
+#endif
+
+	.global efi64_config
+efi64_config:
+	.fill	11,8,0
+	.quad	efi_call6
+	.byte	1
+#endif /* CONFIG_EFI_STUB */
+
 /*
  * Stack and heap for uncompression
  */
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 100a9a1..f0d0b20 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -67,6 +67,13 @@
 	       cpu_vendor[2] == A32('M', 'x', '8', '6');
 }
 
+static int is_intel(void)
+{
+	return cpu_vendor[0] == A32('G', 'e', 'n', 'u') &&
+	       cpu_vendor[1] == A32('i', 'n', 'e', 'I') &&
+	       cpu_vendor[2] == A32('n', 't', 'e', 'l');
+}
+
 /* Returns a bitmask of which words we have error bits in */
 static int check_cpuflags(void)
 {
@@ -153,6 +160,19 @@
 		asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
 
 		err = check_cpuflags();
+	} else if (err == 0x01 &&
+		   !(err_flags[0] & ~(1 << X86_FEATURE_PAE)) &&
+		   is_intel() && cpu.level == 6 &&
+		   (cpu.model == 9 || cpu.model == 13)) {
+		/* PAE is disabled on this Pentium M but can be forced */
+		if (cmdline_find_option_bool("forcepae")) {
+			puts("WARNING: Forcing PAE in CPU flags\n");
+			set_bit(X86_FEATURE_PAE, cpu.flags);
+			err = check_cpuflags();
+		}
+		else {
+			puts("WARNING: PAE disabled. Use parameter 'forcepae' to enable at your own risk!\n");
+		}
 	}
 
 	if (err_flags_ptr)
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index ec3b8ba..0ca9a5c 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -283,7 +283,7 @@
 	# Part 2 of the header, from the old setup.S
 
 		.ascii	"HdrS"		# header signature
-		.word	0x020c		# header version number (>= 0x0105)
+		.word	0x020d		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 		.globl realmode_swtch
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
@@ -350,7 +350,7 @@
 					# can be located anywhere in
 					# low memory 0x10000 or higher.
 
-ramdisk_max:	.long 0x7fffffff
+initrd_addr_max: .long 0x7fffffff
 					# (Header version 0x0203 or later)
 					# The highest safe address for
 					# the contents of an initrd
@@ -375,7 +375,8 @@
 # define XLF0 0
 #endif
 
-#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64)
+#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64) && \
+	!defined(CONFIG_EFI_MIXED)
    /* kernel/boot_param/ramdisk could be loaded above 4g */
 # define XLF1 XLF_CAN_BE_LOADED_ABOVE_4G
 #else
@@ -383,10 +384,14 @@
 #endif
 
 #ifdef CONFIG_EFI_STUB
-# ifdef CONFIG_X86_64
-#  define XLF23 XLF_EFI_HANDOVER_64		/* 64-bit EFI handover ok */
+# ifdef CONFIG_EFI_MIXED
+#  define XLF23 (XLF_EFI_HANDOVER_32|XLF_EFI_HANDOVER_64)
 # else
-#  define XLF23 XLF_EFI_HANDOVER_32		/* 32-bit EFI handover ok */
+#  ifdef CONFIG_X86_64
+#   define XLF23 XLF_EFI_HANDOVER_64		/* 64-bit EFI handover ok */
+#  else
+#   define XLF23 XLF_EFI_HANDOVER_32		/* 32-bit EFI handover ok */
+#  endif
 # endif
 #else
 # define XLF23 0
@@ -426,13 +431,7 @@
 #define INIT_SIZE VO_INIT_SIZE
 #endif
 init_size:		.long INIT_SIZE		# kernel initialization size
-handover_offset:
-#ifdef CONFIG_EFI_STUB
-  			.long 0x30		# offset to the handover
-						# protocol entry point
-#else
-			.long 0
-#endif
+handover_offset:	.long 0			# Filled in by build.c
 
 # End of setup header #####################################################
 
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 8e15b22..1a2f212 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -53,7 +53,8 @@
 
 #define PECOFF_RELOC_RESERVE 0x20
 
-unsigned long efi_stub_entry;
+unsigned long efi32_stub_entry;
+unsigned long efi64_stub_entry;
 unsigned long efi_pe_entry;
 unsigned long startup_64;
 
@@ -219,6 +220,52 @@
 	update_pecoff_section_header(".text", text_start, text_sz);
 }
 
+static int reserve_pecoff_reloc_section(int c)
+{
+	/* Reserve 0x20 bytes for .reloc section */
+	memset(buf+c, 0, PECOFF_RELOC_RESERVE);
+	return PECOFF_RELOC_RESERVE;
+}
+
+static void efi_stub_defaults(void)
+{
+	/* Defaults for old kernel */
+#ifdef CONFIG_X86_32
+	efi_pe_entry = 0x10;
+#else
+	efi_pe_entry = 0x210;
+	startup_64 = 0x200;
+#endif
+}
+
+static void efi_stub_entry_update(void)
+{
+	unsigned long addr = efi32_stub_entry;
+
+#ifdef CONFIG_X86_64
+	/* Yes, this is really how we defined it :( */
+	addr = efi64_stub_entry - 0x200;
+#endif
+
+#ifdef CONFIG_EFI_MIXED
+	if (efi32_stub_entry != addr)
+		die("32-bit and 64-bit EFI entry points do not match\n");
+#endif
+	put_unaligned_le32(addr, &buf[0x264]);
+}
+
+#else
+
+static inline void update_pecoff_setup_and_reloc(unsigned int size) {}
+static inline void update_pecoff_text(unsigned int text_start,
+				      unsigned int file_sz) {}
+static inline void efi_stub_defaults(void) {}
+static inline void efi_stub_entry_update(void) {}
+
+static inline int reserve_pecoff_reloc_section(int c)
+{
+	return 0;
+}
 #endif /* CONFIG_EFI_STUB */
 
 
@@ -250,7 +297,8 @@
 	p = (char *)buf;
 
 	while (p && *p) {
-		PARSE_ZOFS(p, efi_stub_entry);
+		PARSE_ZOFS(p, efi32_stub_entry);
+		PARSE_ZOFS(p, efi64_stub_entry);
 		PARSE_ZOFS(p, efi_pe_entry);
 		PARSE_ZOFS(p, startup_64);
 
@@ -271,15 +319,7 @@
 	void *kernel;
 	u32 crc = 0xffffffffUL;
 
-	/* Defaults for old kernel */
-#ifdef CONFIG_X86_32
-	efi_pe_entry = 0x10;
-	efi_stub_entry = 0x30;
-#else
-	efi_pe_entry = 0x210;
-	efi_stub_entry = 0x230;
-	startup_64 = 0x200;
-#endif
+	efi_stub_defaults();
 
 	if (argc != 5)
 		usage();
@@ -302,11 +342,7 @@
 		die("Boot block hasn't got boot flag (0xAA55)");
 	fclose(file);
 
-#ifdef CONFIG_EFI_STUB
-	/* Reserve 0x20 bytes for .reloc section */
-	memset(buf+c, 0, PECOFF_RELOC_RESERVE);
-	c += PECOFF_RELOC_RESERVE;
-#endif
+	c += reserve_pecoff_reloc_section(c);
 
 	/* Pad unused space with zeros */
 	setup_sectors = (c + 511) / 512;
@@ -315,9 +351,7 @@
 	i = setup_sectors*512;
 	memset(buf+c, 0, i-c);
 
-#ifdef CONFIG_EFI_STUB
 	update_pecoff_setup_and_reloc(i);
-#endif
 
 	/* Set the default root device */
 	put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
@@ -342,14 +376,9 @@
 	buf[0x1f1] = setup_sectors-1;
 	put_unaligned_le32(sys_size, &buf[0x1f4]);
 
-#ifdef CONFIG_EFI_STUB
 	update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
 
-#ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */
-	efi_stub_entry -= 0x200;
-#endif
-	put_unaligned_le32(efi_stub_entry, &buf[0x264]);
-#endif
+	efi_stub_entry_update();
 
 	crc = partial_crc32(buf, i, crc);
 	if (fwrite(buf, 1, i, dest) != i)
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index a54ee1d..aaac3b2 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -19,7 +19,7 @@
 extern void amd_flush_garts(void);
 extern int amd_numa_init(void);
 extern int amd_get_subcaches(int);
-extern int amd_set_subcaches(int, int);
+extern int amd_set_subcaches(int, unsigned long);
 
 struct amd_l3_cache {
 	unsigned indices;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 1d2091a..19b0eba 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -93,9 +93,6 @@
 	return 0;
 }
 #endif
-extern void xapic_wait_icr_idle(void);
-extern u32 safe_xapic_wait_icr_idle(void);
-extern void xapic_icr_write(u32, u32);
 extern int setup_profiling_timer(unsigned int);
 
 static inline void native_apic_mem_write(u32 reg, u32 v)
@@ -184,7 +181,6 @@
 extern int x2apic_preenabled;
 extern void check_x2apic(void);
 extern void enable_x2apic(void);
-extern void x2apic_icr_write(u32 low, u32 id);
 static inline int x2apic_enabled(void)
 {
 	u64 msr;
@@ -221,7 +217,6 @@
 {
 }
 
-#define	nox2apic	0
 #define	x2apic_preenabled 0
 #define	x2apic_supported()	0
 #endif
@@ -351,7 +346,7 @@
 	int trampoline_phys_low;
 	int trampoline_phys_high;
 
-	void (*wait_for_init_deassert)(atomic_t *deassert);
+	bool wait_for_init_deassert;
 	void (*smp_callin_clear_local_apic)(void);
 	void (*inquire_remote_apic)(int apicid);
 
@@ -517,13 +512,6 @@
 extern int default_check_phys_apicid_present(int phys_apicid);
 #endif
 
-static inline void default_wait_for_init_deassert(atomic_t *deassert)
-{
-	while (!atomic_read(deassert))
-		cpu_relax();
-	return;
-}
-
 extern void generic_bigsmp_probe(void);
 
 
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 04a4890..69bbb48 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -85,11 +85,7 @@
 #else
 # define smp_rmb()	barrier()
 #endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() 	wmb()
-#else
-# define smp_wmb()	barrier()
-#endif
+#define smp_wmb()	barrier()
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
 #else /* !SMP */
@@ -100,7 +96,7 @@
 #define set_mb(var, value) do { var = value; barrier(); } while (0)
 #endif /* SMP */
 
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
 
 /*
  * For either of these options x86 doesn't have a strong TSO memory
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e099f95..63211ef 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -37,7 +37,7 @@
 #define X86_FEATURE_PAT		(0*32+16) /* Page Attribute Table */
 #define X86_FEATURE_PSE36	(0*32+17) /* 36-bit PSEs */
 #define X86_FEATURE_PN		(0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLSH	(0*32+19) /* "clflush" CLFLUSH instruction */
+#define X86_FEATURE_CLFLUSH	(0*32+19) /* CLFLUSH instruction */
 #define X86_FEATURE_DS		(0*32+21) /* "dts" Debug Store */
 #define X86_FEATURE_ACPI	(0*32+22) /* ACPI via MSR */
 #define X86_FEATURE_MMX		(0*32+23) /* Multimedia Extensions */
@@ -217,9 +217,14 @@
 #define X86_FEATURE_INVPCID	(9*32+10) /* Invalidate Processor Context ID */
 #define X86_FEATURE_RTM		(9*32+11) /* Restricted Transactional Memory */
 #define X86_FEATURE_MPX		(9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F	(9*32+16) /* AVX-512 Foundation */
 #define X86_FEATURE_RDSEED	(9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX		(9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP	(9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_CLFLUSHOPT	(9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_AVX512PF	(9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER	(9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD	(9*32+28) /* AVX-512 Conflict Detection */
 
 /*
  * BUG word(s)
@@ -313,7 +318,7 @@
 #define cpu_has_pmm_enabled	boot_cpu_has(X86_FEATURE_PMM_EN)
 #define cpu_has_ds		boot_cpu_has(X86_FEATURE_DS)
 #define cpu_has_pebs		boot_cpu_has(X86_FEATURE_PEBS)
-#define cpu_has_clflush		boot_cpu_has(X86_FEATURE_CLFLSH)
+#define cpu_has_clflush		boot_cpu_has(X86_FEATURE_CLFLUSH)
 #define cpu_has_bts		boot_cpu_has(X86_FEATURE_BTS)
 #define cpu_has_gbpages		boot_cpu_has(X86_FEATURE_GBPAGES)
 #define cpu_has_arch_perfmon	boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3b978c4..0869434 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -19,9 +19,11 @@
  */
 #define EFI_OLD_MEMMAP		EFI_ARCH_1
 
+#define EFI32_LOADER_SIGNATURE	"EL32"
+#define EFI64_LOADER_SIGNATURE	"EL64"
+
 #ifdef CONFIG_X86_32
 
-#define EFI_LOADER_SIGNATURE	"EL32"
 
 extern unsigned long asmlinkage efi_call_phys(void *, ...);
 
@@ -57,8 +59,6 @@
 
 #else /* !CONFIG_X86_32 */
 
-#define EFI_LOADER_SIGNATURE	"EL64"
-
 extern u64 efi_call0(void *fp);
 extern u64 efi_call1(void *fp, u64 arg1);
 extern u64 efi_call2(void *fp, u64 arg1, u64 arg2);
@@ -119,7 +119,6 @@
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
-extern unsigned long x86_efi_facility;
 extern struct efi_scratch efi_scratch;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
@@ -130,8 +129,13 @@
 extern void __init efi_map_region(efi_memory_desc_t *md);
 extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
-extern void efi_setup_page_tables(void);
+extern int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
+extern void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init old_map_region(efi_memory_desc_t *md);
+extern void __init runtime_code_page_mkexec(void);
+extern void __init efi_runtime_mkexec(void);
+extern void __init efi_dump_pagetable(void);
+extern void __init efi_apply_memmap_quirks(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;
@@ -150,8 +154,40 @@
 	return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
 }
 
+static inline bool efi_runtime_supported(void)
+{
+	if (efi_is_native())
+		return true;
+
+	if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_enabled(EFI_OLD_MEMMAP))
+		return true;
+
+	return false;
+}
+
 extern struct console early_efi_console;
 extern void parse_efi_setup(u64 phys_addr, u32 data_len);
+
+#ifdef CONFIG_EFI_MIXED
+extern void efi_thunk_runtime_setup(void);
+extern efi_status_t efi_thunk_set_virtual_address_map(
+	void *phys_set_virtual_address_map,
+	unsigned long memory_map_size,
+	unsigned long descriptor_size,
+	u32 descriptor_version,
+	efi_memory_desc_t *virtual_map);
+#else
+static inline void efi_thunk_runtime_setup(void) {}
+static inline efi_status_t efi_thunk_set_virtual_address_map(
+	void *phys_set_virtual_address_map,
+	unsigned long memory_map_size,
+	unsigned long descriptor_size,
+	u32 descriptor_version,
+	efi_memory_desc_t *virtual_map)
+{
+	return EFI_SUCCESS;
+}
+#endif /* CONFIG_EFI_MIXED */
 #else
 /*
  * IF EFI is not configured, have the EFI calls return -ENOSYS.
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 34f69cb..91d9c69 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -237,7 +237,7 @@
 
 static inline void flush_write_buffers(void)
 {
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
 	asm volatile("lock; addl $0,0(%%esp)": : :"memory");
 #endif
 }
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index e139b13..de36f22 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -214,6 +214,8 @@
 
 struct msr *msrs_alloc(void);
 void msrs_free(struct msr *msrs);
+int msr_set_bit(u32 msr, u8 bit);
+int msr_clear_bit(u32 msr, u8 bit);
 
 #ifdef CONFIG_SMP
 int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 86f9301..5f2fc44 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_NMI_H
 #define _ASM_X86_NMI_H
 
+#include <linux/irq_work.h>
 #include <linux/pm.h>
 #include <asm/irq.h>
 #include <asm/io.h>
@@ -38,6 +39,8 @@
 struct nmiaction {
 	struct list_head	list;
 	nmi_handler_t		handler;
+	u64			max_duration;
+	struct irq_work		irq_work;
 	unsigned long		flags;
 	const char		*name;
 };
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index bbc8b12..b459ddf 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -15,9 +15,10 @@
 	 : (prot))
 
 #ifndef __ASSEMBLY__
-
 #include <asm/x86_init.h>
 
+void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 1aa9ccd..708f19f 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -382,9 +382,13 @@
  * as a pte too.
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
+extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+				    unsigned int *level);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags);
+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
+			       unsigned numpages);
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 645cad2..e820c08 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -191,6 +191,14 @@
 	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
 }
 
+static inline void clflushopt(volatile void *__p)
+{
+	alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0",
+		       ".byte 0x66; clflush %P0",
+		       X86_FEATURE_CLFLUSHOPT,
+		       "+m" (*(volatile char __force *)__p));
+}
+
 #define nop() asm volatile ("nop")
 
 
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index bf156de..0f62f54 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -26,10 +26,9 @@
 # define LOCK_PTR_REG "D"
 #endif
 
-#if defined(CONFIG_X86_32) && \
-	(defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
+#if defined(CONFIG_X86_32) && (defined(CONFIG_X86_PPRO_FENCE))
 /*
- * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
+ * On PPro SMP, we use a locked operation to unlock
  * (PPro errata 66, 92)
  */
 # define UNLOCK_LOCK_PREFIX LOCK_PREFIX
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index e6d90ba..04905bf 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -62,7 +62,7 @@
 
 static inline void __flush_tlb_one(unsigned long addr)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 	__flush_tlb_single(addr);
 }
 
@@ -93,13 +93,13 @@
  */
 static inline void __flush_tlb_up(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 }
 
 static inline void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb_all();
 }
 
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index d35f24e..b28097e 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -119,9 +119,10 @@
 
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
-#ifdef ENABLE_TOPO_DEFINES
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
+
+#ifdef ENABLE_TOPO_DEFINES
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_thread_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 #endif
@@ -133,12 +134,6 @@
 struct pci_bus;
 void x86_pci_root_bus_resources(int bus, struct list_head *resources);
 
-#ifdef CONFIG_SMP
-#define mc_capable()	((boot_cpu_data.x86_max_cores > 1) && \
-			(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))
-#define smt_capable()			(smp_num_siblings > 1)
-#endif
-
 #ifdef CONFIG_NUMA
 extern int get_mp_bus_to_node(int busnum);
 extern void set_mp_bus_to_node(int busnum, int node);
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 57ae63c..94605c0 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -66,6 +66,6 @@
 extern void tsc_restore_sched_clock_state(void);
 
 /* MSR based TSC calibration for Intel Atom SoC platforms */
-int try_msr_calibrate_tsc(unsigned long *fast_calibrate);
+unsigned long try_msr_calibrate_tsc(void);
 
 #endif /* _ASM_X86_TSC_H */
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index c2a4813..3f556c6 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -23,6 +23,9 @@
 #  include <asm/unistd_64.h>
 #  include <asm/unistd_64_x32.h>
 #  define __ARCH_WANT_COMPAT_SYS_TIME
+#  define __ARCH_WANT_COMPAT_SYS_GETDENTS64
+#  define __ARCH_WANT_COMPAT_SYS_PREADV64
+#  define __ARCH_WANT_COMPAT_SYS_PWRITEV64
 
 # endif
 
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 787e1bb..3e276eb 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -52,8 +52,7 @@
 extern int m2p_add_override(unsigned long mfn, struct page *page,
 			    struct gnttab_map_grant_ref *kmap_op);
 extern int m2p_remove_override(struct page *page,
-			       struct gnttab_map_grant_ref *kmap_op,
-			       unsigned long mfn);
+				struct gnttab_map_grant_ref *kmap_op);
 extern struct page *m2p_find_override(unsigned long mfn);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
@@ -122,7 +121,7 @@
 		pfn = m2p_find_override_pfn(mfn, ~0);
 	}
 
-	/*
+	/* 
 	 * pfn is ~0 if there are no entries in the m2p for mfn or if the
 	 * entry doesn't map back to the mfn and m2p_override doesn't have a
 	 * valid entry for it.
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 5547389..6c1d741 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -6,11 +6,14 @@
 
 #define XSTATE_CPUID		0x0000000d
 
-#define XSTATE_FP	0x1
-#define XSTATE_SSE	0x2
-#define XSTATE_YMM	0x4
-#define XSTATE_BNDREGS	0x8
-#define XSTATE_BNDCSR	0x10
+#define XSTATE_FP		0x1
+#define XSTATE_SSE		0x2
+#define XSTATE_YMM		0x4
+#define XSTATE_BNDREGS		0x8
+#define XSTATE_BNDCSR		0x10
+#define XSTATE_OPMASK		0x20
+#define XSTATE_ZMM_Hi256	0x40
+#define XSTATE_Hi16_ZMM		0x80
 
 #define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
 
@@ -23,7 +26,8 @@
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
 /* Supported features which support lazy state saving */
-#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM)
+#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM		      \
+			| XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
 
 /* Supported features which require eager state saving */
 #define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index c19fc60..4924f4b 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -368,33 +368,58 @@
 #define THERM_LOG_THRESHOLD1           (1 << 9)
 
 /* MISC_ENABLE bits: architectural */
-#define MSR_IA32_MISC_ENABLE_FAST_STRING	(1ULL << 0)
-#define MSR_IA32_MISC_ENABLE_TCC		(1ULL << 1)
-#define MSR_IA32_MISC_ENABLE_EMON		(1ULL << 7)
-#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL	(1ULL << 11)
-#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL	(1ULL << 12)
-#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP	(1ULL << 16)
-#define MSR_IA32_MISC_ENABLE_MWAIT		(1ULL << 18)
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID	(1ULL << 22)
-#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE	(1ULL << 23)
-#define MSR_IA32_MISC_ENABLE_XD_DISABLE		(1ULL << 34)
+#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT		0
+#define MSR_IA32_MISC_ENABLE_FAST_STRING		(1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
+#define MSR_IA32_MISC_ENABLE_TCC_BIT			1
+#define MSR_IA32_MISC_ENABLE_TCC			(1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT)
+#define MSR_IA32_MISC_ENABLE_EMON_BIT			7
+#define MSR_IA32_MISC_ENABLE_EMON			(1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT)
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT		11
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT		12
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT	16
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP		(1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT)
+#define MSR_IA32_MISC_ENABLE_MWAIT_BIT			18
+#define MSR_IA32_MISC_ENABLE_MWAIT			(1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT		22
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID		(1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT);
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT		23
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT		34
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE			(1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT)
 
 /* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
-#define MSR_IA32_MISC_ENABLE_X87_COMPAT		(1ULL << 2)
-#define MSR_IA32_MISC_ENABLE_TM1		(1ULL << 3)
-#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE	(1ULL << 4)
-#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE	(1ULL << 6)
-#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK	(1ULL << 8)
-#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE	(1ULL << 9)
-#define MSR_IA32_MISC_ENABLE_FERR		(1ULL << 10)
-#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX	(1ULL << 10)
-#define MSR_IA32_MISC_ENABLE_TM2		(1ULL << 13)
-#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE	(1ULL << 19)
-#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK	(1ULL << 20)
-#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT	(1ULL << 24)
-#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE	(1ULL << 37)
-#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE	(1ULL << 38)
-#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE	(1ULL << 39)
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT		2
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT			(1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT)
+#define MSR_IA32_MISC_ENABLE_TM1_BIT			3
+#define MSR_IA32_MISC_ENABLE_TM1			(1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT)
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT	4
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT	6
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT		8
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT	9
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_BIT			10
+#define MSR_IA32_MISC_ENABLE_FERR			(1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT		10
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX		(1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT)
+#define MSR_IA32_MISC_ENABLE_TM2_BIT			13
+#define MSR_IA32_MISC_ENABLE_TM2			(1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT)
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT	19
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT		20
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT		24
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT		(1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT)
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT	37
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT		38
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT	39
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
 
 #define MSR_IA32_TSC_DEADLINE		0x000006E0
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 1dac942..9f46f2b 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -613,10 +613,10 @@
 	int nid;
 
 	nid = acpi_get_node(handle);
-	if (nid == -1 || !node_online(nid))
-		return;
-	set_apicid_to_node(physid, nid);
-	numa_set_node(cpu, nid);
+	if (nid != -1) {
+		set_apicid_to_node(physid, nid);
+		numa_set_node(cpu, nid);
+	}
 #endif
 }
 
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 59554dc..dec8de4 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -179,7 +179,7 @@
 	return (mask >> (4 * cuid)) & 0xf;
 }
 
-int amd_set_subcaches(int cpu, int mask)
+int amd_set_subcaches(int cpu, unsigned long mask)
 {
 	static unsigned int reset, ban;
 	struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu));
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index fd972a3..9fa8aa0 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -18,7 +18,6 @@
 #include <linux/pci_ids.h>
 #include <linux/pci.h>
 #include <linux/bitops.h>
-#include <linux/ioport.h>
 #include <linux/suspend.h>
 #include <asm/e820.h>
 #include <asm/io.h>
@@ -54,18 +53,6 @@
 
 int fix_aperture __initdata = 1;
 
-static struct resource gart_resource = {
-	.name	= "GART",
-	.flags	= IORESOURCE_MEM,
-};
-
-static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
-{
-	gart_resource.start = aper_base;
-	gart_resource.end = aper_base + aper_size - 1;
-	insert_resource(&iomem_resource, &gart_resource);
-}
-
 /* This code runs before the PCI subsystem is initialized, so just
    access the northbridge directly. */
 
@@ -96,7 +83,6 @@
 	memblock_reserve(addr, aper_size);
 	printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
 			aper_size >> 10, addr);
-	insert_aperture_resource((u32)addr, aper_size);
 	register_nosave_region(addr >> PAGE_SHIFT,
 			       (addr+aper_size) >> PAGE_SHIFT);
 
@@ -444,12 +430,8 @@
 
 out:
 	if (!fix && !fallback_aper_force) {
-		if (last_aper_base) {
-			unsigned long n = (32 * 1024 * 1024) << last_aper_order;
-
-			insert_aperture_resource((u32)last_aper_base, n);
+		if (last_aper_base)
 			return 1;
-		}
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 7f26c9a..53e2053 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -133,6 +133,10 @@
  * +1=force-enable
  */
 static int force_enable_local_apic __initdata;
+
+/* Control whether x2APIC mode is enabled or not */
+static bool nox2apic __initdata;
+
 /*
  * APIC command line parameters
  */
@@ -162,8 +166,7 @@
 /* x2apic enabled before OS handover */
 int x2apic_preenabled;
 static int x2apic_disabled;
-static int nox2apic;
-static __init int setup_nox2apic(char *str)
+static int __init setup_nox2apic(char *str)
 {
 	if (x2apic_enabled()) {
 		int apicid = native_apic_msr_read(APIC_ID);
@@ -178,7 +181,7 @@
 	} else
 		setup_clear_cpu_cap(X86_FEATURE_X2APIC);
 
-	nox2apic = 1;
+	nox2apic = true;
 
 	return 0;
 }
@@ -283,8 +286,12 @@
 
 void native_apic_icr_write(u32 low, u32 id)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id));
 	apic_write(APIC_ICR, low);
+	local_irq_restore(flags);
 }
 
 u64 native_apic_icr_read(void)
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 2c621a6..7c1b294 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -198,7 +198,7 @@
 
 	.trampoline_phys_low		= DEFAULT_TRAMPOLINE_PHYS_LOW,
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
-	.wait_for_init_deassert		= NULL,
+	.wait_for_init_deassert		= false,
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= default_inquire_remote_apic,
 
@@ -314,7 +314,7 @@
 
 	.trampoline_phys_low		= DEFAULT_TRAMPOLINE_PHYS_LOW,
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
-	.wait_for_init_deassert		= NULL,
+	.wait_for_init_deassert		= false,
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= default_inquire_remote_apic,
 
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 191ce75..8c7c982 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -172,8 +172,7 @@
 	.trampoline_phys_low		= DEFAULT_TRAMPOLINE_PHYS_LOW,
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
 
-	.wait_for_init_deassert		= NULL,
-
+	.wait_for_init_deassert		= false,
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= NULL,
 
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 3e67f9e..a5b45df 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -248,7 +248,7 @@
 	.wakeup_secondary_cpu		= numachip_wakeup_secondary,
 	.trampoline_phys_low		= DEFAULT_TRAMPOLINE_PHYS_LOW,
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
-	.wait_for_init_deassert		= NULL,
+	.wait_for_init_deassert		= false,
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= NULL, /* REMRD not supported */
 
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index d50e364..e4840aa 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -199,8 +199,7 @@
 	.trampoline_phys_low		= DEFAULT_TRAMPOLINE_PHYS_LOW,
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
 
-	.wait_for_init_deassert		= default_wait_for_init_deassert,
-
+	.wait_for_init_deassert		= true,
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= default_inquire_remote_apic,
 
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index c552247..6f8f8b3 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -394,12 +394,6 @@
 		WARN(1, "Command failed, status = %x\n", mip_status);
 }
 
-static void es7000_wait_for_init_deassert(atomic_t *deassert)
-{
-	while (!atomic_read(deassert))
-		cpu_relax();
-}
-
 static unsigned int es7000_get_apic_id(unsigned long x)
 {
 	return (x >> 24) & 0xFF;
@@ -658,8 +652,7 @@
 	.trampoline_phys_low		= 0x467,
 	.trampoline_phys_high		= 0x469,
 
-	.wait_for_init_deassert		= NULL,
-
+	.wait_for_init_deassert		= false,
 	/* Nothing to do for most platforms, since cleared by the INIT cycle: */
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= default_inquire_remote_apic,
@@ -722,8 +715,7 @@
 	.trampoline_phys_low		= 0x467,
 	.trampoline_phys_high		= 0x469,
 
-	.wait_for_init_deassert		= es7000_wait_for_init_deassert,
-
+	.wait_for_init_deassert		= true,
 	/* Nothing to do for most platforms, since cleared by the INIT cycle: */
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= default_inquire_remote_apic,
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 1e42e8f..030ea1c 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -505,8 +505,7 @@
 	.trampoline_phys_high		= NUMAQ_TRAMPOLINE_PHYS_HIGH,
 
 	/* We don't do anything here because we use NMI's to boot instead */
-	.wait_for_init_deassert		= NULL,
-
+	.wait_for_init_deassert		= false,
 	.smp_callin_clear_local_apic	= numaq_smp_callin_clear_local_apic,
 	.inquire_remote_apic		= NULL,
 
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index eb35ef9..cceb352 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -119,8 +119,7 @@
 	.trampoline_phys_low		= DEFAULT_TRAMPOLINE_PHYS_LOW,
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
 
-	.wait_for_init_deassert		= default_wait_for_init_deassert,
-
+	.wait_for_init_deassert		= true,
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= default_inquire_remote_apic,
 
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index 00146f9..b656128 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -532,8 +532,7 @@
 	.trampoline_phys_low		= DEFAULT_TRAMPOLINE_PHYS_LOW,
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
 
-	.wait_for_init_deassert		= default_wait_for_init_deassert,
-
+	.wait_for_init_deassert		= true,
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= default_inquire_remote_apic,
 
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index cac85ee..e66766b 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -279,7 +279,7 @@
 
 	.trampoline_phys_low		= DEFAULT_TRAMPOLINE_PHYS_LOW,
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
-	.wait_for_init_deassert		= NULL,
+	.wait_for_init_deassert		= false,
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= NULL,
 
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index de231e3..6d600eb 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -133,7 +133,7 @@
 
 	.trampoline_phys_low		= DEFAULT_TRAMPOLINE_PHYS_LOW,
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
-	.wait_for_init_deassert		= NULL,
+	.wait_for_init_deassert		= false,
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= NULL,
 
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d263b13..7834389 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -396,7 +396,7 @@
 	.wakeup_secondary_cpu		= uv_wakeup_secondary,
 	.trampoline_phys_low		= DEFAULT_TRAMPOLINE_PHYS_LOW,
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
-	.wait_for_init_deassert		= NULL,
+	.wait_for_init_deassert		= false,
 	.smp_callin_clear_local_apic	= NULL,
 	.inquire_remote_apic		= NULL,
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d3153e2..ce8b8ff 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -218,7 +218,7 @@
 	 */
 	WARN_ONCE(1, "WARNING: This combination of AMD"
 		" processors is not suitable for SMP.\n");
-	add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE);
+	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
 }
 
 static void init_amd_k7(struct cpuinfo_x86 *c)
@@ -233,9 +233,7 @@
 	if (c->x86_model >= 6 && c->x86_model <= 10) {
 		if (!cpu_has(c, X86_FEATURE_XMM)) {
 			printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
-			rdmsr(MSR_K7_HWCR, l, h);
-			l &= ~0x00008000;
-			wrmsr(MSR_K7_HWCR, l, h);
+			msr_clear_bit(MSR_K7_HWCR, 15);
 			set_cpu_cap(c, X86_FEATURE_XMM);
 		}
 	}
@@ -509,14 +507,8 @@
 #endif
 
 	/* F16h erratum 793, CVE-2013-6885 */
-	if (c->x86 == 0x16 && c->x86_model <= 0xf) {
-		u64 val;
-
-		rdmsrl(MSR_AMD64_LS_CFG, val);
-		if (!(val & BIT(15)))
-			wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15));
-	}
-
+	if (c->x86 == 0x16 && c->x86_model <= 0xf)
+		msr_set_bit(MSR_AMD64_LS_CFG, 15);
 }
 
 static const int amd_erratum_383[];
@@ -536,11 +528,8 @@
 	 * Errata 63 for SH-B3 steppings
 	 * Errata 122 for all steppings (F+ have it disabled by default)
 	 */
-	if (c->x86 == 0xf) {
-		rdmsrl(MSR_K7_HWCR, value);
-		value |= 1 << 6;
-		wrmsrl(MSR_K7_HWCR, value);
-	}
+	if (c->x86 == 0xf)
+		msr_set_bit(MSR_K7_HWCR, 6);
 #endif
 
 	early_init_amd(c);
@@ -623,14 +612,11 @@
 	    (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
 	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
 
-		if (!rdmsrl_safe(0xc0011005, &value)) {
-			value |= 1ULL << 54;
-			wrmsrl_safe(0xc0011005, value);
+		if (msr_set_bit(0xc0011005, 54) > 0) {
 			rdmsrl(0xc0011005, value);
-			if (value & (1ULL << 54)) {
+			if (value & BIT_64(54)) {
 				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
-				printk(KERN_INFO FW_INFO "CPU: Re-enabling "
-				  "disabled Topology Extensions Support\n");
+				pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
 			}
 		}
 	}
@@ -709,19 +695,12 @@
 		 * Disable GART TLB Walk Errors on Fam10h. We do this here
 		 * because this is always needed when GART is enabled, even in a
 		 * kernel which has no MCE support built in.
-		 * BIOS should disable GartTlbWlk Errors themself. If
-		 * it doesn't do it here as suggested by the BKDG.
+		 * BIOS should disable GartTlbWlk Errors already. If
+		 * it doesn't, do it here as suggested by the BKDG.
 		 *
 		 * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
 		 */
-		u64 mask;
-		int err;
-
-		err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask);
-		if (err == 0) {
-			mask |= (1 << 10);
-			wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask);
-		}
+		msr_set_bit(MSR_AMD64_MCx_MASK(4), 10);
 
 		/*
 		 * On family 10h BIOS may not have properly enabled WC+ support,
@@ -733,10 +712,7 @@
 		 * NOTE: we want to use the _safe accessors so as not to #GP kvm
 		 * guests on older kvm hosts.
 		 */
-
-		rdmsrl_safe(MSR_AMD64_BU_CFG2, &value);
-		value &= ~(1ULL << 24);
-		wrmsrl_safe(MSR_AMD64_BU_CFG2, value);
+		msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
 
 		if (cpu_has_amd_erratum(c, amd_erratum_383))
 			set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
@@ -767,10 +743,7 @@
 
 static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
 {
-	tlb_flushall_shift = 5;
-
-	if (c->x86 <= 0x11)
-		tlb_flushall_shift = 4;
+	tlb_flushall_shift = 6;
 }
 
 static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 8779eda..d8fba5c 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -8,236 +8,6 @@
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_OOSTORE
-
-static u32 power2(u32 x)
-{
-	u32 s = 1;
-
-	while (s <= x)
-		s <<= 1;
-
-	return s >>= 1;
-}
-
-
-/*
- * Set up an actual MCR
- */
-static void centaur_mcr_insert(int reg, u32 base, u32 size, int key)
-{
-	u32 lo, hi;
-
-	hi = base & ~0xFFF;
-	lo = ~(size-1);		/* Size is a power of 2 so this makes a mask */
-	lo &= ~0xFFF;		/* Remove the ctrl value bits */
-	lo |= key;		/* Attribute we wish to set */
-	wrmsr(reg+MSR_IDT_MCR0, lo, hi);
-	mtrr_centaur_report_mcr(reg, lo, hi);	/* Tell the mtrr driver */
-}
-
-/*
- * Figure what we can cover with MCR's
- *
- * Shortcut: We know you can't put 4Gig of RAM on a winchip
- */
-static u32 ramtop(void)
-{
-	u32 clip = 0xFFFFFFFFUL;
-	u32 top = 0;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		unsigned long start, end;
-
-		if (e820.map[i].addr > 0xFFFFFFFFUL)
-			continue;
-		/*
-		 * Don't MCR over reserved space. Ignore the ISA hole
-		 * we frob around that catastrophe already
-		 */
-		if (e820.map[i].type == E820_RESERVED) {
-			if (e820.map[i].addr >= 0x100000UL &&
-			    e820.map[i].addr < clip)
-				clip = e820.map[i].addr;
-			continue;
-		}
-		start = e820.map[i].addr;
-		end = e820.map[i].addr + e820.map[i].size;
-		if (start >= end)
-			continue;
-		if (end > top)
-			top = end;
-	}
-	/*
-	 * Everything below 'top' should be RAM except for the ISA hole.
-	 * Because of the limited MCR's we want to map NV/ACPI into our
-	 * MCR range for gunk in RAM
-	 *
-	 * Clip might cause us to MCR insufficient RAM but that is an
-	 * acceptable failure mode and should only bite obscure boxes with
-	 * a VESA hole at 15Mb
-	 *
-	 * The second case Clip sometimes kicks in is when the EBDA is marked
-	 * as reserved. Again we fail safe with reasonable results
-	 */
-	if (top > clip)
-		top = clip;
-
-	return top;
-}
-
-/*
- * Compute a set of MCR's to give maximum coverage
- */
-static int centaur_mcr_compute(int nr, int key)
-{
-	u32 mem = ramtop();
-	u32 root = power2(mem);
-	u32 base = root;
-	u32 top = root;
-	u32 floor = 0;
-	int ct = 0;
-
-	while (ct < nr) {
-		u32 fspace = 0;
-		u32 high;
-		u32 low;
-
-		/*
-		 * Find the largest block we will fill going upwards
-		 */
-		high = power2(mem-top);
-
-		/*
-		 * Find the largest block we will fill going downwards
-		 */
-		low = base/2;
-
-		/*
-		 * Don't fill below 1Mb going downwards as there
-		 * is an ISA hole in the way.
-		 */
-		if (base <= 1024*1024)
-			low = 0;
-
-		/*
-		 * See how much space we could cover by filling below
-		 * the ISA hole
-		 */
-
-		if (floor == 0)
-			fspace = 512*1024;
-		else if (floor == 512*1024)
-			fspace = 128*1024;
-
-		/* And forget ROM space */
-
-		/*
-		 * Now install the largest coverage we get
-		 */
-		if (fspace > high && fspace > low) {
-			centaur_mcr_insert(ct, floor, fspace, key);
-			floor += fspace;
-		} else if (high > low) {
-			centaur_mcr_insert(ct, top, high, key);
-			top += high;
-		} else if (low > 0) {
-			base -= low;
-			centaur_mcr_insert(ct, base, low, key);
-		} else
-			break;
-		ct++;
-	}
-	/*
-	 * We loaded ct values. We now need to set the mask. The caller
-	 * must do this bit.
-	 */
-	return ct;
-}
-
-static void centaur_create_optimal_mcr(void)
-{
-	int used;
-	int i;
-
-	/*
-	 * Allocate up to 6 mcrs to mark as much of ram as possible
-	 * as write combining and weak write ordered.
-	 *
-	 * To experiment with: Linux never uses stack operations for
-	 * mmio spaces so we could globally enable stack operation wc
-	 *
-	 * Load the registers with type 31 - full write combining, all
-	 * writes weakly ordered.
-	 */
-	used = centaur_mcr_compute(6, 31);
-
-	/*
-	 * Wipe unused MCRs
-	 */
-	for (i = used; i < 8; i++)
-		wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-static void winchip2_create_optimal_mcr(void)
-{
-	u32 lo, hi;
-	int used;
-	int i;
-
-	/*
-	 * Allocate up to 6 mcrs to mark as much of ram as possible
-	 * as write combining, weak store ordered.
-	 *
-	 * Load the registers with type 25
-	 *	8	-	weak write ordering
-	 *	16	-	weak read ordering
-	 *	1	-	write combining
-	 */
-	used = centaur_mcr_compute(6, 25);
-
-	/*
-	 * Mark the registers we are using.
-	 */
-	rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-	for (i = 0; i < used; i++)
-		lo |= 1<<(9+i);
-	wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-
-	/*
-	 * Wipe unused MCRs
-	 */
-
-	for (i = used; i < 8; i++)
-		wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-/*
- * Handle the MCR key on the Winchip 2.
- */
-static void winchip2_unprotect_mcr(void)
-{
-	u32 lo, hi;
-	u32 key;
-
-	rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-	lo &= ~0x1C0;	/* blank bits 8-6 */
-	key = (lo>>17) & 7;
-	lo |= key<<6;	/* replace with unlock key */
-	wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-
-static void winchip2_protect_mcr(void)
-{
-	u32 lo, hi;
-
-	rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-	lo &= ~0x1C0;	/* blank bits 8-6 */
-	wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-#endif /* CONFIG_X86_OOSTORE */
-
 #define ACE_PRESENT	(1 << 6)
 #define ACE_ENABLED	(1 << 7)
 #define ACE_FCR		(1 << 28)	/* MSR_VIA_FCR */
@@ -362,20 +132,6 @@
 			fcr_clr = DPDC;
 			printk(KERN_NOTICE "Disabling bugged TSC.\n");
 			clear_cpu_cap(c, X86_FEATURE_TSC);
-#ifdef CONFIG_X86_OOSTORE
-			centaur_create_optimal_mcr();
-			/*
-			 * Enable:
-			 *	write combining on non-stack, non-string
-			 *	write combining on string, all types
-			 *	weak write ordering
-			 *
-			 * The C6 original lacks weak read order
-			 *
-			 * Note 0x120 is write only on Winchip 1
-			 */
-			wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0);
-#endif
 			break;
 		case 8:
 			switch (c->x86_mask) {
@@ -392,40 +148,12 @@
 			fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
 				  E2MMX|EAMD3D;
 			fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
-			winchip2_unprotect_mcr();
-			winchip2_create_optimal_mcr();
-			rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			/*
-			 * Enable:
-			 *	write combining on non-stack, non-string
-			 *	write combining on string, all types
-			 *	weak write ordering
-			 */
-			lo |= 31;
-			wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			winchip2_protect_mcr();
-#endif
 			break;
 		case 9:
 			name = "3";
 			fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
 				  E2MMX|EAMD3D;
 			fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
-			winchip2_unprotect_mcr();
-			winchip2_create_optimal_mcr();
-			rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			/*
-			 * Enable:
-			 *	write combining on non-stack, non-string
-			 *	write combining on string, all types
-			 *	weak write ordering
-			 */
-			lo |= 31;
-			wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			winchip2_protect_mcr();
-#endif
 			break;
 		default:
 			name = "??";
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 24b6fd1..cca53d8 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -284,8 +284,13 @@
 	raw_local_save_flags(eflags);
 	BUG_ON(eflags & X86_EFLAGS_AC);
 
-	if (cpu_has(c, X86_FEATURE_SMAP))
+	if (cpu_has(c, X86_FEATURE_SMAP)) {
+#ifdef CONFIG_X86_SMAP
 		set_in_cr4(X86_CR4_SMAP);
+#else
+		clear_in_cr4(X86_CR4_SMAP);
+#endif
+	}
 }
 
 /*
@@ -1020,7 +1025,8 @@
 
 static __init int setup_noclflush(char *arg)
 {
-	setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
+	setup_clear_cpu_cap(X86_FEATURE_CLFLUSH);
+	setup_clear_cpu_cap(X86_FEATURE_CLFLUSHOPT);
 	return 1;
 }
 __setup("noclflush", setup_noclflush);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3db61c6..897d620 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -31,11 +31,8 @@
 
 	/* Unmask CPUID levels if masked: */
 	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
-		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-
-		if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
-			misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID;
-			wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+		if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
+				  MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) {
 			c->cpuid_level = cpuid_eax(0);
 			get_cpu_cap(c);
 		}
@@ -129,16 +126,10 @@
 	 * Ingo Molnar reported a Pentium D (model 6) and a Xeon
 	 * (model 2) with the same problem.
 	 */
-	if (c->x86 == 15) {
-		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-
-		if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
-			printk(KERN_INFO "kmemcheck: Disabling fast string operations\n");
-
-			misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING;
-			wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-		}
-	}
+	if (c->x86 == 15)
+		if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
+				  MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0)
+			pr_info("kmemcheck: Disabling fast string operations\n");
 #endif
 
 	/*
@@ -195,10 +186,16 @@
 	}
 }
 
+static int forcepae;
+static int __init forcepae_setup(char *__unused)
+{
+	forcepae = 1;
+	return 1;
+}
+__setup("forcepae", forcepae_setup);
+
 static void intel_workarounds(struct cpuinfo_x86 *c)
 {
-	unsigned long lo, hi;
-
 #ifdef CONFIG_X86_F00F_BUG
 	/*
 	 * All current models of Pentium and Pentium with MMX technology CPUs
@@ -225,16 +222,26 @@
 		clear_cpu_cap(c, X86_FEATURE_SEP);
 
 	/*
+	 * PAE CPUID issue: many Pentium M report no PAE but may have a
+	 * functionally usable PAE implementation.
+	 * Forcefully enable PAE if kernel parameter "forcepae" is present.
+	 */
+	if (forcepae) {
+		printk(KERN_WARNING "PAE forced!\n");
+		set_cpu_cap(c, X86_FEATURE_PAE);
+		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
+	}
+
+	/*
 	 * P4 Xeon errata 037 workaround.
 	 * Hardware prefetcher may cause stale data to be loaded into the cache.
 	 */
 	if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
-		rdmsr(MSR_IA32_MISC_ENABLE, lo, hi);
-		if ((lo & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE) == 0) {
-			printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n");
-			printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n");
-			lo |= MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE;
-			wrmsr(MSR_IA32_MISC_ENABLE, lo, hi);
+		if (msr_set_bit(MSR_IA32_MISC_ENABLE,
+				MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+		    > 0) {
+			pr_info("CPU: C0 stepping P4 Xeon detected.\n");
+			pr_info("CPU: Disabling hardware prefetching (Errata 037)\n");
 		}
 	}
 
@@ -640,21 +647,17 @@
 	case 0x61d: /* six-core 45 nm xeon "Dunnington" */
 		tlb_flushall_shift = -1;
 		break;
+	case 0x63a: /* Ivybridge */
+		tlb_flushall_shift = 2;
+		break;
 	case 0x61a: /* 45 nm nehalem, "Bloomfield" */
 	case 0x61e: /* 45 nm nehalem, "Lynnfield" */
 	case 0x625: /* 32 nm nehalem, "Clarkdale" */
 	case 0x62c: /* 32 nm nehalem, "Gulftown" */
 	case 0x62e: /* 45 nm nehalem-ex, "Beckton" */
 	case 0x62f: /* 32 nm Xeon E7 */
-		tlb_flushall_shift = 6;
-		break;
 	case 0x62a: /* SandyBridge */
 	case 0x62d: /* SandyBridge, "Romely-EP" */
-		tlb_flushall_shift = 5;
-		break;
-	case 0x63a: /* Ivybridge */
-		tlb_flushall_shift = 1;
-		break;
 	default:
 		tlb_flushall_shift = 6;
 	}
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 8384c0f..617a9e2 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -285,6 +285,15 @@
 
 	uci->cpu_sig.sig = cpuid_eax(0x00000001);
 }
+
+static void __init get_bsp_sig(void)
+{
+	unsigned int bsp = boot_cpu_data.cpu_index;
+	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
+
+	if (!uci->cpu_sig.sig)
+		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+}
 #else
 void load_ucode_amd_ap(void)
 {
@@ -337,31 +346,37 @@
 
 int __init save_microcode_in_initrd_amd(void)
 {
+	unsigned long cont;
 	enum ucode_state ret;
 	u32 eax;
 
-#ifdef CONFIG_X86_32
-	unsigned int bsp = boot_cpu_data.cpu_index;
-	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
+	if (!container)
+		return -EINVAL;
 
-	if (!uci->cpu_sig.sig)
-		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+#ifdef CONFIG_X86_32
+	get_bsp_sig();
+	cont = (unsigned long)container;
+#else
+	/*
+	 * We need the physical address of the container for both bitness since
+	 * boot_params.hdr.ramdisk_image is a physical address.
+	 */
+	cont = __pa(container);
+#endif
 
 	/*
-	 * Take into account the fact that the ramdisk might get relocated
-	 * and therefore we need to recompute the container's position in
-	 * virtual memory space.
+	 * Take into account the fact that the ramdisk might get relocated and
+	 * therefore we need to recompute the container's position in virtual
+	 * memory space.
 	 */
-	container = (u8 *)(__va((u32)relocated_ramdisk) +
-			   ((u32)container - boot_params.hdr.ramdisk_image));
-#endif
+	if (relocated_ramdisk)
+		container = (u8 *)(__va(relocated_ramdisk) +
+			     (cont - boot_params.hdr.ramdisk_image));
+
 	if (ucode_new_rev)
 		pr_info("microcode: updated early to new patch_level=0x%08x\n",
 			ucode_new_rev);
 
-	if (!container)
-		return -EINVAL;
-
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 9f7ca26..832d05a 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -26,6 +26,7 @@
 #include <asm/irq_regs.h>
 #include <asm/i8259.h>
 #include <asm/apic.h>
+#include <asm/timer.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
@@ -105,6 +106,11 @@
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
+
+#ifdef CONFIG_X86_IO_APIC
+	no_timer_check = 1;
+#endif
+
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index ce2d0a2..0e25a1b 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -683,7 +683,7 @@
 	}
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Save MTRR state */
@@ -697,7 +697,7 @@
 static void post_set(void) __releases(set_atomicity_lock)
 {
 	/* Flush TLBs (no need to flush caches - they are disabled) */
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Intel (P6) standard MTRRs */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b886451..ae407f7 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -892,7 +892,6 @@
 		 * hw_perf_group_sched_in() or x86_pmu_enable()
 		 *
 		 * step1: save events moving to new counters
-		 * step2: reprogram moved events into new counters
 		 */
 		for (i = 0; i < n_running; i++) {
 			event = cpuc->event_list[i];
@@ -918,6 +917,9 @@
 			x86_pmu_stop(event, PERF_EF_UPDATE);
 		}
 
+		/*
+		 * step2: reprogram moved events into new counters
+		 */
 		for (i = 0; i < cpuc->n_events; i++) {
 			event = cpuc->event_list[i];
 			hwc = &event->hw;
@@ -1043,7 +1045,7 @@
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be performed
-	 * at commit time (->commit_txn) as a whole
+	 * at commit time (->commit_txn) as a whole.
 	 */
 	if (cpuc->group_flag & PERF_EVENT_TXN)
 		goto done_collect;
@@ -1058,6 +1060,10 @@
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 done_collect:
+	/*
+	 * Commit the collect_events() state. See x86_pmu_del() and
+	 * x86_pmu_*_txn().
+	 */
 	cpuc->n_events = n;
 	cpuc->n_added += n - n0;
 	cpuc->n_txn += n - n0;
@@ -1183,25 +1189,38 @@
 	 * If we're called during a txn, we don't need to do anything.
 	 * The events never got scheduled and ->cancel_txn will truncate
 	 * the event_list.
+	 *
+	 * XXX assumes any ->del() called during a TXN will only be on
+	 * an event added during that same TXN.
 	 */
 	if (cpuc->group_flag & PERF_EVENT_TXN)
 		return;
 
+	/*
+	 * Not a TXN, therefore cleanup properly.
+	 */
 	x86_pmu_stop(event, PERF_EF_UPDATE);
 
 	for (i = 0; i < cpuc->n_events; i++) {
-		if (event == cpuc->event_list[i]) {
-
-			if (x86_pmu.put_event_constraints)
-				x86_pmu.put_event_constraints(cpuc, event);
-
-			while (++i < cpuc->n_events)
-				cpuc->event_list[i-1] = cpuc->event_list[i];
-
-			--cpuc->n_events;
+		if (event == cpuc->event_list[i])
 			break;
-		}
 	}
+
+	if (WARN_ON_ONCE(i == cpuc->n_events)) /* called ->del() without ->add() ? */
+		return;
+
+	/* If we have a newly added event; make sure to decrease n_added. */
+	if (i >= cpuc->n_events - cpuc->n_added)
+		--cpuc->n_added;
+
+	if (x86_pmu.put_event_constraints)
+		x86_pmu.put_event_constraints(cpuc, event);
+
+	/* Delete the array entry. */
+	while (++i < cpuc->n_events)
+		cpuc->event_list[i-1] = cpuc->event_list[i];
+	--cpuc->n_events;
+
 	perf_event_update_userpage(event);
 }
 
@@ -1521,6 +1540,8 @@
 
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
+	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+
 	for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
 		quirk->func();
 
@@ -1534,7 +1555,6 @@
 		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
 				   0, x86_pmu.num_counters, 0, 0);
 
-	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
 	x86_pmu_format_group.attrs = x86_pmu.format_attrs;
 
 	if (x86_pmu.event_attrs)
@@ -1594,7 +1614,8 @@
 {
 	__this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN);
 	/*
-	 * Truncate the collected events.
+	 * Truncate collected array by the number of events added in this
+	 * transaction. See x86_pmu_add() and x86_pmu_*_txn().
 	 */
 	__this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn));
 	__this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn));
@@ -1605,6 +1626,8 @@
  * Commit group events scheduling transaction
  * Perform the group schedulability test as a whole
  * Return 0 if success
+ *
+ * Does not cancel the transaction on failure; expects the caller to do this.
  */
 static int x86_pmu_commit_txn(struct pmu *pmu)
 {
@@ -1820,9 +1843,12 @@
 	if (ret)
 		return ret;
 
+	if (x86_pmu.attr_rdpmc_broken)
+		return -ENOTSUPP;
+
 	if (!!val != !!x86_pmu.attr_rdpmc) {
 		x86_pmu.attr_rdpmc = !!val;
-		smp_call_function(change_rdpmc, (void *)val, 1);
+		on_each_cpu(change_rdpmc, (void *)val, 1);
 	}
 
 	return count;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index c1a8618..3b2f9bd 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -130,9 +130,11 @@
 	unsigned long		running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	int			enabled;
 
-	int			n_events;
-	int			n_added;
-	int			n_txn;
+	int			n_events; /* the # of events in the below arrays */
+	int			n_added;  /* the # last events in the below arrays;
+					     they've never been enabled yet */
+	int			n_txn;    /* the # last events in the below arrays;
+					     added in the current transaction */
 	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
 	u64			tags[X86_PMC_IDX_MAX];
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
@@ -409,6 +411,7 @@
 	/*
 	 * sysfs attrs
 	 */
+	int		attr_rdpmc_broken;
 	int		attr_rdpmc;
 	struct attribute **format_attrs;
 	struct attribute **event_attrs;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 0fa4f24..aa333d9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1361,10 +1361,8 @@
 	intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
-	if (!status) {
-		intel_pmu_enable_all(0);
-		return handled;
-	}
+	if (!status)
+		goto done;
 
 	loops = 0;
 again:
@@ -2310,10 +2308,7 @@
 	if (version > 1)
 		x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
 
-	/*
-	 * v2 and above have a perf capabilities MSR
-	 */
-	if (version > 1) {
+	if (boot_cpu_has(X86_FEATURE_PDCM)) {
 		u64 capabilities;
 
 		rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 29c2487..bd2253d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -66,6 +66,47 @@
 DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
 DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
 
+static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
+static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
+static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
+static void uncore_pmu_event_read(struct perf_event *event);
+
+static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+{
+	return container_of(event->pmu, struct intel_uncore_pmu, pmu);
+}
+
+static struct intel_uncore_box *
+uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
+{
+	struct intel_uncore_box *box;
+
+	box = *per_cpu_ptr(pmu->box, cpu);
+	if (box)
+		return box;
+
+	raw_spin_lock(&uncore_box_lock);
+	list_for_each_entry(box, &pmu->box_list, list) {
+		if (box->phys_id == topology_physical_package_id(cpu)) {
+			atomic_inc(&box->refcnt);
+			*per_cpu_ptr(pmu->box, cpu) = box;
+			break;
+		}
+	}
+	raw_spin_unlock(&uncore_box_lock);
+
+	return *per_cpu_ptr(pmu->box, cpu);
+}
+
+static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+{
+	/*
+	 * perf core schedules event on the basis of cpu, uncore events are
+	 * collected by one of the cpus inside a physical package.
+	 */
+	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
+}
+
 static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
 {
 	u64 count;
@@ -501,8 +542,11 @@
 	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
 				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
@@ -1178,10 +1222,15 @@
 	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
 				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
@@ -1631,6 +1680,349 @@
 	&snb_uncore_cbox,
 	NULL,
 };
+
+enum {
+	SNB_PCI_UNCORE_IMC,
+};
+
+static struct uncore_event_desc snb_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(data_reads,  "event=0x01"),
+	INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"),
+
+	INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"),
+	INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
+
+	{ /* end: all zeroes */ },
+};
+
+#define SNB_UNCORE_PCI_IMC_EVENT_MASK		0xff
+#define SNB_UNCORE_PCI_IMC_BAR_OFFSET		0x48
+
+/* page size multiple covering all config regs */
+#define SNB_UNCORE_PCI_IMC_MAP_SIZE		0x6000
+
+#define SNB_UNCORE_PCI_IMC_DATA_READS		0x1
+#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE	0x5050
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES		0x2
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE	0x5054
+#define SNB_UNCORE_PCI_IMC_CTR_BASE		SNB_UNCORE_PCI_IMC_DATA_READS_BASE
+
+static struct attribute *snb_uncore_imc_formats_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group snb_uncore_imc_format_group = {
+	.name = "format",
+	.attrs = snb_uncore_imc_formats_attr,
+};
+
+static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
+	resource_size_t addr;
+	u32 pci_dword;
+
+	pci_read_config_dword(pdev, where, &pci_dword);
+	addr = pci_dword;
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	pci_read_config_dword(pdev, where + 4, &pci_dword);
+	addr |= ((resource_size_t)pci_dword << 32);
+#endif
+
+	addr &= ~(PAGE_SIZE - 1);
+
+	box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+	box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
+}
+
+static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_disable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
+}
+
+/*
+ * custom event_init() function because we define our own fixed, free
+ * running counters, so we do not want to conflict with generic uncore
+ * logic. Also simplifies processing
+ */
+static int snb_uncore_imc_event_init(struct perf_event *event)
+{
+	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_box *box;
+	struct hw_perf_event *hwc = &event->hw;
+	u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK;
+	int idx, base;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	pmu = uncore_event_to_pmu(event);
+	/* no device found for this pmu */
+	if (pmu->func_id < 0)
+		return -ENOENT;
+
+	/* Sampling not supported yet */
+	if (hwc->sample_period)
+		return -EINVAL;
+
+	/* unsupported modes and filters */
+	if (event->attr.exclude_user   ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv     ||
+	    event->attr.exclude_idle   ||
+	    event->attr.exclude_host   ||
+	    event->attr.exclude_guest  ||
+	    event->attr.sample_period) /* no sampling */
+		return -EINVAL;
+
+	/*
+	 * Place all uncore events for a particular physical package
+	 * onto a single cpu
+	 */
+	if (event->cpu < 0)
+		return -EINVAL;
+
+	/* check only supported bits are set */
+	if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK)
+		return -EINVAL;
+
+	box = uncore_pmu_to_box(pmu, event->cpu);
+	if (!box || box->cpu < 0)
+		return -EINVAL;
+
+	event->cpu = box->cpu;
+
+	event->hw.idx = -1;
+	event->hw.last_tag = ~0ULL;
+	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
+	/*
+	 * check event is known (whitelist, determines counter)
+	 */
+	switch (cfg) {
+	case SNB_UNCORE_PCI_IMC_DATA_READS:
+		base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
+		idx = UNCORE_PMC_IDX_FIXED;
+		break;
+	case SNB_UNCORE_PCI_IMC_DATA_WRITES:
+		base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
+		idx = UNCORE_PMC_IDX_FIXED + 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* must be done before validate_group */
+	event->hw.event_base = base;
+	event->hw.config = cfg;
+	event->hw.idx = idx;
+
+	/* no group validation needed, we have free running counters */
+
+	return 0;
+}
+
+static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return 0;
+}
+
+static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	u64 count;
+
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	event->hw.state = 0;
+	box->n_active++;
+
+	list_add_tail(&event->active_entry, &box->active_list);
+
+	count = snb_uncore_imc_read_counter(box, event);
+	local64_set(&event->hw.prev_count, count);
+
+	if (box->n_active == 1)
+		uncore_pmu_start_hrtimer(box);
+}
+
+static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		box->n_active--;
+
+		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+		hwc->state |= PERF_HES_STOPPED;
+
+		list_del(&event->active_entry);
+
+		if (box->n_active == 0)
+			uncore_pmu_cancel_hrtimer(box);
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		/*
+		 * Drain the remaining delta count out of a event
+		 * that we are disabling:
+		 */
+		uncore_perf_event_update(box, event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+}
+
+static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!box)
+		return -ENODEV;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_ARCH;
+
+	snb_uncore_imc_event_start(event, 0);
+
+	box->n_events++;
+
+	return 0;
+}
+
+static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	int i;
+
+	snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
+
+	for (i = 0; i < box->n_events; i++) {
+		if (event == box->event_list[i]) {
+			--box->n_events;
+			break;
+		}
+	}
+}
+
+static int snb_pci2phy_map_init(int devid)
+{
+	struct pci_dev *dev = NULL;
+	int bus;
+
+	dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
+	if (!dev)
+		return -ENOTTY;
+
+	bus = dev->bus->number;
+
+	pcibus_to_physid[bus] = 0;
+
+	pci_dev_put(dev);
+
+	return 0;
+}
+
+static struct pmu snb_uncore_imc_pmu = {
+	.task_ctx_nr	= perf_invalid_context,
+	.event_init	= snb_uncore_imc_event_init,
+	.add		= snb_uncore_imc_event_add,
+	.del		= snb_uncore_imc_event_del,
+	.start		= snb_uncore_imc_event_start,
+	.stop		= snb_uncore_imc_event_stop,
+	.read		= uncore_pmu_event_read,
+};
+
+static struct intel_uncore_ops snb_uncore_imc_ops = {
+	.init_box	= snb_uncore_imc_init_box,
+	.enable_box	= snb_uncore_imc_enable_box,
+	.disable_box	= snb_uncore_imc_disable_box,
+	.disable_event	= snb_uncore_imc_disable_event,
+	.enable_event	= snb_uncore_imc_enable_event,
+	.hw_config	= snb_uncore_imc_hw_config,
+	.read_counter	= snb_uncore_imc_read_counter,
+};
+
+static struct intel_uncore_type snb_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 2,
+	.num_boxes	= 1,
+	.fixed_ctr_bits	= 32,
+	.fixed_ctr	= SNB_UNCORE_PCI_IMC_CTR_BASE,
+	.event_descs	= snb_uncore_imc_events,
+	.format_group	= &snb_uncore_imc_format_group,
+	.perf_ctr	= SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
+	.event_mask	= SNB_UNCORE_PCI_IMC_EVENT_MASK,
+	.ops		= &snb_uncore_imc_ops,
+	.pmu		= &snb_uncore_imc_pmu,
+};
+
+static struct intel_uncore_type *snb_pci_uncores[] = {
+	[SNB_PCI_UNCORE_IMC]	= &snb_uncore_imc,
+	NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(snb_uncore_pci_ids) = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static DEFINE_PCI_DEVICE_TABLE(ivb_uncore_pci_ids) = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static DEFINE_PCI_DEVICE_TABLE(hsw_uncore_pci_ids) = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static struct pci_driver snb_uncore_pci_driver = {
+	.name		= "snb_uncore",
+	.id_table	= snb_uncore_pci_ids,
+};
+
+static struct pci_driver ivb_uncore_pci_driver = {
+	.name		= "ivb_uncore",
+	.id_table	= ivb_uncore_pci_ids,
+};
+
+static struct pci_driver hsw_uncore_pci_driver = {
+	.name		= "hsw_uncore",
+	.id_table	= hsw_uncore_pci_ids,
+};
+
 /* end of Sandy Bridge uncore support */
 
 /* Nehalem uncore support */
@@ -2781,6 +3173,7 @@
 static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 {
 	struct intel_uncore_box *box;
+	struct perf_event *event;
 	unsigned long flags;
 	int bit;
 
@@ -2793,19 +3186,27 @@
 	 */
 	local_irq_save(flags);
 
+	/*
+	 * handle boxes with an active event list as opposed to active
+	 * counters
+	 */
+	list_for_each_entry(event, &box->active_list, active_entry) {
+		uncore_perf_event_update(box, event);
+	}
+
 	for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX)
 		uncore_perf_event_update(box, box->events[bit]);
 
 	local_irq_restore(flags);
 
-	hrtimer_forward_now(hrtimer, ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL));
+	hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration));
 	return HRTIMER_RESTART;
 }
 
 static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
 	__hrtimer_start_range_ns(&box->hrtimer,
-			ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL), 0,
+			ns_to_ktime(box->hrtimer_duration), 0,
 			HRTIMER_MODE_REL_PINNED, 0);
 }
 
@@ -2839,45 +3240,14 @@
 	box->cpu = -1;
 	box->phys_id = -1;
 
+	/* set default hrtimer timeout */
+	box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL;
+
+	INIT_LIST_HEAD(&box->active_list);
+
 	return box;
 }
 
-static struct intel_uncore_box *
-uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
-{
-	struct intel_uncore_box *box;
-
-	box = *per_cpu_ptr(pmu->box, cpu);
-	if (box)
-		return box;
-
-	raw_spin_lock(&uncore_box_lock);
-	list_for_each_entry(box, &pmu->box_list, list) {
-		if (box->phys_id == topology_physical_package_id(cpu)) {
-			atomic_inc(&box->refcnt);
-			*per_cpu_ptr(pmu->box, cpu) = box;
-			break;
-		}
-	}
-	raw_spin_unlock(&uncore_box_lock);
-
-	return *per_cpu_ptr(pmu->box, cpu);
-}
-
-static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
-{
-	return container_of(event->pmu, struct intel_uncore_pmu, pmu);
-}
-
-static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
-{
-	/*
-	 * perf core schedules event on the basis of cpu, uncore events are
-	 * collected by one of the cpus inside a physical package.
-	 */
-	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
-}
-
 static int
 uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
 {
@@ -3271,16 +3641,21 @@
 {
 	int ret;
 
-	pmu->pmu = (struct pmu) {
-		.attr_groups	= pmu->type->attr_groups,
-		.task_ctx_nr	= perf_invalid_context,
-		.event_init	= uncore_pmu_event_init,
-		.add		= uncore_pmu_event_add,
-		.del		= uncore_pmu_event_del,
-		.start		= uncore_pmu_event_start,
-		.stop		= uncore_pmu_event_stop,
-		.read		= uncore_pmu_event_read,
-	};
+	if (!pmu->type->pmu) {
+		pmu->pmu = (struct pmu) {
+			.attr_groups	= pmu->type->attr_groups,
+			.task_ctx_nr	= perf_invalid_context,
+			.event_init	= uncore_pmu_event_init,
+			.add		= uncore_pmu_event_add,
+			.del		= uncore_pmu_event_del,
+			.start		= uncore_pmu_event_start,
+			.stop		= uncore_pmu_event_stop,
+			.read		= uncore_pmu_event_read,
+		};
+	} else {
+		pmu->pmu = *pmu->type->pmu;
+		pmu->pmu.attr_groups = pmu->type->attr_groups;
+	}
 
 	if (pmu->type->num_boxes == 1) {
 		if (strlen(pmu->type->name) > 0)
@@ -3326,6 +3701,8 @@
 	if (!pmus)
 		return -ENOMEM;
 
+	type->pmus = pmus;
+
 	type->unconstrainted = (struct event_constraint)
 		__EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
 				0, type->num_counters, 0, 0);
@@ -3361,7 +3738,6 @@
 	}
 
 	type->pmu_group = &uncore_pmu_attr_group;
-	type->pmus = pmus;
 	return 0;
 fail:
 	uncore_type_exit(type);
@@ -3493,6 +3869,28 @@
 		pci_uncores = ivt_pci_uncores;
 		uncore_pci_driver = &ivt_uncore_pci_driver;
 		break;
+	case 42: /* Sandy Bridge */
+		ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC);
+		if (ret)
+			return ret;
+		pci_uncores = snb_pci_uncores;
+		uncore_pci_driver = &snb_uncore_pci_driver;
+		break;
+	case 58: /* Ivy Bridge */
+		ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC);
+		if (ret)
+			return ret;
+		pci_uncores = snb_pci_uncores;
+		uncore_pci_driver = &ivb_uncore_pci_driver;
+		break;
+	case 60: /* Haswell */
+	case 69: /* Haswell Celeron */
+		ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC);
+		if (ret)
+			return ret;
+		pci_uncores = snb_pci_uncores;
+		uncore_pci_driver = &hsw_uncore_pci_driver;
+		break;
 	default:
 		return 0;
 	}
@@ -3764,7 +4162,7 @@
 
 static int __init uncore_cpu_init(void)
 {
-	int ret, cpu, max_cores;
+	int ret, max_cores;
 
 	max_cores = boot_cpu_data.x86_max_cores;
 	switch (boot_cpu_data.x86_model) {
@@ -3808,29 +4206,6 @@
 	if (ret)
 		return ret;
 
-	get_online_cpus();
-
-	for_each_online_cpu(cpu) {
-		int i, phys_id = topology_physical_package_id(cpu);
-
-		for_each_cpu(i, &uncore_cpu_mask) {
-			if (phys_id == topology_physical_package_id(i)) {
-				phys_id = -1;
-				break;
-			}
-		}
-		if (phys_id < 0)
-			continue;
-
-		uncore_cpu_prepare(cpu, phys_id);
-		uncore_event_init_cpu(cpu);
-	}
-	on_each_cpu(uncore_cpu_setup, NULL, 1);
-
-	register_cpu_notifier(&uncore_cpu_nb);
-
-	put_online_cpus();
-
 	return 0;
 }
 
@@ -3859,6 +4234,41 @@
 	return 0;
 }
 
+static void __init uncore_cpumask_init(void)
+{
+	int cpu;
+
+	/*
+	 * ony invoke once from msr or pci init code
+	 */
+	if (!cpumask_empty(&uncore_cpu_mask))
+		return;
+
+	get_online_cpus();
+
+	for_each_online_cpu(cpu) {
+		int i, phys_id = topology_physical_package_id(cpu);
+
+		for_each_cpu(i, &uncore_cpu_mask) {
+			if (phys_id == topology_physical_package_id(i)) {
+				phys_id = -1;
+				break;
+			}
+		}
+		if (phys_id < 0)
+			continue;
+
+		uncore_cpu_prepare(cpu, phys_id);
+		uncore_event_init_cpu(cpu);
+	}
+	on_each_cpu(uncore_cpu_setup, NULL, 1);
+
+	register_cpu_notifier(&uncore_cpu_nb);
+
+	put_online_cpus();
+}
+
+
 static int __init intel_uncore_init(void)
 {
 	int ret;
@@ -3877,6 +4287,7 @@
 		uncore_pci_exit();
 		goto fail;
 	}
+	uncore_cpumask_init();
 
 	uncore_pmus_register();
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index a80ab71..90236f0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -6,6 +6,7 @@
 
 #define UNCORE_PMU_NAME_LEN		32
 #define UNCORE_PMU_HRTIMER_INTERVAL	(60LL * NSEC_PER_SEC)
+#define UNCORE_SNB_IMC_HRTIMER_INTERVAL (5ULL * NSEC_PER_SEC)
 
 #define UNCORE_FIXED_EVENT		0xff
 #define UNCORE_PMC_IDX_MAX_GENERIC	8
@@ -440,6 +441,7 @@
 	struct intel_uncore_ops *ops;
 	struct uncore_event_desc *event_descs;
 	const struct attribute_group *attr_groups[4];
+	struct pmu *pmu; /* for custom pmu ops */
 };
 
 #define pmu_group attr_groups[0]
@@ -488,8 +490,11 @@
 	u64 tags[UNCORE_PMC_IDX_MAX];
 	struct pci_dev *pci_dev;
 	struct intel_uncore_pmu *pmu;
+	u64 hrtimer_duration; /* hrtimer timeout for this box */
 	struct hrtimer hrtimer;
 	struct list_head list;
+	struct list_head active_list;
+	void *io_addr;
 	struct intel_uncore_extra_reg shared_regs[0];
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 3486e66..5d466b7 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1257,7 +1257,24 @@
 			pass++;
 			goto again;
 		}
-
+		/*
+		 * Perf does test runs to see if a whole group can be assigned
+		 * together succesfully.  There can be multiple rounds of this.
+		 * Unfortunately, p4_pmu_swap_config_ts touches the hwc->config
+		 * bits, such that the next round of group assignments will
+		 * cause the above p4_should_swap_ts to pass instead of fail.
+		 * This leads to counters exclusive to thread0 being used by
+		 * thread1.
+		 *
+		 * Solve this with a cheap hack, reset the idx back to -1 to
+		 * force a new lookup (p4_next_cntr) to get the right counter
+		 * for the right thread.
+		 *
+		 * This probably doesn't comply with the general spirit of how
+		 * perf wants to work, but P4 is special. :-(
+		 */
+		if (p4_should_swap_ts(hwc->config, cpu))
+			hwc->idx = -1;
 		p4_pmu_swap_config_ts(hwc, cpu);
 		if (assign)
 			assign[i] = cntr_idx;
@@ -1322,6 +1339,7 @@
 __init int p4_pmu_init(void)
 {
 	unsigned int low, high;
+	int i, reg;
 
 	/* If we get stripped -- indexing fails */
 	BUILD_BUG_ON(ARCH_P4_MAX_CCCR > INTEL_PMC_MAX_GENERIC);
@@ -1340,5 +1358,19 @@
 
 	x86_pmu = p4_pmu;
 
+	/*
+	 * Even though the counters are configured to interrupt a particular
+	 * logical processor when an overflow happens, testing has shown that
+	 * on kdump kernels (which uses a single cpu), thread1's counter
+	 * continues to run and will report an NMI on thread0.  Due to the
+	 * overflow bug, this leads to a stream of unknown NMIs.
+	 *
+	 * Solve this by zero'ing out the registers to mimic a reset.
+	 */
+	for (i = 0; i < x86_pmu.num_counters; i++) {
+		reg = x86_pmu_config_addr(i);
+		wrmsrl_safe(reg, 0ULL);
+	}
+
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index b1e2fe1..7c1a0c0 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -231,31 +231,49 @@
 
 };
 
+static __init void p6_pmu_rdpmc_quirk(void)
+{
+	if (boot_cpu_data.x86_mask < 9) {
+		/*
+		 * PPro erratum 26; fixed in stepping 9 and above.
+		 */
+		pr_warn("Userspace RDPMC support disabled due to a CPU erratum\n");
+		x86_pmu.attr_rdpmc_broken = 1;
+		x86_pmu.attr_rdpmc = 0;
+	}
+}
+
 __init int p6_pmu_init(void)
 {
+	x86_pmu = p6_pmu;
+
 	switch (boot_cpu_data.x86_model) {
-	case 1:
-	case 3:  /* Pentium Pro */
-	case 5:
-	case 6:  /* Pentium II */
-	case 7:
-	case 8:
-	case 11: /* Pentium III */
-	case 9:
-	case 13:
-		/* Pentium M */
+	case  1: /* Pentium Pro */
+		x86_add_quirk(p6_pmu_rdpmc_quirk);
 		break;
+
+	case  3: /* Pentium II - Klamath */
+	case  5: /* Pentium II - Deschutes */
+	case  6: /* Pentium II - Mendocino */
+		break;
+
+	case  7: /* Pentium III - Katmai */
+	case  8: /* Pentium III - Coppermine */
+	case 10: /* Pentium III Xeon */
+	case 11: /* Pentium III - Tualatin */
+		break;
+
+	case  9: /* Pentium M - Banias */
+	case 13: /* Pentium M - Dothan */
+		break;
+
 	default:
-		pr_cont("unsupported p6 CPU model %d ",
-			boot_cpu_data.x86_model);
+		pr_cont("unsupported p6 CPU model %d ", boot_cpu_data.x86_model);
 		return -ENODEV;
 	}
 
-	x86_pmu = p6_pmu;
-
 	memcpy(hw_cache_event_ids, p6_hw_cache_event_ids,
 		sizeof(hw_cache_event_ids));
 
-
 	return 0;
 }
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a57902e..507de80 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -57,9 +57,7 @@
 {
 #ifdef CONFIG_X86_32
 	struct pt_regs fixed_regs;
-#endif
 
-#ifdef CONFIG_X86_32
 	if (!user_mode_vm(regs)) {
 		crash_fixup_ss_esp(&fixed_regs, regs);
 		regs = &fixed_regs;
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index f2a1770..a21d49c 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -30,7 +30,7 @@
 		unsigned long dummy;
 
 		stack = &dummy;
-		if (task && task != current)
+		if (task != current)
 			stack = (unsigned long *)task->thread.sp;
 	}
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index d4bdd25..e625319 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -77,8 +77,7 @@
 	return addr >= start && addr < end;
 }
 
-static int
-do_ftrace_mod_code(unsigned long ip, const void *new_code)
+static unsigned long text_ip_addr(unsigned long ip)
 {
 	/*
 	 * On x86_64, kernel text mappings are mapped read-only with
@@ -91,7 +90,7 @@
 	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
 		ip = (unsigned long)__va(__pa_symbol(ip));
 
-	return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
+	return ip;
 }
 
 static const unsigned char *ftrace_nop_replace(void)
@@ -123,8 +122,10 @@
 	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
 		return -EINVAL;
 
+	ip = text_ip_addr(ip);
+
 	/* replace the text with the new text */
-	if (do_ftrace_mod_code(ip, new_code))
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	sync_core();
@@ -221,37 +222,51 @@
 	return -EINVAL;
 }
 
-int ftrace_update_ftrace_func(ftrace_func_t func)
+static unsigned long ftrace_update_func;
+
+static int update_ftrace_func(unsigned long ip, void *new)
 {
-	unsigned long ip = (unsigned long)(&ftrace_call);
-	unsigned char old[MCOUNT_INSN_SIZE], *new;
+	unsigned char old[MCOUNT_INSN_SIZE];
 	int ret;
 
-	memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
-	new = ftrace_call_replace(ip, (unsigned long)func);
+	memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);
+
+	ftrace_update_func = ip;
+	/* Make sure the breakpoints see the ftrace_update_func update */
+	smp_wmb();
 
 	/* See comment above by declaration of modifying_ftrace_code */
 	atomic_inc(&modifying_ftrace_code);
 
 	ret = ftrace_modify_code(ip, old, new);
 
+	atomic_dec(&modifying_ftrace_code);
+
+	return ret;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	unsigned char *new;
+	int ret;
+
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	ret = update_ftrace_func(ip, new);
+
 	/* Also update the regs callback function */
 	if (!ret) {
 		ip = (unsigned long)(&ftrace_regs_call);
-		memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
 		new = ftrace_call_replace(ip, (unsigned long)func);
-		ret = ftrace_modify_code(ip, old, new);
+		ret = update_ftrace_func(ip, new);
 	}
 
-	atomic_dec(&modifying_ftrace_code);
-
 	return ret;
 }
 
 static int is_ftrace_caller(unsigned long ip)
 {
-	if (ip == (unsigned long)(&ftrace_call) ||
-		ip == (unsigned long)(&ftrace_regs_call))
+	if (ip == ftrace_update_func)
 		return 1;
 
 	return 0;
@@ -677,45 +692,41 @@
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern void ftrace_graph_call(void);
 
-static int ftrace_mod_jmp(unsigned long ip,
-			  int old_offset, int new_offset)
+static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 {
-	unsigned char code[MCOUNT_INSN_SIZE];
+	static union ftrace_code_union calc;
 
-	if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
-		return -EFAULT;
+	/* Jmp not a call (ignore the .e8) */
+	calc.e8		= 0xe9;
+	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
 
-	if (code[0] != 0xe9 || old_offset != *(int *)(&code[1]))
-		return -EINVAL;
+	/*
+	 * ftrace external locks synchronize the access to the static variable.
+	 */
+	return calc.code;
+}
 
-	*(int *)(&code[1]) = new_offset;
+static int ftrace_mod_jmp(unsigned long ip, void *func)
+{
+	unsigned char *new;
 
-	if (do_ftrace_mod_code(ip, &code))
-		return -EPERM;
+	new = ftrace_jmp_replace(ip, (unsigned long)func);
 
-	return 0;
+	return update_ftrace_func(ip, new);
 }
 
 int ftrace_enable_ftrace_graph_caller(void)
 {
 	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	int old_offset, new_offset;
 
-	old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
-	new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-
-	return ftrace_mod_jmp(ip, old_offset, new_offset);
+	return ftrace_mod_jmp(ip, &ftrace_graph_caller);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
 	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	int old_offset, new_offset;
 
-	old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-	new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
-
-	return ftrace_mod_jmp(ip, old_offset, new_offset);
+	return ftrace_mod_jmp(ip, &ftrace_stub);
 }
 
 #endif /* !CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 81ba276..f36bd42 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -544,6 +544,10 @@
 	/* This is global to keep gas from relaxing the jumps */
 ENTRY(early_idt_handler)
 	cld
+
+	cmpl $2,(%esp)		# X86_TRAP_NMI
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,%ss:early_recursion_flag
 	je hlt_loop
 	incl %ss:early_recursion_flag
@@ -594,8 +598,9 @@
 	pop %edx
 	pop %ecx
 	pop %eax
-	addl $8,%esp		/* drop vector number and error code */
 	decl %ss:early_recursion_flag
+is_nmi:
+	addl $8,%esp		/* drop vector number and error code */
 	iret
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e1aabdb..a468c0a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -343,6 +343,9 @@
 ENTRY(early_idt_handler)
 	cld
 
+	cmpl $2,(%rsp)		# X86_TRAP_NMI
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,early_recursion_flag(%rip)
 	jz  1f
 	incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@
 	popq %rdx
 	popq %rcx
 	popq %rax
-	addq $16,%rsp		# drop vector number and error code
 	decl early_recursion_flag(%rip)
+is_nmi:
+	addq $16,%rsp		# drop vector number and error code
 	INTERRUPT_RETURN
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e8368c6..d5dd808 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@
 
 void __kernel_fpu_end(void)
 {
-	if (use_eager_fpu())
-		math_state_restore();
-	else
+	if (use_eager_fpu()) {
+		/*
+		 * For eager fpu, most the time, tsk_used_math() is true.
+		 * Restore the user math as we are done with the kernel usage.
+		 * At few instances during thread exit, signal handling etc,
+		 * tsk_used_math() is false. Those few places will take proper
+		 * actions, so we don't need to restore the math here.
+		 */
+		if (likely(tsk_used_math(current)))
+			math_state_restore();
+	} else {
 		stts();
+	}
 }
 EXPORT_SYMBOL(__kernel_fpu_end);
 
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index dbb6087..d99f31d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -266,6 +266,14 @@
 EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+/* These two declarations are only used in check_irq_vectors_for_cpu_disable()
+ * below, which is protected by stop_machine().  Putting them on the stack
+ * results in a stack frame overflow.  Dynamically allocating could result in a
+ * failure so declare these two cpumasks as global.
+ */
+static struct cpumask affinity_new, online_new;
+
 /*
  * This cpu is going to be removed and its vectors migrated to the remaining
  * online cpus.  Check to see if there are enough vectors in the remaining cpus.
@@ -277,7 +285,6 @@
 	unsigned int this_cpu, vector, this_count, count;
 	struct irq_desc *desc;
 	struct irq_data *data;
-	struct cpumask affinity_new, online_new;
 
 	this_cpu = smp_processor_id();
 	cpumask_copy(&online_new, cpu_online_mask);
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4eabc16..679cef0 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -279,5 +279,7 @@
 	VMCOREINFO_SYMBOL(node_data);
 	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
 #endif
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
+			      (unsigned long)&_text - __START_KERNEL);
 }
 
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 18be189..e69f988 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -28,6 +28,7 @@
 #include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/jump_label.h>
+#include <linux/random.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -43,13 +44,52 @@
 } while (0)
 #endif
 
+#ifdef CONFIG_RANDOMIZE_BASE
+static unsigned long module_load_offset;
+static int randomize_modules = 1;
+
+/* Mutex protects the module_load_offset. */
+static DEFINE_MUTEX(module_kaslr_mutex);
+
+static int __init parse_nokaslr(char *p)
+{
+	randomize_modules = 0;
+	return 0;
+}
+early_param("nokaslr", parse_nokaslr);
+
+static unsigned long int get_module_load_offset(void)
+{
+	if (randomize_modules) {
+		mutex_lock(&module_kaslr_mutex);
+		/*
+		 * Calculate the module_load_offset the first time this
+		 * code is called. Once calculated it stays the same until
+		 * reboot.
+		 */
+		if (module_load_offset == 0)
+			module_load_offset =
+				(get_random_int() % 1024 + 1) * PAGE_SIZE;
+		mutex_unlock(&module_kaslr_mutex);
+	}
+	return module_load_offset;
+}
+#else
+static unsigned long int get_module_load_offset(void)
+{
+	return 0;
+}
+#endif
+
 void *module_alloc(unsigned long size)
 {
 	if (PAGE_ALIGN(size) > MODULES_LEN)
 		return NULL;
-	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
-				GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
-				NUMA_NO_NODE, __builtin_return_address(0));
+	return __vmalloc_node_range(size, 1,
+				    MODULES_VADDR + get_module_load_offset(),
+				    MODULES_END, GFP_KERNEL | __GFP_HIGHMEM,
+				    PAGE_KERNEL_EXEC, NUMA_NO_NODE,
+				    __builtin_return_address(0));
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 6fcb49c..b4872b9 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -87,6 +87,7 @@
 #define nmi_to_desc(type) (&nmi_desc[type])
 
 static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC;
+
 static int __init nmi_warning_debugfs(void)
 {
 	debugfs_create_u64("nmi_longest_ns", 0644,
@@ -95,6 +96,20 @@
 }
 fs_initcall(nmi_warning_debugfs);
 
+static void nmi_max_handler(struct irq_work *w)
+{
+	struct nmiaction *a = container_of(w, struct nmiaction, irq_work);
+	int remainder_ns, decimal_msecs;
+	u64 whole_msecs = ACCESS_ONCE(a->max_duration);
+
+	remainder_ns = do_div(whole_msecs, (1000 * 1000));
+	decimal_msecs = remainder_ns / 1000;
+
+	printk_ratelimited(KERN_INFO
+		"INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
+		a->handler, whole_msecs, decimal_msecs);
+}
+
 static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
@@ -110,26 +125,20 @@
 	 * to handle those situations.
 	 */
 	list_for_each_entry_rcu(a, &desc->head, list) {
-		u64 before, delta, whole_msecs;
-		int remainder_ns, decimal_msecs, thishandled;
+		int thishandled;
+		u64 delta;
 
-		before = sched_clock();
+		delta = sched_clock();
 		thishandled = a->handler(type, regs);
 		handled += thishandled;
-		delta = sched_clock() - before;
+		delta = sched_clock() - delta;
 		trace_nmi_handler(a->handler, (int)delta, thishandled);
 
-		if (delta < nmi_longest_ns)
+		if (delta < nmi_longest_ns || delta < a->max_duration)
 			continue;
 
-		nmi_longest_ns = delta;
-		whole_msecs = delta;
-		remainder_ns = do_div(whole_msecs, (1000 * 1000));
-		decimal_msecs = remainder_ns / 1000;
-		printk_ratelimited(KERN_INFO
-			"INFO: NMI handler (%ps) took too long to run: "
-			"%lld.%03d msecs\n", a->handler, whole_msecs,
-			decimal_msecs);
+		a->max_duration = delta;
+		irq_work_queue(&a->irq_work);
 	}
 
 	rcu_read_unlock();
@@ -146,6 +155,8 @@
 	if (!action->handler)
 		return -EINVAL;
 
+	init_irq_work(&action->irq_work, nmi_max_handler);
+
 	spin_lock_irqsave(&desc->lock, flags);
 
 	/*
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 872079a..f7d0672 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -100,8 +100,10 @@
 	flag |= __GFP_ZERO;
 again:
 	page = NULL;
-	if (!(flag & GFP_ATOMIC))
+	/* CMA can be used only in the context which permits sleeping */
+	if (flag & __GFP_WAIT)
 		page = dma_alloc_from_contiguous(dev, count, get_order(size));
+	/* fallback */
 	if (!page)
 		page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
 	if (!page)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 3fb8d95..4505e2a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -298,10 +298,7 @@
  */
 void arch_cpu_idle(void)
 {
-	if (cpuidle_idle_call())
-		x86_idle();
-	else
-		local_irq_enable();
+	x86_idle();
 }
 
 /*
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 04ee1e2..ff898bb 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -529,7 +529,7 @@
 		return;
 
 	pci_read_config_dword(nb_ht, 0x60, &val);
-	node = val & 7;
+	node = pcibus_to_node(dev->bus) | (val & 7);
 	/*
 	 * Some hardware may return an invalid node ID,
 	 * so check it first:
@@ -571,3 +571,40 @@
 			quirk_amd_nb_node);
 
 #endif
+
+#ifdef CONFIG_PCI
+/*
+ * Processor does not ensure DRAM scrub read/write sequence
+ * is atomic wrt accesses to CC6 save state area. Therefore
+ * if a concurrent scrub read/write access is to same address
+ * the entry may appear as if it is not written. This quirk
+ * applies to Fam16h models 00h-0Fh
+ *
+ * See "Revision Guide" for AMD F16h models 00h-0fh,
+ * document 51810 rev. 3.04, Nov 2013
+ */
+static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev)
+{
+	u32 val;
+
+	/*
+	 * Suggested workaround:
+	 * set D18F3x58[4:0] = 00h and set D18F3x5C[0] = 0b
+	 */
+	pci_read_config_dword(dev, 0x58, &val);
+	if (val & 0x1F) {
+		val &= ~(0x1F);
+		pci_write_config_dword(dev, 0x58, val);
+	}
+
+	pci_read_config_dword(dev, 0x5C, &val);
+	if (val & BIT(0)) {
+		val &= ~BIT(0);
+		pci_write_config_dword(dev, 0x5c, val);
+	}
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
+			amd_disable_seq_and_redirect_scrub);
+
+#endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index c752cb4..654b465 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -464,9 +464,12 @@
  * 2) If still alive, write to the keyboard controller
  * 3) If still alive, write to the ACPI reboot register again
  * 4) If still alive, write to the keyboard controller again
+ * 5) If still alive, call the EFI runtime service to reboot
+ * 6) If still alive, write to the PCI IO port 0xCF9 to reboot
+ * 7) If still alive, inform BIOS to do a proper reboot
  *
  * If the machine is still alive at this stage, it gives up. We default to
- * following the same pattern, except that if we're still alive after (4) we'll
+ * following the same pattern, except that if we're still alive after (7) we'll
  * try to force a triple fault and then cycle between hitting the keyboard
  * controller and doing that
  */
@@ -502,7 +505,7 @@
 				attempt = 1;
 				reboot_type = BOOT_ACPI;
 			} else {
-				reboot_type = BOOT_TRIPLE;
+				reboot_type = BOOT_EFI;
 			}
 			break;
 
@@ -510,13 +513,15 @@
 			load_idt(&no_idt);
 			__asm__ __volatile__("int3");
 
+			/* We're probably dead after this, but... */
 			reboot_type = BOOT_KBD;
 			break;
 
 		case BOOT_BIOS:
 			machine_real_restart(MRR_BIOS);
 
-			reboot_type = BOOT_KBD;
+			/* We're probably dead after this, but... */
+			reboot_type = BOOT_TRIPLE;
 			break;
 
 		case BOOT_ACPI:
@@ -530,7 +535,7 @@
 						 EFI_RESET_WARM :
 						 EFI_RESET_COLD,
 						 EFI_SUCCESS, 0, NULL);
-			reboot_type = BOOT_KBD;
+			reboot_type = BOOT_CF9_COND;
 			break;
 
 		case BOOT_CF9:
@@ -548,7 +553,7 @@
 				outb(cf9|reboot_code, 0xcf9);
 				udelay(50);
 			}
-			reboot_type = BOOT_KBD;
+			reboot_type = BOOT_BIOS;
 			break;
 		}
 	}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 06853e6..fa511ac 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -926,11 +926,11 @@
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL32", 4)) {
-		set_bit(EFI_BOOT, &x86_efi_facility);
+		set_bit(EFI_BOOT, &efi.flags);
 	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL64", 4)) {
-		set_bit(EFI_BOOT, &x86_efi_facility);
-		set_bit(EFI_64BIT, &x86_efi_facility);
+		set_bit(EFI_BOOT, &efi.flags);
+		set_bit(EFI_64BIT, &efi.flags);
 	}
 
 	if (efi_enabled(EFI_BOOT))
@@ -1239,14 +1239,8 @@
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
-	/* Once setup is done above, unmap the EFI memory map on
-	 * mismatched firmware/kernel archtectures since there is no
-	 * support for runtime services.
-	 */
-	if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
-		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
-		efi_unmap_memmap();
-	}
+	if (efi_enabled(EFI_BOOT))
+		efi_apply_memmap_quirks();
 #endif
 }
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a32da80..5aad5a3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -122,8 +122,9 @@
 	 * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI.
 	 */
 	cpuid = smp_processor_id();
-	if (apic->wait_for_init_deassert && cpuid != 0)
-		apic->wait_for_init_deassert(&init_deasserted);
+	if (apic->wait_for_init_deassert && cpuid)
+		while (!atomic_read(&init_deasserted))
+			cpu_relax();
 
 	/*
 	 * (This works even if the APIC is not enabled.)
@@ -701,11 +702,15 @@
 	int id;
 	int boot_error;
 
+	preempt_disable();
+
 	/*
 	 * Wake up AP by INIT, INIT, STARTUP sequence.
 	 */
-	if (cpu)
-		return wakeup_secondary_cpu_via_init(apicid, start_ip);
+	if (cpu) {
+		boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip);
+		goto out;
+	}
 
 	/*
 	 * Wake up BSP by nmi.
@@ -725,6 +730,9 @@
 		boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip);
 	}
 
+out:
+	preempt_enable();
+
 	return boot_error;
 }
 
@@ -1379,7 +1387,7 @@
 
 	if (!this_cpu_has(X86_FEATURE_MWAIT))
 		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLSH))
+	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
 		return;
 	if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
 		return;
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 24d3c91..6ec91c0 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -23,7 +23,7 @@
 #include <asm/time.h>
 
 #ifdef CONFIG_X86_64
-DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES;
+__visible DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES;
 #endif
 
 unsigned long profile_pc(struct pt_regs *regs)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 19e5adb..cfbe99f 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -209,7 +209,7 @@
 	 * dance when its actually needed.
 	 */
 
-	preempt_disable();
+	preempt_disable_notrace();
 	data = this_cpu_read(cyc2ns.head);
 	tail = this_cpu_read(cyc2ns.tail);
 
@@ -229,7 +229,7 @@
 		if (!--data->__count)
 			this_cpu_write(cyc2ns.tail, data);
 	}
-	preempt_enable();
+	preempt_enable_notrace();
 
 	return ns;
 }
@@ -653,13 +653,10 @@
 
 	/* Calibrate TSC using MSR for Intel Atom SoCs */
 	local_irq_save(flags);
-	i = try_msr_calibrate_tsc(&fast_calibrate);
+	fast_calibrate = try_msr_calibrate_tsc();
 	local_irq_restore(flags);
-	if (i >= 0) {
-		if (i == 0)
-			pr_warn("Fast TSC calibration using MSR failed\n");
+	if (fast_calibrate)
 		return fast_calibrate;
-	}
 
 	local_irq_save(flags);
 	fast_calibrate = quick_pit_calibrate();
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 8b5434f..92ae6ac 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -53,7 +53,7 @@
 	/* TNG */
 	{ 6, 0x4a, 1, { 0, FREQ_100, FREQ_133, 0, 0, 0, 0, 0 } },
 	/* VLV2 */
-	{ 6, 0x37, 1, { 0, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } },
+	{ 6, 0x37, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } },
 	/* ANN */
 	{ 6, 0x5a, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_100, 0, 0, 0, 0 } },
 };
@@ -77,21 +77,18 @@
 
 /*
  * Do MSR calibration only for known/supported CPUs.
- * Return values:
- * -1: CPU is unknown/unsupported for MSR based calibration
- *  0: CPU is known/supported, but calibration failed
- *  1: CPU is known/supported, and calibration succeeded
+ *
+ * Returns the calibration value or 0 if MSR calibration failed.
  */
-int try_msr_calibrate_tsc(unsigned long *fast_calibrate)
+unsigned long try_msr_calibrate_tsc(void)
 {
-	int cpu_index;
 	u32 lo, hi, ratio, freq_id, freq;
+	unsigned long res;
+	int cpu_index;
 
 	cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model);
 	if (cpu_index < 0)
-		return -1;
-
-	*fast_calibrate = 0;
+		return 0;
 
 	if (freq_desc_tables[cpu_index].msr_plat) {
 		rdmsr(MSR_PLATFORM_INFO, lo, hi);
@@ -103,7 +100,7 @@
 	pr_info("Maximum core-clock to bus-clock ratio: 0x%x\n", ratio);
 
 	if (!ratio)
-		return 0;
+		goto fail;
 
 	/* Get FSB FREQ ID */
 	rdmsr(MSR_FSB_FREQ, lo, hi);
@@ -112,16 +109,19 @@
 	pr_info("Resolved frequency ID: %u, frequency: %u KHz\n",
 				freq_id, freq);
 	if (!freq)
-		return 0;
+		goto fail;
 
 	/* TSC frequency = maximum resolved freq * maximum resolved bus ratio */
-	*fast_calibrate = freq * ratio;
-	pr_info("TSC runs at %lu KHz\n", *fast_calibrate);
+	res = freq * ratio;
+	pr_info("TSC runs at %lu KHz\n", res);
 
 #ifdef CONFIG_X86_LOCAL_APIC
 	lapic_timer_frequency = (freq * 1000) / HZ;
 	pr_info("lapic_timer_frequency = %d\n", lapic_timer_frequency);
 #endif
+	return res;
 
-	return 1;
+fail:
+	pr_warn("Fast TSC calibration using MSR failed\n");
+	return 0;
 }
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index c697625..e5503d8 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -263,7 +263,7 @@
 		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
 		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) |
 		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
-		F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) |
+		F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) |
 		0 /* Reserved, DS, ACPI */ | F(MMX) |
 		F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) |
 		0 /* HTT, TM, Reserved, PBE */;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e50425d..9b53135 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2672,6 +2672,7 @@
 			break;
 		}
 
+		drop_large_spte(vcpu, iterator.sptep);
 		if (!is_shadow_present_pte(*iterator.sptep)) {
 			u64 base_addr = iterator.addr;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e81df8f..2de1bc0 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3002,10 +3002,8 @@
 	u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
 	/* instruction emulation calls kvm_set_cr8() */
 	r = cr_interception(svm);
-	if (irqchip_in_kernel(svm->vcpu.kvm)) {
-		clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+	if (irqchip_in_kernel(svm->vcpu.kvm))
 		return r;
-	}
 	if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
 		return r;
 	kvm_run->exit_reason = KVM_EXIT_SET_TPR;
@@ -3567,6 +3565,8 @@
 	if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
 		return;
 
+	clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+
 	if (irr == -1)
 		return;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a06f101..3927528 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6688,7 +6688,7 @@
 		else if (is_page_fault(intr_info))
 			return enable_ept;
 		else if (is_no_device(intr_info) &&
-			 !(nested_read_cr0(vmcs12) & X86_CR0_TS))
+			 !(vmcs12->guest_cr0 & X86_CR0_TS))
 			return 0;
 		return vmcs12->exception_bitmap &
 				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 39c28f09..2b85784 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6186,7 +6186,7 @@
 		frag->len -= len;
 	}
 
-	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
 
 		/* FIXME: return into emulator if single-stepping.  */
diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c
index 3056702..ff4fa51 100644
--- a/arch/x86/lib/hash.c
+++ b/arch/x86/lib/hash.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/hash.h>
+#include <linux/init.h>
 
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
@@ -39,7 +40,11 @@
 
 static inline u32 crc32_u32(u32 crc, u32 val)
 {
+#ifdef CONFIG_AS_CRC32
 	asm ("crc32l %1,%0\n" : "+r" (crc) : "rm" (val));
+#else
+	asm (".byte 0xf2, 0x0f, 0x38, 0xf1, 0xc1" : "+a" (crc) : "c" (val));
+#endif
 	return crc;
 }
 
@@ -49,19 +54,18 @@
 	u32 i, tmp = 0;
 
 	for (i = 0; i < len / 4; i++)
-		seed = crc32_u32(*p32++, seed);
+		seed = crc32_u32(seed, *p32++);
 
-	switch (3 - (len & 0x03)) {
-	case 0:
+	switch (len & 3) {
+	case 3:
 		tmp |= *((const u8 *) p32 + 2) << 16;
 		/* fallthrough */
-	case 1:
+	case 2:
 		tmp |= *((const u8 *) p32 + 1) << 8;
 		/* fallthrough */
-	case 2:
+	case 1:
 		tmp |= *((const u8 *) p32);
-		seed = crc32_u32(tmp, seed);
-	default:
+		seed = crc32_u32(seed, tmp);
 		break;
 	}
 
@@ -74,12 +78,12 @@
 	u32 i;
 
 	for (i = 0; i < len; i++)
-		seed = crc32_u32(*p32++, seed);
+		seed = crc32_u32(seed, *p32++);
 
 	return seed;
 }
 
-void setup_arch_fast_hash(struct fast_hash_ops *ops)
+void __init setup_arch_fast_hash(struct fast_hash_ops *ops)
 {
 	if (cpu_has_xmm4_2) {
 		ops->hash  = intel_crc4_2_hash;
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index e78761d..a404b4b 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -4,7 +4,7 @@
 #undef memcpy
 #undef memset
 
-void *memcpy(void *to, const void *from, size_t n)
+__visible void *memcpy(void *to, const void *from, size_t n)
 {
 #ifdef CONFIG_X86_USE_3DNOW
 	return __memcpy3d(to, from, n);
@@ -14,13 +14,13 @@
 }
 EXPORT_SYMBOL(memcpy);
 
-void *memset(void *s, int c, size_t count)
+__visible void *memset(void *s, int c, size_t count)
 {
 	return __memset(s, c, count);
 }
 EXPORT_SYMBOL(memset);
 
-void *memmove(void *dest, const void *src, size_t n)
+__visible void *memmove(void *dest, const void *src, size_t n)
 {
 	int d0,d1,d2,d3,d4,d5;
 	char *ret = dest;
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 8f8eebd..db9db44 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -8,7 +8,7 @@
 
 	msrs = alloc_percpu(struct msr);
 	if (!msrs) {
-		pr_warning("%s: error allocating msrs\n", __func__);
+		pr_warn("%s: error allocating msrs\n", __func__);
 		return NULL;
 	}
 
@@ -21,3 +21,90 @@
 	free_percpu(msrs);
 }
 EXPORT_SYMBOL(msrs_free);
+
+/**
+ * Read an MSR with error handling
+ *
+ * @msr: MSR to read
+ * @m: value to read into
+ *
+ * It returns read data only on success, otherwise it doesn't change the output
+ * argument @m.
+ *
+ */
+int msr_read(u32 msr, struct msr *m)
+{
+	int err;
+	u64 val;
+
+	err = rdmsrl_safe(msr, &val);
+	if (!err)
+		m->q = val;
+
+	return err;
+}
+
+/**
+ * Write an MSR with error handling
+ *
+ * @msr: MSR to write
+ * @m: value to write
+ */
+int msr_write(u32 msr, struct msr *m)
+{
+	return wrmsrl_safe(msr, m->q);
+}
+
+static inline int __flip_bit(u32 msr, u8 bit, bool set)
+{
+	struct msr m, m1;
+	int err = -EINVAL;
+
+	if (bit > 63)
+		return err;
+
+	err = msr_read(msr, &m);
+	if (err)
+		return err;
+
+	m1 = m;
+	if (set)
+		m1.q |=  BIT_64(bit);
+	else
+		m1.q &= ~BIT_64(bit);
+
+	if (m1.q == m.q)
+		return 0;
+
+	err = msr_write(msr, &m);
+	if (err)
+		return err;
+
+	return 1;
+}
+
+/**
+ * Set @bit in a MSR @msr.
+ *
+ * Retval:
+ * < 0: An error was encountered.
+ * = 0: Bit was already set.
+ * > 0: Hardware accepted the MSR write.
+ */
+int msr_set_bit(u32 msr, u8 bit)
+{
+	return __flip_bit(msr, bit, true);
+}
+
+/**
+ * Clear @bit in a MSR @msr.
+ *
+ * Retval:
+ * < 0: An error was encountered.
+ * = 0: Bit was already cleared.
+ * > 0: Hardware accepted the MSR write.
+ */
+int msr_clear_bit(u32 msr, u8 bit)
+{
+	return __flip_bit(msr, bit, false);
+}
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0002a3a..20621d7 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -30,6 +30,7 @@
 	unsigned long start_address;
 	unsigned long current_address;
 	const struct addr_marker *marker;
+	bool to_dmesg;
 };
 
 struct addr_marker {
@@ -88,10 +89,28 @@
 #define PUD_LEVEL_MULT (PTRS_PER_PMD * PMD_LEVEL_MULT)
 #define PGD_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT)
 
+#define pt_dump_seq_printf(m, to_dmesg, fmt, args...)		\
+({								\
+	if (to_dmesg)					\
+		printk(KERN_INFO fmt, ##args);			\
+	else							\
+		if (m)						\
+			seq_printf(m, fmt, ##args);		\
+})
+
+#define pt_dump_cont_printf(m, to_dmesg, fmt, args...)		\
+({								\
+	if (to_dmesg)					\
+		printk(KERN_CONT fmt, ##args);			\
+	else							\
+		if (m)						\
+			seq_printf(m, fmt, ##args);		\
+})
+
 /*
  * Print a readable form of a pgprot_t to the seq_file
  */
-static void printk_prot(struct seq_file *m, pgprot_t prot, int level)
+static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
 {
 	pgprotval_t pr = pgprot_val(prot);
 	static const char * const level_name[] =
@@ -99,47 +118,47 @@
 
 	if (!pgprot_val(prot)) {
 		/* Not present */
-		seq_printf(m, "                          ");
+		pt_dump_cont_printf(m, dmsg, "                          ");
 	} else {
 		if (pr & _PAGE_USER)
-			seq_printf(m, "USR ");
+			pt_dump_cont_printf(m, dmsg, "USR ");
 		else
-			seq_printf(m, "    ");
+			pt_dump_cont_printf(m, dmsg, "    ");
 		if (pr & _PAGE_RW)
-			seq_printf(m, "RW ");
+			pt_dump_cont_printf(m, dmsg, "RW ");
 		else
-			seq_printf(m, "ro ");
+			pt_dump_cont_printf(m, dmsg, "ro ");
 		if (pr & _PAGE_PWT)
-			seq_printf(m, "PWT ");
+			pt_dump_cont_printf(m, dmsg, "PWT ");
 		else
-			seq_printf(m, "    ");
+			pt_dump_cont_printf(m, dmsg, "    ");
 		if (pr & _PAGE_PCD)
-			seq_printf(m, "PCD ");
+			pt_dump_cont_printf(m, dmsg, "PCD ");
 		else
-			seq_printf(m, "    ");
+			pt_dump_cont_printf(m, dmsg, "    ");
 
 		/* Bit 9 has a different meaning on level 3 vs 4 */
 		if (level <= 3) {
 			if (pr & _PAGE_PSE)
-				seq_printf(m, "PSE ");
+				pt_dump_cont_printf(m, dmsg, "PSE ");
 			else
-				seq_printf(m, "    ");
+				pt_dump_cont_printf(m, dmsg, "    ");
 		} else {
 			if (pr & _PAGE_PAT)
-				seq_printf(m, "pat ");
+				pt_dump_cont_printf(m, dmsg, "pat ");
 			else
-				seq_printf(m, "    ");
+				pt_dump_cont_printf(m, dmsg, "    ");
 		}
 		if (pr & _PAGE_GLOBAL)
-			seq_printf(m, "GLB ");
+			pt_dump_cont_printf(m, dmsg, "GLB ");
 		else
-			seq_printf(m, "    ");
+			pt_dump_cont_printf(m, dmsg, "    ");
 		if (pr & _PAGE_NX)
-			seq_printf(m, "NX ");
+			pt_dump_cont_printf(m, dmsg, "NX ");
 		else
-			seq_printf(m, "x  ");
+			pt_dump_cont_printf(m, dmsg, "x  ");
 	}
-	seq_printf(m, "%s\n", level_name[level]);
+	pt_dump_cont_printf(m, dmsg, "%s\n", level_name[level]);
 }
 
 /*
@@ -178,7 +197,8 @@
 		st->current_prot = new_prot;
 		st->level = level;
 		st->marker = address_markers;
-		seq_printf(m, "---[ %s ]---\n", st->marker->name);
+		pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
+				   st->marker->name);
 	} else if (prot != cur || level != st->level ||
 		   st->current_address >= st->marker[1].start_address) {
 		const char *unit = units;
@@ -188,17 +208,17 @@
 		/*
 		 * Now print the actual finished series
 		 */
-		seq_printf(m, "0x%0*lx-0x%0*lx   ",
-			   width, st->start_address,
-			   width, st->current_address);
+		pt_dump_seq_printf(m, st->to_dmesg,  "0x%0*lx-0x%0*lx   ",
+				   width, st->start_address,
+				   width, st->current_address);
 
 		delta = (st->current_address - st->start_address) >> 10;
 		while (!(delta & 1023) && unit[1]) {
 			delta >>= 10;
 			unit++;
 		}
-		seq_printf(m, "%9lu%c ", delta, *unit);
-		printk_prot(m, st->current_prot, st->level);
+		pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ", delta, *unit);
+		printk_prot(m, st->current_prot, st->level, st->to_dmesg);
 
 		/*
 		 * We print markers for special areas of address space,
@@ -207,7 +227,8 @@
 		 */
 		if (st->current_address >= st->marker[1].start_address) {
 			st->marker++;
-			seq_printf(m, "---[ %s ]---\n", st->marker->name);
+			pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
+					   st->marker->name);
 		}
 
 		st->start_address = st->current_address;
@@ -296,7 +317,7 @@
 #define pgd_none(a)  pud_none(__pud(pgd_val(a)))
 #endif
 
-static void walk_pgd_level(struct seq_file *m)
+void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
 {
 #ifdef CONFIG_X86_64
 	pgd_t *start = (pgd_t *) &init_level4_pgt;
@@ -304,9 +325,12 @@
 	pgd_t *start = swapper_pg_dir;
 #endif
 	int i;
-	struct pg_state st;
+	struct pg_state st = {};
 
-	memset(&st, 0, sizeof(st));
+	if (pgd) {
+		start = pgd;
+		st.to_dmesg = true;
+	}
 
 	for (i = 0; i < PTRS_PER_PGD; i++) {
 		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
@@ -331,7 +355,7 @@
 
 static int ptdump_show(struct seq_file *m, void *v)
 {
-	walk_pgd_level(m);
+	ptdump_walk_pgd_level(m, NULL);
 	return 0;
 }
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9d591c8..8e57229 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -584,8 +584,13 @@
 
 	if (error_code & PF_INSTR) {
 		unsigned int level;
+		pgd_t *pgd;
+		pte_t *pte;
 
-		pte_t *pte = lookup_address(address, &level);
+		pgd = __va(read_cr3() & PHYSICAL_PAGE_MASK);
+		pgd += pgd_index(address);
+
+		pte = lookup_address_in_pgd(pgd, address, &level);
 
 		if (pte && pte_present(*pte) && !pte_exec(*pte))
 			printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
@@ -1001,6 +1006,12 @@
 
 static inline bool smap_violation(int error_code, struct pt_regs *regs)
 {
+	if (!IS_ENABLED(CONFIG_X86_SMAP))
+		return false;
+
+	if (!static_cpu_has(X86_FEATURE_SMAP))
+		return false;
+
 	if (error_code & PF_USER)
 		return false;
 
@@ -1014,13 +1025,17 @@
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
  * routines.
+ *
+ * This function must have noinline because both callers
+ * {,trace_}do_page_fault() have notrace on. Having this an actual function
+ * guarantees there's a function trace entry.
  */
-static void __kprobes
-__do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes noinline
+__do_page_fault(struct pt_regs *regs, unsigned long error_code,
+		unsigned long address)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
-	unsigned long address;
 	struct mm_struct *mm;
 	int fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -1028,9 +1043,6 @@
 	tsk = current;
 	mm = tsk->mm;
 
-	/* Get the faulting address: */
-	address = read_cr2();
-
 	/*
 	 * Detect and handle instructions that would cause a page fault for
 	 * both a tracked kernel page and a userspace page.
@@ -1087,11 +1099,9 @@
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
 
-	if (static_cpu_has(X86_FEATURE_SMAP)) {
-		if (unlikely(smap_violation(error_code, regs))) {
-			bad_area_nosemaphore(regs, error_code, address);
-			return;
-		}
+	if (unlikely(smap_violation(error_code, regs))) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
 	}
 
 	/*
@@ -1244,32 +1254,50 @@
 	up_read(&mm->mmap_sem);
 }
 
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
 do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+	unsigned long address = read_cr2(); /* Get the faulting address */
 	enum ctx_state prev_state;
 
+	/*
+	 * We must have this function tagged with __kprobes, notrace and call
+	 * read_cr2() before calling anything else. To avoid calling any kind
+	 * of tracing machinery before we've observed the CR2 value.
+	 *
+	 * exception_{enter,exit}() contain all sorts of tracepoints.
+	 */
+
 	prev_state = exception_enter();
-	__do_page_fault(regs, error_code);
+	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
 
-static void trace_page_fault_entries(struct pt_regs *regs,
+#ifdef CONFIG_TRACING
+static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
 				     unsigned long error_code)
 {
 	if (user_mode(regs))
-		trace_page_fault_user(read_cr2(), regs, error_code);
+		trace_page_fault_user(address, regs, error_code);
 	else
-		trace_page_fault_kernel(read_cr2(), regs, error_code);
+		trace_page_fault_kernel(address, regs, error_code);
 }
 
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
 trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+	/*
+	 * The exception_enter and tracepoint processing could
+	 * trigger another page faults (user space callchain
+	 * reading) and destroy the original cr2 value, so read
+	 * the faulting address now.
+	 */
+	unsigned long address = read_cr2();
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
-	trace_page_fault_entries(regs, error_code);
-	__do_page_fault(regs, error_code);
+	trace_page_fault_entries(address, regs, error_code);
+	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
+#endif /* CONFIG_TRACING */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 81b2750..27aa0455 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -493,14 +493,6 @@
 		struct numa_memblk *mb = &mi->blk[i];
 		memblock_set_node(mb->start, mb->end - mb->start,
 				  &memblock.memory, mb->nid);
-
-		/*
-		 * At this time, all memory regions reserved by memblock are
-		 * used by the kernel. Set the nid in memblock.reserved will
-		 * mark out all the nodes the kernel resides in.
-		 */
-		memblock_set_node(mb->start, mb->end - mb->start,
-				  &memblock.reserved, mb->nid);
 	}
 
 	/*
@@ -565,10 +557,21 @@
 static void __init numa_clear_kernel_node_hotplug(void)
 {
 	int i, nid;
-	nodemask_t numa_kernel_nodes;
+	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
 	unsigned long start, end;
 	struct memblock_type *type = &memblock.reserved;
 
+	/*
+	 * At this time, all memory regions reserved by memblock are
+	 * used by the kernel. Set the nid in memblock.reserved will
+	 * mark out all the nodes the kernel resides in.
+	 */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		struct numa_memblk *mb = &numa_meminfo.blk[i];
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.reserved, mb->nid);
+	}
+
 	/* Mark all kernel nodes. */
 	for (i = 0; i < type->cnt; i++)
 		node_set(type->regions[i].nid, numa_kernel_nodes);
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 0342d27..47b6436 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -52,6 +52,8 @@
 			nid, start, end);
 	printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
 	printk(KERN_DEBUG "  ");
+	start = round_down(start, PAGES_PER_SECTION);
+	end = round_up(end, PAGES_PER_SECTION);
 	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
 		physnode_map[pfn / PAGES_PER_SECTION] = nid;
 		printk(KERN_CONT "%lx ", pfn);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index b3b19f4..ae242a7 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -126,8 +126,8 @@
  * @vaddr:	virtual start address
  * @size:	number of bytes to flush
  *
- * clflush is an unordered instruction which needs fencing with mfence
- * to avoid ordering issues.
+ * clflushopt is an unordered instruction which needs fencing with mfence or
+ * sfence to avoid ordering issues.
  */
 void clflush_cache_range(void *vaddr, unsigned int size)
 {
@@ -136,11 +136,11 @@
 	mb();
 
 	for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size)
-		clflush(vaddr);
+		clflushopt(vaddr);
 	/*
 	 * Flush any possible final partial cacheline:
 	 */
-	clflush(vend);
+	clflushopt(vend);
 
 	mb();
 }
@@ -323,8 +323,12 @@
 	return prot;
 }
 
-static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
-				      unsigned int *level)
+/*
+ * Lookup the page table entry for a virtual address in a specific pgd.
+ * Return a pointer to the entry and the level of the mapping.
+ */
+pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+			     unsigned int *level)
 {
 	pud_t *pud;
 	pmd_t *pmd;
@@ -365,7 +369,7 @@
  */
 pte_t *lookup_address(unsigned long address, unsigned int *level)
 {
-        return __lookup_address_in_pgd(pgd_offset_k(address), address, level);
+        return lookup_address_in_pgd(pgd_offset_k(address), address, level);
 }
 EXPORT_SYMBOL_GPL(lookup_address);
 
@@ -373,7 +377,7 @@
 				  unsigned int *level)
 {
         if (cpa->pgd)
-		return __lookup_address_in_pgd(cpa->pgd + pgd_index(address),
+		return lookup_address_in_pgd(cpa->pgd + pgd_index(address),
 					       address, level);
 
         return lookup_address(address, level);
@@ -692,6 +696,18 @@
 	return true;
 }
 
+static bool try_to_free_pud_page(pud_t *pud)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		if (!pud_none(pud[i]))
+			return false;
+
+	free_page((unsigned long)pud);
+	return true;
+}
+
 static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
 {
 	pte_t *pte = pte_offset_kernel(pmd, start);
@@ -805,6 +821,16 @@
 	 */
 }
 
+static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
+{
+	pgd_t *pgd_entry = root + pgd_index(addr);
+
+	unmap_pud_range(pgd_entry, addr, end);
+
+	if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry)))
+		pgd_clear(pgd_entry);
+}
+
 static int alloc_pte_page(pmd_t *pmd)
 {
 	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
@@ -999,9 +1025,8 @@
 static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 {
 	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
-	bool allocd_pgd = false;
-	pgd_t *pgd_entry;
 	pud_t *pud = NULL;	/* shut up gcc */
+	pgd_t *pgd_entry;
 	int ret;
 
 	pgd_entry = cpa->pgd + pgd_index(addr);
@@ -1015,7 +1040,6 @@
 			return -1;
 
 		set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
-		allocd_pgd = true;
 	}
 
 	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
@@ -1023,19 +1047,11 @@
 
 	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
 	if (ret < 0) {
-		unmap_pud_range(pgd_entry, addr,
+		unmap_pgd_range(cpa->pgd, addr,
 				addr + (cpa->numpages << PAGE_SHIFT));
-
-		if (allocd_pgd) {
-			/*
-			 * If I allocated this PUD page, I can just as well
-			 * free it in this error path.
-			 */
-			pgd_clear(pgd_entry);
-			free_page((unsigned long)pud);
-		}
 		return ret;
 	}
+
 	cpa->numpages = ret;
 	return 0;
 }
@@ -1377,10 +1393,10 @@
 	cache = cache_attr(mask_set);
 
 	/*
-	 * On success we use clflush, when the CPU supports it to
-	 * avoid the wbindv. If the CPU does not support it and in the
+	 * On success we use CLFLUSH, when the CPU supports it to
+	 * avoid the WBINVD. If the CPU does not support it and in the
 	 * error case we fall back to cpa_flush_all (which uses
-	 * wbindv):
+	 * WBINVD):
 	 */
 	if (!ret && cpu_has_clflush) {
 		if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
@@ -1861,6 +1877,12 @@
 	return retval;
 }
 
+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
+			       unsigned numpages)
+{
+	unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT));
+}
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 1a25187..66338a6 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -42,15 +42,31 @@
 	return acpi_numa < 0;
 }
 
-/* Callback for SLIT parsing */
+/*
+ * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
+ * I/O localities since SRAT does not list them.  I/O localities are
+ * not supported at this point.
+ */
 void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 {
 	int i, j;
 
-	for (i = 0; i < slit->locality_count; i++)
-		for (j = 0; j < slit->locality_count; j++)
-			numa_set_distance(pxm_to_node(i), pxm_to_node(j),
+	for (i = 0; i < slit->locality_count; i++) {
+		const int from_node = pxm_to_node(i);
+
+		if (from_node == NUMA_NO_NODE)
+			continue;
+
+		for (j = 0; j < slit->locality_count; j++) {
+			const int to_node = pxm_to_node(j);
+
+			if (to_node == NUMA_NO_NODE)
+				continue;
+
+			numa_set_distance(from_node, to_node,
 				slit->entry[slit->locality_count * i + j]);
+		}
+	}
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index ae699b3..dd8dda1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,7 +103,7 @@
 	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
 		if (f->flush_end == TLB_FLUSH_ALL)
 			local_flush_tlb();
@@ -131,7 +131,7 @@
 	info.flush_start = start;
 	info.flush_end = end;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (is_uv_system()) {
 		unsigned int cpu;
 
@@ -151,44 +151,19 @@
 
 	preempt_disable();
 
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	local_flush_tlb();
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
-/*
- * It can find out the THP large page, or
- * HUGETLB page in tlb_flush when THP disabled
- */
-static inline unsigned long has_large_page(struct mm_struct *mm,
-				 unsigned long start, unsigned long end)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	unsigned long addr = ALIGN(start, HPAGE_SIZE);
-	for (; addr < end; addr += HPAGE_SIZE) {
-		pgd = pgd_offset(mm, addr);
-		if (likely(!pgd_none(*pgd))) {
-			pud = pud_offset(pgd, addr);
-			if (likely(!pud_none(*pud))) {
-				pmd = pmd_offset(pud, addr);
-				if (likely(!pmd_none(*pmd)))
-					if (pmd_large(*pmd))
-						return addr;
-			}
-		}
-	}
-	return 0;
-}
-
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag)
 {
 	unsigned long addr;
 	unsigned act_entries, tlb_entries = 0;
+	unsigned long nr_base_pages;
 
 	preempt_disable();
 	if (current->active_mm != mm)
@@ -210,21 +185,20 @@
 		tlb_entries = tlb_lli_4k[ENTRIES];
 	else
 		tlb_entries = tlb_lld_4k[ENTRIES];
+
 	/* Assume all of TLB entries was occupied by this task */
-	act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
+	act_entries = tlb_entries >> tlb_flushall_shift;
+	act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm;
+	nr_base_pages = (end - start) >> PAGE_SHIFT;
 
 	/* tlb_flushall_shift is on balance point, details in commit log */
-	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
-		count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	if (nr_base_pages > act_entries) {
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
-		if (has_large_page(mm, start, end)) {
-			local_flush_tlb();
-			goto flush_all;
-		}
 		/* flush range by one by one 'invlpg' */
 		for (addr = start; addr < end;	addr += PAGE_SIZE) {
-			count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 			__flush_tlb_single(addr);
 		}
 
@@ -262,7 +236,7 @@
 
 static void do_flush_tlb_all(void *info)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	__flush_tlb_all();
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
 		leave_mm(smp_processor_id());
@@ -270,7 +244,7 @@
 
 void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 877b9a1..0149575 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -140,7 +140,7 @@
 	push	%r9;						\
 	push	SKBDATA;					\
 /* rsi already has offset */					\
-	mov	$SIZE,%ecx;	/* size */			\
+	mov	$SIZE,%edx;	/* size */			\
 	call	bpf_internal_load_pointer_neg_helper;		\
 	test	%rax,%rax;					\
 	pop	SKBDATA;					\
diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile
index b7b0b35..d51045a 100644
--- a/arch/x86/platform/efi/Makefile
+++ b/arch/x86/platform/efi/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_EFI) 		+= efi.o efi_$(BITS).o efi_stub_$(BITS).o
 obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
 obj-$(CONFIG_EARLY_PRINTK_EFI)	+= early_printk.o
+obj-$(CONFIG_EFI_MIXED)		+= efi_thunk_$(BITS).o
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index 7145ec6..f15103d 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -42,14 +42,15 @@
 
 	if (bgrt_tab->header.length < sizeof(*bgrt_tab))
 		return;
-	if (bgrt_tab->version != 1)
+	if (bgrt_tab->version != 1 || bgrt_tab->status != 1)
 		return;
 	if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address)
 		return;
 
 	image = efi_lookup_mapped_addr(bgrt_tab->image_address);
 	if (!image) {
-		image = ioremap(bgrt_tab->image_address, sizeof(bmp_header));
+		image = early_memremap(bgrt_tab->image_address,
+				       sizeof(bmp_header));
 		ioremapped = true;
 		if (!image)
 			return;
@@ -57,7 +58,7 @@
 
 	memcpy_fromio(&bmp_header, image, sizeof(bmp_header));
 	if (ioremapped)
-		iounmap(image);
+		early_iounmap(image, sizeof(bmp_header));
 	bgrt_image_size = bmp_header.size;
 
 	bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL);
@@ -65,7 +66,8 @@
 		return;
 
 	if (ioremapped) {
-		image = ioremap(bgrt_tab->image_address, bmp_header.size);
+		image = early_memremap(bgrt_tab->image_address,
+				       bmp_header.size);
 		if (!image) {
 			kfree(bgrt_image);
 			bgrt_image = NULL;
@@ -75,5 +77,5 @@
 
 	memcpy_fromio(bgrt_image, image, bgrt_image_size);
 	if (ioremapped)
-		iounmap(image);
+		early_iounmap(image, bmp_header.size);
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index d62ec87..3781dd3 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -52,6 +52,7 @@
 #include <asm/tlbflush.h>
 #include <asm/x86_init.h>
 #include <asm/rtc.h>
+#include <asm/uv/uv.h>
 
 #define EFI_DEBUG
 
@@ -67,9 +68,7 @@
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
-unsigned long x86_efi_facility;
-
-static __initdata efi_config_table_type_t arch_tables[] = {
+static efi_config_table_type_t arch_tables[] __initdata = {
 #ifdef CONFIG_X86_UV
 	{UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab},
 #endif
@@ -78,16 +77,7 @@
 
 u64 efi_setup;		/* efi setup_data physical address */
 
-/*
- * Returns 1 if 'facility' is enabled, 0 otherwise.
- */
-int efi_enabled(int facility)
-{
-	return test_bit(facility, &x86_efi_facility) != 0;
-}
-EXPORT_SYMBOL(efi_enabled);
-
-static bool __initdata disable_runtime = false;
+static bool disable_runtime __initdata = false;
 static int __init setup_noefi(char *arg)
 {
 	disable_runtime = true;
@@ -256,27 +246,12 @@
 	return status;
 }
 
-static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
-					     efi_time_cap_t *tc)
-{
-	unsigned long flags;
-	efi_status_t status;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	efi_call_phys_prelog();
-	status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm),
-				virt_to_phys(tc));
-	efi_call_phys_epilog();
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return status;
-}
-
 int efi_set_rtc_mmss(const struct timespec *now)
 {
 	unsigned long nowtime = now->tv_sec;
-	efi_status_t 	status;
-	efi_time_t 	eft;
-	efi_time_cap_t 	cap;
+	efi_status_t	status;
+	efi_time_t	eft;
+	efi_time_cap_t	cap;
 	struct rtc_time	tm;
 
 	status = efi.get_time(&eft, &cap);
@@ -294,9 +269,8 @@
 		eft.second = tm.tm_sec;
 		eft.nanosecond = 0;
 	} else {
-		printk(KERN_ERR
-		       "%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n",
-		       __FUNCTION__, nowtime);
+		pr_err("%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n",
+		       __func__, nowtime);
 		return -1;
 	}
 
@@ -412,8 +386,7 @@
 	     p < memmap.map_end;
 	     p += memmap.desc_size, i++) {
 		md = p;
-		pr_info("mem%02u: type=%u, attr=0x%llx, "
-			"range=[0x%016llx-0x%016llx) (%lluMB)\n",
+		pr_info("mem%02u: type=%u, attr=0x%llx, range=[0x%016llx-0x%016llx) (%lluMB)\n",
 			i, md->type, md->attribute, md->phys_addr,
 			md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT),
 			(md->num_pages >> (20 - EFI_PAGE_SHIFT)));
@@ -445,9 +418,8 @@
 			memblock_is_region_reserved(start, size)) {
 			/* Could not reserve, skip it */
 			md->num_pages = 0;
-			memblock_dbg("Could not reserve boot range "
-					"[0x%010llx-0x%010llx]\n",
-						start, start+size-1);
+			memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n",
+				     start, start+size-1);
 		} else
 			memblock_reserve(start, size);
 	}
@@ -455,7 +427,7 @@
 
 void __init efi_unmap_memmap(void)
 {
-	clear_bit(EFI_MEMMAP, &x86_efi_facility);
+	clear_bit(EFI_MEMMAP, &efi.flags);
 	if (memmap.map) {
 		early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
 		memmap.map = NULL;
@@ -466,9 +438,6 @@
 {
 	void *p;
 
-	if (!efi_is_native())
-		return;
-
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		efi_memory_desc_t *md = p;
 		unsigned long long start = md->phys_addr;
@@ -583,17 +552,66 @@
 		return -EINVAL;
 	}
 	if ((efi.systab->hdr.revision >> 16) == 0)
-		pr_err("Warning: System table version "
-		       "%d.%02d, expected 1.00 or greater!\n",
+		pr_err("Warning: System table version %d.%02d, expected 1.00 or greater!\n",
 		       efi.systab->hdr.revision >> 16,
 		       efi.systab->hdr.revision & 0xffff);
 
+	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
+	return 0;
+}
+
+static int __init efi_runtime_init32(void)
+{
+	efi_runtime_services_32_t *runtime;
+
+	runtime = early_ioremap((unsigned long)efi.systab->runtime,
+			sizeof(efi_runtime_services_32_t));
+	if (!runtime) {
+		pr_err("Could not map the runtime service table!\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * We will only need *early* access to the following two
+	 * EFI runtime services before set_virtual_address_map
+	 * is invoked.
+	 */
+	efi_phys.set_virtual_address_map =
+			(efi_set_virtual_address_map_t *)
+			(unsigned long)runtime->set_virtual_address_map;
+	early_iounmap(runtime, sizeof(efi_runtime_services_32_t));
+
+	return 0;
+}
+
+static int __init efi_runtime_init64(void)
+{
+	efi_runtime_services_64_t *runtime;
+
+	runtime = early_ioremap((unsigned long)efi.systab->runtime,
+			sizeof(efi_runtime_services_64_t));
+	if (!runtime) {
+		pr_err("Could not map the runtime service table!\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * We will only need *early* access to the following two
+	 * EFI runtime services before set_virtual_address_map
+	 * is invoked.
+	 */
+	efi_phys.set_virtual_address_map =
+			(efi_set_virtual_address_map_t *)
+			(unsigned long)runtime->set_virtual_address_map;
+	early_iounmap(runtime, sizeof(efi_runtime_services_64_t));
+
 	return 0;
 }
 
 static int __init efi_runtime_init(void)
 {
-	efi_runtime_services_t *runtime;
+	int rv;
 
 	/*
 	 * Check out the runtime services table. We need to map
@@ -601,27 +619,15 @@
 	 * address of several of the EFI runtime functions, needed to
 	 * set the firmware into virtual mode.
 	 */
-	runtime = early_ioremap((unsigned long)efi.systab->runtime,
-				sizeof(efi_runtime_services_t));
-	if (!runtime) {
-		pr_err("Could not map the runtime service table!\n");
-		return -ENOMEM;
-	}
-	/*
-	 * We will only need *early* access to the following
-	 * two EFI runtime services before set_virtual_address_map
-	 * is invoked.
-	 */
-	efi_phys.get_time = (efi_get_time_t *)runtime->get_time;
-	efi_phys.set_virtual_address_map =
-		(efi_set_virtual_address_map_t *)
-		runtime->set_virtual_address_map;
-	/*
-	 * Make efi_get_time can be called before entering
-	 * virtual mode.
-	 */
-	efi.get_time = phys_efi_get_time;
-	early_iounmap(runtime, sizeof(efi_runtime_services_t));
+	if (efi_enabled(EFI_64BIT))
+		rv = efi_runtime_init64();
+	else
+		rv = efi_runtime_init32();
+
+	if (rv)
+		return rv;
+
+	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 
 	return 0;
 }
@@ -640,6 +646,8 @@
 	if (add_efi_memmap)
 		do_add_efi_memmap();
 
+	set_bit(EFI_MEMMAP, &efi.flags);
+
 	return 0;
 }
 
@@ -722,7 +730,7 @@
 	if (efi_systab_init(efi_phys.systab))
 		return;
 
-	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
+	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
 
 	efi.config_table = (unsigned long)efi.systab->tables;
 	efi.fw_vendor	 = (unsigned long)efi.systab->fw_vendor;
@@ -750,24 +758,21 @@
 	if (efi_config_init(arch_tables))
 		return;
 
-	set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
-
 	/*
 	 * Note: We currently don't support runtime services on an EFI
 	 * that doesn't match the kernel 32/64-bit mode.
 	 */
 
-	if (!efi_is_native())
+	if (!efi_runtime_supported())
 		pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
 	else {
 		if (disable_runtime || efi_runtime_init())
 			return;
-		set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
 	}
 	if (efi_memmap_init())
 		return;
 
-	set_bit(EFI_MEMMAP, &x86_efi_facility);
+	set_bit(EFI_MEMMAP, &efi.flags);
 
 	print_efi_memmap();
 }
@@ -792,7 +797,7 @@
 		set_memory_nx(addr, npages);
 }
 
-static void __init runtime_code_page_mkexec(void)
+void __init runtime_code_page_mkexec(void)
 {
 	efi_memory_desc_t *md;
 	void *p;
@@ -844,6 +849,22 @@
 		       (unsigned long long)md->phys_addr);
 }
 
+static void native_runtime_setup(void)
+{
+	efi.get_time = virt_efi_get_time;
+	efi.set_time = virt_efi_set_time;
+	efi.get_wakeup_time = virt_efi_get_wakeup_time;
+	efi.set_wakeup_time = virt_efi_set_wakeup_time;
+	efi.get_variable = virt_efi_get_variable;
+	efi.get_next_variable = virt_efi_get_next_variable;
+	efi.set_variable = virt_efi_set_variable;
+	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
+	efi.reset_system = virt_efi_reset_system;
+	efi.query_variable_info = virt_efi_query_variable_info;
+	efi.update_capsule = virt_efi_update_capsule;
+	efi.query_capsule_caps = virt_efi_query_capsule_caps;
+}
+
 /* Merge contiguous regions of the same type and attribute */
 static void __init efi_merge_regions(void)
 {
@@ -891,8 +912,9 @@
 	}
 }
 
-static int __init save_runtime_map(void)
+static void __init save_runtime_map(void)
 {
+#ifdef CONFIG_KEXEC
 	efi_memory_desc_t *md;
 	void *tmp, *p, *q = NULL;
 	int count = 0;
@@ -914,41 +936,47 @@
 	}
 
 	efi_runtime_map_setup(q, count, memmap.desc_size);
+	return;
 
-	return 0;
 out:
 	kfree(q);
-	return -ENOMEM;
+	pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+#endif
+}
+
+static void *realloc_pages(void *old_memmap, int old_shift)
+{
+	void *ret;
+
+	ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1);
+	if (!ret)
+		goto out;
+
+	/*
+	 * A first-time allocation doesn't have anything to copy.
+	 */
+	if (!old_memmap)
+		return ret;
+
+	memcpy(ret, old_memmap, PAGE_SIZE << old_shift);
+
+out:
+	free_pages((unsigned long)old_memmap, old_shift);
+	return ret;
 }
 
 /*
- * Map efi regions which were passed via setup_data. The virt_addr is a fixed
- * addr which was used in first kernel of a kexec boot.
+ * Map the efi memory ranges of the runtime services and update new_mmap with
+ * virtual addresses.
  */
-static void __init efi_map_regions_fixed(void)
+static void * __init efi_map_regions(int *count, int *pg_shift)
 {
-	void *p;
+	void *p, *new_memmap = NULL;
+	unsigned long left = 0;
 	efi_memory_desc_t *md;
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
-		efi_map_region_fixed(md); /* FIXME: add error handling */
-		get_systab_virt_addr(md);
-	}
-
-}
-
-/*
- * Map efi memory ranges for runtime serivce and update new_memmap with virtual
- * addresses.
- */
-static void * __init efi_map_regions(int *count)
-{
-	efi_memory_desc_t *md;
-	void *p, *tmp, *new_memmap = NULL;
-
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		md = p;
 		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
 #ifdef CONFIG_X86_64
 			if (md->type != EFI_BOOT_SERVICES_CODE &&
@@ -960,20 +988,80 @@
 		efi_map_region(md);
 		get_systab_virt_addr(md);
 
-		tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size,
-			       GFP_KERNEL);
-		if (!tmp)
-			goto out;
-		new_memmap = tmp;
+		if (left < memmap.desc_size) {
+			new_memmap = realloc_pages(new_memmap, *pg_shift);
+			if (!new_memmap)
+				return NULL;
+
+			left += PAGE_SIZE << *pg_shift;
+			(*pg_shift)++;
+		}
+
 		memcpy(new_memmap + (*count * memmap.desc_size), md,
 		       memmap.desc_size);
+
+		left -= memmap.desc_size;
 		(*count)++;
 	}
 
 	return new_memmap;
-out:
-	kfree(new_memmap);
-	return NULL;
+}
+
+static void __init kexec_enter_virtual_mode(void)
+{
+#ifdef CONFIG_KEXEC
+	efi_memory_desc_t *md;
+	void *p;
+
+	efi.systab = NULL;
+
+	/*
+	 * We don't do virtual mode, since we don't do runtime services, on
+	 * non-native EFI
+	 */
+	if (!efi_is_native()) {
+		efi_unmap_memmap();
+		return;
+	}
+
+	/*
+	* Map efi regions which were passed via setup_data. The virt_addr is a
+	* fixed addr which was used in first kernel of a kexec boot.
+	*/
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		efi_map_region_fixed(md); /* FIXME: add error handling */
+		get_systab_virt_addr(md);
+	}
+
+	save_runtime_map();
+
+	BUG_ON(!efi.systab);
+
+	efi_sync_low_kernel_mappings();
+
+	/*
+	 * Now that EFI is in virtual mode, update the function
+	 * pointers in the runtime service table to the new virtual addresses.
+	 *
+	 * Call EFI services through wrapper functions.
+	 */
+	efi.runtime_version = efi_systab.hdr.revision;
+
+	native_runtime_setup();
+
+	efi.set_virtual_address_map = NULL;
+
+	if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
+		runtime_code_page_mkexec();
+
+	/* clean DUMMY object */
+	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+			 EFI_VARIABLE_NON_VOLATILE |
+			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
+			 EFI_VARIABLE_RUNTIME_ACCESS,
+			 0, NULL);
+#endif
 }
 
 /*
@@ -995,57 +1083,53 @@
  *
  * Specially for kexec boot, efi runtime maps in previous kernel should
  * be passed in via setup_data. In that case runtime ranges will be mapped
- * to the same virtual addresses as the first kernel.
+ * to the same virtual addresses as the first kernel, see
+ * kexec_enter_virtual_mode().
  */
-void __init efi_enter_virtual_mode(void)
+static void __init __efi_enter_virtual_mode(void)
 {
-	efi_status_t status;
+	int count = 0, pg_shift = 0;
 	void *new_memmap = NULL;
-	int err, count = 0;
+	efi_status_t status;
 
 	efi.systab = NULL;
 
-	/*
-	 * We don't do virtual mode, since we don't do runtime services, on
-	 * non-native EFI
-	 */
-	if (!efi_is_native()) {
-		efi_unmap_memmap();
+	efi_merge_regions();
+	new_memmap = efi_map_regions(&count, &pg_shift);
+	if (!new_memmap) {
+		pr_err("Error reallocating memory, EFI runtime non-functional!\n");
 		return;
 	}
 
-	if (efi_setup) {
-		efi_map_regions_fixed();
-	} else {
-		efi_merge_regions();
-		new_memmap = efi_map_regions(&count);
-		if (!new_memmap) {
-			pr_err("Error reallocating memory, EFI runtime non-functional!\n");
-			return;
-		}
-	}
-
-	err = save_runtime_map();
-	if (err)
-		pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+	save_runtime_map();
 
 	BUG_ON(!efi.systab);
 
-	efi_setup_page_tables();
+	if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift))
+		return;
+
 	efi_sync_low_kernel_mappings();
+	efi_dump_pagetable();
 
-	if (!efi_setup) {
+	if (efi_is_native()) {
 		status = phys_efi_set_virtual_address_map(
-			memmap.desc_size * count,
-			memmap.desc_size,
-			memmap.desc_version,
-			(efi_memory_desc_t *)__pa(new_memmap));
+				memmap.desc_size * count,
+				memmap.desc_size,
+				memmap.desc_version,
+				(efi_memory_desc_t *)__pa(new_memmap));
+	} else {
+		status = efi_thunk_set_virtual_address_map(
+				efi_phys.set_virtual_address_map,
+				memmap.desc_size * count,
+				memmap.desc_size,
+				memmap.desc_version,
+				(efi_memory_desc_t *)__pa(new_memmap));
+	}
 
-		if (status != EFI_SUCCESS) {
-			pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
-				 status);
-			panic("EFI call to SetVirtualAddressMap() failed!");
-		}
+	if (status != EFI_SUCCESS) {
+		pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
+			 status);
+		panic("EFI call to SetVirtualAddressMap() failed!");
 	}
 
 	/*
@@ -1055,24 +1139,43 @@
 	 * Call EFI services through wrapper functions.
 	 */
 	efi.runtime_version = efi_systab.hdr.revision;
-	efi.get_time = virt_efi_get_time;
-	efi.set_time = virt_efi_set_time;
-	efi.get_wakeup_time = virt_efi_get_wakeup_time;
-	efi.set_wakeup_time = virt_efi_set_wakeup_time;
-	efi.get_variable = virt_efi_get_variable;
-	efi.get_next_variable = virt_efi_get_next_variable;
-	efi.set_variable = virt_efi_set_variable;
-	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
-	efi.reset_system = virt_efi_reset_system;
+
+	if (efi_is_native())
+		native_runtime_setup();
+	else
+		efi_thunk_runtime_setup();
+
 	efi.set_virtual_address_map = NULL;
-	efi.query_variable_info = virt_efi_query_variable_info;
-	efi.update_capsule = virt_efi_update_capsule;
-	efi.query_capsule_caps = virt_efi_query_capsule_caps;
 
-	if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
-		runtime_code_page_mkexec();
+	efi_runtime_mkexec();
 
-	kfree(new_memmap);
+	/*
+	 * We mapped the descriptor array into the EFI pagetable above but we're
+	 * not unmapping it here. Here's why:
+	 *
+	 * We're copying select PGDs from the kernel page table to the EFI page
+	 * table and when we do so and make changes to those PGDs like unmapping
+	 * stuff from them, those changes appear in the kernel page table and we
+	 * go boom.
+	 *
+	 * From setup_real_mode():
+	 *
+	 * ...
+	 * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
+	 *
+	 * In this particular case, our allocation is in PGD 0 of the EFI page
+	 * table but we've copied that PGD from PGD[272] of the EFI page table:
+	 *
+	 *	pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272
+	 *
+	 * where the direct memory mapping in kernel space is.
+	 *
+	 * new_memmap's VA comes from that direct mapping and thus clearing it,
+	 * it would get cleared in the kernel page table too.
+	 *
+	 * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
+	 */
+	free_pages((unsigned long)new_memmap, pg_shift);
 
 	/* clean DUMMY object */
 	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
@@ -1082,6 +1185,14 @@
 			 0, NULL);
 }
 
+void __init efi_enter_virtual_mode(void)
+{
+	if (efi_setup)
+		kexec_enter_virtual_mode();
+	else
+		__efi_enter_virtual_mode();
+}
+
 /*
  * Convenience functions to obtain memory types and attributes
  */
@@ -1119,9 +1230,8 @@
 }
 
 /*
- * Some firmware has serious problems when using more than 50% of the EFI
- * variable store, i.e. it triggers bugs that can brick machines. Ensure that
- * we never use more than this safe limit.
+ * Some firmware implementations refuse to boot if there's insufficient space
+ * in the variable store. Ensure that we never use more than a safe limit.
  *
  * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
  * store.
@@ -1140,10 +1250,9 @@
 		return status;
 
 	/*
-	 * Some firmware implementations refuse to boot if there's insufficient
-	 * space in the variable store. We account for that by refusing the
-	 * write if permitting it would reduce the available space to under
-	 * 5KB. This figure was provided by Samsung, so should be safe.
+	 * We account for that by refusing the write if permitting it would
+	 * reduce the available space to under 5KB. This figure was provided by
+	 * Samsung, so should be safe.
 	 */
 	if ((remaining_size - size < EFI_MIN_RESERVE) &&
 		!efi_no_storage_paranoia) {
@@ -1206,8 +1315,27 @@
 		str++;
 
 	if (!strncmp(str, "old_map", 7))
-		set_bit(EFI_OLD_MEMMAP, &x86_efi_facility);
+		set_bit(EFI_OLD_MEMMAP, &efi.flags);
 
 	return 0;
 }
 early_param("efi", parse_efi_cmdline);
+
+void __init efi_apply_memmap_quirks(void)
+{
+	/*
+	 * Once setup is done earlier, unmap the EFI memory map on mismatched
+	 * firmware/kernel architectures since there is no support for runtime
+	 * services.
+	 */
+	if (!efi_runtime_supported()) {
+		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_unmap_memmap();
+	}
+
+	/*
+	 * UV doesn't support the new EFI pagetable mapping yet.
+	 */
+	if (is_uv_system())
+		set_bit(EFI_OLD_MEMMAP, &efi.flags);
+}
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 249b183..9ee3491 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -40,7 +40,12 @@
 static unsigned long efi_rt_eflags;
 
 void efi_sync_low_kernel_mappings(void) {}
-void efi_setup_page_tables(void) {}
+void __init efi_dump_pagetable(void) {}
+int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	return 0;
+}
+void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) {}
 
 void __init efi_map_region(efi_memory_desc_t *md)
 {
@@ -77,3 +82,9 @@
 
 	local_irq_restore(efi_rt_eflags);
 }
+
+void __init efi_runtime_mkexec(void)
+{
+	if (__supported_pte_mask & _PAGE_NX)
+		runtime_code_page_mkexec();
+}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6284f15..290d397 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -39,6 +39,7 @@
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 #include <asm/realmode.h>
+#include <asm/time.h>
 
 static pgd_t *save_pgd __initdata;
 static unsigned long efi_flags __initdata;
@@ -58,7 +59,8 @@
 	u64 prev_cr3;
 	pgd_t *efi_pgt;
 	bool use_pgd;
-};
+	u64 phys_stack;
+} __packed;
 
 static void __init early_code_mapping_set_exec(int executable)
 {
@@ -137,12 +139,64 @@
 		sizeof(pgd_t) * num_pgds);
 }
 
-void efi_setup_page_tables(void)
+int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
-	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+	unsigned long text;
+	struct page *page;
+	unsigned npages;
+	pgd_t *pgd;
 
-	if (!efi_enabled(EFI_OLD_MEMMAP))
-		efi_scratch.use_pgd = true;
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return 0;
+
+	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+	pgd = __va(efi_scratch.efi_pgt);
+
+	/*
+	 * It can happen that the physical address of new_memmap lands in memory
+	 * which is not mapped in the EFI page table. Therefore we need to go
+	 * and ident-map those pages containing the map before calling
+	 * phys_efi_set_virtual_address_map().
+	 */
+	if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) {
+		pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap);
+		return 1;
+	}
+
+	efi_scratch.use_pgd = true;
+
+	/*
+	 * When making calls to the firmware everything needs to be 1:1
+	 * mapped and addressable with 32-bit pointers. Map the kernel
+	 * text and allocate a new stack because we can't rely on the
+	 * stack pointer being < 4GB.
+	 */
+	if (!IS_ENABLED(CONFIG_EFI_MIXED))
+		return 0;
+
+	page = alloc_page(GFP_KERNEL|__GFP_DMA32);
+	if (!page)
+		panic("Unable to allocate EFI runtime stack < 4GB\n");
+
+	efi_scratch.phys_stack = virt_to_phys(page_address(page));
+	efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */
+
+	npages = (_end - _text) >> PAGE_SHIFT;
+	text = __pa(_text);
+
+	if (kernel_map_pages_in_pgd(pgd, text >> PAGE_SHIFT, text, npages, 0)) {
+		pr_err("Failed to map kernel text 1:1\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages);
 }
 
 static void __init __map_region(efi_memory_desc_t *md, u64 va)
@@ -173,6 +227,16 @@
 	 */
 	__map_region(md, md->phys_addr);
 
+	/*
+	 * Enforce the 1:1 mapping as the default virtual address when
+	 * booting in EFI mixed mode, because even though we may be
+	 * running a 64-bit kernel, the firmware may only be 32-bit.
+	 */
+	if (!efi_is_native () && IS_ENABLED(CONFIG_EFI_MIXED)) {
+		md->virt_addr = md->phys_addr;
+		return;
+	}
+
 	efi_va -= size;
 
 	/* Is PA 2M-aligned? */
@@ -233,3 +297,308 @@
 {
 	efi_setup = phys_addr + sizeof(struct setup_data);
 }
+
+void __init efi_runtime_mkexec(void)
+{
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	if (__supported_pte_mask & _PAGE_NX)
+		runtime_code_page_mkexec();
+}
+
+void __init efi_dump_pagetable(void)
+{
+#ifdef CONFIG_EFI_PGT_DUMP
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	ptdump_walk_pgd_level(NULL, pgd);
+#endif
+}
+
+#ifdef CONFIG_EFI_MIXED
+extern efi_status_t efi64_thunk(u32, ...);
+
+#define runtime_service32(func)						 \
+({									 \
+	u32 table = (u32)(unsigned long)efi.systab;			 \
+	u32 *rt, *___f;							 \
+									 \
+	rt = (u32 *)(table + offsetof(efi_system_table_32_t, runtime));	 \
+	___f = (u32 *)(*rt + offsetof(efi_runtime_services_32_t, func)); \
+	*___f;								 \
+})
+
+/*
+ * Switch to the EFI page tables early so that we can access the 1:1
+ * runtime services mappings which are not mapped in any other page
+ * tables. This function must be called before runtime_service32().
+ *
+ * Also, disable interrupts because the IDT points to 64-bit handlers,
+ * which aren't going to function correctly when we switch to 32-bit.
+ */
+#define efi_thunk(f, ...)						\
+({									\
+	efi_status_t __s;						\
+	unsigned long flags;						\
+	u32 func;							\
+									\
+	efi_sync_low_kernel_mappings();					\
+	local_irq_save(flags);						\
+									\
+	efi_scratch.prev_cr3 = read_cr3();				\
+	write_cr3((unsigned long)efi_scratch.efi_pgt);			\
+	__flush_tlb_all();						\
+									\
+	func = runtime_service32(f);					\
+	__s = efi64_thunk(func, __VA_ARGS__);			\
+									\
+	write_cr3(efi_scratch.prev_cr3);				\
+	__flush_tlb_all();						\
+	local_irq_restore(flags);					\
+									\
+	__s;								\
+})
+
+efi_status_t efi_thunk_set_virtual_address_map(
+	void *phys_set_virtual_address_map,
+	unsigned long memory_map_size,
+	unsigned long descriptor_size,
+	u32 descriptor_version,
+	efi_memory_desc_t *virtual_map)
+{
+	efi_status_t status;
+	unsigned long flags;
+	u32 func;
+
+	efi_sync_low_kernel_mappings();
+	local_irq_save(flags);
+
+	efi_scratch.prev_cr3 = read_cr3();
+	write_cr3((unsigned long)efi_scratch.efi_pgt);
+	__flush_tlb_all();
+
+	func = (u32)(unsigned long)phys_set_virtual_address_map;
+	status = efi64_thunk(func, memory_map_size, descriptor_size,
+			     descriptor_version, virtual_map);
+
+	write_cr3(efi_scratch.prev_cr3);
+	__flush_tlb_all();
+	local_irq_restore(flags);
+
+	return status;
+}
+
+static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+{
+	efi_status_t status;
+	u32 phys_tm, phys_tc;
+
+	spin_lock(&rtc_lock);
+
+	phys_tm = virt_to_phys(tm);
+	phys_tc = virt_to_phys(tc);
+
+	status = efi_thunk(get_time, phys_tm, phys_tc);
+
+	spin_unlock(&rtc_lock);
+
+	return status;
+}
+
+static efi_status_t efi_thunk_set_time(efi_time_t *tm)
+{
+	efi_status_t status;
+	u32 phys_tm;
+
+	spin_lock(&rtc_lock);
+
+	phys_tm = virt_to_phys(tm);
+
+	status = efi_thunk(set_time, phys_tm);
+
+	spin_unlock(&rtc_lock);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
+			  efi_time_t *tm)
+{
+	efi_status_t status;
+	u32 phys_enabled, phys_pending, phys_tm;
+
+	spin_lock(&rtc_lock);
+
+	phys_enabled = virt_to_phys(enabled);
+	phys_pending = virt_to_phys(pending);
+	phys_tm = virt_to_phys(tm);
+
+	status = efi_thunk(get_wakeup_time, phys_enabled,
+			     phys_pending, phys_tm);
+
+	spin_unlock(&rtc_lock);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+{
+	efi_status_t status;
+	u32 phys_tm;
+
+	spin_lock(&rtc_lock);
+
+	phys_tm = virt_to_phys(tm);
+
+	status = efi_thunk(set_wakeup_time, enabled, phys_tm);
+
+	spin_unlock(&rtc_lock);
+
+	return status;
+}
+
+
+static efi_status_t
+efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
+		       u32 *attr, unsigned long *data_size, void *data)
+{
+	efi_status_t status;
+	u32 phys_name, phys_vendor, phys_attr;
+	u32 phys_data_size, phys_data;
+
+	phys_data_size = virt_to_phys(data_size);
+	phys_vendor = virt_to_phys(vendor);
+	phys_name = virt_to_phys(name);
+	phys_attr = virt_to_phys(attr);
+	phys_data = virt_to_phys(data);
+
+	status = efi_thunk(get_variable, phys_name, phys_vendor,
+			   phys_attr, phys_data_size, phys_data);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
+		       u32 attr, unsigned long data_size, void *data)
+{
+	u32 phys_name, phys_vendor, phys_data;
+	efi_status_t status;
+
+	phys_name = virt_to_phys(name);
+	phys_vendor = virt_to_phys(vendor);
+	phys_data = virt_to_phys(data);
+
+	/* If data_size is > sizeof(u32) we've got problems */
+	status = efi_thunk(set_variable, phys_name, phys_vendor,
+			   attr, data_size, phys_data);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_get_next_variable(unsigned long *name_size,
+			    efi_char16_t *name,
+			    efi_guid_t *vendor)
+{
+	efi_status_t status;
+	u32 phys_name_size, phys_name, phys_vendor;
+
+	phys_name_size = virt_to_phys(name_size);
+	phys_vendor = virt_to_phys(vendor);
+	phys_name = virt_to_phys(name);
+
+	status = efi_thunk(get_next_variable, phys_name_size,
+			   phys_name, phys_vendor);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_get_next_high_mono_count(u32 *count)
+{
+	efi_status_t status;
+	u32 phys_count;
+
+	phys_count = virt_to_phys(count);
+	status = efi_thunk(get_next_high_mono_count, phys_count);
+
+	return status;
+}
+
+static void
+efi_thunk_reset_system(int reset_type, efi_status_t status,
+		       unsigned long data_size, efi_char16_t *data)
+{
+	u32 phys_data;
+
+	phys_data = virt_to_phys(data);
+
+	efi_thunk(reset_system, reset_type, status, data_size, phys_data);
+}
+
+static efi_status_t
+efi_thunk_update_capsule(efi_capsule_header_t **capsules,
+			 unsigned long count, unsigned long sg_list)
+{
+	/*
+	 * To properly support this function we would need to repackage
+	 * 'capsules' because the firmware doesn't understand 64-bit
+	 * pointers.
+	 */
+	return EFI_UNSUPPORTED;
+}
+
+static efi_status_t
+efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
+			      u64 *remaining_space,
+			      u64 *max_variable_size)
+{
+	efi_status_t status;
+	u32 phys_storage, phys_remaining, phys_max;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	phys_storage = virt_to_phys(storage_space);
+	phys_remaining = virt_to_phys(remaining_space);
+	phys_max = virt_to_phys(max_variable_size);
+
+	status = efi_thunk(query_variable_info, attr, phys_storage,
+			   phys_remaining, phys_max);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_query_capsule_caps(efi_capsule_header_t **capsules,
+			     unsigned long count, u64 *max_size,
+			     int *reset_type)
+{
+	/*
+	 * To properly support this function we would need to repackage
+	 * 'capsules' because the firmware doesn't understand 64-bit
+	 * pointers.
+	 */
+	return EFI_UNSUPPORTED;
+}
+
+void efi_thunk_runtime_setup(void)
+{
+	efi.get_time = efi_thunk_get_time;
+	efi.set_time = efi_thunk_set_time;
+	efi.get_wakeup_time = efi_thunk_get_wakeup_time;
+	efi.set_wakeup_time = efi_thunk_set_wakeup_time;
+	efi.get_variable = efi_thunk_get_variable;
+	efi.get_next_variable = efi_thunk_get_next_variable;
+	efi.set_variable = efi_thunk_set_variable;
+	efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count;
+	efi.reset_system = efi_thunk_reset_system;
+	efi.query_variable_info = efi_thunk_query_variable_info;
+	efi.update_capsule = efi_thunk_update_capsule;
+	efi.query_capsule_caps = efi_thunk_query_capsule_caps;
+}
+#endif /* CONFIG_EFI_MIXED */
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 88073b1..e0984ef 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -7,6 +7,10 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/msr.h>
+#include <asm/processor-flags.h>
+#include <asm/page_types.h>
 
 #define SAVE_XMM			\
 	mov %rsp, %rax;			\
@@ -164,7 +168,169 @@
 	ret
 ENDPROC(efi_call6)
 
+#ifdef CONFIG_EFI_MIXED
+
+/*
+ * We run this function from the 1:1 mapping.
+ *
+ * This function must be invoked with a 1:1 mapped stack.
+ */
+ENTRY(__efi64_thunk)
+	movl	%ds, %eax
+	push	%rax
+	movl	%es, %eax
+	push	%rax
+	movl	%ss, %eax
+	push	%rax
+
+	subq	$32, %rsp
+	movl	%esi, 0x0(%rsp)
+	movl	%edx, 0x4(%rsp)
+	movl	%ecx, 0x8(%rsp)
+	movq	%r8, %rsi
+	movl	%esi, 0xc(%rsp)
+	movq	%r9, %rsi
+	movl	%esi,  0x10(%rsp)
+
+	sgdt	save_gdt(%rip)
+
+	leaq	1f(%rip), %rbx
+	movq	%rbx, func_rt_ptr(%rip)
+
+	/* Switch to gdt with 32-bit segments */
+	movl	64(%rsp), %eax
+	lgdt	(%rax)
+
+	leaq	efi_enter32(%rip), %rax
+	pushq	$__KERNEL_CS
+	pushq	%rax
+	lretq
+
+1:	addq	$32, %rsp
+
+	lgdt	save_gdt(%rip)
+
+	pop	%rbx
+	movl	%ebx, %ss
+	pop	%rbx
+	movl	%ebx, %es
+	pop	%rbx
+	movl	%ebx, %ds
+
+	/*
+	 * Convert 32-bit status code into 64-bit.
+	 */
+	test	%rax, %rax
+	jz	1f
+	movl	%eax, %ecx
+	andl	$0x0fffffff, %ecx
+	andl	$0xf0000000, %eax
+	shl	$32, %rax
+	or	%rcx, %rax
+1:
+	ret
+ENDPROC(__efi64_thunk)
+
+ENTRY(efi_exit32)
+	movq	func_rt_ptr(%rip), %rax
+	push	%rax
+	mov	%rdi, %rax
+	ret
+ENDPROC(efi_exit32)
+
+	.code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+	movl	$__KERNEL_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+
+	/* Reload pgtables */
+	movl	%cr3, %eax
+	movl	%eax, %cr3
+
+	/* Disable paging */
+	movl	%cr0, %eax
+	btrl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+
+	/* Disable long mode via EFER */
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btrl	$_EFER_LME, %eax
+	wrmsr
+
+	call	*%edi
+
+	/* We must preserve return value */
+	movl	%eax, %edi
+
+	/*
+	 * Some firmware will return with interrupts enabled. Be sure to
+	 * disable them before we switch GDTs.
+	 */
+	cli
+
+	movl	68(%esp), %eax
+	movl	%eax, 2(%eax)
+	lgdtl	(%eax)
+
+	movl	%cr4, %eax
+	btsl	$(X86_CR4_PAE_BIT), %eax
+	movl	%eax, %cr4
+
+	movl	%cr3, %eax
+	movl	%eax, %cr3
+
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btsl	$_EFER_LME, %eax
+	wrmsr
+
+	xorl	%eax, %eax
+	lldt	%ax
+
+	movl	72(%esp), %eax
+	pushl	$__KERNEL_CS
+	pushl	%eax
+
+	/* Enable paging */
+	movl	%cr0, %eax
+	btsl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+	lret
+ENDPROC(efi_enter32)
+
+	.data
+	.balign	8
+	.global	efi32_boot_gdt
+efi32_boot_gdt:	.word	0
+		.quad	0
+
+save_gdt:	.word	0
+		.quad	0
+func_rt_ptr:	.quad	0
+
+	.global efi_gdt64
+efi_gdt64:
+	.word	efi_gdt64_end - efi_gdt64
+	.long	0			/* Filled out by user */
+	.word	0
+	.quad	0x0000000000000000	/* NULL descriptor */
+	.quad	0x00af9a000000ffff	/* __KERNEL_CS */
+	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
+	.quad	0x0080890000000000	/* TS descriptor */
+	.quad   0x0000000000000000	/* TS continued */
+efi_gdt64_end:
+#endif /* CONFIG_EFI_MIXED */
+
 	.data
 ENTRY(efi_scratch)
 	.fill 3,8,0
 	.byte 0
+	.quad 0
diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S
new file mode 100644
index 0000000..8806fa7
--- /dev/null
+++ b/arch/x86/platform/efi/efi_thunk_64.S
@@ -0,0 +1,65 @@
+/*
+ * Copyright (C) 2014 Intel Corporation; author Matt Fleming
+ */
+
+#include <linux/linkage.h>
+#include <asm/page_types.h>
+
+	.text
+	.code64
+ENTRY(efi64_thunk)
+	push	%rbp
+	push	%rbx
+
+	/*
+	 * Switch to 1:1 mapped 32-bit stack pointer.
+	 */
+	movq	%rsp, efi_saved_sp(%rip)
+	movq	efi_scratch+25(%rip), %rsp
+
+	/*
+	 * Calculate the physical address of the kernel text.
+	 */
+	movq	$__START_KERNEL_map, %rax
+	subq	phys_base(%rip), %rax
+
+	/*
+	 * Push some physical addresses onto the stack. This is easier
+	 * to do now in a code64 section while the assembler can address
+	 * 64-bit values. Note that all the addresses on the stack are
+	 * 32-bit.
+	 */
+	subq	$16, %rsp
+	leaq	efi_exit32(%rip), %rbx
+	subq	%rax, %rbx
+	movl	%ebx, 8(%rsp)
+	leaq	efi_gdt64(%rip), %rbx
+	subq	%rax, %rbx
+	movl	%ebx, 2(%ebx)
+	movl	%ebx, 4(%rsp)
+	leaq	efi_gdt32(%rip), %rbx
+	subq	%rax, %rbx
+	movl	%ebx, 2(%ebx)
+	movl	%ebx, (%rsp)
+
+	leaq	__efi64_thunk(%rip), %rbx
+	subq	%rax, %rbx
+	call	*%rbx
+
+	movq	efi_saved_sp(%rip), %rsp
+	pop	%rbx
+	pop	%rbp
+	retq
+ENDPROC(efi64_thunk)
+
+	.data
+efi_gdt32:
+	.word 	efi_gdt32_end - efi_gdt32
+	.long	0			/* Filled out above */
+	.word	0
+	.quad	0x0000000000000000	/* NULL descriptor */
+	.quad	0x00cf9a000000ffff	/* __KERNEL_CS */
+	.quad	0x00cf93000000ffff	/* __KERNEL_DS */
+efi_gdt32_end:
+
+efi_saved_sp:		.quad 0
diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c
index 39febb2..9471b94 100644
--- a/arch/x86/platform/ts5500/ts5500.c
+++ b/arch/x86/platform/ts5500/ts5500.c
@@ -88,7 +88,7 @@
 static const struct {
 	const char * const string;
 	const ssize_t offset;
-} ts5500_signatures[] __initdata = {
+} ts5500_signatures[] __initconst = {
 	{ "TS-5x00 AMD Elan", 0xb14 },
 };
 
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 7d01b8c..cc04e67 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -40,11 +40,7 @@
 #define smp_rmb()	barrier()
 #endif /* CONFIG_X86_PPRO_FENCE */
 
-#ifdef CONFIG_X86_OOSTORE
-#define smp_wmb()	wmb()
-#else /* CONFIG_X86_OOSTORE */
 #define smp_wmb()	barrier()
-#endif /* CONFIG_X86_OOSTORE */
 
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index fd14be1..9206ac7 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -2,6 +2,8 @@
 # Building vDSO images for x86.
 #
 
+KBUILD_CFLAGS += $(DISABLE_LTO)
+
 VDSO64-$(CONFIG_X86_64)		:= y
 VDSOX32-$(CONFIG_X86_X32_ABI)	:= y
 VDSO32-$(CONFIG_X86_32)		:= y
@@ -35,7 +37,8 @@
 
 VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
 			-Wl,--no-undefined \
-		      	-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
+			-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
+			$(DISABLE_LTO)
 
 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
 
@@ -127,7 +130,7 @@
 vdso32-images			= $(vdso32.so-y:%=vdso32-%.so)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-soname=linux-gate.so.1
+VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
 
 # This makes sure the $(obj) subdirectory exists even though vdso32/
 # is not a kbuild sub-make subdirectory.
@@ -181,7 +184,8 @@
 		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
+		$(LTO_CFLAGS)
 GCOV_PROFILE := n
 
 #
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index a4d7b64..201d09a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1473,6 +1473,18 @@
 	 * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests
 	 * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */
 	write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM);
+
+	if (!cpu)
+		return;
+	/*
+	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
+	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init.
+	*/
+	if (cpu_has_pse)
+		set_in_cr4(X86_CR4_PSE);
+
+	if (cpu_has_pge)
+		set_in_cr4(X86_CR4_PGE);
 }
 
 /*
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 8009acb..696c694 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -899,6 +899,13 @@
 					"m2p_add_override: pfn %lx not mapped", pfn))
 			return -EINVAL;
 	}
+	WARN_ON(PagePrivate(page));
+	SetPagePrivate(page);
+	set_page_private(page, mfn);
+	page->index = pfn_to_mfn(pfn);
+
+	if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
+		return -ENOMEM;
 
 	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
@@ -937,16 +944,19 @@
 }
 EXPORT_SYMBOL_GPL(m2p_add_override);
 int m2p_remove_override(struct page *page,
-			struct gnttab_map_grant_ref *kmap_op,
-			unsigned long mfn)
+		struct gnttab_map_grant_ref *kmap_op)
 {
 	unsigned long flags;
+	unsigned long mfn;
 	unsigned long pfn;
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
 
 	pfn = page_to_pfn(page);
+	mfn = get_phys_to_machine(pfn);
+	if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT))
+		return -EINVAL;
 
 	if (!PageHighMem(page)) {
 		address = (unsigned long)__va(pfn << PAGE_SHIFT);
@@ -960,7 +970,10 @@
 	spin_lock_irqsave(&m2p_override_lock, flags);
 	list_del(&page->lru);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
+	WARN_ON(!PagePrivate(page));
+	ClearPagePrivate(page);
 
+	set_phys_to_machine(pfn, page->index);
 	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
 			struct multicall_space mcs;
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index ba56e11..c87ae7c 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -20,6 +20,7 @@
 	select HAVE_FUNCTION_TRACER
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_PERF_EVENTS
+	select COMMON_CLK
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
 	  primarily for embedded systems.  These processors are both
@@ -80,7 +81,6 @@
 config XTENSA_VARIANT_FSF
 	bool "fsf - default (not generic) configuration"
 	select MMU
-	select HAVE_XTENSA_GPIO32
 
 config XTENSA_VARIANT_DC232B
 	bool "dc232b - Diamond 232L Standard Core Rev.B (LE)"
@@ -135,7 +135,6 @@
 config SMP
 	bool "Enable Symmetric multi-processing support"
 	depends on HAVE_SMP
-	select USE_GENERIC_SMP_HELPERS
 	select GENERIC_SMP_IDLE_THREAD
 	help
 	  Enabled SMP Software; allows more than one CPU/CORE
diff --git a/arch/xtensa/boot/dts/xtfpga.dtsi b/arch/xtensa/boot/dts/xtfpga.dtsi
index 46b4f5e..e7370b1 100644
--- a/arch/xtensa/boot/dts/xtfpga.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga.dtsi
@@ -35,6 +35,13 @@
 		interrupt-controller;
 	};
 
+	clocks {
+		osc: main-oscillator {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+		};
+	};
+
 	serial0: serial@fd050020 {
 		device_type = "serial";
 		compatible = "ns16550a";
@@ -42,9 +49,7 @@
 		reg = <0xfd050020 0x20>;
 		reg-shift = <2>;
 		interrupts = <0 1>; /* external irq 0 */
-		/* Filled in by platform_setup from FPGA register
-		 * clock-frequency = <100000000>;
-		 */
+		clocks = <&osc>;
 	};
 
 	enet0: ethoc@fd030000 {
@@ -52,5 +57,6 @@
 		reg = <0xfd030000 0x4000 0xfd800000 0x4000>;
 		interrupts = <1 1>; /* external irq 1 */
 		local-mac-address = [00 50 c2 13 6f 00];
+		clocks = <&osc>;
 	};
 };
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index 2a042d4..7494420 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -25,7 +25,7 @@
 
 #ifdef CONFIG_MMU
 
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 extern unsigned long xtensa_kio_paddr;
 
 static inline unsigned long xtensa_get_kio_paddr(void)
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 8c194f6..677bfcf 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -23,25 +23,37 @@
 
 static inline void spill_registers(void)
 {
-
+#if XCHAL_NUM_AREGS > 16
 	__asm__ __volatile__ (
-		"movi	a14, "__stringify((1 << PS_EXCM_BIT) | LOCKLEVEL)"\n\t"
-		"mov	a12, a0\n\t"
-		"rsr	a13, sar\n\t"
-		"xsr	a14, ps\n\t"
-		"movi	a0, _spill_registers\n\t"
-		"rsync\n\t"
-		"callx0 a0\n\t"
-		"mov	a0, a12\n\t"
-		"wsr	a13, sar\n\t"
-		"wsr	a14, ps\n\t"
-		: :
-#if defined(CONFIG_FRAME_POINTER)
-		: "a2", "a3", "a4",       "a11", "a12", "a13", "a14", "a15",
-#else
-		: "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15",
+		"	call12	1f\n"
+		"	_j	2f\n"
+		"	retw\n"
+		"	.align	4\n"
+		"1:\n"
+		"	_entry	a1, 48\n"
+		"	addi	a12, a0, 3\n"
+#if XCHAL_NUM_AREGS > 32
+		"	.rept	(" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n"
+		"	_entry	a1, 48\n"
+		"	mov	a12, a0\n"
+		"	.endr\n"
 #endif
-		  "memory");
+		"	_entry	a1, 48\n"
+#if XCHAL_NUM_AREGS % 12 == 0
+		"	mov	a8, a8\n"
+#elif XCHAL_NUM_AREGS % 12 == 4
+		"	mov	a12, a12\n"
+#elif XCHAL_NUM_AREGS % 12 == 8
+		"	mov	a4, a4\n"
+#endif
+		"	retw\n"
+		"2:\n"
+		: : : "a12", "a13", "memory");
+#else
+	__asm__ __volatile__ (
+		"	mov	a12, a12\n"
+		: : : "memory");
+#endif
 }
 
 #endif /* _XTENSA_TRAPS_H */
diff --git a/arch/xtensa/include/asm/vectors.h b/arch/xtensa/include/asm/vectors.h
index 5791b45..f74ddfb 100644
--- a/arch/xtensa/include/asm/vectors.h
+++ b/arch/xtensa/include/asm/vectors.h
@@ -25,7 +25,7 @@
 #define XCHAL_KIO_DEFAULT_PADDR		0xf0000000
 #define XCHAL_KIO_SIZE			0x10000000
 
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 #define XCHAL_KIO_PADDR			xtensa_get_kio_paddr()
 #else
 #define XCHAL_KIO_PADDR			XCHAL_KIO_DEFAULT_PADDR
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index 51940fe..b939552 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -734,7 +734,12 @@
 #define __NR_accept4				333
 __SYSCALL(333, sys_accept4, 4)
 
-#define __NR_syscall_count			334
+#define __NR_sched_setattr			334
+__SYSCALL(334, sys_sched_setattr, 2)
+#define __NR_sched_getattr			335
+__SYSCALL(335, sys_sched_getattr, 3)
+
+#define __NR_syscall_count			336
 
 /*
  * sysxtensa syscall handler
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 21dbe6b..ef7f499 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1081,34 +1081,202 @@
 
 	rsr	a0, sar
 	s32i	a3, a2, PT_AREG3
+	s32i	a0, a2, PT_SAR
+
+	/* The spill routine might clobber a4, a7, a8, a11, a12, and a15. */
+
 	s32i	a4, a2, PT_AREG4
-	s32i	a0, a2, PT_AREG5	# store SAR to PT_AREG5
-
-	/* The spill routine might clobber a7, a11, and a15. */
-
 	s32i	a7, a2, PT_AREG7
+	s32i	a8, a2, PT_AREG8
 	s32i	a11, a2, PT_AREG11
+	s32i	a12, a2, PT_AREG12
 	s32i	a15, a2, PT_AREG15
 
-	call0	_spill_registers	# destroys a3, a4, and SAR
+	/*
+	 * Rotate ws so that the current windowbase is at bit 0.
+	 * Assume ws = xxxwww1yy (www1 current window frame).
+	 * Rotate ws right so that a4 = yyxxxwww1.
+	 */
+
+	rsr	a0, windowbase
+	rsr	a3, windowstart		# a3 = xxxwww1yy
+	ssr	a0			# holds WB
+	slli	a0, a3, WSBITS
+	or	a3, a3, a0		# a3 = xxxwww1yyxxxwww1yy
+	srl	a3, a3			# a3 = 00xxxwww1yyxxxwww1
+
+	/* We are done if there are no more than the current register frame. */
+
+	extui	a3, a3, 1, WSBITS-1	# a3 = 0yyxxxwww
+	movi	a0, (1 << (WSBITS-1))
+	_beqz	a3, .Lnospill		# only one active frame? jump
+
+	/* We want 1 at the top, so that we return to the current windowbase */
+
+	or	a3, a3, a0		# 1yyxxxwww
+
+	/* Skip empty frames - get 'oldest' WINDOWSTART-bit. */
+
+	wsr	a3, windowstart		# save shifted windowstart
+	neg	a0, a3
+	and	a3, a0, a3		# first bit set from right: 000010000
+
+	ffs_ws	a0, a3			# a0: shifts to skip empty frames
+	movi	a3, WSBITS
+	sub	a0, a3, a0		# WSBITS-a0:number of 0-bits from right
+	ssr	a0			# save in SAR for later.
+
+	rsr	a3, windowbase
+	add	a3, a3, a0
+	wsr	a3, windowbase
+	rsync
+
+	rsr	a3, windowstart
+	srl	a3, a3			# shift windowstart
+
+	/* WB is now just one frame below the oldest frame in the register
+	   window. WS is shifted so the oldest frame is in bit 0, thus, WB
+	   and WS differ by one 4-register frame. */
+
+	/* Save frames. Depending what call was used (call4, call8, call12),
+	 * we have to save 4,8. or 12 registers.
+	 */
+
+
+.Lloop: _bbsi.l	a3, 1, .Lc4
+	_bbci.l	a3, 2, .Lc12
+
+.Lc8:	s32e	a4, a13, -16
+	l32e	a4, a5, -12
+	s32e	a8, a4, -32
+	s32e	a5, a13, -12
+	s32e	a6, a13, -8
+	s32e	a7, a13, -4
+	s32e	a9, a4, -28
+	s32e	a10, a4, -24
+	s32e	a11, a4, -20
+	srli	a11, a3, 2		# shift windowbase by 2
+	rotw	2
+	_bnei	a3, 1, .Lloop
+	j	.Lexit
+
+.Lc4:	s32e	a4, a9, -16
+	s32e	a5, a9, -12
+	s32e	a6, a9, -8
+	s32e	a7, a9, -4
+
+	srli	a7, a3, 1
+	rotw	1
+	_bnei	a3, 1, .Lloop
+	j	.Lexit
+
+.Lc12:	_bbci.l	a3, 3, .Linvalid_mask	# bit 2 shouldn't be zero!
+
+	/* 12-register frame (call12) */
+
+	l32e	a0, a5, -12
+	s32e	a8, a0, -48
+	mov	a8, a0
+
+	s32e	a9, a8, -44
+	s32e	a10, a8, -40
+	s32e	a11, a8, -36
+	s32e	a12, a8, -32
+	s32e	a13, a8, -28
+	s32e	a14, a8, -24
+	s32e	a15, a8, -20
+	srli	a15, a3, 3
+
+	/* The stack pointer for a4..a7 is out of reach, so we rotate the
+	 * window, grab the stackpointer, and rotate back.
+	 * Alternatively, we could also use the following approach, but that
+	 * makes the fixup routine much more complicated:
+	 * rotw	1
+	 * s32e	a0, a13, -16
+	 * ...
+	 * rotw 2
+	 */
+
+	rotw	1
+	mov	a4, a13
+	rotw	-1
+
+	s32e	a4, a8, -16
+	s32e	a5, a8, -12
+	s32e	a6, a8, -8
+	s32e	a7, a8, -4
+
+	rotw	3
+
+	_beqi	a3, 1, .Lexit
+	j	.Lloop
+
+.Lexit:
+
+	/* Done. Do the final rotation and set WS */
+
+	rotw	1
+	rsr	a3, windowbase
+	ssl	a3
+	movi	a3, 1
+	sll	a3, a3
+	wsr	a3, windowstart
+.Lnospill:
 
 	/* Advance PC, restore registers and SAR, and return from exception. */
 
-	l32i	a3, a2, PT_AREG5
-	l32i	a4, a2, PT_AREG4
+	l32i	a3, a2, PT_SAR
 	l32i	a0, a2, PT_AREG0
 	wsr	a3, sar
 	l32i	a3, a2, PT_AREG3
 
 	/* Restore clobbered registers. */
 
+	l32i	a4, a2, PT_AREG4
 	l32i	a7, a2, PT_AREG7
+	l32i	a8, a2, PT_AREG8
 	l32i	a11, a2, PT_AREG11
+	l32i	a12, a2, PT_AREG12
 	l32i	a15, a2, PT_AREG15
 
 	movi	a2, 0
 	rfe
 
+.Linvalid_mask:
+
+	/* We get here because of an unrecoverable error in the window
+	 * registers, so set up a dummy frame and kill the user application.
+	 * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer.
+	 */
+
+	movi	a0, 1
+	movi	a1, 0
+
+	wsr	a0, windowstart
+	wsr	a1, windowbase
+	rsync
+
+	movi	a0, 0
+
+	rsr	a3, excsave1
+	l32i	a1, a3, EXC_TABLE_KSTK
+
+	movi	a4, (1 << PS_WOE_BIT) | LOCKLEVEL
+	wsr	a4, ps
+	rsync
+
+	movi	a6, SIGSEGV
+	movi	a4, do_exit
+	callx4	a4
+
+	/* shouldn't return, so panic */
+
+	wsr	a0, excsave1
+	movi	a0, unrecoverable_exception
+	callx0	a0		# should not return
+1:	j	1b
+
+
 ENDPROC(fast_syscall_spill_registers)
 
 /* Fixup handler.
@@ -1117,6 +1285,13 @@
  * We basically restore WINDOWBASE and WINDOWSTART to the condition when
  * we entered the spill routine and jump to the user exception handler.
  *
+ * Note that we only need to restore the bits in windowstart that have not
+ * been spilled yet by the _spill_register routine. Luckily, a3 contains a
+ * rotated windowstart with only those bits set for frames that haven't been
+ * spilled yet. Because a3 is rotated such that bit 0 represents the register
+ * frame for the current windowbase - 1, we need to rotate a3 left by the
+ * value of the current windowbase + 1 and move it to windowstart.
+ *
  * a0: value of depc, original value in depc
  * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
  * a3: exctable, original value in excsave1
@@ -1131,10 +1306,15 @@
 	/* We need to make sure the current registers (a0-a3) are preserved.
 	 * To do this, we simply set the bit for the current window frame
 	 * in WS, so that the exception handlers save them to the task stack.
+	 *
+	 * Note: we use a3 to set the windowbase, so we take a special care
+	 * of it, saving it in the original _spill_registers frame across
+	 * the exception handler call.
 	 */
 
 	xsr	a3, excsave1	# get spill-mask
 	slli	a3, a3, 1	# shift left by one
+	addi	a3, a3, 1	# set the bit for the current window frame
 
 	slli	a2, a3, 32-WSBITS
 	src	a2, a3, a2	# a2 = xxwww1yyxxxwww1yy......
@@ -1220,209 +1400,6 @@
 
 ENDPROC(fast_syscall_spill_registers_fixup_return)
 
-/*
- * spill all registers.
- *
- * This is not a real function. The following conditions must be met:
- *
- *  - must be called with call0.
- *  - uses a3, a4 and SAR.
- *  - the last 'valid' register of each frame are clobbered.
- *  - the caller must have registered a fixup handler
- *    (or be inside a critical section)
- *  - PS_EXCM must be set (PS_WOE cleared?)
- */
-
-ENTRY(_spill_registers)
-
-	/*
-	 * Rotate ws so that the current windowbase is at bit 0.
-	 * Assume ws = xxxwww1yy (www1 current window frame).
-	 * Rotate ws right so that a4 = yyxxxwww1.
-	 */
-
-	rsr	a4, windowbase
-	rsr	a3, windowstart		# a3 = xxxwww1yy
-	ssr	a4			# holds WB
-	slli	a4, a3, WSBITS
-	or	a3, a3, a4		# a3 = xxxwww1yyxxxwww1yy
-	srl	a3, a3			# a3 = 00xxxwww1yyxxxwww1
-
-	/* We are done if there are no more than the current register frame. */
-
-	extui	a3, a3, 1, WSBITS-1	# a3 = 0yyxxxwww
-	movi	a4, (1 << (WSBITS-1))
-	_beqz	a3, .Lnospill		# only one active frame? jump
-
-	/* We want 1 at the top, so that we return to the current windowbase */
-
-	or	a3, a3, a4		# 1yyxxxwww
-
-	/* Skip empty frames - get 'oldest' WINDOWSTART-bit. */
-
-	wsr	a3, windowstart		# save shifted windowstart
-	neg	a4, a3
-	and	a3, a4, a3		# first bit set from right: 000010000
-
-	ffs_ws	a4, a3			# a4: shifts to skip empty frames
-	movi	a3, WSBITS
-	sub	a4, a3, a4		# WSBITS-a4:number of 0-bits from right
-	ssr	a4			# save in SAR for later.
-
-	rsr	a3, windowbase
-	add	a3, a3, a4
-	wsr	a3, windowbase
-	rsync
-
-	rsr	a3, windowstart
-	srl	a3, a3			# shift windowstart
-
-	/* WB is now just one frame below the oldest frame in the register
-	   window. WS is shifted so the oldest frame is in bit 0, thus, WB
-	   and WS differ by one 4-register frame. */
-
-	/* Save frames. Depending what call was used (call4, call8, call12),
-	 * we have to save 4,8. or 12 registers.
-	 */
-
-	_bbsi.l	a3, 1, .Lc4
-	_bbsi.l	a3, 2, .Lc8
-
-	/* Special case: we have a call12-frame starting at a4. */
-
-	_bbci.l	a3, 3, .Lc12	# bit 3 shouldn't be zero! (Jump to Lc12 first)
-
-	s32e	a4, a1, -16	# a1 is valid with an empty spill area
-	l32e	a4, a5, -12
-	s32e	a8, a4, -48
-	mov	a8, a4
-	l32e	a4, a1, -16
-	j	.Lc12c
-
-.Lnospill:
-	ret
-
-.Lloop: _bbsi.l	a3, 1, .Lc4
-	_bbci.l	a3, 2, .Lc12
-
-.Lc8:	s32e	a4, a13, -16
-	l32e	a4, a5, -12
-	s32e	a8, a4, -32
-	s32e	a5, a13, -12
-	s32e	a6, a13, -8
-	s32e	a7, a13, -4
-	s32e	a9, a4, -28
-	s32e	a10, a4, -24
-	s32e	a11, a4, -20
-
-	srli	a11, a3, 2		# shift windowbase by 2
-	rotw	2
-	_bnei	a3, 1, .Lloop
-
-.Lexit: /* Done. Do the final rotation, set WS, and return. */
-
-	rotw	1
-	rsr	a3, windowbase
-	ssl	a3
-	movi	a3, 1
-	sll	a3, a3
-	wsr	a3, windowstart
-	ret
-
-.Lc4:	s32e	a4, a9, -16
-	s32e	a5, a9, -12
-	s32e	a6, a9, -8
-	s32e	a7, a9, -4
-
-	srli	a7, a3, 1
-	rotw	1
-	_bnei	a3, 1, .Lloop
-	j	.Lexit
-
-.Lc12:	_bbci.l	a3, 3, .Linvalid_mask	# bit 2 shouldn't be zero!
-
-	/* 12-register frame (call12) */
-
-	l32e	a2, a5, -12
-	s32e	a8, a2, -48
-	mov	a8, a2
-
-.Lc12c: s32e	a9, a8, -44
-	s32e	a10, a8, -40
-	s32e	a11, a8, -36
-	s32e	a12, a8, -32
-	s32e	a13, a8, -28
-	s32e	a14, a8, -24
-	s32e	a15, a8, -20
-	srli	a15, a3, 3
-
-	/* The stack pointer for a4..a7 is out of reach, so we rotate the
-	 * window, grab the stackpointer, and rotate back.
-	 * Alternatively, we could also use the following approach, but that
-	 * makes the fixup routine much more complicated:
-	 * rotw	1
-	 * s32e	a0, a13, -16
-	 * ...
-	 * rotw 2
-	 */
-
-	rotw	1
-	mov	a5, a13
-	rotw	-1
-
-	s32e	a4, a9, -16
-	s32e	a5, a9, -12
-	s32e	a6, a9, -8
-	s32e	a7, a9, -4
-
-	rotw	3
-
-	_beqi	a3, 1, .Lexit
-	j	.Lloop
-
-.Linvalid_mask:
-
-	/* We get here because of an unrecoverable error in the window
-	 * registers. If we are in user space, we kill the application,
-	 * however, this condition is unrecoverable in kernel space.
-	 */
-
-	rsr	a0, ps
-	_bbci.l	a0, PS_UM_BIT, 1f
-
-	/* User space: Setup a dummy frame and kill application.
-	 * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer.
-	 */
-
-	movi	a0, 1
-	movi	a1, 0
-
-	wsr	a0, windowstart
-	wsr	a1, windowbase
-	rsync
-
-	movi	a0, 0
-
-	rsr	a3, excsave1
-	l32i	a1, a3, EXC_TABLE_KSTK
-
-	movi	a4, (1 << PS_WOE_BIT) | LOCKLEVEL
-	wsr	a4, ps
-	rsync
-
-	movi	a6, SIGSEGV
-	movi	a4, do_exit
-	callx4	a4
-
-1:	/* Kernel space: PANIC! */
-
-	wsr	a0, excsave1
-	movi	a0, unrecoverable_exception
-	callx0	a0		# should not return
-1:	j	1b
-
-ENDPROC(_spill_registers)
-
 #ifdef CONFIG_MMU
 /*
  * We should never get here. Bail out!
@@ -1794,6 +1771,43 @@
 
 ENDPROC(system_call)
 
+/*
+ * Spill live registers on the kernel stack macro.
+ *
+ * Entry condition: ps.woe is set, ps.excm is cleared
+ * Exit condition: windowstart has single bit set
+ * May clobber: a12, a13
+ */
+	.macro	spill_registers_kernel
+
+#if XCHAL_NUM_AREGS > 16
+	call12	1f
+	_j	2f
+	retw
+	.align	4
+1:
+	_entry	a1, 48
+	addi	a12, a0, 3
+#if XCHAL_NUM_AREGS > 32
+	.rept	(XCHAL_NUM_AREGS - 32) / 12
+	_entry	a1, 48
+	mov	a12, a0
+	.endr
+#endif
+	_entry	a1, 48
+#if XCHAL_NUM_AREGS % 12 == 0
+	mov	a8, a8
+#elif XCHAL_NUM_AREGS % 12 == 4
+	mov	a12, a12
+#elif XCHAL_NUM_AREGS % 12 == 8
+	mov	a4, a4
+#endif
+	retw
+2:
+#else
+	mov	a12, a12
+#endif
+	.endm
 
 /*
  * Task switch.
@@ -1806,21 +1820,20 @@
 
 	entry	a1, 16
 
-	mov	a12, a2			# preserve 'prev' (a2)
-	mov	a13, a3			# and 'next' (a3)
+	mov	a10, a2			# preserve 'prev' (a2)
+	mov	a11, a3			# and 'next' (a3)
 
 	l32i	a4, a2, TASK_THREAD_INFO
 	l32i	a5, a3, TASK_THREAD_INFO
 
-	save_xtregs_user a4 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+	save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
-	s32i	a0, a12, THREAD_RA	# save return address
-	s32i	a1, a12, THREAD_SP	# save stack pointer
+	s32i	a0, a10, THREAD_RA	# save return address
+	s32i	a1, a10, THREAD_SP	# save stack pointer
 
 	/* Disable ints while we manipulate the stack pointer. */
 
-	movi	a14, (1 << PS_EXCM_BIT) | LOCKLEVEL
-	xsr	a14, ps
+	rsil	a14, LOCKLEVEL
 	rsr	a3, excsave1
 	rsync
 	s32i	a3, a3, EXC_TABLE_FIXUP	/* enter critical section */
@@ -1835,7 +1848,7 @@
 
 	/* Flush register file. */
 
-	call0	_spill_registers	# destroys a3, a4, and SAR
+	spill_registers_kernel
 
 	/* Set kernel stack (and leave critical section)
 	 * Note: It's save to set it here. The stack will not be overwritten
@@ -1851,13 +1864,13 @@
 
 	/* restore context of the task 'next' */
 
-	l32i	a0, a13, THREAD_RA	# restore return address
-	l32i	a1, a13, THREAD_SP	# restore stack pointer
+	l32i	a0, a11, THREAD_RA	# restore return address
+	l32i	a1, a11, THREAD_SP	# restore stack pointer
 
-	load_xtregs_user a5 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+	load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
 	wsr	a14, ps
-	mov	a2, a12			# return 'prev'
+	mov	a2, a10			# return 'prev'
 	rsync
 
 	retw
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 7d12af1..84fe931 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -22,6 +22,7 @@
 #include <linux/bootmem.h>
 #include <linux/kernel.h>
 #include <linux/percpu.h>
+#include <linux/clk-provider.h>
 #include <linux/cpu.h>
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
@@ -276,6 +277,7 @@
 
 static int __init xtensa_device_probe(void)
 {
+	of_clk_init(NULL);
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	return 0;
 }
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 08b769d..2a1823d 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -30,6 +30,7 @@
 #include <asm/platform.h>
 
 unsigned long ccount_freq;		/* ccount Hz */
+EXPORT_SYMBOL(ccount_freq);
 
 static cycle_t ccount_read(struct clocksource *cs)
 {
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index cb8fd44..f9e1ec3 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -235,7 +235,7 @@
 
 	/* Check for overflow/underflow exception, jump if overflow. */
 
-	_bbci.l	a0, 6, _DoubleExceptionVector_WindowOverflow
+	bbci.l	a0, 6, _DoubleExceptionVector_WindowOverflow
 
 	/*
 	 * Restart window underflow exception.
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 74a60c7..80b33ed 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -122,9 +122,7 @@
 EXPORT_SYMBOL(insl);
 
 extern long common_exception_return;
-extern long _spill_registers;
 EXPORT_SYMBOL(common_exception_return);
-EXPORT_SYMBOL(_spill_registers);
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 479d753..aff108d 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -90,7 +90,7 @@
 
 
 /*
- * Initialize the bootmem system and give it all the memory we have available.
+ * Initialize the bootmem system and give it all low memory we have available.
  */
 
 void __init bootmem_init(void)
@@ -142,9 +142,14 @@
 
 	/* Add all remaining memory pieces into the bootmem map */
 
-	for (i=0; i<sysmem.nr_banks; i++)
-		free_bootmem(sysmem.bank[i].start,
-			     sysmem.bank[i].end - sysmem.bank[i].start);
+	for (i = 0; i < sysmem.nr_banks; i++) {
+		if (sysmem.bank[i].start >> PAGE_SHIFT < max_low_pfn) {
+			unsigned long end = min(max_low_pfn << PAGE_SHIFT,
+						sysmem.bank[i].end);
+			free_bootmem(sysmem.bank[i].start,
+				     end - sysmem.bank[i].start);
+		}
+	}
 
 }
 
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 36ec171..861203e 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -39,7 +39,7 @@
 	set_itlbcfg_register(0);
 	set_dtlbcfg_register(0);
 #endif
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 	/*
 	 * Update the IO area mapping in case xtensa_kio_paddr has changed
 	 */
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 8002278..57fd08b 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -135,11 +135,11 @@
 
 static int __init machine_setup(void)
 {
-	struct device_node *serial;
+	struct device_node *clock;
 	struct device_node *eth = NULL;
 
-	for_each_compatible_node(serial, NULL, "ns16550a")
-		update_clock_frequency(serial);
+	for_each_node_by_name(clock, "main-oscillator")
+		update_clock_frequency(clock);
 
 	if ((eth = of_find_compatible_node(eth, NULL, "opencores,ethoc")))
 		update_local_mac(eth);
@@ -290,6 +290,7 @@
 	 * knows whether they set it correctly on the DIP switches.
 	 */
 	pr_info("XTFPGA: Ethernet MAC %pM\n", ethoc_pdata.hwaddr);
+	ethoc_pdata.eth_clkfreq = *(long *)XTFPGA_CLKFRQ_VADDR;
 
 	return 0;
 }
diff --git a/arch/xtensa/variants/fsf/include/variant/tie.h b/arch/xtensa/variants/fsf/include/variant/tie.h
index bf40201..244cdea 100644
--- a/arch/xtensa/variants/fsf/include/variant/tie.h
+++ b/arch/xtensa/variants/fsf/include/variant/tie.h
@@ -18,13 +18,6 @@
 #define XCHAL_CP_MASK			0x00	/* bitmask of all CPs by ID */
 #define XCHAL_CP_PORT_MASK		0x00	/* bitmask of only port CPs */
 
-/*  Basic parameters of each coprocessor:  */
-#define XCHAL_CP7_NAME			"XTIOP"
-#define XCHAL_CP7_IDENT			XTIOP
-#define XCHAL_CP7_SA_SIZE		0	/* size of state save area */
-#define XCHAL_CP7_SA_ALIGN		1	/* min alignment of save area */
-#define XCHAL_CP_ID_XTIOP		7	/* coprocessor ID (0..7) */
-
 /*  Filler info for unassigned coprocessors, to simplify arrays etc:  */
 #define XCHAL_NCP_SA_SIZE		0
 #define XCHAL_NCP_SA_ALIGN		1
@@ -42,6 +35,8 @@
 #define XCHAL_CP5_SA_ALIGN		1
 #define XCHAL_CP6_SA_SIZE		0
 #define XCHAL_CP6_SA_ALIGN		1
+#define XCHAL_CP7_SA_SIZE		0
+#define XCHAL_CP7_SA_ALIGN		1
 
 /*  Save area for non-coprocessor optional and custom (TIE) state:  */
 #define XCHAL_NCP_SA_SIZE		0
diff --git a/block/blk-core.c b/block/blk-core.c
index c00e0bd..bfe16d5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -708,9 +708,13 @@
 	if (!q)
 		return NULL;
 
-	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+	q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+	if (!q->flush_rq)
 		return NULL;
 
+	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+		goto fail;
+
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unprep_rq_fn		= NULL;
@@ -733,12 +737,16 @@
 	/* init elevator */
 	if (elevator_init(q, NULL)) {
 		mutex_unlock(&q->sysfs_lock);
-		return NULL;
+		goto fail;
 	}
 
 	mutex_unlock(&q->sysfs_lock);
 
 	return q;
+
+fail:
+	kfree(q->flush_rq);
+	return NULL;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
 
@@ -1127,7 +1135,7 @@
 struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 {
 	if (q->mq_ops)
-		return blk_mq_alloc_request(q, rw, gfp_mask, false);
+		return blk_mq_alloc_request(q, rw, gfp_mask);
 	else
 		return blk_old_get_request(q, rw, gfp_mask);
 }
@@ -1278,6 +1286,11 @@
 	if (unlikely(!q))
 		return;
 
+	if (q->mq_ops) {
+		blk_mq_free_request(req);
+		return;
+	}
+
 	blk_pm_put_request(req);
 
 	elv_completed_request(q, req);
diff --git a/block/blk-exec.c b/block/blk-exec.c
index bbfc072..dbf4502 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -65,7 +65,7 @@
 	 * be resued after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_insert_request(q, rq, true);
+		blk_mq_insert_request(rq, at_head, true, false);
 		return;
 	}
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 9288aaf..43e6b47 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -130,20 +130,29 @@
 	blk_clear_rq_complete(rq);
 }
 
-static void mq_flush_data_run(struct work_struct *work)
+static void mq_flush_run(struct work_struct *work)
 {
 	struct request *rq;
 
-	rq = container_of(work, struct request, mq_flush_data);
+	rq = container_of(work, struct request, mq_flush_work);
 
 	memset(&rq->csd, 0, sizeof(rq->csd));
-	blk_mq_run_request(rq, true, false);
+	blk_mq_insert_request(rq, false, true, false);
 }
 
-static void blk_mq_flush_data_insert(struct request *rq)
+static bool blk_flush_queue_rq(struct request *rq, bool add_front)
 {
-	INIT_WORK(&rq->mq_flush_data, mq_flush_data_run);
-	kblockd_schedule_work(rq->q, &rq->mq_flush_data);
+	if (rq->q->mq_ops) {
+		INIT_WORK(&rq->mq_flush_work, mq_flush_run);
+		kblockd_schedule_work(rq->q, &rq->mq_flush_work);
+		return false;
+	} else {
+		if (add_front)
+			list_add(&rq->queuelist, &rq->q->queue_head);
+		else
+			list_add_tail(&rq->queuelist, &rq->q->queue_head);
+		return true;
+	}
 }
 
 /**
@@ -187,12 +196,7 @@
 
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
-		if (q->mq_ops)
-			blk_mq_flush_data_insert(rq);
-		else {
-			list_add(&rq->queuelist, &q->queue_head);
-			queued = true;
-		}
+		queued = blk_flush_queue_rq(rq, true);
 		break;
 
 	case REQ_FSEQ_DONE:
@@ -216,9 +220,6 @@
 	}
 
 	kicked = blk_kick_flush(q);
-	/* blk_mq_run_flush will run queue */
-	if (q->mq_ops)
-		return queued;
 	return kicked | queued;
 }
 
@@ -230,10 +231,9 @@
 	struct request *rq, *n;
 	unsigned long flags = 0;
 
-	if (q->mq_ops) {
-		blk_mq_free_request(flush_rq);
+	if (q->mq_ops)
 		spin_lock_irqsave(&q->mq_flush_lock, flags);
-	}
+
 	running = &q->flush_queue[q->flush_running_idx];
 	BUG_ON(q->flush_pending_idx == q->flush_running_idx);
 
@@ -263,49 +263,14 @@
 	 * kblockd.
 	 */
 	if (queued || q->flush_queue_delayed) {
-		if (!q->mq_ops)
-			blk_run_queue_async(q);
-		else
-		/*
-		 * This can be optimized to only run queues with requests
-		 * queued if necessary.
-		 */
-			blk_mq_run_queues(q, true);
+		WARN_ON(q->mq_ops);
+		blk_run_queue_async(q);
 	}
 	q->flush_queue_delayed = 0;
 	if (q->mq_ops)
 		spin_unlock_irqrestore(&q->mq_flush_lock, flags);
 }
 
-static void mq_flush_work(struct work_struct *work)
-{
-	struct request_queue *q;
-	struct request *rq;
-
-	q = container_of(work, struct request_queue, mq_flush_work);
-
-	/* We don't need set REQ_FLUSH_SEQ, it's for consistency */
-	rq = blk_mq_alloc_request(q, WRITE_FLUSH|REQ_FLUSH_SEQ,
-		__GFP_WAIT|GFP_ATOMIC, true);
-	rq->cmd_type = REQ_TYPE_FS;
-	rq->end_io = flush_end_io;
-
-	blk_mq_run_request(rq, true, false);
-}
-
-/*
- * We can't directly use q->flush_rq, because it doesn't have tag and is not in
- * hctx->rqs[]. so we must allocate a new request, since we can't sleep here,
- * so offload the work to workqueue.
- *
- * Note: we assume a flush request finished in any hardware queue will flush
- * the whole disk cache.
- */
-static void mq_run_flush(struct request_queue *q)
-{
-	kblockd_schedule_work(q, &q->mq_flush_work);
-}
-
 /**
  * blk_kick_flush - consider issuing flush request
  * @q: request_queue being kicked
@@ -340,19 +305,31 @@
 	 * different from running_idx, which means flush is in flight.
 	 */
 	q->flush_pending_idx ^= 1;
+
 	if (q->mq_ops) {
-		mq_run_flush(q);
-		return true;
+		struct blk_mq_ctx *ctx = first_rq->mq_ctx;
+		struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+		blk_mq_rq_init(hctx, q->flush_rq);
+		q->flush_rq->mq_ctx = ctx;
+
+		/*
+		 * Reuse the tag value from the fist waiting request,
+		 * with blk-mq the tag is generated during request
+		 * allocation and drivers can rely on it being inside
+		 * the range they asked for.
+		 */
+		q->flush_rq->tag = first_rq->tag;
+	} else {
+		blk_rq_init(q, q->flush_rq);
 	}
 
-	blk_rq_init(q, &q->flush_rq);
-	q->flush_rq.cmd_type = REQ_TYPE_FS;
-	q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
-	q->flush_rq.rq_disk = first_rq->rq_disk;
-	q->flush_rq.end_io = flush_end_io;
+	q->flush_rq->cmd_type = REQ_TYPE_FS;
+	q->flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+	q->flush_rq->rq_disk = first_rq->rq_disk;
+	q->flush_rq->end_io = flush_end_io;
 
-	list_add_tail(&q->flush_rq.queuelist, &q->queue_head);
-	return true;
+	return blk_flush_queue_rq(q->flush_rq, false);
 }
 
 static void flush_data_end_io(struct request *rq, int error)
@@ -437,7 +414,7 @@
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		if (q->mq_ops) {
-			blk_mq_run_request(rq, false, true);
+			blk_mq_insert_request(rq, false, false, true);
 		} else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
@@ -558,5 +535,4 @@
 void blk_mq_init_flush(struct request_queue *q)
 {
 	spin_lock_init(&q->mq_flush_lock);
-	INIT_WORK(&q->mq_flush_work, mq_flush_work);
 }
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 2da76c9..97a733c 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -119,6 +119,14 @@
 
 		atomic_inc(&bb.done);
 		submit_bio(type, bio);
+
+		/*
+		 * We can loop for a long time in here, if someone does
+		 * full device discards (like mkfs). Be nice and allow
+		 * us to schedule out to avoid softlocking if preempt
+		 * is disabled.
+		 */
+		cond_resched();
 	}
 	blk_finish_plug(&plug);
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 8f8adaa..6c583f9 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -21,6 +21,16 @@
 	if (!bio)
 		return 0;
 
+	/*
+	 * This should probably be returning 0, but blk_add_request_payload()
+	 * (Christoph!!!!)
+	 */
+	if (bio->bi_rw & REQ_DISCARD)
+		return 1;
+
+	if (bio->bi_rw & REQ_WRITE_SAME)
+		return 1;
+
 	fbio = bio;
 	cluster = blk_queue_cluster(q);
 	seg_size = 0;
@@ -161,6 +171,48 @@
 	*bvprv = *bvec;
 }
 
+static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
+			     struct scatterlist *sglist,
+			     struct scatterlist **sg)
+{
+	struct bio_vec bvec, bvprv = { NULL };
+	struct bvec_iter iter;
+	int nsegs, cluster;
+
+	nsegs = 0;
+	cluster = blk_queue_cluster(q);
+
+	if (bio->bi_rw & REQ_DISCARD) {
+		/*
+		 * This is a hack - drivers should be neither modifying the
+		 * biovec, nor relying on bi_vcnt - but because of
+		 * blk_add_request_payload(), a discard bio may or may not have
+		 * a payload we need to set up here (thank you Christoph) and
+		 * bi_vcnt is really the only way of telling if we need to.
+		 */
+
+		if (bio->bi_vcnt)
+			goto single_segment;
+
+		return 0;
+	}
+
+	if (bio->bi_rw & REQ_WRITE_SAME) {
+single_segment:
+		*sg = sglist;
+		bvec = bio_iovec(bio);
+		sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
+		return 1;
+	}
+
+	for_each_bio(bio)
+		bio_for_each_segment(bvec, bio, iter)
+			__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
+					     &nsegs, &cluster);
+
+	return nsegs;
+}
+
 /*
  * map a request to scatterlist, return number of sg entries setup. Caller
  * must make sure sg can hold rq->nr_phys_segments entries
@@ -168,23 +220,11 @@
 int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 		  struct scatterlist *sglist)
 {
-	struct bio_vec bvec, bvprv = { NULL };
-	struct req_iterator iter;
-	struct scatterlist *sg;
-	int nsegs, cluster;
+	struct scatterlist *sg = NULL;
+	int nsegs = 0;
 
-	nsegs = 0;
-	cluster = blk_queue_cluster(q);
-
-	/*
-	 * for each bio in rq
-	 */
-	sg = NULL;
-	rq_for_each_segment(bvec, rq, iter) {
-		__blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg,
-				     &nsegs, &cluster);
-	} /* segments in rq */
-
+	if (rq->bio)
+		nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
 
 	if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
 	    (blk_rq_bytes(rq) & q->dma_pad_mask)) {
@@ -230,20 +270,13 @@
 int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
 		   struct scatterlist *sglist)
 {
-	struct bio_vec bvec, bvprv = { NULL };
-	struct scatterlist *sg;
-	int nsegs, cluster;
-	struct bvec_iter iter;
+	struct scatterlist *sg = NULL;
+	int nsegs;
+	struct bio *next = bio->bi_next;
+	bio->bi_next = NULL;
 
-	nsegs = 0;
-	cluster = blk_queue_cluster(q);
-
-	sg = NULL;
-	bio_for_each_segment(bvec, bio, iter) {
-		__blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg,
-				     &nsegs, &cluster);
-	} /* segments in bio */
-
+	nsegs = __blk_bios_map_sg(q, bio, sglist, &sg);
+	bio->bi_next = next;
 	if (sg)
 		sg_mark_end(sg);
 
diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
index 3146bef..136ef86 100644
--- a/block/blk-mq-cpu.c
+++ b/block/blk-mq-cpu.c
@@ -11,7 +11,7 @@
 #include "blk-mq.h"
 
 static LIST_HEAD(blk_mq_cpu_notify_list);
-static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock);
+static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock);
 
 static int blk_mq_main_cpu_notify(struct notifier_block *self,
 				  unsigned long action, void *hcpu)
@@ -19,12 +19,12 @@
 	unsigned int cpu = (unsigned long) hcpu;
 	struct blk_mq_cpu_notifier *notify;
 
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 
 	list_for_each_entry(notify, &blk_mq_cpu_notify_list, list)
 		notify->notify(notify->data, action, cpu);
 
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 	return NOTIFY_OK;
 }
 
@@ -32,16 +32,16 @@
 {
 	BUG_ON(!notifier->notify);
 
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 	list_add_tail(&notifier->list, &blk_mq_cpu_notify_list);
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 }
 
 void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
 {
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 	list_del(&notifier->list);
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 }
 
 void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 5d70edc..83ae96c 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -184,7 +184,7 @@
 ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
 {
 	char *orig_page = page;
-	int cpu;
+	unsigned int cpu;
 
 	if (!tags)
 		return 0;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 57039fc..883f720 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -73,8 +73,8 @@
 		set_bit(ctx->index_hw, hctx->ctx_map);
 }
 
-static struct request *blk_mq_alloc_rq(struct blk_mq_hw_ctx *hctx, gfp_t gfp,
-				       bool reserved)
+static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
+					      gfp_t gfp, bool reserved)
 {
 	struct request *rq;
 	unsigned int tag;
@@ -193,12 +193,6 @@
 	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
 }
 
-static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
-					      gfp_t gfp, bool reserved)
-{
-	return blk_mq_alloc_rq(hctx, gfp, reserved);
-}
-
 static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
 						   int rw, gfp_t gfp,
 						   bool reserved)
@@ -226,15 +220,14 @@
 	return rq;
 }
 
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
-		gfp_t gfp, bool reserved)
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp)
 {
 	struct request *rq;
 
 	if (blk_mq_queue_enter(q))
 		return NULL;
 
-	rq = blk_mq_alloc_request_pinned(q, rw, gfp, reserved);
+	rq = blk_mq_alloc_request_pinned(q, rw, gfp, false);
 	if (rq)
 		blk_mq_put_ctx(rq->mq_ctx);
 	return rq;
@@ -258,7 +251,7 @@
 /*
  * Re-init and set pdu, if we have it
  */
-static void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
+void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
 	blk_rq_init(hctx->queue, rq);
 
@@ -290,38 +283,10 @@
 	__blk_mq_free_request(hctx, ctx, rq);
 }
 
-static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error)
+bool blk_mq_end_io_partial(struct request *rq, int error, unsigned int nr_bytes)
 {
-	if (error)
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-		error = -EIO;
-
-	if (unlikely(rq->cmd_flags & REQ_QUIET))
-		set_bit(BIO_QUIET, &bio->bi_flags);
-
-	/* don't actually finish bio if it's part of flush sequence */
-	if (!(rq->cmd_flags & REQ_FLUSH_SEQ))
-		bio_endio(bio, error);
-}
-
-void blk_mq_complete_request(struct request *rq, int error)
-{
-	struct bio *bio = rq->bio;
-	unsigned int bytes = 0;
-
-	trace_block_rq_complete(rq->q, rq);
-
-	while (bio) {
-		struct bio *next = bio->bi_next;
-
-		bio->bi_next = NULL;
-		bytes += bio->bi_iter.bi_size;
-		blk_mq_bio_endio(rq, bio, error);
-		bio = next;
-	}
-
-	blk_account_io_completion(rq, bytes);
+	if (blk_update_request(rq, error, blk_rq_bytes(rq)))
+		return true;
 
 	blk_account_io_done(rq);
 
@@ -329,49 +294,57 @@
 		rq->end_io(rq, error);
 	else
 		blk_mq_free_request(rq);
+	return false;
 }
+EXPORT_SYMBOL(blk_mq_end_io_partial);
 
-void __blk_mq_end_io(struct request *rq, int error)
-{
-	if (!blk_mark_rq_complete(rq))
-		blk_mq_complete_request(rq, error);
-}
-
-static void blk_mq_end_io_remote(void *data)
+static void __blk_mq_complete_request_remote(void *data)
 {
 	struct request *rq = data;
 
-	__blk_mq_end_io(rq, rq->errors);
+	rq->q->softirq_done_fn(rq);
 }
 
-/*
- * End IO on this request on a multiqueue enabled driver. We'll either do
- * it directly inline, or punt to a local IPI handler on the matching
- * remote CPU.
- */
-void blk_mq_end_io(struct request *rq, int error)
+void __blk_mq_complete_request(struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	int cpu;
 
-	if (!ctx->ipi_redirect)
-		return __blk_mq_end_io(rq, error);
+	if (!ctx->ipi_redirect) {
+		rq->q->softirq_done_fn(rq);
+		return;
+	}
 
 	cpu = get_cpu();
 	if (cpu != ctx->cpu && cpu_online(ctx->cpu)) {
-		rq->errors = error;
-		rq->csd.func = blk_mq_end_io_remote;
+		rq->csd.func = __blk_mq_complete_request_remote;
 		rq->csd.info = rq;
 		rq->csd.flags = 0;
 		__smp_call_function_single(ctx->cpu, &rq->csd, 0);
 	} else {
-		__blk_mq_end_io(rq, error);
+		rq->q->softirq_done_fn(rq);
 	}
 	put_cpu();
 }
-EXPORT_SYMBOL(blk_mq_end_io);
 
-static void blk_mq_start_request(struct request *rq)
+/**
+ * blk_mq_complete_request - end I/O on a request
+ * @rq:		the request being processed
+ *
+ * Description:
+ *	Ends all I/O on a request. It does not handle partial completions.
+ *	The actual completion happens out-of-order, through a IPI handler.
+ **/
+void blk_mq_complete_request(struct request *rq)
+{
+	if (unlikely(blk_should_fake_timeout(rq->q)))
+		return;
+	if (!blk_mark_rq_complete(rq))
+		__blk_mq_complete_request(rq);
+}
+EXPORT_SYMBOL(blk_mq_complete_request);
+
+static void blk_mq_start_request(struct request *rq, bool last)
 {
 	struct request_queue *q = rq->q;
 
@@ -384,6 +357,25 @@
 	 */
 	rq->deadline = jiffies + q->rq_timeout;
 	set_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+
+	if (q->dma_drain_size && blk_rq_bytes(rq)) {
+		/*
+		 * Make sure space for the drain appears.  We know we can do
+		 * this because max_hw_segments has been adjusted to be one
+		 * fewer than the device can handle.
+		 */
+		rq->nr_phys_segments++;
+	}
+
+	/*
+	 * Flag the last request in the series so that drivers know when IO
+	 * should be kicked off, if they don't do it on a per-request basis.
+	 *
+	 * Note: the flag isn't the only condition drivers should do kick off.
+	 * If drive is busy, the last request might not have the bit set.
+	 */
+	if (last)
+		rq->cmd_flags |= REQ_END;
 }
 
 static void blk_mq_requeue_request(struct request *rq)
@@ -392,6 +384,11 @@
 
 	trace_block_rq_requeue(q, rq);
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+
+	rq->cmd_flags &= ~REQ_END;
+
+	if (q->dma_drain_size && blk_rq_bytes(rq))
+		rq->nr_phys_segments--;
 }
 
 struct blk_mq_timeout_data {
@@ -559,19 +556,8 @@
 
 		rq = list_first_entry(&rq_list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		blk_mq_start_request(rq);
 
-		/*
-		 * Last request in the series. Flag it as such, this
-		 * enables drivers to know when IO should be kicked off,
-		 * if they don't do it on a per-request basis.
-		 *
-		 * Note: the flag isn't the only condition drivers
-		 * should do kick off. If drive is busy, the last
-		 * request might not have the bit set.
-		 */
-		if (list_empty(&rq_list))
-			rq->cmd_flags |= REQ_END;
+		blk_mq_start_request(rq, list_empty(&rq_list));
 
 		ret = q->mq_ops->queue_rq(hctx, rq);
 		switch (ret) {
@@ -589,8 +575,8 @@
 			break;
 		default:
 			pr_err("blk-mq: bad return on queue: %d\n", ret);
-			rq->errors = -EIO;
 		case BLK_MQ_RQ_QUEUE_ERROR:
+			rq->errors = -EIO;
 			blk_mq_end_io(rq, rq->errors);
 			break;
 		}
@@ -693,13 +679,16 @@
 }
 
 static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
-				    struct request *rq)
+				    struct request *rq, bool at_head)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
 	trace_block_rq_insert(hctx->queue, rq);
 
-	list_add_tail(&rq->queuelist, &ctx->rq_list);
+	if (at_head)
+		list_add(&rq->queuelist, &ctx->rq_list);
+	else
+		list_add_tail(&rq->queuelist, &ctx->rq_list);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 
 	/*
@@ -708,60 +697,27 @@
 	blk_mq_add_timer(rq);
 }
 
-void blk_mq_insert_request(struct request_queue *q, struct request *rq,
-			   bool run_queue)
-{
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx, *current_ctx;
-
-	ctx = rq->mq_ctx;
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
-	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
-		blk_insert_flush(rq);
-	} else {
-		current_ctx = blk_mq_get_ctx(q);
-
-		if (!cpu_online(ctx->cpu)) {
-			ctx = current_ctx;
-			hctx = q->mq_ops->map_queue(q, ctx->cpu);
-			rq->mq_ctx = ctx;
-		}
-		spin_lock(&ctx->lock);
-		__blk_mq_insert_request(hctx, rq);
-		spin_unlock(&ctx->lock);
-
-		blk_mq_put_ctx(current_ctx);
-	}
-
-	if (run_queue)
-		__blk_mq_run_hw_queue(hctx);
-}
-EXPORT_SYMBOL(blk_mq_insert_request);
-
-/*
- * This is a special version of blk_mq_insert_request to bypass FLUSH request
- * check. Should only be used internally.
- */
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async)
+void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
+		bool async)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx, *current_ctx;
+	struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
 
 	current_ctx = blk_mq_get_ctx(q);
+	if (!cpu_online(ctx->cpu))
+		rq->mq_ctx = ctx = current_ctx;
 
-	ctx = rq->mq_ctx;
-	if (!cpu_online(ctx->cpu)) {
-		ctx = current_ctx;
-		rq->mq_ctx = ctx;
-	}
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	/* ctx->cpu might be offline */
-	spin_lock(&ctx->lock);
-	__blk_mq_insert_request(hctx, rq);
-	spin_unlock(&ctx->lock);
+	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA) &&
+	    !(rq->cmd_flags & (REQ_FLUSH_SEQ))) {
+		blk_insert_flush(rq);
+	} else {
+		spin_lock(&ctx->lock);
+		__blk_mq_insert_request(hctx, rq, at_head);
+		spin_unlock(&ctx->lock);
+	}
 
 	blk_mq_put_ctx(current_ctx);
 
@@ -798,7 +754,7 @@
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		rq->mq_ctx = ctx;
-		__blk_mq_insert_request(hctx, rq);
+		__blk_mq_insert_request(hctx, rq, false);
 	}
 	spin_unlock(&ctx->lock);
 
@@ -888,6 +844,11 @@
 
 	blk_queue_bounce(q, &bio);
 
+	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
+		bio_endio(bio, -EIO);
+		return;
+	}
+
 	if (use_plug && blk_attempt_plug_merge(q, bio, &request_count))
 		return;
 
@@ -899,6 +860,8 @@
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
+	if (is_sync)
+		rw |= REQ_SYNC;
 	trace_block_getrq(q, bio, rw);
 	rq = __blk_mq_alloc_request(hctx, GFP_ATOMIC, false);
 	if (likely(rq))
@@ -950,7 +913,7 @@
 		__blk_mq_free_request(hctx, ctx, rq);
 	else {
 		blk_mq_bio_to_request(rq, bio);
-		__blk_mq_insert_request(hctx, rq);
+		__blk_mq_insert_request(hctx, rq, false);
 	}
 
 	spin_unlock(&ctx->lock);
@@ -1309,15 +1272,6 @@
 		reg->queue_depth = BLK_MQ_MAX_DEPTH;
 	}
 
-	/*
-	 * Set aside a tag for flush requests.  It will only be used while
-	 * another flush request is in progress but outside the driver.
-	 *
-	 * TODO: only allocate if flushes are supported
-	 */
-	reg->queue_depth++;
-	reg->reserved_tags++;
-
 	if (reg->queue_depth < (reg->reserved_tags + BLK_MQ_TAG_MIN))
 		return ERR_PTR(-EINVAL);
 
@@ -1360,17 +1314,27 @@
 	q->mq_ops = reg->ops;
 	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
 
+	q->sg_reserved_size = INT_MAX;
+
 	blk_queue_make_request(q, blk_mq_make_request);
 	blk_queue_rq_timed_out(q, reg->ops->timeout);
 	if (reg->timeout)
 		blk_queue_rq_timeout(q, reg->timeout);
 
+	if (reg->ops->complete)
+		blk_queue_softirq_done(q, reg->ops->complete);
+
 	blk_mq_init_flush(q);
 	blk_mq_init_cpu_queues(q, reg->nr_hw_queues);
 
-	if (blk_mq_init_hw_queues(q, reg, driver_data))
+	q->flush_rq = kzalloc(round_up(sizeof(struct request) + reg->cmd_size,
+				cache_line_size()), GFP_KERNEL);
+	if (!q->flush_rq)
 		goto err_hw;
 
+	if (blk_mq_init_hw_queues(q, reg, driver_data))
+		goto err_flush_rq;
+
 	blk_mq_map_swqueue(q);
 
 	mutex_lock(&all_q_mutex);
@@ -1378,6 +1342,9 @@
 	mutex_unlock(&all_q_mutex);
 
 	return q;
+
+err_flush_rq:
+	kfree(q->flush_rq);
 err_hw:
 	kfree(q->mq_map);
 err_map:
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 5c39179..72beba1 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -22,13 +22,12 @@
 	struct kobject		kobj;
 };
 
-void __blk_mq_end_io(struct request *rq, int error);
-void blk_mq_complete_request(struct request *rq, int error);
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async);
+void __blk_mq_complete_request(struct request *rq);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_init_flush(struct request_queue *q);
 void blk_mq_drain_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
+void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq);
 
 /*
  * CPU hotplug helpers
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 8095c4a..7500f87 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -549,6 +549,8 @@
 	if (q->mq_ops)
 		blk_mq_free_queue(q);
 
+	kfree(q->flush_rq);
+
 	blk_trace_shutdown(q);
 
 	bdi_destroy(&q->backing_dev_info);
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index bba81c9..d96f706 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -91,7 +91,7 @@
 	case BLK_EH_HANDLED:
 		/* Can we use req->errors here? */
 		if (q->mq_ops)
-			blk_mq_complete_request(req, req->errors);
+			__blk_mq_complete_request(req);
 		else
 			__blk_complete_request(req);
 		break;
diff --git a/block/blk.h b/block/blk.h
index c90e1d8..d23b415 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -113,7 +113,7 @@
 			q->flush_queue_delayed = 1;
 			return NULL;
 		}
-		if (unlikely(blk_queue_dying(q)) ||
+		if (unlikely(blk_queue_bypass(q)) ||
 		    !q->elevator->type->ops.elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index e7515aa..6f190bc 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -243,6 +243,8 @@
 		kobject_uevent(&ac->charger.dev->kobj, KOBJ_CHANGE);
 	return 0;
 }
+#else
+#define acpi_ac_resume NULL
 #endif
 static SIMPLE_DEV_PM_OPS(acpi_ac_pm_ops, NULL, acpi_ac_resume);
 
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 470e754..797a693 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -549,7 +549,7 @@
 {
 	unsigned long x;
 	struct acpi_battery *battery = to_acpi_battery(dev_get_drvdata(dev));
-	if (sscanf(buf, "%ld\n", &x) == 1)
+	if (sscanf(buf, "%lu\n", &x) == 1)
 		battery->alarm = x/1000;
 	if (acpi_battery_present(battery))
 		acpi_battery_set_alarm(battery);
@@ -841,6 +841,8 @@
 	acpi_battery_update(battery);
 	return 0;
 }
+#else
+#define acpi_battery_resume NULL
 #endif
 
 static SIMPLE_DEV_PM_OPS(acpi_battery_pm, NULL, acpi_battery_resume);
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index 10e4964..afec452 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -260,14 +260,6 @@
 	},
 	{
 	.callback = dmi_disable_osi_win8,
-	.ident = "Dell Inspiron 15R SE",
-	.matches = {
-		     DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7520"),
-		},
-	},
-	{
-	.callback = dmi_disable_osi_win8,
 	.ident = "ThinkPad Edge E530",
 	.matches = {
 		     DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -322,56 +314,6 @@
 		     DMI_MATCH(DMI_PRODUCT_VERSION, "2349D15"),
 		},
 	},
-	{
-	.callback = dmi_disable_osi_win8,
-	.ident = "HP ProBook 2013 models",
-	.matches = {
-		     DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook "),
-		     DMI_MATCH(DMI_PRODUCT_NAME, " G1"),
-		},
-	},
-	{
-	.callback = dmi_disable_osi_win8,
-	.ident = "HP EliteBook 2013 models",
-	.matches = {
-		     DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook "),
-		     DMI_MATCH(DMI_PRODUCT_NAME, " G1"),
-		},
-	},
-	{
-	.callback = dmi_disable_osi_win8,
-	.ident = "HP ZBook 14",
-	.matches = {
-		     DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 14"),
-		},
-	},
-	{
-	.callback = dmi_disable_osi_win8,
-	.ident = "HP ZBook 15",
-	.matches = {
-		     DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 15"),
-		},
-	},
-	{
-	.callback = dmi_disable_osi_win8,
-	.ident = "HP ZBook 17",
-	.matches = {
-		     DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 17"),
-		},
-	},
-	{
-	.callback = dmi_disable_osi_win8,
-	.ident = "HP EliteBook 8780w",
-	.matches = {
-		     DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8780w"),
-		},
-	},
 
 	/*
 	 * BIOS invocation of _OSI(Linux) is almost always a BIOS bug.
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 11c11f6..714e957 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -80,6 +80,8 @@
 
 #ifdef CONFIG_PM_SLEEP
 static int acpi_button_resume(struct device *dev);
+#else
+#define acpi_button_resume NULL
 #endif
 static SIMPLE_DEV_PM_OPS(acpi_button_pm, NULL, acpi_button_resume);
 
diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c
index 0b6ae6e..368f9dd 100644
--- a/drivers/acpi/container.c
+++ b/drivers/acpi/container.c
@@ -79,9 +79,10 @@
 	ACPI_COMPANION_SET(dev, adev);
 	dev->release = acpi_container_release;
 	ret = device_register(dev);
-	if (ret)
+	if (ret) {
+		put_device(dev);
 		return ret;
-
+	}
 	adev->driver_data = dev;
 	return 1;
 }
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index c431c88..5bfd769 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -609,7 +609,7 @@
 static void dock_notify(struct dock_station *ds, u32 event)
 {
 	acpi_handle handle = ds->handle;
-	struct acpi_device *ad;
+	struct acpi_device *adev = NULL;
 	int surprise_removal = 0;
 
 	/*
@@ -632,7 +632,8 @@
 	switch (event) {
 	case ACPI_NOTIFY_BUS_CHECK:
 	case ACPI_NOTIFY_DEVICE_CHECK:
-		if (!dock_in_progress(ds) && acpi_bus_get_device(handle, &ad)) {
+		acpi_bus_get_device(handle, &adev);
+		if (!dock_in_progress(ds) && !acpi_device_enumerated(adev)) {
 			begin_dock(ds);
 			dock(ds);
 			if (!dock_present(ds)) {
@@ -712,13 +713,11 @@
 static ssize_t show_docked(struct device *dev,
 			   struct device_attribute *attr, char *buf)
 {
-	struct acpi_device *tmp;
-
 	struct dock_station *dock_station = dev->platform_data;
+	struct acpi_device *adev = NULL;
 
-	if (!acpi_bus_get_device(dock_station->handle, &tmp))
-		return snprintf(buf, PAGE_SIZE, "1\n");
-	return snprintf(buf, PAGE_SIZE, "0\n");
+	acpi_bus_get_device(dock_station->handle, &adev);
+	return snprintf(buf, PAGE_SIZE, "%u\n", acpi_device_enumerated(adev));
 }
 static DEVICE_ATTR(docked, S_IRUGO, show_docked, NULL);
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 959d41a..d7d32c2 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -67,6 +67,8 @@
 #define ACPI_EC_DELAY		500	/* Wait 500ms max. during EC ops */
 #define ACPI_EC_UDELAY_GLK	1000	/* Wait 1ms max. to get global lock */
 #define ACPI_EC_MSI_UDELAY	550	/* Wait 550us for MSI EC */
+#define ACPI_EC_CLEAR_MAX	100	/* Maximum number of events to query
+					 * when trying to clear the EC */
 
 enum {
 	EC_FLAGS_QUERY_PENDING,		/* Query is pending */
@@ -116,6 +118,7 @@
 static int EC_FLAGS_MSI; /* Out-of-spec MSI controller */
 static int EC_FLAGS_VALIDATE_ECDT; /* ASUStec ECDTs need to be validated */
 static int EC_FLAGS_SKIP_DSDT_SCAN; /* Not all BIOS survive early DSDT scan */
+static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */
 
 /* --------------------------------------------------------------------------
                              Transaction Management
@@ -440,6 +443,29 @@
 
 EXPORT_SYMBOL(ec_get_handle);
 
+static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 *data);
+
+/*
+ * Clears stale _Q events that might have accumulated in the EC.
+ * Run with locked ec mutex.
+ */
+static void acpi_ec_clear(struct acpi_ec *ec)
+{
+	int i, status;
+	u8 value = 0;
+
+	for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) {
+		status = acpi_ec_query_unlocked(ec, &value);
+		if (status || !value)
+			break;
+	}
+
+	if (unlikely(i == ACPI_EC_CLEAR_MAX))
+		pr_warn("Warning: Maximum of %d stale EC events cleared\n", i);
+	else
+		pr_info("%d stale EC events cleared\n", i);
+}
+
 void acpi_ec_block_transactions(void)
 {
 	struct acpi_ec *ec = first_ec;
@@ -463,6 +489,10 @@
 	mutex_lock(&ec->mutex);
 	/* Allow transactions to be carried out again */
 	clear_bit(EC_FLAGS_BLOCKED, &ec->flags);
+
+	if (EC_FLAGS_CLEAR_ON_RESUME)
+		acpi_ec_clear(ec);
+
 	mutex_unlock(&ec->mutex);
 }
 
@@ -821,6 +851,13 @@
 
 	/* EC is fully operational, allow queries */
 	clear_bit(EC_FLAGS_QUERY_PENDING, &ec->flags);
+
+	/* Clear stale _Q events if hardware might require that */
+	if (EC_FLAGS_CLEAR_ON_RESUME) {
+		mutex_lock(&ec->mutex);
+		acpi_ec_clear(ec);
+		mutex_unlock(&ec->mutex);
+	}
 	return ret;
 }
 
@@ -922,6 +959,30 @@
 	return 0;
 }
 
+/*
+ * On some hardware it is necessary to clear events accumulated by the EC during
+ * sleep. These ECs stop reporting GPEs until they are manually polled, if too
+ * many events are accumulated. (e.g. Samsung Series 5/9 notebooks)
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=44161
+ *
+ * Ideally, the EC should also be instructed NOT to accumulate events during
+ * sleep (which Windows seems to do somehow), but the interface to control this
+ * behaviour is not known at this time.
+ *
+ * Models known to be affected are Samsung 530Uxx/535Uxx/540Uxx/550Pxx/900Xxx,
+ * however it is very likely that other Samsung models are affected.
+ *
+ * On systems which don't accumulate _Q events during sleep, this extra check
+ * should be harmless.
+ */
+static int ec_clear_on_resume(const struct dmi_system_id *id)
+{
+	pr_debug("Detected system needing EC poll on resume.\n");
+	EC_FLAGS_CLEAR_ON_RESUME = 1;
+	return 0;
+}
+
 static struct dmi_system_id ec_dmi_table[] __initdata = {
 	{
 	ec_skip_dsdt_scan, "Compal JFL92", {
@@ -965,6 +1026,9 @@
 	ec_validate_ecdt, "ASUS hardware", {
 	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek Computer Inc."),
 	DMI_MATCH(DMI_PRODUCT_NAME, "L4R"),}, NULL},
+	{
+	ec_clear_on_resume, "Samsung hardware", {
+	DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD.")}, NULL},
 	{},
 };
 
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 1fb6290..09e423f 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -55,6 +55,9 @@
 #ifdef CONFIG_PM_SLEEP
 static int acpi_fan_suspend(struct device *dev);
 static int acpi_fan_resume(struct device *dev);
+#else
+#define acpi_fan_suspend NULL
+#define acpi_fan_resume NULL
 #endif
 static SIMPLE_DEV_PM_OPS(acpi_fan_pm, acpi_fan_suspend, acpi_fan_resume);
 
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 52d45ea..361b40c 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -430,6 +430,7 @@
 				 pin_name(pin));
 		}
 
+		kfree(entry);
 		return 0;
 	}
 
diff --git a/drivers/acpi/proc.c b/drivers/acpi/proc.c
index 50fe34f..75c28ea 100644
--- a/drivers/acpi/proc.c
+++ b/drivers/acpi/proc.c
@@ -60,7 +60,7 @@
 				seq_printf(seq, "%c%-8s  %s:%s\n",
 					dev->wakeup.flags.run_wake ? '*' : ' ',
 					(device_may_wakeup(&dev->dev) ||
-					(ldev && device_may_wakeup(ldev))) ?
+					device_may_wakeup(ldev)) ?
 					"enabled" : "disabled",
 					ldev->bus ? ldev->bus->name :
 					"no-bus", dev_name(ldev));
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index 28baa05..84243c3 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -56,6 +56,12 @@
 	int target_state;		/* target T-state */
 };
 
+struct acpi_processor_throttling_arg {
+	struct acpi_processor *pr;
+	int target_state;
+	bool force;
+};
+
 #define THROTTLING_PRECHANGE       (1)
 #define THROTTLING_POSTCHANGE      (2)
 
@@ -1060,16 +1066,24 @@
 	return 0;
 }
 
+static long acpi_processor_throttling_fn(void *data)
+{
+	struct acpi_processor_throttling_arg *arg = data;
+	struct acpi_processor *pr = arg->pr;
+
+	return pr->throttling.acpi_processor_set_throttling(pr,
+			arg->target_state, arg->force);
+}
+
 int acpi_processor_set_throttling(struct acpi_processor *pr,
 						int state, bool force)
 {
-	cpumask_var_t saved_mask;
 	int ret = 0;
 	unsigned int i;
 	struct acpi_processor *match_pr;
 	struct acpi_processor_throttling *p_throttling;
+	struct acpi_processor_throttling_arg arg;
 	struct throttling_tstate t_state;
-	cpumask_var_t online_throttling_cpus;
 
 	if (!pr)
 		return -EINVAL;
@@ -1080,14 +1094,6 @@
 	if ((state < 0) || (state > (pr->throttling.state_count - 1)))
 		return -EINVAL;
 
-	if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL))
-		return -ENOMEM;
-
-	if (!alloc_cpumask_var(&online_throttling_cpus, GFP_KERNEL)) {
-		free_cpumask_var(saved_mask);
-		return -ENOMEM;
-	}
-
 	if (cpu_is_offline(pr->id)) {
 		/*
 		 * the cpu pointed by pr->id is offline. Unnecessary to change
@@ -1096,17 +1102,15 @@
 		return -ENODEV;
 	}
 
-	cpumask_copy(saved_mask, &current->cpus_allowed);
 	t_state.target_state = state;
 	p_throttling = &(pr->throttling);
-	cpumask_and(online_throttling_cpus, cpu_online_mask,
-		    p_throttling->shared_cpu_map);
+
 	/*
 	 * The throttling notifier will be called for every
 	 * affected cpu in order to get one proper T-state.
 	 * The notifier event is THROTTLING_PRECHANGE.
 	 */
-	for_each_cpu(i, online_throttling_cpus) {
+	for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) {
 		t_state.cpu = i;
 		acpi_processor_throttling_notifier(THROTTLING_PRECHANGE,
 							&t_state);
@@ -1118,21 +1122,18 @@
 	 * it can be called only for the cpu pointed by pr.
 	 */
 	if (p_throttling->shared_type == DOMAIN_COORD_TYPE_SW_ANY) {
-		/* FIXME: use work_on_cpu() */
-		if (set_cpus_allowed_ptr(current, cpumask_of(pr->id))) {
-			/* Can't migrate to the pr->id CPU. Exit */
-			ret = -ENODEV;
-			goto exit;
-		}
-		ret = p_throttling->acpi_processor_set_throttling(pr,
-						t_state.target_state, force);
+		arg.pr = pr;
+		arg.target_state = state;
+		arg.force = force;
+		ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, &arg);
 	} else {
 		/*
 		 * When the T-state coordination is SW_ALL or HW_ALL,
 		 * it is necessary to set T-state for every affected
 		 * cpus.
 		 */
-		for_each_cpu(i, online_throttling_cpus) {
+		for_each_cpu_and(i, cpu_online_mask,
+		    p_throttling->shared_cpu_map) {
 			match_pr = per_cpu(processors, i);
 			/*
 			 * If the pointer is invalid, we will report the
@@ -1153,13 +1154,12 @@
 					"on CPU %d\n", i));
 				continue;
 			}
-			t_state.cpu = i;
-			/* FIXME: use work_on_cpu() */
-			if (set_cpus_allowed_ptr(current, cpumask_of(i)))
-				continue;
-			ret = match_pr->throttling.
-				acpi_processor_set_throttling(
-				match_pr, t_state.target_state, force);
+
+			arg.pr = match_pr;
+			arg.target_state = state;
+			arg.force = force;
+			ret = work_on_cpu(pr->id, acpi_processor_throttling_fn,
+				&arg);
 		}
 	}
 	/*
@@ -1168,17 +1168,12 @@
 	 * affected cpu to update the T-states.
 	 * The notifier event is THROTTLING_POSTCHANGE
 	 */
-	for_each_cpu(i, online_throttling_cpus) {
+	for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) {
 		t_state.cpu = i;
 		acpi_processor_throttling_notifier(THROTTLING_POSTCHANGE,
 							&t_state);
 	}
-	/* restore the previous state */
-	/* FIXME: use work_on_cpu() */
-	set_cpus_allowed_ptr(current, saved_mask);
-exit:
-	free_cpumask_var(online_throttling_cpus);
-	free_cpumask_var(saved_mask);
+
 	return ret;
 }
 
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index b7201fc..0bdacc5 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -77,18 +77,24 @@
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_MEMORY24:
 		memory24 = &ares->data.memory24;
+		if (!memory24->address_length)
+			return false;
 		acpi_dev_get_memresource(res, memory24->minimum,
 					 memory24->address_length,
 					 memory24->write_protect);
 		break;
 	case ACPI_RESOURCE_TYPE_MEMORY32:
 		memory32 = &ares->data.memory32;
+		if (!memory32->address_length)
+			return false;
 		acpi_dev_get_memresource(res, memory32->minimum,
 					 memory32->address_length,
 					 memory32->write_protect);
 		break;
 	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
 		fixed_memory32 = &ares->data.fixed_memory32;
+		if (!fixed_memory32->address_length)
+			return false;
 		acpi_dev_get_memresource(res, fixed_memory32->address,
 					 fixed_memory32->address_length,
 					 fixed_memory32->write_protect);
@@ -144,12 +150,16 @@
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_IO:
 		io = &ares->data.io;
+		if (!io->address_length)
+			return false;
 		acpi_dev_get_ioresource(res, io->minimum,
 					io->address_length,
 					io->io_decode);
 		break;
 	case ACPI_RESOURCE_TYPE_FIXED_IO:
 		fixed_io = &ares->data.fixed_io;
+		if (!fixed_io->address_length)
+			return false;
 		acpi_dev_get_ioresource(res, fixed_io->address,
 					fixed_io->address_length,
 					ACPI_DECODE_10);
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index d465ae6..dbd4849 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -450,7 +450,7 @@
 {
 	unsigned long x;
 	struct acpi_battery *battery = to_acpi_battery(dev_get_drvdata(dev));
-	if (sscanf(buf, "%ld\n", &x) == 1)
+	if (sscanf(buf, "%lu\n", &x) == 1)
 		battery->alarm_capacity = x /
 			(1000 * acpi_battery_scale(battery));
 	if (battery->present)
@@ -668,6 +668,8 @@
 	acpi_sbs_callback(sbs);
 	return 0;
 }
+#else
+#define acpi_sbs_resume NULL
 #endif
 
 static SIMPLE_DEV_PM_OPS(acpi_sbs_pm, NULL, acpi_sbs_resume);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 7384158..57b053f 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -484,7 +484,6 @@
 static void acpi_hotplug_notify_cb(acpi_handle handle, u32 type, void *data)
 {
 	u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE;
-	struct acpi_scan_handler *handler = data;
 	struct acpi_device *adev;
 	acpi_status status;
 
@@ -500,7 +499,10 @@
 		break;
 	case ACPI_NOTIFY_EJECT_REQUEST:
 		acpi_handle_debug(handle, "ACPI_NOTIFY_EJECT_REQUEST event\n");
-		if (!handler->hotplug.enabled) {
+		if (!adev->handler)
+			goto err_out;
+
+		if (!adev->handler->hotplug.enabled) {
 			acpi_handle_err(handle, "Eject disabled\n");
 			ost_code = ACPI_OST_SC_EJECT_NOT_SUPPORTED;
 			goto err_out;
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index b718806..c40fb2e 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -71,6 +71,17 @@
 	return 0;
 }
 
+static bool acpi_sleep_state_supported(u8 sleep_state)
+{
+	acpi_status status;
+	u8 type_a, type_b;
+
+	status = acpi_get_sleep_type_data(sleep_state, &type_a, &type_b);
+	return ACPI_SUCCESS(status) && (!acpi_gbl_reduced_hardware
+		|| (acpi_gbl_FADT.sleep_control.address
+			&& acpi_gbl_FADT.sleep_status.address));
+}
+
 #ifdef CONFIG_ACPI_SLEEP
 static u32 acpi_target_sleep_state = ACPI_STATE_S0;
 
@@ -604,15 +615,9 @@
 {
 	int i;
 
-	for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++) {
-		acpi_status status;
-		u8 type_a, type_b;
-
-		status = acpi_get_sleep_type_data(i, &type_a, &type_b);
-		if (ACPI_SUCCESS(status)) {
+	for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++)
+		if (acpi_sleep_state_supported(i))
 			sleep_states[i] = 1;
-		}
-	}
 
 	suspend_set_ops(old_suspend_ordering ?
 		&acpi_suspend_ops_old : &acpi_suspend_ops);
@@ -740,11 +745,7 @@
 
 static void acpi_sleep_hibernate_setup(void)
 {
-	acpi_status status;
-	u8 type_a, type_b;
-
-	status = acpi_get_sleep_type_data(ACPI_STATE_S4, &type_a, &type_b);
-	if (ACPI_FAILURE(status))
+	if (!acpi_sleep_state_supported(ACPI_STATE_S4))
 		return;
 
 	hibernation_set_ops(old_suspend_ordering ?
@@ -793,8 +794,6 @@
 
 int __init acpi_sleep_init(void)
 {
-	acpi_status status;
-	u8 type_a, type_b;
 	char supported[ACPI_S_STATE_COUNT * 3 + 1];
 	char *pos = supported;
 	int i;
@@ -806,8 +805,7 @@
 	acpi_sleep_suspend_setup();
 	acpi_sleep_hibernate_setup();
 
-	status = acpi_get_sleep_type_data(ACPI_STATE_S5, &type_a, &type_b);
-	if (ACPI_SUCCESS(status)) {
+	if (acpi_sleep_state_supported(ACPI_STATE_S5)) {
 		sleep_states[ACPI_STATE_S5] = 1;
 		pm_power_off_prepare = acpi_power_off_prepare;
 		pm_power_off = acpi_power_off;
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 8349a55..08626c8 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -102,6 +102,8 @@
 
 #ifdef CONFIG_PM_SLEEP
 static int acpi_thermal_resume(struct device *dev);
+#else
+#define acpi_thermal_resume NULL
 #endif
 static SIMPLE_DEV_PM_OPS(acpi_thermal_pm, NULL, acpi_thermal_resume);
 
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 0347a37..85e3b61 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -99,10 +99,6 @@
 
 		union acpi_object *element = &(package->package.elements[i]);
 
-		if (!element) {
-			return AE_BAD_DATA;
-		}
-
 		switch (element->type) {
 
 		case ACPI_TYPE_INTEGER:
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index b727d10..b6ba88e 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -81,11 +81,12 @@
 module_param(allow_duplicates, bool, 0644);
 
 /*
- * For Windows 8 systems: if set ture and the GPU driver has
- * registered a backlight interface, skip registering ACPI video's.
+ * For Windows 8 systems: used to decide if video module
+ * should skip registering backlight interface of its own.
  */
-static bool use_native_backlight = false;
-module_param(use_native_backlight, bool, 0644);
+static int use_native_backlight_param = -1;
+module_param_named(use_native_backlight, use_native_backlight_param, int, 0444);
+static bool use_native_backlight_dmi = false;
 
 static int register_count;
 static struct mutex video_list_lock;
@@ -231,9 +232,17 @@
 static int acpi_video_switch_brightness(struct acpi_video_device *device,
 					 int event);
 
+static bool acpi_video_use_native_backlight(void)
+{
+	if (use_native_backlight_param != -1)
+		return use_native_backlight_param;
+	else
+		return use_native_backlight_dmi;
+}
+
 static bool acpi_video_verify_backlight_support(void)
 {
-	if (acpi_osi_is_win8() && use_native_backlight &&
+	if (acpi_osi_is_win8() && acpi_video_use_native_backlight() &&
 	    backlight_device_registered(BACKLIGHT_RAW))
 		return false;
 	return acpi_video_backlight_support();
@@ -398,6 +407,12 @@
 	return 0;
 }
 
+static int __init video_set_use_native_backlight(const struct dmi_system_id *d)
+{
+	use_native_backlight_dmi = true;
+	return 0;
+}
+
 static struct dmi_system_id video_dmi_table[] __initdata = {
 	/*
 	 * Broken _BQC workaround http://bugzilla.kernel.org/show_bug.cgi?id=13121
@@ -442,6 +457,120 @@
 		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7720"),
 		},
 	},
+	{
+	 .callback = video_set_use_native_backlight,
+	 .ident = "ThinkPad T430s",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430s"),
+		},
+	},
+	{
+	 .callback = video_set_use_native_backlight,
+	 .ident = "ThinkPad X230",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X230"),
+		},
+	},
+	{
+	.callback = video_set_use_native_backlight,
+	.ident = "ThinkPad X1 Carbon",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X1 Carbon"),
+		},
+	},
+	{
+	 .callback = video_set_use_native_backlight,
+	 .ident = "Lenovo Yoga 13",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo IdeaPad Yoga 13"),
+		},
+	},
+	{
+	 .callback = video_set_use_native_backlight,
+	 .ident = "Dell Inspiron 7520",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "Inspiron 7520"),
+		},
+	},
+	{
+	 .callback = video_set_use_native_backlight,
+	 .ident = "Acer Aspire 5733Z",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5733Z"),
+		},
+	},
+	{
+	 .callback = video_set_use_native_backlight,
+	 .ident = "Acer Aspire V5-431",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-431"),
+		},
+	},
+	{
+	.callback = video_set_use_native_backlight,
+	.ident = "HP ProBook 4340s",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "HP ProBook 4340s"),
+		},
+	},
+	{
+	.callback = video_set_use_native_backlight,
+	.ident = "HP ProBook 2013 models",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook "),
+		DMI_MATCH(DMI_PRODUCT_NAME, " G1"),
+		},
+	},
+	{
+	.callback = video_set_use_native_backlight,
+	.ident = "HP EliteBook 2013 models",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook "),
+		DMI_MATCH(DMI_PRODUCT_NAME, " G1"),
+		},
+	},
+	{
+	.callback = video_set_use_native_backlight,
+	.ident = "HP ZBook 14",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 14"),
+		},
+	},
+	{
+	.callback = video_set_use_native_backlight,
+	.ident = "HP ZBook 15",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 15"),
+		},
+	},
+	{
+	.callback = video_set_use_native_backlight,
+	.ident = "HP ZBook 17",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 17"),
+		},
+	},
+	{
+	.callback = video_set_use_native_backlight,
+	.ident = "HP EliteBook 8780w",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8780w"),
+		},
+	},
 	{}
 };
 
@@ -685,6 +814,7 @@
 	union acpi_object *o;
 	struct acpi_video_device_brightness *br = NULL;
 	int result = -EINVAL;
+	u32 value;
 
 	if (!ACPI_SUCCESS(acpi_video_device_lcd_query_levels(device, &obj))) {
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Could not query available "
@@ -715,7 +845,12 @@
 			printk(KERN_ERR PREFIX "Invalid data\n");
 			continue;
 		}
-		br->levels[count] = (u32) o->integer.value;
+		value = (u32) o->integer.value;
+		/* Skip duplicate entries */
+		if (count > 2 && br->levels[count - 1] == value)
+			continue;
+
+		br->levels[count] = value;
 
 		if (br->levels[count] > max_level)
 			max_level = br->levels[count];
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index f0447d3..19080c8 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -168,14 +168,6 @@
 		DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"),
 		},
 	},
-	{
-	.callback = video_detect_force_vendor,
-	.ident = "Lenovo Yoga 13",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo IdeaPad Yoga 13"),
-		},
-	},
 	{ },
 };
 
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 4e73772..20e03a7 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -11,13 +11,13 @@
 	  to update the PATA_PLATFORM entry.
 
 menuconfig ATA
-	tristate "Serial ATA and Parallel ATA drivers"
+	tristate "Serial ATA and Parallel ATA drivers (libata)"
 	depends on HAS_IOMEM
 	depends on BLOCK
 	depends on !(M32R || M68K || S390) || BROKEN
 	select SCSI
 	---help---
-	  If you want to use a ATA hard disk, ATA tape drive, ATA CD-ROM or
+	  If you want to use an ATA hard disk, ATA tape drive, ATA CD-ROM or
 	  any other ATA device under Linux, say Y and make sure that you know
 	  the name of your ATA host adapter (the card inside your computer
 	  that "speaks" the ATA protocol, also called ATA controller),
@@ -60,7 +60,7 @@
 
 config SATA_ZPODD
 	bool "SATA Zero Power Optical Disc Drive (ZPODD) support"
-	depends on ATA_ACPI
+	depends on ATA_ACPI && PM_RUNTIME
 	default n
 	help
 	  This option adds support for SATA Zero Power Optical Disc
@@ -97,15 +97,48 @@
 
 	  If unsure, say N.
 
+config AHCI_DA850
+	tristate "DaVinci DA850 AHCI SATA support"
+	depends on ARCH_DAVINCI_DA850
+	help
+	  This option enables support for the DaVinci DA850 SoC's
+	  onboard AHCI SATA.
+
+	  If unsure, say N.
+
+config AHCI_ST
+	tristate "ST AHCI SATA support"
+	depends on ARCH_STI
+	help
+	  This option enables support for ST AHCI SATA controller.
+
+	  If unsure, say N.
+
 config AHCI_IMX
 	tristate "Freescale i.MX AHCI SATA support"
-	depends on SATA_AHCI_PLATFORM && MFD_SYSCON
+	depends on MFD_SYSCON
 	help
 	  This option enables support for the Freescale i.MX SoC's
 	  onboard AHCI SATA.
 
 	  If unsure, say N.
 
+config AHCI_SUNXI
+	tristate "Allwinner sunxi AHCI SATA support"
+	depends on ARCH_SUNXI
+	help
+	  This option enables support for the Allwinner sunxi SoC's
+	  onboard AHCI SATA.
+
+	  If unsure, say N.
+
+config AHCI_XGENE
+	tristate "APM X-Gene 6.0Gbps AHCI SATA host controller support"
+	depends on ARM64 || COMPILE_TEST
+	select PHY_XGENE
+	help
+	 This option enables support for APM X-Gene SoC SATA host controller.
+
 config SATA_FSL
 	tristate "Freescale 3.0Gbps SATA support"
 	depends on FSL_SOC
@@ -239,6 +272,7 @@
 
 config SATA_HIGHBANK
 	tristate "Calxeda Highbank SATA support"
+	depends on ARCH_HIGHBANK || COMPILE_TEST
 	help
 	  This option enables support for the Calxeda Highbank SoC's
 	  onboard SATA.
@@ -247,6 +281,9 @@
 
 config SATA_MV
 	tristate "Marvell SATA support"
+	depends on PCI || ARCH_DOVE || ARCH_KIRKWOOD || ARCH_MV78XX0 || \
+		   ARCH_MVEBU || ARCH_ORION5X || COMPILE_TEST
+	select GENERIC_PHY
 	help
 	  This option enables support for the Marvell Serial ATA family.
 	  Currently supports 88SX[56]0[48][01] PCI(-X) chips,
@@ -272,6 +309,7 @@
 
 config SATA_RCAR
 	tristate "Renesas R-Car SATA support"
+	depends on ARCH_SHMOBILE || COMPILE_TEST
 	help
 	  This option enables support for Renesas R-Car Serial ATA.
 
@@ -351,6 +389,7 @@
 
 config PATA_ARASAN_CF
 	tristate "ARASAN CompactFlash PATA Controller Support"
+	depends on ARCH_SPEAR13XX || COMPILE_TEST
 	depends on DMADEVICES
 	select DMA_ENGINE
 	help
@@ -402,7 +441,7 @@
 
 config PATA_CS5520
 	tristate "CS5510/5520 PATA support"
-	depends on PCI
+	depends on PCI && (X86_32 || COMPILE_TEST)
 	help
 	  This option enables support for the Cyrix 5510/5520
 	  companion chip used with the MediaGX/Geode processor family.
@@ -411,7 +450,7 @@
 
 config PATA_CS5530
 	tristate "CS5530 PATA support"
-	depends on PCI
+	depends on PCI && (X86_32 || COMPILE_TEST)
 	help
 	  This option enables support for the Cyrix/NatSemi/AMD CS5530
 	  companion chip used with the MediaGX/Geode processor family.
@@ -420,7 +459,7 @@
 
 config PATA_CS5535
 	tristate "CS5535 PATA support (Experimental)"
-	depends on PCI && X86 && !X86_64
+	depends on PCI && X86_32
 	help
 	  This option enables support for the NatSemi/AMD CS5535
 	  companion chip used with the Geode processor family.
@@ -429,7 +468,7 @@
 
 config PATA_CS5536
 	tristate "CS5536 PATA support"
-	depends on PCI
+	depends on PCI && (X86_32 || MIPS || COMPILE_TEST)
 	help
 	  This option enables support for the AMD CS5536
 	  companion chip used with the Geode LX processor family.
@@ -665,7 +704,7 @@
 
 config PATA_SC1200
 	tristate "SC1200 PATA support"
-	depends on PCI
+	depends on PCI && (X86_32 || COMPILE_TEST)
 	help
 	  This option enables support for the NatSemi/AMD SC1200 SoC
 	  companion chip used with the Geode processor family.
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index 46518c6..44c8016 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -4,13 +4,17 @@
 # non-SFF interface
 obj-$(CONFIG_SATA_AHCI)		+= ahci.o libahci.o
 obj-$(CONFIG_SATA_ACARD_AHCI)	+= acard-ahci.o libahci.o
-obj-$(CONFIG_SATA_AHCI_PLATFORM) += ahci_platform.o libahci.o
+obj-$(CONFIG_SATA_AHCI_PLATFORM) += ahci_platform.o libahci.o libahci_platform.o
 obj-$(CONFIG_SATA_FSL)		+= sata_fsl.o
 obj-$(CONFIG_SATA_INIC162X)	+= sata_inic162x.o
 obj-$(CONFIG_SATA_SIL24)	+= sata_sil24.o
 obj-$(CONFIG_SATA_DWC)		+= sata_dwc_460ex.o
 obj-$(CONFIG_SATA_HIGHBANK)	+= sata_highbank.o libahci.o
-obj-$(CONFIG_AHCI_IMX)		+= ahci_imx.o
+obj-$(CONFIG_AHCI_DA850)	+= ahci_da850.o libahci.o libahci_platform.o
+obj-$(CONFIG_AHCI_IMX)		+= ahci_imx.o libahci.o libahci_platform.o
+obj-$(CONFIG_AHCI_SUNXI)	+= ahci_sunxi.o libahci.o libahci_platform.o
+obj-$(CONFIG_AHCI_ST)		+= ahci_st.o libahci.o libahci_platform.o
+obj-$(CONFIG_AHCI_XGENE)	+= ahci_xgene.o libahci.o libahci_platform.o
 
 # SFF w/ custom DMA
 obj-$(CONFIG_PDC_ADMA)		+= pdc_adma.o
diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c
index fd665d9..b51605a 100644
--- a/drivers/ata/acard-ahci.c
+++ b/drivers/ata/acard-ahci.c
@@ -36,7 +36,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index dc2756f..a52a5b6 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -35,7 +35,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
@@ -61,6 +60,7 @@
 	/* board IDs by feature in alphabetical order */
 	board_ahci,
 	board_ahci_ign_iferr,
+	board_ahci_noncq,
 	board_ahci_nosntf,
 	board_ahci_yes_fbs,
 
@@ -121,6 +121,13 @@
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
+	[board_ahci_noncq] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_NO_NCQ),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 	[board_ahci_nosntf] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_SNTF),
 		.flags		= AHCI_FLAG_COMMON,
@@ -452,6 +459,12 @@
 	{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci },	/* ASM1061 */
 	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci },	/* ASM1062 */
 
+	/*
+	 * Samsung SSDs found on some macbooks.  NCQ times out.
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=60731
+	 */
+	{ PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_noncq },
+
 	/* Enmotus */
 	{ PCI_DEVICE(0x1c44, 0x8000), board_ahci },
 
@@ -564,6 +577,7 @@
 				 unsigned long deadline)
 {
 	struct ata_port *ap = link->ap;
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	bool online;
 	int rc;
 
@@ -574,7 +588,7 @@
 	rc = sata_link_hardreset(link, sata_ehc_deb_timing(&link->eh_context),
 				 deadline, &online, NULL);
 
-	ahci_start_engine(ap);
+	hpriv->start_engine(ap);
 
 	DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class);
 
@@ -589,6 +603,7 @@
 {
 	struct ata_port *ap = link->ap;
 	struct ahci_port_priv *pp = ap->private_data;
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	u8 *d2h_fis = pp->rx_fis + RX_FIS_D2H_REG;
 	struct ata_taskfile tf;
 	bool online;
@@ -604,7 +619,7 @@
 	rc = sata_link_hardreset(link, sata_ehc_deb_timing(&link->eh_context),
 				 deadline, &online, NULL);
 
-	ahci_start_engine(ap);
+	hpriv->start_engine(ap);
 
 	/* The pseudo configuration device on SIMG4726 attached to
 	 * ASUS P5W-DH Deluxe doesn't send signature FIS after
@@ -1170,8 +1185,10 @@
 
 	nvec = rc;
 	rc = pci_enable_msi_block(pdev, nvec);
-	if (rc)
+	if (rc < 0)
 		goto intx;
+	else if (rc > 0)
+		goto single_msi;
 
 	return nvec;
 
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 2289efd..51af275 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -37,6 +37,8 @@
 
 #include <linux/clk.h>
 #include <linux/libata.h>
+#include <linux/phy/phy.h>
+#include <linux/regulator/consumer.h>
 
 /* Enclosure Management Control */
 #define EM_CTRL_MSG_TYPE              0x000f0000
@@ -51,6 +53,7 @@
 
 enum {
 	AHCI_MAX_PORTS		= 32,
+	AHCI_MAX_CLKS		= 3,
 	AHCI_MAX_SG		= 168, /* hardware max is 64K */
 	AHCI_DMA_BOUNDARY	= 0xffffffff,
 	AHCI_MAX_CMDS		= 32,
@@ -321,8 +324,17 @@
 	u32 			em_loc; /* enclosure management location */
 	u32			em_buf_sz;	/* EM buffer size in byte */
 	u32			em_msg_type;	/* EM message type */
-	struct clk		*clk;		/* Only for platforms supporting clk */
+	bool			got_runtime_pm; /* Did we do pm_runtime_get? */
+	struct clk		*clks[AHCI_MAX_CLKS]; /* Optional */
+	struct regulator	*target_pwr;	/* Optional */
+	struct phy		*phy;		/* If platform uses phy */
 	void			*plat_data;	/* Other platform data */
+	/*
+	 * Optional ahci_start_engine override, if not set this gets set to the
+	 * default ahci_start_engine during ahci_save_initial_config, this can
+	 * be overridden anytime before the host is activated.
+	 */
+	void			(*start_engine)(struct ata_port *ap);
 };
 
 extern int ahci_ignore_sss;
diff --git a/drivers/ata/ahci_da850.c b/drivers/ata/ahci_da850.c
new file mode 100644
index 0000000..2c83613
--- /dev/null
+++ b/drivers/ata/ahci_da850.c
@@ -0,0 +1,114 @@
+/*
+ * DaVinci DA850 AHCI SATA platform driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pm.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/libata.h>
+#include <linux/ahci_platform.h>
+#include "ahci.h"
+
+/* SATA PHY Control Register offset from AHCI base */
+#define SATA_P0PHYCR_REG	0x178
+
+#define SATA_PHY_MPY(x)		((x) << 0)
+#define SATA_PHY_LOS(x)		((x) << 6)
+#define SATA_PHY_RXCDR(x)	((x) << 10)
+#define SATA_PHY_RXEQ(x)	((x) << 13)
+#define SATA_PHY_TXSWING(x)	((x) << 19)
+#define SATA_PHY_ENPLL(x)	((x) << 31)
+
+/*
+ * The multiplier needed for 1.5GHz PLL output.
+ *
+ * NOTE: This is currently hardcoded to be suitable for 100MHz crystal
+ * frequency (which is used by DA850 EVM board) and may need to be changed
+ * if you would like to use this driver on some other board.
+ */
+#define DA850_SATA_CLK_MULTIPLIER	7
+
+static void da850_sata_init(struct device *dev, void __iomem *pwrdn_reg,
+			    void __iomem *ahci_base)
+{
+	unsigned int val;
+
+	/* Enable SATA clock receiver */
+	val = readl(pwrdn_reg);
+	val &= ~BIT(0);
+	writel(val, pwrdn_reg);
+
+	val = SATA_PHY_MPY(DA850_SATA_CLK_MULTIPLIER + 1) | SATA_PHY_LOS(1) |
+	      SATA_PHY_RXCDR(4) | SATA_PHY_RXEQ(1) | SATA_PHY_TXSWING(3) |
+	      SATA_PHY_ENPLL(1);
+
+	writel(val, ahci_base + SATA_P0PHYCR_REG);
+}
+
+static const struct ata_port_info ahci_da850_port_info = {
+	.flags		= AHCI_FLAG_COMMON,
+	.pio_mask	= ATA_PIO4,
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &ahci_platform_ops,
+};
+
+static int ahci_da850_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ahci_host_priv *hpriv;
+	struct resource *res;
+	void __iomem *pwrdn_reg;
+	int rc;
+
+	hpriv = ahci_platform_get_resources(pdev);
+	if (IS_ERR(hpriv))
+		return PTR_ERR(hpriv);
+
+	rc = ahci_platform_enable_resources(hpriv);
+	if (rc)
+		return rc;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res)
+		goto disable_resources;
+
+	pwrdn_reg = devm_ioremap(dev, res->start, resource_size(res));
+	if (!pwrdn_reg)
+		goto disable_resources;
+
+	da850_sata_init(dev, pwrdn_reg, hpriv->mmio);
+
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_da850_port_info, 0, 0);
+	if (rc)
+		goto disable_resources;
+
+	return 0;
+disable_resources:
+	ahci_platform_disable_resources(hpriv);
+	return rc;
+}
+
+static SIMPLE_DEV_PM_OPS(ahci_da850_pm_ops, ahci_platform_suspend,
+			 ahci_platform_resume);
+
+static struct platform_driver ahci_da850_driver = {
+	.probe = ahci_da850_probe,
+	.remove = ata_platform_remove_one,
+	.driver = {
+		.name = "ahci_da850",
+		.owner = THIS_MODULE,
+		.pm = &ahci_da850_pm_ops,
+	},
+};
+module_platform_driver(ahci_da850_driver);
+
+MODULE_DESCRIPTION("DaVinci DA850 AHCI SATA platform driver");
+MODULE_AUTHOR("Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c
index dd4d6f7..497c7ab 100644
--- a/drivers/ata/ahci_imx.c
+++ b/drivers/ata/ahci_imx.c
@@ -42,13 +42,7 @@
 struct imx_ahci_priv {
 	struct platform_device *ahci_pdev;
 	enum ahci_imx_type type;
-
-	/* i.MX53 clock */
-	struct clk *sata_gate_clk;
-	/* Common clock */
-	struct clk *sata_ref_clk;
 	struct clk *ahb_clk;
-
 	struct regmap *gpr;
 	bool no_device;
 	bool first_time;
@@ -58,288 +52,32 @@
 module_param_named(hotplug, ahci_imx_hotplug, int, 0644);
 MODULE_PARM_DESC(hotplug, "AHCI IMX hot-plug support (0=Don't support, 1=support)");
 
-static int imx_sata_clock_enable(struct device *dev)
+static void ahci_imx_host_stop(struct ata_host *host);
+
+static int imx_sata_enable(struct ahci_host_priv *hpriv)
 {
-	struct imx_ahci_priv *imxpriv = dev_get_drvdata(dev->parent);
+	struct imx_ahci_priv *imxpriv = hpriv->plat_data;
 	int ret;
 
-	if (imxpriv->type == AHCI_IMX53) {
-		ret = clk_prepare_enable(imxpriv->sata_gate_clk);
-		if (ret < 0) {
-			dev_err(dev, "prepare-enable sata_gate clock err:%d\n",
-				ret);
+	if (imxpriv->no_device)
+		return 0;
+
+	if (hpriv->target_pwr) {
+		ret = regulator_enable(hpriv->target_pwr);
+		if (ret)
 			return ret;
-		}
 	}
 
-	ret = clk_prepare_enable(imxpriv->sata_ref_clk);
-	if (ret < 0) {
-		dev_err(dev, "prepare-enable sata_ref clock err:%d\n",
-			ret);
-		goto clk_err;
-	}
-
-	if (imxpriv->type == AHCI_IMX6Q) {
-		regmap_update_bits(imxpriv->gpr, IOMUXC_GPR13,
-				   IMX6Q_GPR13_SATA_MPLL_CLK_EN,
-				   IMX6Q_GPR13_SATA_MPLL_CLK_EN);
-	}
-
-	usleep_range(1000, 2000);
-
-	return 0;
-
-clk_err:
-	if (imxpriv->type == AHCI_IMX53)
-		clk_disable_unprepare(imxpriv->sata_gate_clk);
-	return ret;
-}
-
-static void imx_sata_clock_disable(struct device *dev)
-{
-	struct imx_ahci_priv *imxpriv = dev_get_drvdata(dev->parent);
-
-	if (imxpriv->type == AHCI_IMX6Q) {
-		regmap_update_bits(imxpriv->gpr, IOMUXC_GPR13,
-				   IMX6Q_GPR13_SATA_MPLL_CLK_EN,
-				   !IMX6Q_GPR13_SATA_MPLL_CLK_EN);
-	}
-
-	clk_disable_unprepare(imxpriv->sata_ref_clk);
-
-	if (imxpriv->type == AHCI_IMX53)
-		clk_disable_unprepare(imxpriv->sata_gate_clk);
-}
-
-static void ahci_imx_error_handler(struct ata_port *ap)
-{
-	u32 reg_val;
-	struct ata_device *dev;
-	struct ata_host *host = dev_get_drvdata(ap->dev);
-	struct ahci_host_priv *hpriv = host->private_data;
-	void __iomem *mmio = hpriv->mmio;
-	struct imx_ahci_priv *imxpriv = dev_get_drvdata(ap->dev->parent);
-
-	ahci_error_handler(ap);
-
-	if (!(imxpriv->first_time) || ahci_imx_hotplug)
-		return;
-
-	imxpriv->first_time = false;
-
-	ata_for_each_dev(dev, &ap->link, ENABLED)
-		return;
-	/*
-	 * Disable link to save power.  An imx ahci port can't be recovered
-	 * without full reset once the pddq mode is enabled making it
-	 * impossible to use as part of libata LPM.
-	 */
-	reg_val = readl(mmio + PORT_PHY_CTL);
-	writel(reg_val | PORT_PHY_CTL_PDDQ_LOC, mmio + PORT_PHY_CTL);
-	imx_sata_clock_disable(ap->dev);
-	imxpriv->no_device = true;
-}
-
-static int ahci_imx_softreset(struct ata_link *link, unsigned int *class,
-		       unsigned long deadline)
-{
-	struct ata_port *ap = link->ap;
-	struct imx_ahci_priv *imxpriv = dev_get_drvdata(ap->dev->parent);
-	int ret = -EIO;
-
-	if (imxpriv->type == AHCI_IMX53)
-		ret = ahci_pmp_retry_srst_ops.softreset(link, class, deadline);
-	else if (imxpriv->type == AHCI_IMX6Q)
-		ret = ahci_ops.softreset(link, class, deadline);
-
-	return ret;
-}
-
-static struct ata_port_operations ahci_imx_ops = {
-	.inherits	= &ahci_platform_ops,
-	.error_handler	= ahci_imx_error_handler,
-	.softreset	= ahci_imx_softreset,
-};
-
-static const struct ata_port_info ahci_imx_port_info = {
-	.flags		= AHCI_FLAG_COMMON,
-	.pio_mask	= ATA_PIO4,
-	.udma_mask	= ATA_UDMA6,
-	.port_ops	= &ahci_imx_ops,
-};
-
-static int imx_sata_init(struct device *dev, void __iomem *mmio)
-{
-	int ret = 0;
-	unsigned int reg_val;
-	struct imx_ahci_priv *imxpriv = dev_get_drvdata(dev->parent);
-
-	ret = imx_sata_clock_enable(dev);
+	ret = ahci_platform_enable_clks(hpriv);
 	if (ret < 0)
-		return ret;
+		goto disable_regulator;
 
-	/*
-	 * Configure the HWINIT bits of the HOST_CAP and HOST_PORTS_IMPL,
-	 * and IP vendor specific register HOST_TIMER1MS.
-	 * Configure CAP_SSS (support stagered spin up).
-	 * Implement the port0.
-	 * Get the ahb clock rate, and configure the TIMER1MS register.
-	 */
-	reg_val = readl(mmio + HOST_CAP);
-	if (!(reg_val & HOST_CAP_SSS)) {
-		reg_val |= HOST_CAP_SSS;
-		writel(reg_val, mmio + HOST_CAP);
-	}
-	reg_val = readl(mmio + HOST_PORTS_IMPL);
-	if (!(reg_val & 0x1)) {
-		reg_val |= 0x1;
-		writel(reg_val, mmio + HOST_PORTS_IMPL);
-	}
-
-	reg_val = clk_get_rate(imxpriv->ahb_clk) / 1000;
-	writel(reg_val, mmio + HOST_TIMER1MS);
-
-	return 0;
-}
-
-static void imx_sata_exit(struct device *dev)
-{
-	imx_sata_clock_disable(dev);
-}
-
-static int imx_ahci_suspend(struct device *dev)
-{
-	struct imx_ahci_priv *imxpriv =  dev_get_drvdata(dev->parent);
-
-	/*
-	 * If no_device is set, The CLKs had been gated off in the
-	 * initialization so don't do it again here.
-	 */
-	if (!imxpriv->no_device)
-		imx_sata_clock_disable(dev);
-
-	return 0;
-}
-
-static int imx_ahci_resume(struct device *dev)
-{
-	struct imx_ahci_priv *imxpriv =  dev_get_drvdata(dev->parent);
-	int ret = 0;
-
-	if (!imxpriv->no_device)
-		ret = imx_sata_clock_enable(dev);
-
-	return ret;
-}
-
-static struct ahci_platform_data imx_sata_pdata = {
-	.init		= imx_sata_init,
-	.exit		= imx_sata_exit,
-	.ata_port_info	= &ahci_imx_port_info,
-	.suspend	= imx_ahci_suspend,
-	.resume		= imx_ahci_resume,
-
-};
-
-static const struct of_device_id imx_ahci_of_match[] = {
-	{ .compatible = "fsl,imx53-ahci", .data = (void *)AHCI_IMX53 },
-	{ .compatible = "fsl,imx6q-ahci", .data = (void *)AHCI_IMX6Q },
-	{},
-};
-MODULE_DEVICE_TABLE(of, imx_ahci_of_match);
-
-static int imx_ahci_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct resource *mem, *irq, res[2];
-	const struct of_device_id *of_id;
-	enum ahci_imx_type type;
-	const struct ahci_platform_data *pdata = NULL;
-	struct imx_ahci_priv *imxpriv;
-	struct device *ahci_dev;
-	struct platform_device *ahci_pdev;
-	int ret;
-
-	of_id = of_match_device(imx_ahci_of_match, dev);
-	if (!of_id)
-		return -EINVAL;
-
-	type = (enum ahci_imx_type)of_id->data;
-	pdata = &imx_sata_pdata;
-
-	imxpriv = devm_kzalloc(dev, sizeof(*imxpriv), GFP_KERNEL);
-	if (!imxpriv) {
-		dev_err(dev, "can't alloc ahci_host_priv\n");
-		return -ENOMEM;
-	}
-
-	ahci_pdev = platform_device_alloc("ahci", -1);
-	if (!ahci_pdev)
-		return -ENODEV;
-
-	ahci_dev = &ahci_pdev->dev;
-	ahci_dev->parent = dev;
-
-	imxpriv->no_device = false;
-	imxpriv->first_time = true;
-	imxpriv->type = type;
-
-	imxpriv->ahb_clk = devm_clk_get(dev, "ahb");
-	if (IS_ERR(imxpriv->ahb_clk)) {
-		dev_err(dev, "can't get ahb clock.\n");
-		ret = PTR_ERR(imxpriv->ahb_clk);
-		goto err_out;
-	}
-
-	if (type == AHCI_IMX53) {
-		imxpriv->sata_gate_clk = devm_clk_get(dev, "sata_gate");
-		if (IS_ERR(imxpriv->sata_gate_clk)) {
-			dev_err(dev, "can't get sata_gate clock.\n");
-			ret = PTR_ERR(imxpriv->sata_gate_clk);
-			goto err_out;
-		}
-	}
-
-	imxpriv->sata_ref_clk = devm_clk_get(dev, "sata_ref");
-	if (IS_ERR(imxpriv->sata_ref_clk)) {
-		dev_err(dev, "can't get sata_ref clock.\n");
-		ret = PTR_ERR(imxpriv->sata_ref_clk);
-		goto err_out;
-	}
-
-	imxpriv->ahci_pdev = ahci_pdev;
-	platform_set_drvdata(pdev, imxpriv);
-
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!mem || !irq) {
-		dev_err(dev, "no mmio/irq resource\n");
-		ret = -ENOMEM;
-		goto err_out;
-	}
-
-	res[0] = *mem;
-	res[1] = *irq;
-
-	ahci_dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	ahci_dev->dma_mask = &ahci_dev->coherent_dma_mask;
-	ahci_dev->of_node = dev->of_node;
-
-	if (type == AHCI_IMX6Q) {
-		imxpriv->gpr = syscon_regmap_lookup_by_compatible(
-							"fsl,imx6q-iomuxc-gpr");
-		if (IS_ERR(imxpriv->gpr)) {
-			dev_err(dev,
-				"failed to find fsl,imx6q-iomux-gpr regmap\n");
-			ret = PTR_ERR(imxpriv->gpr);
-			goto err_out;
-		}
-
+	if (imxpriv->type == AHCI_IMX6Q) {
 		/*
-		 * Set PHY Paremeters, two steps to configure the GPR13,
+		 * set PHY Paremeters, two steps to configure the GPR13,
 		 * one write for rest of parameters, mask of first write
-		 * is 0x07fffffe, and the other one write for setting
-		 * the mpll_clk_en happens in imx_sata_clock_enable().
+		 * is 0x07ffffff, and the other one write for setting
+		 * the mpll_clk_en.
 		 */
 		regmap_update_bits(imxpriv->gpr, IOMUXC_GPR13,
 				   IMX6Q_GPR13_SATA_RX_EQ_VAL_MASK |
@@ -360,42 +98,229 @@
 				   IMX6Q_GPR13_SATA_TX_ATTEN_9_16 |
 				   IMX6Q_GPR13_SATA_TX_BOOST_3_33_DB |
 				   IMX6Q_GPR13_SATA_TX_LVL_1_025_V);
+		regmap_update_bits(imxpriv->gpr, IOMUXC_GPR13,
+				   IMX6Q_GPR13_SATA_MPLL_CLK_EN,
+				   IMX6Q_GPR13_SATA_MPLL_CLK_EN);
 	}
 
-	ret = platform_device_add_resources(ahci_pdev, res, 2);
-	if (ret)
-		goto err_out;
-
-	ret = platform_device_add_data(ahci_pdev, pdata, sizeof(*pdata));
-	if (ret)
-		goto err_out;
-
-	ret = platform_device_add(ahci_pdev);
-	if (ret) {
-err_out:
-		platform_device_put(ahci_pdev);
-		return ret;
-	}
+	usleep_range(1000, 2000);
 
 	return 0;
+
+disable_regulator:
+	if (hpriv->target_pwr)
+		regulator_disable(hpriv->target_pwr);
+
+	return ret;
 }
 
-static int imx_ahci_remove(struct platform_device *pdev)
+static void imx_sata_disable(struct ahci_host_priv *hpriv)
 {
-	struct imx_ahci_priv *imxpriv = platform_get_drvdata(pdev);
-	struct platform_device *ahci_pdev = imxpriv->ahci_pdev;
+	struct imx_ahci_priv *imxpriv = hpriv->plat_data;
 
-	platform_device_unregister(ahci_pdev);
+	if (imxpriv->no_device)
+		return;
+
+	if (imxpriv->type == AHCI_IMX6Q) {
+		regmap_update_bits(imxpriv->gpr, IOMUXC_GPR13,
+				   IMX6Q_GPR13_SATA_MPLL_CLK_EN,
+				   !IMX6Q_GPR13_SATA_MPLL_CLK_EN);
+	}
+
+	ahci_platform_disable_clks(hpriv);
+
+	if (hpriv->target_pwr)
+		regulator_disable(hpriv->target_pwr);
+}
+
+static void ahci_imx_error_handler(struct ata_port *ap)
+{
+	u32 reg_val;
+	struct ata_device *dev;
+	struct ata_host *host = dev_get_drvdata(ap->dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	void __iomem *mmio = hpriv->mmio;
+	struct imx_ahci_priv *imxpriv = hpriv->plat_data;
+
+	ahci_error_handler(ap);
+
+	if (!(imxpriv->first_time) || ahci_imx_hotplug)
+		return;
+
+	imxpriv->first_time = false;
+
+	ata_for_each_dev(dev, &ap->link, ENABLED)
+		return;
+	/*
+	 * Disable link to save power.  An imx ahci port can't be recovered
+	 * without full reset once the pddq mode is enabled making it
+	 * impossible to use as part of libata LPM.
+	 */
+	reg_val = readl(mmio + PORT_PHY_CTL);
+	writel(reg_val | PORT_PHY_CTL_PDDQ_LOC, mmio + PORT_PHY_CTL);
+	imx_sata_disable(hpriv);
+	imxpriv->no_device = true;
+}
+
+static int ahci_imx_softreset(struct ata_link *link, unsigned int *class,
+		       unsigned long deadline)
+{
+	struct ata_port *ap = link->ap;
+	struct ata_host *host = dev_get_drvdata(ap->dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	struct imx_ahci_priv *imxpriv = hpriv->plat_data;
+	int ret = -EIO;
+
+	if (imxpriv->type == AHCI_IMX53)
+		ret = ahci_pmp_retry_srst_ops.softreset(link, class, deadline);
+	else if (imxpriv->type == AHCI_IMX6Q)
+		ret = ahci_ops.softreset(link, class, deadline);
+
+	return ret;
+}
+
+static struct ata_port_operations ahci_imx_ops = {
+	.inherits	= &ahci_ops,
+	.host_stop	= ahci_imx_host_stop,
+	.error_handler	= ahci_imx_error_handler,
+	.softreset	= ahci_imx_softreset,
+};
+
+static const struct ata_port_info ahci_imx_port_info = {
+	.flags		= AHCI_FLAG_COMMON,
+	.pio_mask	= ATA_PIO4,
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &ahci_imx_ops,
+};
+
+static const struct of_device_id imx_ahci_of_match[] = {
+	{ .compatible = "fsl,imx53-ahci", .data = (void *)AHCI_IMX53 },
+	{ .compatible = "fsl,imx6q-ahci", .data = (void *)AHCI_IMX6Q },
+	{},
+};
+MODULE_DEVICE_TABLE(of, imx_ahci_of_match);
+
+static int imx_ahci_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct of_device_id *of_id;
+	struct ahci_host_priv *hpriv;
+	struct imx_ahci_priv *imxpriv;
+	unsigned int reg_val;
+	int ret;
+
+	of_id = of_match_device(imx_ahci_of_match, dev);
+	if (!of_id)
+		return -EINVAL;
+
+	imxpriv = devm_kzalloc(dev, sizeof(*imxpriv), GFP_KERNEL);
+	if (!imxpriv)
+		return -ENOMEM;
+
+	imxpriv->no_device = false;
+	imxpriv->first_time = true;
+	imxpriv->type = (enum ahci_imx_type)of_id->data;
+	imxpriv->ahb_clk = devm_clk_get(dev, "ahb");
+	if (IS_ERR(imxpriv->ahb_clk)) {
+		dev_err(dev, "can't get ahb clock.\n");
+		return PTR_ERR(imxpriv->ahb_clk);
+	}
+
+	if (imxpriv->type == AHCI_IMX6Q) {
+		imxpriv->gpr = syscon_regmap_lookup_by_compatible(
+							"fsl,imx6q-iomuxc-gpr");
+		if (IS_ERR(imxpriv->gpr)) {
+			dev_err(dev,
+				"failed to find fsl,imx6q-iomux-gpr regmap\n");
+			return PTR_ERR(imxpriv->gpr);
+		}
+	}
+
+	hpriv = ahci_platform_get_resources(pdev);
+	if (IS_ERR(hpriv))
+		return PTR_ERR(hpriv);
+
+	hpriv->plat_data = imxpriv;
+
+	ret = imx_sata_enable(hpriv);
+	if (ret)
+		return ret;
+
+	/*
+	 * Configure the HWINIT bits of the HOST_CAP and HOST_PORTS_IMPL,
+	 * and IP vendor specific register HOST_TIMER1MS.
+	 * Configure CAP_SSS (support stagered spin up).
+	 * Implement the port0.
+	 * Get the ahb clock rate, and configure the TIMER1MS register.
+	 */
+	reg_val = readl(hpriv->mmio + HOST_CAP);
+	if (!(reg_val & HOST_CAP_SSS)) {
+		reg_val |= HOST_CAP_SSS;
+		writel(reg_val, hpriv->mmio + HOST_CAP);
+	}
+	reg_val = readl(hpriv->mmio + HOST_PORTS_IMPL);
+	if (!(reg_val & 0x1)) {
+		reg_val |= 0x1;
+		writel(reg_val, hpriv->mmio + HOST_PORTS_IMPL);
+	}
+
+	reg_val = clk_get_rate(imxpriv->ahb_clk) / 1000;
+	writel(reg_val, hpriv->mmio + HOST_TIMER1MS);
+
+	ret = ahci_platform_init_host(pdev, hpriv, &ahci_imx_port_info, 0, 0);
+	if (ret)
+		imx_sata_disable(hpriv);
+
+	return ret;
+}
+
+static void ahci_imx_host_stop(struct ata_host *host)
+{
+	struct ahci_host_priv *hpriv = host->private_data;
+
+	imx_sata_disable(hpriv);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int imx_ahci_suspend(struct device *dev)
+{
+	struct ata_host *host = dev_get_drvdata(dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	int ret;
+
+	ret = ahci_platform_suspend_host(dev);
+	if (ret)
+		return ret;
+
+	imx_sata_disable(hpriv);
+
 	return 0;
 }
 
+static int imx_ahci_resume(struct device *dev)
+{
+	struct ata_host *host = dev_get_drvdata(dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	int ret;
+
+	ret = imx_sata_enable(hpriv);
+	if (ret)
+		return ret;
+
+	return ahci_platform_resume_host(dev);
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(ahci_imx_pm_ops, imx_ahci_suspend, imx_ahci_resume);
+
 static struct platform_driver imx_ahci_driver = {
 	.probe = imx_ahci_probe,
-	.remove = imx_ahci_remove,
+	.remove = ata_platform_remove_one,
 	.driver = {
 		.name = "ahci-imx",
 		.owner = THIS_MODULE,
 		.of_match_table = imx_ahci_of_match,
+		.pm = &ahci_imx_pm_ops,
 	},
 };
 module_platform_driver(imx_ahci_driver);
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index 4b231ba..ef67e79 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -12,135 +12,36 @@
  * any later version.
  */
 
-#include <linux/clk.h>
 #include <linux/kernel.h>
-#include <linux/gfp.h>
 #include <linux/module.h>
 #include <linux/pm.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/libata.h>
 #include <linux/ahci_platform.h>
 #include "ahci.h"
 
-static void ahci_host_stop(struct ata_host *host);
-
-enum ahci_type {
-	AHCI,		/* standard platform ahci */
-	IMX53_AHCI,	/* ahci on i.mx53 */
-	STRICT_AHCI,	/* delayed DMA engine start */
-};
-
-static struct platform_device_id ahci_devtype[] = {
-	{
-		.name = "ahci",
-		.driver_data = AHCI,
-	}, {
-		.name = "imx53-ahci",
-		.driver_data = IMX53_AHCI,
-	}, {
-		.name = "strict-ahci",
-		.driver_data = STRICT_AHCI,
-	}, {
-		/* sentinel */
-	}
-};
-MODULE_DEVICE_TABLE(platform, ahci_devtype);
-
-struct ata_port_operations ahci_platform_ops = {
-	.inherits	= &ahci_ops,
-	.host_stop	= ahci_host_stop,
-};
-EXPORT_SYMBOL_GPL(ahci_platform_ops);
-
-static struct ata_port_operations ahci_platform_retry_srst_ops = {
-	.inherits	= &ahci_pmp_retry_srst_ops,
-	.host_stop	= ahci_host_stop,
-};
-
-static const struct ata_port_info ahci_port_info[] = {
-	/* by features */
-	[AHCI] = {
-		.flags		= AHCI_FLAG_COMMON,
-		.pio_mask	= ATA_PIO4,
-		.udma_mask	= ATA_UDMA6,
-		.port_ops	= &ahci_platform_ops,
-	},
-	[IMX53_AHCI] = {
-		.flags		= AHCI_FLAG_COMMON,
-		.pio_mask	= ATA_PIO4,
-		.udma_mask	= ATA_UDMA6,
-		.port_ops	= &ahci_platform_retry_srst_ops,
-	},
-	[STRICT_AHCI] = {
-		AHCI_HFLAGS	(AHCI_HFLAG_DELAY_ENGINE),
-		.flags		= AHCI_FLAG_COMMON,
-		.pio_mask	= ATA_PIO4,
-		.udma_mask	= ATA_UDMA6,
-		.port_ops	= &ahci_platform_ops,
-	},
-};
-
-static struct scsi_host_template ahci_platform_sht = {
-	AHCI_SHT("ahci_platform"),
+static const struct ata_port_info ahci_port_info = {
+	.flags		= AHCI_FLAG_COMMON,
+	.pio_mask	= ATA_PIO4,
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &ahci_platform_ops,
 };
 
 static int ahci_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct ahci_platform_data *pdata = dev_get_platdata(dev);
-	const struct platform_device_id *id = platform_get_device_id(pdev);
-	struct ata_port_info pi = ahci_port_info[id ? id->driver_data : 0];
-	const struct ata_port_info *ppi[] = { &pi, NULL };
 	struct ahci_host_priv *hpriv;
-	struct ata_host *host;
-	struct resource *mem;
-	int irq;
-	int n_ports;
-	int i;
 	int rc;
 
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!mem) {
-		dev_err(dev, "no mmio space\n");
-		return -EINVAL;
-	}
+	hpriv = ahci_platform_get_resources(pdev);
+	if (IS_ERR(hpriv))
+		return PTR_ERR(hpriv);
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq <= 0) {
-		dev_err(dev, "no irq\n");
-		return -EINVAL;
-	}
-
-	if (pdata && pdata->ata_port_info)
-		pi = *pdata->ata_port_info;
-
-	hpriv = devm_kzalloc(dev, sizeof(*hpriv), GFP_KERNEL);
-	if (!hpriv) {
-		dev_err(dev, "can't alloc ahci_host_priv\n");
-		return -ENOMEM;
-	}
-
-	hpriv->flags |= (unsigned long)pi.private_data;
-
-	hpriv->mmio = devm_ioremap(dev, mem->start, resource_size(mem));
-	if (!hpriv->mmio) {
-		dev_err(dev, "can't map %pR\n", mem);
-		return -ENOMEM;
-	}
-
-	hpriv->clk = clk_get(dev, NULL);
-	if (IS_ERR(hpriv->clk)) {
-		dev_err(dev, "can't get clock\n");
-	} else {
-		rc = clk_prepare_enable(hpriv->clk);
-		if (rc) {
-			dev_err(dev, "clock prepare enable failed");
-			goto free_clk;
-		}
-	}
+	rc = ahci_platform_enable_resources(hpriv);
+	if (rc)
+		return rc;
 
 	/*
 	 * Some platforms might need to prepare for mmio region access,
@@ -151,69 +52,10 @@
 	if (pdata && pdata->init) {
 		rc = pdata->init(dev, hpriv->mmio);
 		if (rc)
-			goto disable_unprepare_clk;
+			goto disable_resources;
 	}
 
-	ahci_save_initial_config(dev, hpriv,
-		pdata ? pdata->force_port_map : 0,
-		pdata ? pdata->mask_port_map  : 0);
-
-	/* prepare host */
-	if (hpriv->cap & HOST_CAP_NCQ)
-		pi.flags |= ATA_FLAG_NCQ;
-
-	if (hpriv->cap & HOST_CAP_PMP)
-		pi.flags |= ATA_FLAG_PMP;
-
-	ahci_set_em_messages(hpriv, &pi);
-
-	/* CAP.NP sometimes indicate the index of the last enabled
-	 * port, at other times, that of the last possible port, so
-	 * determining the maximum port number requires looking at
-	 * both CAP.NP and port_map.
-	 */
-	n_ports = max(ahci_nr_ports(hpriv->cap), fls(hpriv->port_map));
-
-	host = ata_host_alloc_pinfo(dev, ppi, n_ports);
-	if (!host) {
-		rc = -ENOMEM;
-		goto pdata_exit;
-	}
-
-	host->private_data = hpriv;
-
-	if (!(hpriv->cap & HOST_CAP_SSS) || ahci_ignore_sss)
-		host->flags |= ATA_HOST_PARALLEL_SCAN;
-	else
-		dev_info(dev, "SSS flag set, parallel bus scan disabled\n");
-
-	if (pi.flags & ATA_FLAG_EM)
-		ahci_reset_em(host);
-
-	for (i = 0; i < host->n_ports; i++) {
-		struct ata_port *ap = host->ports[i];
-
-		ata_port_desc(ap, "mmio %pR", mem);
-		ata_port_desc(ap, "port 0x%x", 0x100 + ap->port_no * 0x80);
-
-		/* set enclosure management message type */
-		if (ap->flags & ATA_FLAG_EM)
-			ap->em_message_type = hpriv->em_msg_type;
-
-		/* disabled/not-implemented port */
-		if (!(hpriv->port_map & (1 << i)))
-			ap->ops = &ata_dummy_port_ops;
-	}
-
-	rc = ahci_reset_controller(host);
-	if (rc)
-		goto pdata_exit;
-
-	ahci_init_controller(host);
-	ahci_print_info(host, "platform");
-
-	rc = ata_host_activate(host, irq, ahci_interrupt, IRQF_SHARED,
-			       &ahci_platform_sht);
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info, 0, 0);
 	if (rc)
 		goto pdata_exit;
 
@@ -221,115 +63,19 @@
 pdata_exit:
 	if (pdata && pdata->exit)
 		pdata->exit(dev);
-disable_unprepare_clk:
-	if (!IS_ERR(hpriv->clk))
-		clk_disable_unprepare(hpriv->clk);
-free_clk:
-	if (!IS_ERR(hpriv->clk))
-		clk_put(hpriv->clk);
+disable_resources:
+	ahci_platform_disable_resources(hpriv);
 	return rc;
 }
 
-static void ahci_host_stop(struct ata_host *host)
-{
-	struct device *dev = host->dev;
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
-	struct ahci_host_priv *hpriv = host->private_data;
-
-	if (pdata && pdata->exit)
-		pdata->exit(dev);
-
-	if (!IS_ERR(hpriv->clk)) {
-		clk_disable_unprepare(hpriv->clk);
-		clk_put(hpriv->clk);
-	}
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int ahci_suspend(struct device *dev)
-{
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
-	struct ata_host *host = dev_get_drvdata(dev);
-	struct ahci_host_priv *hpriv = host->private_data;
-	void __iomem *mmio = hpriv->mmio;
-	u32 ctl;
-	int rc;
-
-	if (hpriv->flags & AHCI_HFLAG_NO_SUSPEND) {
-		dev_err(dev, "firmware update required for suspend/resume\n");
-		return -EIO;
-	}
-
-	/*
-	 * AHCI spec rev1.1 section 8.3.3:
-	 * Software must disable interrupts prior to requesting a
-	 * transition of the HBA to D3 state.
-	 */
-	ctl = readl(mmio + HOST_CTL);
-	ctl &= ~HOST_IRQ_EN;
-	writel(ctl, mmio + HOST_CTL);
-	readl(mmio + HOST_CTL); /* flush */
-
-	rc = ata_host_suspend(host, PMSG_SUSPEND);
-	if (rc)
-		return rc;
-
-	if (pdata && pdata->suspend)
-		return pdata->suspend(dev);
-
-	if (!IS_ERR(hpriv->clk))
-		clk_disable_unprepare(hpriv->clk);
-
-	return 0;
-}
-
-static int ahci_resume(struct device *dev)
-{
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
-	struct ata_host *host = dev_get_drvdata(dev);
-	struct ahci_host_priv *hpriv = host->private_data;
-	int rc;
-
-	if (!IS_ERR(hpriv->clk)) {
-		rc = clk_prepare_enable(hpriv->clk);
-		if (rc) {
-			dev_err(dev, "clock prepare enable failed");
-			return rc;
-		}
-	}
-
-	if (pdata && pdata->resume) {
-		rc = pdata->resume(dev);
-		if (rc)
-			goto disable_unprepare_clk;
-	}
-
-	if (dev->power.power_state.event == PM_EVENT_SUSPEND) {
-		rc = ahci_reset_controller(host);
-		if (rc)
-			goto disable_unprepare_clk;
-
-		ahci_init_controller(host);
-	}
-
-	ata_host_resume(host);
-
-	return 0;
-
-disable_unprepare_clk:
-	if (!IS_ERR(hpriv->clk))
-		clk_disable_unprepare(hpriv->clk);
-
-	return rc;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(ahci_pm_ops, ahci_suspend, ahci_resume);
+static SIMPLE_DEV_PM_OPS(ahci_pm_ops, ahci_platform_suspend,
+			 ahci_platform_resume);
 
 static const struct of_device_id ahci_of_match[] = {
 	{ .compatible = "snps,spear-ahci", },
 	{ .compatible = "snps,exynos5440-ahci", },
 	{ .compatible = "ibm,476gtr-ahci", },
+	{ .compatible = "snps,dwc-ahci", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, ahci_of_match);
@@ -343,7 +89,6 @@
 		.of_match_table = ahci_of_match,
 		.pm = &ahci_pm_ops,
 	},
-	.id_table	= ahci_devtype,
 };
 module_platform_driver(ahci_driver);
 
diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c
new file mode 100644
index 0000000..6332222
--- /dev/null
+++ b/drivers/ata/ahci_st.c
@@ -0,0 +1,245 @@
+/*
+ * Copyright (C) 2012 STMicroelectronics Limited
+ *
+ * Authors: Francesco Virlinzi <francesco.virlinzi@st.com>
+ *	    Alexandre Torgue <alexandre.torgue@st.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/ahci_platform.h>
+#include <linux/libata.h>
+#include <linux/reset.h>
+#include <linux/io.h>
+#include <linux/dma-mapping.h>
+
+#include "ahci.h"
+
+#define ST_AHCI_OOBR			0xbc
+#define ST_AHCI_OOBR_WE			BIT(31)
+#define ST_AHCI_OOBR_CWMIN_SHIFT	24
+#define ST_AHCI_OOBR_CWMAX_SHIFT	16
+#define ST_AHCI_OOBR_CIMIN_SHIFT	8
+#define ST_AHCI_OOBR_CIMAX_SHIFT	0
+
+struct st_ahci_drv_data {
+	struct platform_device *ahci;
+	struct reset_control *pwr;
+	struct reset_control *sw_rst;
+	struct reset_control *pwr_rst;
+	struct ahci_host_priv *hpriv;
+};
+
+static void st_ahci_configure_oob(void __iomem *mmio)
+{
+	unsigned long old_val, new_val;
+
+	new_val = (0x02 << ST_AHCI_OOBR_CWMIN_SHIFT) |
+		  (0x04 << ST_AHCI_OOBR_CWMAX_SHIFT) |
+		  (0x08 << ST_AHCI_OOBR_CIMIN_SHIFT) |
+		  (0x0C << ST_AHCI_OOBR_CIMAX_SHIFT);
+
+	old_val = readl(mmio + ST_AHCI_OOBR);
+	writel(old_val | ST_AHCI_OOBR_WE, mmio + ST_AHCI_OOBR);
+	writel(new_val | ST_AHCI_OOBR_WE, mmio + ST_AHCI_OOBR);
+	writel(new_val, mmio + ST_AHCI_OOBR);
+}
+
+static int st_ahci_deassert_resets(struct device *dev)
+{
+	struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
+	int err;
+
+	if (drv_data->pwr) {
+		err = reset_control_deassert(drv_data->pwr);
+		if (err) {
+			dev_err(dev, "unable to bring out of pwrdwn\n");
+			return err;
+		}
+	}
+
+	st_ahci_configure_oob(drv_data->hpriv->mmio);
+
+	if (drv_data->sw_rst) {
+		err = reset_control_deassert(drv_data->sw_rst);
+		if (err) {
+			dev_err(dev, "unable to bring out of sw-rst\n");
+			return err;
+		}
+	}
+
+	if (drv_data->pwr_rst) {
+		err = reset_control_deassert(drv_data->pwr_rst);
+		if (err) {
+			dev_err(dev, "unable to bring out of pwr-rst\n");
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void st_ahci_host_stop(struct ata_host *host)
+{
+	struct ahci_host_priv *hpriv = host->private_data;
+	struct device *dev = host->dev;
+	struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
+	int err;
+
+	if (drv_data->pwr) {
+		err = reset_control_assert(drv_data->pwr);
+		if (err)
+			dev_err(dev, "unable to pwrdwn\n");
+	}
+
+	ahci_platform_disable_resources(hpriv);
+}
+
+static int st_ahci_probe_resets(struct platform_device *pdev)
+{
+	struct st_ahci_drv_data *drv_data = platform_get_drvdata(pdev);
+
+	drv_data->pwr = devm_reset_control_get(&pdev->dev, "pwr-dwn");
+	if (IS_ERR(drv_data->pwr)) {
+		dev_info(&pdev->dev, "power reset control not defined\n");
+		drv_data->pwr = NULL;
+	}
+
+	drv_data->sw_rst = devm_reset_control_get(&pdev->dev, "sw-rst");
+	if (IS_ERR(drv_data->sw_rst)) {
+		dev_info(&pdev->dev, "soft reset control not defined\n");
+		drv_data->sw_rst = NULL;
+	}
+
+	drv_data->pwr_rst = devm_reset_control_get(&pdev->dev, "pwr-rst");
+	if (IS_ERR(drv_data->pwr_rst)) {
+		dev_dbg(&pdev->dev, "power soft reset control not defined\n");
+		drv_data->pwr_rst = NULL;
+	}
+
+	return st_ahci_deassert_resets(&pdev->dev);
+}
+
+static struct ata_port_operations st_ahci_port_ops = {
+	.inherits	= &ahci_platform_ops,
+	.host_stop	= st_ahci_host_stop,
+};
+
+static const struct ata_port_info st_ahci_port_info = {
+	.flags          = AHCI_FLAG_COMMON,
+	.pio_mask       = ATA_PIO4,
+	.udma_mask      = ATA_UDMA6,
+	.port_ops       = &st_ahci_port_ops,
+};
+
+static int st_ahci_probe(struct platform_device *pdev)
+{
+	struct st_ahci_drv_data *drv_data;
+	struct ahci_host_priv *hpriv;
+	int err;
+
+	drv_data = devm_kzalloc(&pdev->dev, sizeof(*drv_data), GFP_KERNEL);
+	if (!drv_data)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, drv_data);
+
+	hpriv = ahci_platform_get_resources(pdev);
+	if (IS_ERR(hpriv))
+		return PTR_ERR(hpriv);
+
+	drv_data->hpriv = hpriv;
+
+	err = st_ahci_probe_resets(pdev);
+	if (err)
+		return err;
+
+	err = ahci_platform_enable_resources(hpriv);
+	if (err)
+		return err;
+
+	err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info, 0, 0);
+	if (err) {
+		ahci_platform_disable_resources(hpriv);
+		return err;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int st_ahci_suspend(struct device *dev)
+{
+	struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
+	struct ahci_host_priv *hpriv = drv_data->hpriv;
+	int err;
+
+	err = ahci_platform_suspend_host(dev);
+	if (err)
+		return err;
+
+	if (drv_data->pwr) {
+		err = reset_control_assert(drv_data->pwr);
+		if (err) {
+			dev_err(dev, "unable to pwrdwn");
+			return err;
+		}
+	}
+
+	ahci_platform_disable_resources(hpriv);
+
+	return 0;
+}
+
+static int st_ahci_resume(struct device *dev)
+{
+	struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
+	struct ahci_host_priv *hpriv = drv_data->hpriv;
+	int err;
+
+	err = ahci_platform_enable_resources(hpriv);
+	if (err)
+		return err;
+
+	err = st_ahci_deassert_resets(dev);
+	if (err) {
+		ahci_platform_disable_resources(hpriv);
+		return err;
+	}
+
+	return ahci_platform_resume_host(dev);
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(st_ahci_pm_ops, st_ahci_suspend, st_ahci_resume);
+
+static struct of_device_id st_ahci_match[] = {
+	{ .compatible = "st,ahci", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, st_ahci_match);
+
+static struct platform_driver st_ahci_driver = {
+	.driver = {
+		.name = "st_ahci",
+		.owner = THIS_MODULE,
+		.pm = &st_ahci_pm_ops,
+		.of_match_table = of_match_ptr(st_ahci_match),
+	},
+	.probe = st_ahci_probe,
+	.remove = ata_platform_remove_one,
+};
+module_platform_driver(st_ahci_driver);
+
+MODULE_AUTHOR("Alexandre Torgue <alexandre.torgue@st.com>");
+MODULE_AUTHOR("Francesco Virlinzi <francesco.virlinzi@st.com>");
+MODULE_DESCRIPTION("STMicroelectronics SATA AHCI Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/ata/ahci_sunxi.c b/drivers/ata/ahci_sunxi.c
new file mode 100644
index 0000000..42d3f64
--- /dev/null
+++ b/drivers/ata/ahci_sunxi.c
@@ -0,0 +1,249 @@
+/*
+ * Allwinner sunxi AHCI SATA platform driver
+ * Copyright 2013 Olliver Schinagl <oliver@schinagl.nl>
+ * Copyright 2014 Hans de Goede <hdegoede@redhat.com>
+ *
+ * based on the AHCI SATA platform driver by Jeff Garzik and Anton Vorontsov
+ * Based on code from Allwinner Technology Co., Ltd. <www.allwinnertech.com>,
+ * Daniel Wang <danielwang@allwinnertech.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/ahci_platform.h>
+#include <linux/clk.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include "ahci.h"
+
+#define AHCI_BISTAFR	0x00a0
+#define AHCI_BISTCR	0x00a4
+#define AHCI_BISTFCTR	0x00a8
+#define AHCI_BISTSR	0x00ac
+#define AHCI_BISTDECR	0x00b0
+#define AHCI_DIAGNR0	0x00b4
+#define AHCI_DIAGNR1	0x00b8
+#define AHCI_OOBR	0x00bc
+#define AHCI_PHYCS0R	0x00c0
+#define AHCI_PHYCS1R	0x00c4
+#define AHCI_PHYCS2R	0x00c8
+#define AHCI_TIMER1MS	0x00e0
+#define AHCI_GPARAM1R	0x00e8
+#define AHCI_GPARAM2R	0x00ec
+#define AHCI_PPARAMR	0x00f0
+#define AHCI_TESTR	0x00f4
+#define AHCI_VERSIONR	0x00f8
+#define AHCI_IDR	0x00fc
+#define AHCI_RWCR	0x00fc
+#define AHCI_P0DMACR	0x0170
+#define AHCI_P0PHYCR	0x0178
+#define AHCI_P0PHYSR	0x017c
+
+static void sunxi_clrbits(void __iomem *reg, u32 clr_val)
+{
+	u32 reg_val;
+
+	reg_val = readl(reg);
+	reg_val &= ~(clr_val);
+	writel(reg_val, reg);
+}
+
+static void sunxi_setbits(void __iomem *reg, u32 set_val)
+{
+	u32 reg_val;
+
+	reg_val = readl(reg);
+	reg_val |= set_val;
+	writel(reg_val, reg);
+}
+
+static void sunxi_clrsetbits(void __iomem *reg, u32 clr_val, u32 set_val)
+{
+	u32 reg_val;
+
+	reg_val = readl(reg);
+	reg_val &= ~(clr_val);
+	reg_val |= set_val;
+	writel(reg_val, reg);
+}
+
+static u32 sunxi_getbits(void __iomem *reg, u8 mask, u8 shift)
+{
+	return (readl(reg) >> shift) & mask;
+}
+
+static int ahci_sunxi_phy_init(struct device *dev, void __iomem *reg_base)
+{
+	u32 reg_val;
+	int timeout;
+
+	/* This magic is from the original code */
+	writel(0, reg_base + AHCI_RWCR);
+	msleep(5);
+
+	sunxi_setbits(reg_base + AHCI_PHYCS1R, BIT(19));
+	sunxi_clrsetbits(reg_base + AHCI_PHYCS0R,
+			 (0x7 << 24),
+			 (0x5 << 24) | BIT(23) | BIT(18));
+	sunxi_clrsetbits(reg_base + AHCI_PHYCS1R,
+			 (0x3 << 16) | (0x1f << 8) | (0x3 << 6),
+			 (0x2 << 16) | (0x6 << 8) | (0x2 << 6));
+	sunxi_setbits(reg_base + AHCI_PHYCS1R, BIT(28) | BIT(15));
+	sunxi_clrbits(reg_base + AHCI_PHYCS1R, BIT(19));
+	sunxi_clrsetbits(reg_base + AHCI_PHYCS0R,
+			 (0x7 << 20), (0x3 << 20));
+	sunxi_clrsetbits(reg_base + AHCI_PHYCS2R,
+			 (0x1f << 5), (0x19 << 5));
+	msleep(5);
+
+	sunxi_setbits(reg_base + AHCI_PHYCS0R, (0x1 << 19));
+
+	timeout = 250; /* Power up takes aprox 50 us */
+	do {
+		reg_val = sunxi_getbits(reg_base + AHCI_PHYCS0R, 0x7, 28);
+		if (reg_val == 0x02)
+			break;
+
+		if (--timeout == 0) {
+			dev_err(dev, "PHY power up failed.\n");
+			return -EIO;
+		}
+		udelay(1);
+	} while (1);
+
+	sunxi_setbits(reg_base + AHCI_PHYCS2R, (0x1 << 24));
+
+	timeout = 100; /* Calibration takes aprox 10 us */
+	do {
+		reg_val = sunxi_getbits(reg_base + AHCI_PHYCS2R, 0x1, 24);
+		if (reg_val == 0x00)
+			break;
+
+		if (--timeout == 0) {
+			dev_err(dev, "PHY calibration failed.\n");
+			return -EIO;
+		}
+		udelay(1);
+	} while (1);
+
+	msleep(15);
+
+	writel(0x7, reg_base + AHCI_RWCR);
+
+	return 0;
+}
+
+static void ahci_sunxi_start_engine(struct ata_port *ap)
+{
+	void __iomem *port_mmio = ahci_port_base(ap);
+	struct ahci_host_priv *hpriv = ap->host->private_data;
+
+	/* Setup DMA before DMA start */
+	sunxi_clrsetbits(hpriv->mmio + AHCI_P0DMACR, 0x0000ff00, 0x00004400);
+
+	/* Start DMA */
+	sunxi_setbits(port_mmio + PORT_CMD, PORT_CMD_START);
+}
+
+static const struct ata_port_info ahci_sunxi_port_info = {
+	AHCI_HFLAGS(AHCI_HFLAG_32BIT_ONLY | AHCI_HFLAG_NO_MSI |
+			  AHCI_HFLAG_NO_PMP | AHCI_HFLAG_YES_NCQ),
+	.flags		= AHCI_FLAG_COMMON | ATA_FLAG_NCQ,
+	.pio_mask	= ATA_PIO4,
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &ahci_platform_ops,
+};
+
+static int ahci_sunxi_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ahci_host_priv *hpriv;
+	int rc;
+
+	hpriv = ahci_platform_get_resources(pdev);
+	if (IS_ERR(hpriv))
+		return PTR_ERR(hpriv);
+
+	hpriv->start_engine = ahci_sunxi_start_engine;
+
+	rc = ahci_platform_enable_resources(hpriv);
+	if (rc)
+		return rc;
+
+	rc = ahci_sunxi_phy_init(dev, hpriv->mmio);
+	if (rc)
+		goto disable_resources;
+
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_sunxi_port_info, 0, 0);
+	if (rc)
+		goto disable_resources;
+
+	return 0;
+
+disable_resources:
+	ahci_platform_disable_resources(hpriv);
+	return rc;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int ahci_sunxi_resume(struct device *dev)
+{
+	struct ata_host *host = dev_get_drvdata(dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	int rc;
+
+	rc = ahci_platform_enable_resources(hpriv);
+	if (rc)
+		return rc;
+
+	rc = ahci_sunxi_phy_init(dev, hpriv->mmio);
+	if (rc)
+		goto disable_resources;
+
+	rc = ahci_platform_resume_host(dev);
+	if (rc)
+		goto disable_resources;
+
+	return 0;
+
+disable_resources:
+	ahci_platform_disable_resources(hpriv);
+	return rc;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(ahci_sunxi_pm_ops, ahci_platform_suspend,
+			 ahci_sunxi_resume);
+
+static const struct of_device_id ahci_sunxi_of_match[] = {
+	{ .compatible = "allwinner,sun4i-a10-ahci", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ahci_sunxi_of_match);
+
+static struct platform_driver ahci_sunxi_driver = {
+	.probe = ahci_sunxi_probe,
+	.remove = ata_platform_remove_one,
+	.driver = {
+		.name = "ahci-sunxi",
+		.owner = THIS_MODULE,
+		.of_match_table = ahci_sunxi_of_match,
+		.pm = &ahci_sunxi_pm_ops,
+	},
+};
+module_platform_driver(ahci_sunxi_driver);
+
+MODULE_DESCRIPTION("Allwinner sunxi AHCI SATA driver");
+MODULE_AUTHOR("Olliver Schinagl <oliver@schinagl.nl>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
new file mode 100644
index 0000000..77c89bf
--- /dev/null
+++ b/drivers/ata/ahci_xgene.c
@@ -0,0 +1,486 @@
+/*
+ * AppliedMicro X-Gene SoC SATA Host Controller Driver
+ *
+ * Copyright (c) 2014, Applied Micro Circuits Corporation
+ * Author: Loc Ho <lho@apm.com>
+ *         Tuan Phan <tphan@apm.com>
+ *         Suman Tripathi <stripathi@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * NOTE: PM support is not currently available.
+ *
+ */
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/ahci_platform.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/phy/phy.h>
+#include "ahci.h"
+
+/* Max # of disk per a controller */
+#define MAX_AHCI_CHN_PERCTR		2
+
+/* MUX CSR */
+#define SATA_ENET_CONFIG_REG		0x00000000
+#define  CFG_SATA_ENET_SELECT_MASK	0x00000001
+
+/* SATA core host controller CSR */
+#define SLVRDERRATTRIBUTES		0x00000000
+#define SLVWRERRATTRIBUTES		0x00000004
+#define MSTRDERRATTRIBUTES		0x00000008
+#define MSTWRERRATTRIBUTES		0x0000000c
+#define BUSCTLREG			0x00000014
+#define IOFMSTRWAUX			0x00000018
+#define INTSTATUSMASK			0x0000002c
+#define ERRINTSTATUS			0x00000030
+#define ERRINTSTATUSMASK		0x00000034
+
+/* SATA host AHCI CSR */
+#define PORTCFG				0x000000a4
+#define  PORTADDR_SET(dst, src) \
+		(((dst) & ~0x0000003f) | (((u32)(src)) & 0x0000003f))
+#define PORTPHY1CFG		0x000000a8
+#define PORTPHY1CFG_FRCPHYRDY_SET(dst, src) \
+		(((dst) & ~0x00100000) | (((u32)(src) << 0x14) & 0x00100000))
+#define PORTPHY2CFG			0x000000ac
+#define PORTPHY3CFG			0x000000b0
+#define PORTPHY4CFG			0x000000b4
+#define PORTPHY5CFG			0x000000b8
+#define SCTL0				0x0000012C
+#define PORTPHY5CFG_RTCHG_SET(dst, src) \
+		(((dst) & ~0xfff00000) | (((u32)(src) << 0x14) & 0xfff00000))
+#define PORTAXICFG_EN_CONTEXT_SET(dst, src) \
+		(((dst) & ~0x01000000) | (((u32)(src) << 0x18) & 0x01000000))
+#define PORTAXICFG			0x000000bc
+#define PORTAXICFG_OUTTRANS_SET(dst, src) \
+		(((dst) & ~0x00f00000) | (((u32)(src) << 0x14) & 0x00f00000))
+
+/* SATA host controller AXI CSR */
+#define INT_SLV_TMOMASK			0x00000010
+
+/* SATA diagnostic CSR */
+#define CFG_MEM_RAM_SHUTDOWN		0x00000070
+#define BLOCK_MEM_RDY			0x00000074
+
+struct xgene_ahci_context {
+	struct ahci_host_priv *hpriv;
+	struct device *dev;
+	void __iomem *csr_core;		/* Core CSR address of IP */
+	void __iomem *csr_diag;		/* Diag CSR address of IP */
+	void __iomem *csr_axi;		/* AXI CSR address of IP */
+	void __iomem *csr_mux;		/* MUX CSR address of IP */
+};
+
+static int xgene_ahci_init_memram(struct xgene_ahci_context *ctx)
+{
+	dev_dbg(ctx->dev, "Release memory from shutdown\n");
+	writel(0x0, ctx->csr_diag + CFG_MEM_RAM_SHUTDOWN);
+	readl(ctx->csr_diag + CFG_MEM_RAM_SHUTDOWN); /* Force a barrier */
+	msleep(1);	/* reset may take up to 1ms */
+	if (readl(ctx->csr_diag + BLOCK_MEM_RDY) != 0xFFFFFFFF) {
+		dev_err(ctx->dev, "failed to release memory from shutdown\n");
+		return -ENODEV;
+	}
+	return 0;
+}
+
+/**
+ * xgene_ahci_read_id - Read ID data from the specified device
+ * @dev: device
+ * @tf: proposed taskfile
+ * @id: data buffer
+ *
+ * This custom read ID function is required due to the fact that the HW
+ * does not support DEVSLP and the controller state machine may get stuck
+ * after processing the ID query command.
+ */
+static unsigned int xgene_ahci_read_id(struct ata_device *dev,
+				       struct ata_taskfile *tf, u16 *id)
+{
+	u32 err_mask;
+	void __iomem *port_mmio = ahci_port_base(dev->link->ap);
+
+	err_mask = ata_do_dev_read_id(dev, tf, id);
+	if (err_mask)
+		return err_mask;
+
+	/*
+	 * Mask reserved area. Word78 spec of Link Power Management
+	 * bit15-8: reserved
+	 * bit7: NCQ autosence
+	 * bit6: Software settings preservation supported
+	 * bit5: reserved
+	 * bit4: In-order sata delivery supported
+	 * bit3: DIPM requests supported
+	 * bit2: DMA Setup FIS Auto-Activate optimization supported
+	 * bit1: DMA Setup FIX non-Zero buffer offsets supported
+	 * bit0: Reserved
+	 *
+	 * Clear reserved bit 8 (DEVSLP bit) as we don't support DEVSLP
+	 */
+	id[ATA_ID_FEATURE_SUPP] &= ~(1 << 8);
+
+	/*
+	 * Due to HW errata, restart the port if no other command active.
+	 * Otherwise the controller may get stuck.
+	 */
+	if (!readl(port_mmio + PORT_CMD_ISSUE)) {
+		writel(PORT_CMD_FIS_RX, port_mmio + PORT_CMD);
+		readl(port_mmio + PORT_CMD);	/* Force a barrier */
+		writel(PORT_CMD_FIS_RX | PORT_CMD_START, port_mmio + PORT_CMD);
+		readl(port_mmio + PORT_CMD);	/* Force a barrier */
+	}
+	return 0;
+}
+
+static void xgene_ahci_set_phy_cfg(struct xgene_ahci_context *ctx, int channel)
+{
+	void __iomem *mmio = ctx->hpriv->mmio;
+	u32 val;
+
+	dev_dbg(ctx->dev, "port configure mmio 0x%p channel %d\n",
+		mmio, channel);
+	val = readl(mmio + PORTCFG);
+	val = PORTADDR_SET(val, channel == 0 ? 2 : 3);
+	writel(val, mmio + PORTCFG);
+	readl(mmio + PORTCFG);  /* Force a barrier */
+	/* Disable fix rate */
+	writel(0x0001fffe, mmio + PORTPHY1CFG);
+	readl(mmio + PORTPHY1CFG); /* Force a barrier */
+	writel(0x5018461c, mmio + PORTPHY2CFG);
+	readl(mmio + PORTPHY2CFG); /* Force a barrier */
+	writel(0x1c081907, mmio + PORTPHY3CFG);
+	readl(mmio + PORTPHY3CFG); /* Force a barrier */
+	writel(0x1c080815, mmio + PORTPHY4CFG);
+	readl(mmio + PORTPHY4CFG); /* Force a barrier */
+	/* Set window negotiation */
+	val = readl(mmio + PORTPHY5CFG);
+	val = PORTPHY5CFG_RTCHG_SET(val, 0x300);
+	writel(val, mmio + PORTPHY5CFG);
+	readl(mmio + PORTPHY5CFG); /* Force a barrier */
+	val = readl(mmio + PORTAXICFG);
+	val = PORTAXICFG_EN_CONTEXT_SET(val, 0x1); /* Enable context mgmt */
+	val = PORTAXICFG_OUTTRANS_SET(val, 0xe); /* Set outstanding */
+	writel(val, mmio + PORTAXICFG);
+	readl(mmio + PORTAXICFG); /* Force a barrier */
+}
+
+/**
+ * xgene_ahci_do_hardreset - Issue the actual COMRESET
+ * @link: link to reset
+ * @deadline: deadline jiffies for the operation
+ * @online: Return value to indicate if device online
+ *
+ * Due to the limitation of the hardware PHY, a difference set of setting is
+ * required for each supported disk speed - Gen3 (6.0Gbps), Gen2 (3.0Gbps),
+ * and Gen1 (1.5Gbps). Otherwise during long IO stress test, the PHY will
+ * report disparity error and etc. In addition, during COMRESET, there can
+ * be error reported in the register PORT_SCR_ERR. For SERR_DISPARITY and
+ * SERR_10B_8B_ERR, the PHY receiver line must be reseted. The following
+ * algorithm is followed to proper configure the hardware PHY during COMRESET:
+ *
+ * Alg Part 1:
+ * 1. Start the PHY at Gen3 speed (default setting)
+ * 2. Issue the COMRESET
+ * 3. If no link, go to Alg Part 3
+ * 4. If link up, determine if the negotiated speed matches the PHY
+ *    configured speed
+ * 5. If they matched, go to Alg Part 2
+ * 6. If they do not matched and first time, configure the PHY for the linked
+ *    up disk speed and repeat step 2
+ * 7. Go to Alg Part 2
+ *
+ * Alg Part 2:
+ * 1. On link up, if there are any SERR_DISPARITY and SERR_10B_8B_ERR error
+ *    reported in the register PORT_SCR_ERR, then reset the PHY receiver line
+ * 2. Go to Alg Part 3
+ *
+ * Alg Part 3:
+ * 1. Clear any pending from register PORT_SCR_ERR.
+ *
+ * NOTE: For the initial version, we will NOT support Gen1/Gen2. In addition
+ *       and until the underlying PHY supports an method to reset the receiver
+ *       line, on detection of SERR_DISPARITY or SERR_10B_8B_ERR errors,
+ *       an warning message will be printed.
+ */
+static int xgene_ahci_do_hardreset(struct ata_link *link,
+				   unsigned long deadline, bool *online)
+{
+	const unsigned long *timing = sata_ehc_deb_timing(&link->eh_context);
+	struct ata_port *ap = link->ap;
+	struct ahci_host_priv *hpriv = ap->host->private_data;
+	struct xgene_ahci_context *ctx = hpriv->plat_data;
+	struct ahci_port_priv *pp = ap->private_data;
+	u8 *d2h_fis = pp->rx_fis + RX_FIS_D2H_REG;
+	void __iomem *port_mmio = ahci_port_base(ap);
+	struct ata_taskfile tf;
+	int rc;
+	u32 val;
+
+	/* clear D2H reception area to properly wait for D2H FIS */
+	ata_tf_init(link->device, &tf);
+	tf.command = ATA_BUSY;
+	ata_tf_to_fis(&tf, 0, 0, d2h_fis);
+	rc = sata_link_hardreset(link, timing, deadline, online,
+				 ahci_check_ready);
+
+	val = readl(port_mmio + PORT_SCR_ERR);
+	if (val & (SERR_DISPARITY | SERR_10B_8B_ERR))
+		dev_warn(ctx->dev, "link has error\n");
+
+	/* clear all errors if any pending */
+	val = readl(port_mmio + PORT_SCR_ERR);
+	writel(val, port_mmio + PORT_SCR_ERR);
+
+	return rc;
+}
+
+static int xgene_ahci_hardreset(struct ata_link *link, unsigned int *class,
+				unsigned long deadline)
+{
+	struct ata_port *ap = link->ap;
+        struct ahci_host_priv *hpriv = ap->host->private_data;
+	void __iomem *port_mmio = ahci_port_base(ap);
+	bool online;
+	int rc;
+	u32 portcmd_saved;
+	u32 portclb_saved;
+	u32 portclbhi_saved;
+	u32 portrxfis_saved;
+	u32 portrxfishi_saved;
+
+	/* As hardreset resets these CSR, save it to restore later */
+	portcmd_saved = readl(port_mmio + PORT_CMD);
+	portclb_saved = readl(port_mmio + PORT_LST_ADDR);
+	portclbhi_saved = readl(port_mmio + PORT_LST_ADDR_HI);
+	portrxfis_saved = readl(port_mmio + PORT_FIS_ADDR);
+	portrxfishi_saved = readl(port_mmio + PORT_FIS_ADDR_HI);
+
+	ahci_stop_engine(ap);
+
+	rc = xgene_ahci_do_hardreset(link, deadline, &online);
+
+	/* As controller hardreset clears them, restore them */
+	writel(portcmd_saved, port_mmio + PORT_CMD);
+	writel(portclb_saved, port_mmio + PORT_LST_ADDR);
+	writel(portclbhi_saved, port_mmio + PORT_LST_ADDR_HI);
+	writel(portrxfis_saved, port_mmio + PORT_FIS_ADDR);
+	writel(portrxfishi_saved, port_mmio + PORT_FIS_ADDR_HI);
+
+	hpriv->start_engine(ap);
+
+	if (online)
+		*class = ahci_dev_classify(ap);
+
+	return rc;
+}
+
+static void xgene_ahci_host_stop(struct ata_host *host)
+{
+	struct ahci_host_priv *hpriv = host->private_data;
+
+	ahci_platform_disable_resources(hpriv);
+}
+
+static struct ata_port_operations xgene_ahci_ops = {
+	.inherits = &ahci_ops,
+	.host_stop = xgene_ahci_host_stop,
+	.hardreset = xgene_ahci_hardreset,
+	.read_id = xgene_ahci_read_id,
+};
+
+static const struct ata_port_info xgene_ahci_port_info = {
+	AHCI_HFLAGS(AHCI_HFLAG_NO_PMP | AHCI_HFLAG_YES_NCQ),
+	.flags = AHCI_FLAG_COMMON | ATA_FLAG_NCQ,
+	.pio_mask = ATA_PIO4,
+	.udma_mask = ATA_UDMA6,
+	.port_ops = &xgene_ahci_ops,
+};
+
+static int xgene_ahci_hw_init(struct ahci_host_priv *hpriv)
+{
+	struct xgene_ahci_context *ctx = hpriv->plat_data;
+	int i;
+	int rc;
+	u32 val;
+
+	/* Remove IP RAM out of shutdown */
+	rc = xgene_ahci_init_memram(ctx);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < MAX_AHCI_CHN_PERCTR; i++)
+		xgene_ahci_set_phy_cfg(ctx, i);
+
+	/* AXI disable Mask */
+	writel(0xffffffff, hpriv->mmio + HOST_IRQ_STAT);
+	readl(hpriv->mmio + HOST_IRQ_STAT); /* Force a barrier */
+	writel(0, ctx->csr_core + INTSTATUSMASK);
+	val = readl(ctx->csr_core + INTSTATUSMASK); /* Force a barrier */
+	dev_dbg(ctx->dev, "top level interrupt mask 0x%X value 0x%08X\n",
+		INTSTATUSMASK, val);
+
+	writel(0x0, ctx->csr_core + ERRINTSTATUSMASK);
+	readl(ctx->csr_core + ERRINTSTATUSMASK); /* Force a barrier */
+	writel(0x0, ctx->csr_axi + INT_SLV_TMOMASK);
+	readl(ctx->csr_axi + INT_SLV_TMOMASK);
+
+	/* Enable AXI Interrupt */
+	writel(0xffffffff, ctx->csr_core + SLVRDERRATTRIBUTES);
+	writel(0xffffffff, ctx->csr_core + SLVWRERRATTRIBUTES);
+	writel(0xffffffff, ctx->csr_core + MSTRDERRATTRIBUTES);
+	writel(0xffffffff, ctx->csr_core + MSTWRERRATTRIBUTES);
+
+	/* Enable coherency */
+	val = readl(ctx->csr_core + BUSCTLREG);
+	val &= ~0x00000002;     /* Enable write coherency */
+	val &= ~0x00000001;     /* Enable read coherency */
+	writel(val, ctx->csr_core + BUSCTLREG);
+
+	val = readl(ctx->csr_core + IOFMSTRWAUX);
+	val |= (1 << 3);        /* Enable read coherency */
+	val |= (1 << 9);        /* Enable write coherency */
+	writel(val, ctx->csr_core + IOFMSTRWAUX);
+	val = readl(ctx->csr_core + IOFMSTRWAUX);
+	dev_dbg(ctx->dev, "coherency 0x%X value 0x%08X\n",
+		IOFMSTRWAUX, val);
+
+	return rc;
+}
+
+static int xgene_ahci_mux_select(struct xgene_ahci_context *ctx)
+{
+	u32 val;
+
+	/* Check for optional MUX resource */
+	if (IS_ERR(ctx->csr_mux))
+		return 0;
+
+	val = readl(ctx->csr_mux + SATA_ENET_CONFIG_REG);
+	val &= ~CFG_SATA_ENET_SELECT_MASK;
+	writel(val, ctx->csr_mux + SATA_ENET_CONFIG_REG);
+	val = readl(ctx->csr_mux + SATA_ENET_CONFIG_REG);
+	return val & CFG_SATA_ENET_SELECT_MASK ? -1 : 0;
+}
+
+static int xgene_ahci_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ahci_host_priv *hpriv;
+	struct xgene_ahci_context *ctx;
+	struct resource *res;
+	int rc;
+
+	hpriv = ahci_platform_get_resources(pdev);
+	if (IS_ERR(hpriv))
+		return PTR_ERR(hpriv);
+
+	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	hpriv->plat_data = ctx;
+	ctx->hpriv = hpriv;
+	ctx->dev = dev;
+
+	/* Retrieve the IP core resource */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	ctx->csr_core = devm_ioremap_resource(dev, res);
+	if (IS_ERR(ctx->csr_core))
+		return PTR_ERR(ctx->csr_core);
+
+	/* Retrieve the IP diagnostic resource */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	ctx->csr_diag = devm_ioremap_resource(dev, res);
+	if (IS_ERR(ctx->csr_diag))
+		return PTR_ERR(ctx->csr_diag);
+
+	/* Retrieve the IP AXI resource */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 3);
+	ctx->csr_axi = devm_ioremap_resource(dev, res);
+	if (IS_ERR(ctx->csr_axi))
+		return PTR_ERR(ctx->csr_axi);
+
+	/* Retrieve the optional IP mux resource */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 4);
+	ctx->csr_mux = devm_ioremap_resource(dev, res);
+
+	dev_dbg(dev, "VAddr 0x%p Mmio VAddr 0x%p\n", ctx->csr_core,
+		hpriv->mmio);
+
+	/* Select ATA */
+	if ((rc = xgene_ahci_mux_select(ctx))) {
+		dev_err(dev, "SATA mux selection failed error %d\n", rc);
+		return -ENODEV;
+	}
+
+	/* Due to errata, HW requires full toggle transition */
+	rc = ahci_platform_enable_clks(hpriv);
+	if (rc)
+		goto disable_resources;
+	ahci_platform_disable_clks(hpriv);
+
+	rc = ahci_platform_enable_resources(hpriv);
+	if (rc)
+		goto disable_resources;
+
+	/* Configure the host controller */
+	xgene_ahci_hw_init(hpriv);
+
+	/*
+	 * Setup DMA mask. This is preliminary until the DMA range is sorted
+	 * out.
+	 */
+	rc = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	if (rc) {
+		dev_err(dev, "Unable to set dma mask\n");
+		goto disable_resources;
+	}
+
+	rc = ahci_platform_init_host(pdev, hpriv, &xgene_ahci_port_info, 0, 0);
+	if (rc)
+		goto disable_resources;
+
+	dev_dbg(dev, "X-Gene SATA host controller initialized\n");
+	return 0;
+
+disable_resources:
+	ahci_platform_disable_resources(hpriv);
+	return rc;
+}
+
+static const struct of_device_id xgene_ahci_of_match[] = {
+	{.compatible = "apm,xgene-ahci"},
+	{},
+};
+MODULE_DEVICE_TABLE(of, xgene_ahci_of_match);
+
+static struct platform_driver xgene_ahci_driver = {
+	.probe = xgene_ahci_probe,
+	.remove = ata_platform_remove_one,
+	.driver = {
+		.name = "xgene-ahci",
+		.owner = THIS_MODULE,
+		.of_match_table = xgene_ahci_of_match,
+	},
+};
+
+module_platform_driver(xgene_ahci_driver);
+
+MODULE_DESCRIPTION("APM X-Gene AHCI SATA driver");
+MODULE_AUTHOR("Loc Ho <lho@apm.com>");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("0.4");
diff --git a/drivers/ata/ata_generic.c b/drivers/ata/ata_generic.c
index 7d19665..9498a7d 100644
--- a/drivers/ata/ata_generic.c
+++ b/drivers/ata/ata_generic.c
@@ -19,7 +19,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 36605ab..6bd4f66 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -35,7 +35,6 @@
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
@@ -394,6 +393,9 @@
  *
  *	If inconsistent, config values are fixed up by this function.
  *
+ *	If it is not set already this function sets hpriv->start_engine to
+ *	ahci_start_engine.
+ *
  *	LOCKING:
  *	None.
  */
@@ -500,6 +502,9 @@
 	hpriv->cap = cap;
 	hpriv->cap2 = cap2;
 	hpriv->port_map = port_map;
+
+	if (!hpriv->start_engine)
+		hpriv->start_engine = ahci_start_engine;
 }
 EXPORT_SYMBOL_GPL(ahci_save_initial_config);
 
@@ -766,7 +771,7 @@
 
 	/* enable DMA */
 	if (!(hpriv->flags & AHCI_HFLAG_DELAY_ENGINE))
-		ahci_start_engine(ap);
+		hpriv->start_engine(ap);
 
 	/* turn on LEDs */
 	if (ap->flags & ATA_FLAG_EM) {
@@ -1032,12 +1037,13 @@
 static ssize_t ahci_led_store(struct ata_port *ap, const char *buf,
 				size_t size)
 {
-	int state;
+	unsigned int state;
 	int pmp;
 	struct ahci_port_priv *pp = ap->private_data;
 	struct ahci_em_priv *emp;
 
-	state = simple_strtoul(buf, NULL, 0);
+	if (kstrtouint(buf, 0, &state) < 0)
+		return -EINVAL;
 
 	/* get the slot number from the message */
 	pmp = (state & EM_MSG_LED_PMP_SLOT) >> 8;
@@ -1234,7 +1240,7 @@
 
 	/* restart engine */
  out_restart:
-	ahci_start_engine(ap);
+	hpriv->start_engine(ap);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(ahci_kick_engine);
@@ -1387,8 +1393,8 @@
 	return ata_check_ready(status);
 }
 
-int ahci_pmp_retry_softreset(struct ata_link *link, unsigned int *class,
-				unsigned long deadline)
+static int ahci_pmp_retry_softreset(struct ata_link *link, unsigned int *class,
+				    unsigned long deadline)
 {
 	struct ata_port *ap = link->ap;
 	void __iomem *port_mmio = ahci_port_base(ap);
@@ -1426,6 +1432,7 @@
 	const unsigned long *timing = sata_ehc_deb_timing(&link->eh_context);
 	struct ata_port *ap = link->ap;
 	struct ahci_port_priv *pp = ap->private_data;
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	u8 *d2h_fis = pp->rx_fis + RX_FIS_D2H_REG;
 	struct ata_taskfile tf;
 	bool online;
@@ -1443,7 +1450,7 @@
 	rc = sata_link_hardreset(link, timing, deadline, &online,
 				 ahci_check_ready);
 
-	ahci_start_engine(ap);
+	hpriv->start_engine(ap);
 
 	if (online)
 		*class = ahci_dev_classify(ap);
@@ -1629,7 +1636,7 @@
 	}
 
 	if (irq_stat & PORT_IRQ_UNK_FIS) {
-		u32 *unk = (u32 *)(pp->rx_fis + RX_FIS_UNK);
+		u32 *unk = pp->rx_fis + RX_FIS_UNK;
 
 		active_ehi->err_mask |= AC_ERR_HSM;
 		active_ehi->action |= ATA_EH_RESET;
@@ -2007,10 +2014,12 @@
 
 void ahci_error_handler(struct ata_port *ap)
 {
+	struct ahci_host_priv *hpriv = ap->host->private_data;
+
 	if (!(ap->pflags & ATA_PFLAG_FROZEN)) {
 		/* restart engine */
 		ahci_stop_engine(ap);
-		ahci_start_engine(ap);
+		hpriv->start_engine(ap);
 	}
 
 	sata_pmp_error_handler(ap);
@@ -2031,6 +2040,7 @@
 
 static void ahci_set_aggressive_devslp(struct ata_port *ap, bool sleep)
 {
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	void __iomem *port_mmio = ahci_port_base(ap);
 	struct ata_device *dev = ap->link.device;
 	u32 devslp, dm, dito, mdat, deto;
@@ -2094,7 +2104,7 @@
 		   PORT_DEVSLP_ADSE);
 	writel(devslp, port_mmio + PORT_DEVSLP);
 
-	ahci_start_engine(ap);
+	hpriv->start_engine(ap);
 
 	/* enable device sleep feature for the drive */
 	err_mask = ata_dev_set_feature(dev,
@@ -2106,6 +2116,7 @@
 
 static void ahci_enable_fbs(struct ata_port *ap)
 {
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	struct ahci_port_priv *pp = ap->private_data;
 	void __iomem *port_mmio = ahci_port_base(ap);
 	u32 fbs;
@@ -2134,11 +2145,12 @@
 	} else
 		dev_err(ap->host->dev, "Failed to enable FBS\n");
 
-	ahci_start_engine(ap);
+	hpriv->start_engine(ap);
 }
 
 static void ahci_disable_fbs(struct ata_port *ap)
 {
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	struct ahci_port_priv *pp = ap->private_data;
 	void __iomem *port_mmio = ahci_port_base(ap);
 	u32 fbs;
@@ -2166,7 +2178,7 @@
 		pp->fbs_enabled = false;
 	}
 
-	ahci_start_engine(ap);
+	hpriv->start_engine(ap);
 }
 
 static void ahci_pmp_attach(struct ata_port *ap)
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
new file mode 100644
index 0000000..7cb3a85
--- /dev/null
+++ b/drivers/ata/libahci_platform.c
@@ -0,0 +1,541 @@
+/*
+ * AHCI SATA platform library
+ *
+ * Copyright 2004-2005  Red Hat, Inc.
+ *   Jeff Garzik <jgarzik@pobox.com>
+ * Copyright 2010  MontaVista Software, LLC.
+ *   Anton Vorontsov <avorontsov@ru.mvista.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/module.h>
+#include <linux/pm.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/libata.h>
+#include <linux/ahci_platform.h>
+#include <linux/phy/phy.h>
+#include <linux/pm_runtime.h>
+#include "ahci.h"
+
+static void ahci_host_stop(struct ata_host *host);
+
+struct ata_port_operations ahci_platform_ops = {
+	.inherits	= &ahci_ops,
+	.host_stop	= ahci_host_stop,
+};
+EXPORT_SYMBOL_GPL(ahci_platform_ops);
+
+static struct scsi_host_template ahci_platform_sht = {
+	AHCI_SHT("ahci_platform"),
+};
+
+/**
+ * ahci_platform_enable_clks - Enable platform clocks
+ * @hpriv: host private area to store config values
+ *
+ * This function enables all the clks found in hpriv->clks, starting at
+ * index 0. If any clk fails to enable it disables all the clks already
+ * enabled in reverse order, and then returns an error.
+ *
+ * RETURNS:
+ * 0 on success otherwise a negative error code
+ */
+int ahci_platform_enable_clks(struct ahci_host_priv *hpriv)
+{
+	int c, rc;
+
+	for (c = 0; c < AHCI_MAX_CLKS && hpriv->clks[c]; c++) {
+		rc = clk_prepare_enable(hpriv->clks[c]);
+		if (rc)
+			goto disable_unprepare_clk;
+	}
+	return 0;
+
+disable_unprepare_clk:
+	while (--c >= 0)
+		clk_disable_unprepare(hpriv->clks[c]);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ahci_platform_enable_clks);
+
+/**
+ * ahci_platform_disable_clks - Disable platform clocks
+ * @hpriv: host private area to store config values
+ *
+ * This function disables all the clks found in hpriv->clks, in reverse
+ * order of ahci_platform_enable_clks (starting at the end of the array).
+ */
+void ahci_platform_disable_clks(struct ahci_host_priv *hpriv)
+{
+	int c;
+
+	for (c = AHCI_MAX_CLKS - 1; c >= 0; c--)
+		if (hpriv->clks[c])
+			clk_disable_unprepare(hpriv->clks[c]);
+}
+EXPORT_SYMBOL_GPL(ahci_platform_disable_clks);
+
+/**
+ * ahci_platform_enable_resources - Enable platform resources
+ * @hpriv: host private area to store config values
+ *
+ * This function enables all ahci_platform managed resources in the
+ * following order:
+ * 1) Regulator
+ * 2) Clocks (through ahci_platform_enable_clks)
+ * 3) Phy
+ *
+ * If resource enabling fails at any point the previous enabled resources
+ * are disabled in reverse order.
+ *
+ * RETURNS:
+ * 0 on success otherwise a negative error code
+ */
+int ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
+{
+	int rc;
+
+	if (hpriv->target_pwr) {
+		rc = regulator_enable(hpriv->target_pwr);
+		if (rc)
+			return rc;
+	}
+
+	rc = ahci_platform_enable_clks(hpriv);
+	if (rc)
+		goto disable_regulator;
+
+	if (hpriv->phy) {
+		rc = phy_init(hpriv->phy);
+		if (rc)
+			goto disable_clks;
+
+		rc = phy_power_on(hpriv->phy);
+		if (rc) {
+			phy_exit(hpriv->phy);
+			goto disable_clks;
+		}
+	}
+
+	return 0;
+
+disable_clks:
+	ahci_platform_disable_clks(hpriv);
+
+disable_regulator:
+	if (hpriv->target_pwr)
+		regulator_disable(hpriv->target_pwr);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ahci_platform_enable_resources);
+
+/**
+ * ahci_platform_disable_resources - Disable platform resources
+ * @hpriv: host private area to store config values
+ *
+ * This function disables all ahci_platform managed resources in the
+ * following order:
+ * 1) Phy
+ * 2) Clocks (through ahci_platform_disable_clks)
+ * 3) Regulator
+ */
+void ahci_platform_disable_resources(struct ahci_host_priv *hpriv)
+{
+	if (hpriv->phy) {
+		phy_power_off(hpriv->phy);
+		phy_exit(hpriv->phy);
+	}
+
+	ahci_platform_disable_clks(hpriv);
+
+	if (hpriv->target_pwr)
+		regulator_disable(hpriv->target_pwr);
+}
+EXPORT_SYMBOL_GPL(ahci_platform_disable_resources);
+
+static void ahci_platform_put_resources(struct device *dev, void *res)
+{
+	struct ahci_host_priv *hpriv = res;
+	int c;
+
+	if (hpriv->got_runtime_pm) {
+		pm_runtime_put_sync(dev);
+		pm_runtime_disable(dev);
+	}
+
+	for (c = 0; c < AHCI_MAX_CLKS && hpriv->clks[c]; c++)
+		clk_put(hpriv->clks[c]);
+}
+
+/**
+ * ahci_platform_get_resources - Get platform resources
+ * @pdev: platform device to get resources for
+ *
+ * This function allocates an ahci_host_priv struct, and gets the following
+ * resources, storing a reference to them inside the returned struct:
+ *
+ * 1) mmio registers (IORESOURCE_MEM 0, mandatory)
+ * 2) regulator for controlling the targets power (optional)
+ * 3) 0 - AHCI_MAX_CLKS clocks, as specified in the devs devicetree node,
+ *    or for non devicetree enabled platforms a single clock
+ *	4) phy (optional)
+ *
+ * RETURNS:
+ * The allocated ahci_host_priv on success, otherwise an ERR_PTR value
+ */
+struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ahci_host_priv *hpriv;
+	struct clk *clk;
+	int i, rc = -ENOMEM;
+
+	if (!devres_open_group(dev, NULL, GFP_KERNEL))
+		return ERR_PTR(-ENOMEM);
+
+	hpriv = devres_alloc(ahci_platform_put_resources, sizeof(*hpriv),
+			     GFP_KERNEL);
+	if (!hpriv)
+		goto err_out;
+
+	devres_add(dev, hpriv);
+
+	hpriv->mmio = devm_ioremap_resource(dev,
+			      platform_get_resource(pdev, IORESOURCE_MEM, 0));
+	if (IS_ERR(hpriv->mmio)) {
+		dev_err(dev, "no mmio space\n");
+		rc = PTR_ERR(hpriv->mmio);
+		goto err_out;
+	}
+
+	hpriv->target_pwr = devm_regulator_get_optional(dev, "target");
+	if (IS_ERR(hpriv->target_pwr)) {
+		rc = PTR_ERR(hpriv->target_pwr);
+		if (rc == -EPROBE_DEFER)
+			goto err_out;
+		hpriv->target_pwr = NULL;
+	}
+
+	for (i = 0; i < AHCI_MAX_CLKS; i++) {
+		/*
+		 * For now we must use clk_get(dev, NULL) for the first clock,
+		 * because some platforms (da850, spear13xx) are not yet
+		 * converted to use devicetree for clocks.  For new platforms
+		 * this is equivalent to of_clk_get(dev->of_node, 0).
+		 */
+		if (i == 0)
+			clk = clk_get(dev, NULL);
+		else
+			clk = of_clk_get(dev->of_node, i);
+
+		if (IS_ERR(clk)) {
+			rc = PTR_ERR(clk);
+			if (rc == -EPROBE_DEFER)
+				goto err_out;
+			break;
+		}
+		hpriv->clks[i] = clk;
+	}
+
+	hpriv->phy = devm_phy_get(dev, "sata-phy");
+	if (IS_ERR(hpriv->phy)) {
+		rc = PTR_ERR(hpriv->phy);
+		switch (rc) {
+		case -ENODEV:
+		case -ENOSYS:
+			/* continue normally */
+			hpriv->phy = NULL;
+			break;
+
+		case -EPROBE_DEFER:
+			goto err_out;
+
+		default:
+			dev_err(dev, "couldn't get sata-phy\n");
+			goto err_out;
+		}
+	}
+
+	pm_runtime_enable(dev);
+	pm_runtime_get_sync(dev);
+	hpriv->got_runtime_pm = true;
+
+	devres_remove_group(dev, NULL);
+	return hpriv;
+
+err_out:
+	devres_release_group(dev, NULL);
+	return ERR_PTR(rc);
+}
+EXPORT_SYMBOL_GPL(ahci_platform_get_resources);
+
+/**
+ * ahci_platform_init_host - Bring up an ahci-platform host
+ * @pdev: platform device pointer for the host
+ * @hpriv: ahci-host private data for the host
+ * @pi_template: template for the ata_port_info to use
+ * @force_port_map: param passed to ahci_save_initial_config
+ * @mask_port_map: param passed to ahci_save_initial_config
+ *
+ * This function does all the usual steps needed to bring up an
+ * ahci-platform host, note any necessary resources (ie clks, phy, etc.)
+ * must be initialized / enabled before calling this.
+ *
+ * RETURNS:
+ * 0 on success otherwise a negative error code
+ */
+int ahci_platform_init_host(struct platform_device *pdev,
+			    struct ahci_host_priv *hpriv,
+			    const struct ata_port_info *pi_template,
+			    unsigned int force_port_map,
+			    unsigned int mask_port_map)
+{
+	struct device *dev = &pdev->dev;
+	struct ata_port_info pi = *pi_template;
+	const struct ata_port_info *ppi[] = { &pi, NULL };
+	struct ata_host *host;
+	int i, irq, n_ports, rc;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0) {
+		dev_err(dev, "no irq\n");
+		return -EINVAL;
+	}
+
+	/* prepare host */
+	hpriv->flags |= (unsigned long)pi.private_data;
+
+	ahci_save_initial_config(dev, hpriv, force_port_map, mask_port_map);
+
+	if (hpriv->cap & HOST_CAP_NCQ)
+		pi.flags |= ATA_FLAG_NCQ;
+
+	if (hpriv->cap & HOST_CAP_PMP)
+		pi.flags |= ATA_FLAG_PMP;
+
+	ahci_set_em_messages(hpriv, &pi);
+
+	/* CAP.NP sometimes indicate the index of the last enabled
+	 * port, at other times, that of the last possible port, so
+	 * determining the maximum port number requires looking at
+	 * both CAP.NP and port_map.
+	 */
+	n_ports = max(ahci_nr_ports(hpriv->cap), fls(hpriv->port_map));
+
+	host = ata_host_alloc_pinfo(dev, ppi, n_ports);
+	if (!host)
+		return -ENOMEM;
+
+	host->private_data = hpriv;
+
+	if (!(hpriv->cap & HOST_CAP_SSS) || ahci_ignore_sss)
+		host->flags |= ATA_HOST_PARALLEL_SCAN;
+	else
+		dev_info(dev, "SSS flag set, parallel bus scan disabled\n");
+
+	if (pi.flags & ATA_FLAG_EM)
+		ahci_reset_em(host);
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap = host->ports[i];
+
+		ata_port_desc(ap, "mmio %pR",
+			      platform_get_resource(pdev, IORESOURCE_MEM, 0));
+		ata_port_desc(ap, "port 0x%x", 0x100 + ap->port_no * 0x80);
+
+		/* set enclosure management message type */
+		if (ap->flags & ATA_FLAG_EM)
+			ap->em_message_type = hpriv->em_msg_type;
+
+		/* disabled/not-implemented port */
+		if (!(hpriv->port_map & (1 << i)))
+			ap->ops = &ata_dummy_port_ops;
+	}
+
+	rc = ahci_reset_controller(host);
+	if (rc)
+		return rc;
+
+	ahci_init_controller(host);
+	ahci_print_info(host, "platform");
+
+	return ata_host_activate(host, irq, ahci_interrupt, IRQF_SHARED,
+				 &ahci_platform_sht);
+}
+EXPORT_SYMBOL_GPL(ahci_platform_init_host);
+
+static void ahci_host_stop(struct ata_host *host)
+{
+	struct device *dev = host->dev;
+	struct ahci_platform_data *pdata = dev_get_platdata(dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+
+	if (pdata && pdata->exit)
+		pdata->exit(dev);
+
+	ahci_platform_disable_resources(hpriv);
+}
+
+#ifdef CONFIG_PM_SLEEP
+/**
+ * ahci_platform_suspend_host - Suspend an ahci-platform host
+ * @dev: device pointer for the host
+ *
+ * This function does all the usual steps needed to suspend an
+ * ahci-platform host, note any necessary resources (ie clks, phy, etc.)
+ * must be disabled after calling this.
+ *
+ * RETURNS:
+ * 0 on success otherwise a negative error code
+ */
+int ahci_platform_suspend_host(struct device *dev)
+{
+	struct ata_host *host = dev_get_drvdata(dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	void __iomem *mmio = hpriv->mmio;
+	u32 ctl;
+
+	if (hpriv->flags & AHCI_HFLAG_NO_SUSPEND) {
+		dev_err(dev, "firmware update required for suspend/resume\n");
+		return -EIO;
+	}
+
+	/*
+	 * AHCI spec rev1.1 section 8.3.3:
+	 * Software must disable interrupts prior to requesting a
+	 * transition of the HBA to D3 state.
+	 */
+	ctl = readl(mmio + HOST_CTL);
+	ctl &= ~HOST_IRQ_EN;
+	writel(ctl, mmio + HOST_CTL);
+	readl(mmio + HOST_CTL); /* flush */
+
+	return ata_host_suspend(host, PMSG_SUSPEND);
+}
+EXPORT_SYMBOL_GPL(ahci_platform_suspend_host);
+
+/**
+ * ahci_platform_resume_host - Resume an ahci-platform host
+ * @dev: device pointer for the host
+ *
+ * This function does all the usual steps needed to resume an ahci-platform
+ * host, note any necessary resources (ie clks, phy, etc.)  must be
+ * initialized / enabled before calling this.
+ *
+ * RETURNS:
+ * 0 on success otherwise a negative error code
+ */
+int ahci_platform_resume_host(struct device *dev)
+{
+	struct ata_host *host = dev_get_drvdata(dev);
+	int rc;
+
+	if (dev->power.power_state.event == PM_EVENT_SUSPEND) {
+		rc = ahci_reset_controller(host);
+		if (rc)
+			return rc;
+
+		ahci_init_controller(host);
+	}
+
+	ata_host_resume(host);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ahci_platform_resume_host);
+
+/**
+ * ahci_platform_suspend - Suspend an ahci-platform device
+ * @dev: the platform device to suspend
+ *
+ * This function suspends the host associated with the device, followed by
+ * disabling all the resources of the device.
+ *
+ * RETURNS:
+ * 0 on success otherwise a negative error code
+ */
+int ahci_platform_suspend(struct device *dev)
+{
+	struct ahci_platform_data *pdata = dev_get_platdata(dev);
+	struct ata_host *host = dev_get_drvdata(dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	int rc;
+
+	rc = ahci_platform_suspend_host(dev);
+	if (rc)
+		return rc;
+
+	if (pdata && pdata->suspend) {
+		rc = pdata->suspend(dev);
+		if (rc)
+			goto resume_host;
+	}
+
+	ahci_platform_disable_resources(hpriv);
+
+	return 0;
+
+resume_host:
+	ahci_platform_resume_host(dev);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ahci_platform_suspend);
+
+/**
+ * ahci_platform_resume - Resume an ahci-platform device
+ * @dev: the platform device to resume
+ *
+ * This function enables all the resources of the device followed by
+ * resuming the host associated with the device.
+ *
+ * RETURNS:
+ * 0 on success otherwise a negative error code
+ */
+int ahci_platform_resume(struct device *dev)
+{
+	struct ahci_platform_data *pdata = dev_get_platdata(dev);
+	struct ata_host *host = dev_get_drvdata(dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	int rc;
+
+	rc = ahci_platform_enable_resources(hpriv);
+	if (rc)
+		return rc;
+
+	if (pdata && pdata->resume) {
+		rc = pdata->resume(dev);
+		if (rc)
+			goto disable_resources;
+	}
+
+	rc = ahci_platform_resume_host(dev);
+	if (rc)
+		goto disable_resources;
+
+	/* We resumed so update PM runtime state */
+	pm_runtime_disable(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
+	return 0;
+
+disable_resources:
+	ahci_platform_disable_resources(hpriv);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ahci_platform_resume);
+#endif
+
+MODULE_DESCRIPTION("AHCI SATA platform library");
+MODULE_AUTHOR("Anton Vorontsov <avorontsov@ru.mvista.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index 9e69a53..b4f7cc2 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -835,6 +835,7 @@
 		ata_for_each_dev(dev, &ap->link, ALL) {
 			ata_acpi_clear_gtf(dev);
 			if (ata_dev_enabled(dev) &&
+			    ata_dev_acpi_handle(dev) &&
 			    ata_dev_get_GTF(dev, NULL) >= 0)
 				dev->flags |= ATA_DFLAG_ACPI_PENDING;
 		}
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 1a3dbd1..34406f7 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4175,6 +4175,7 @@
 
 	/* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */
 	{ "ST1000LM024 HN-M101MBB", "2AR10001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
+	{ "ST1000LM024 HN-M101MBB", "2BA30001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
 
 	/* Blacklist entries taken from Silicon Image 3124/3132
 	   Windows driver .inf file - also several Linux problem reports */
@@ -4224,7 +4225,7 @@
 
 	/* devices that don't properly handle queued TRIM commands */
 	{ "Micron_M500*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
-	{ "Crucial_CT???M500SSD1",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
+	{ "Crucial_CT???M500SSD*",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
 
 	/*
 	 * Some WD SATA-I drives spin up and down erratically when the link
@@ -5351,22 +5352,17 @@
 }
 
 #ifdef CONFIG_PM
-static int ata_port_request_pm(struct ata_port *ap, pm_message_t mesg,
-			       unsigned int action, unsigned int ehi_flags,
-			       int *async)
+static void ata_port_request_pm(struct ata_port *ap, pm_message_t mesg,
+				unsigned int action, unsigned int ehi_flags,
+				bool async)
 {
 	struct ata_link *link;
 	unsigned long flags;
-	int rc = 0;
 
 	/* Previous resume operation might still be in
 	 * progress.  Wait for PM_PENDING to clear.
 	 */
 	if (ap->pflags & ATA_PFLAG_PM_PENDING) {
-		if (async) {
-			*async = -EAGAIN;
-			return 0;
-		}
 		ata_port_wait_eh(ap);
 		WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING);
 	}
@@ -5375,11 +5371,6 @@
 	spin_lock_irqsave(ap->lock, flags);
 
 	ap->pm_mesg = mesg;
-	if (async)
-		ap->pm_result = async;
-	else
-		ap->pm_result = &rc;
-
 	ap->pflags |= ATA_PFLAG_PM_PENDING;
 	ata_for_each_link(link, ap, HOST_FIRST) {
 		link->eh_info.action |= action;
@@ -5390,87 +5381,81 @@
 
 	spin_unlock_irqrestore(ap->lock, flags);
 
-	/* wait and check result */
 	if (!async) {
 		ata_port_wait_eh(ap);
 		WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING);
 	}
-
-	return rc;
 }
 
-static int __ata_port_suspend_common(struct ata_port *ap, pm_message_t mesg, int *async)
+/*
+ * On some hardware, device fails to respond after spun down for suspend.  As
+ * the device won't be used before being resumed, we don't need to touch the
+ * device.  Ask EH to skip the usual stuff and proceed directly to suspend.
+ *
+ * http://thread.gmane.org/gmane.linux.ide/46764
+ */
+static const unsigned int ata_port_suspend_ehi = ATA_EHI_QUIET
+						 | ATA_EHI_NO_AUTOPSY
+						 | ATA_EHI_NO_RECOVERY;
+
+static void ata_port_suspend(struct ata_port *ap, pm_message_t mesg)
 {
-	/*
-	 * On some hardware, device fails to respond after spun down
-	 * for suspend.  As the device won't be used before being
-	 * resumed, we don't need to touch the device.  Ask EH to skip
-	 * the usual stuff and proceed directly to suspend.
-	 *
-	 * http://thread.gmane.org/gmane.linux.ide/46764
-	 */
-	unsigned int ehi_flags = ATA_EHI_QUIET | ATA_EHI_NO_AUTOPSY |
-				 ATA_EHI_NO_RECOVERY;
-	return ata_port_request_pm(ap, mesg, 0, ehi_flags, async);
+	ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, false);
 }
 
-static int ata_port_suspend_common(struct device *dev, pm_message_t mesg)
+static void ata_port_suspend_async(struct ata_port *ap, pm_message_t mesg)
+{
+	ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, true);
+}
+
+static int ata_port_pm_suspend(struct device *dev)
 {
 	struct ata_port *ap = to_ata_port(dev);
 
-	return __ata_port_suspend_common(ap, mesg, NULL);
-}
-
-static int ata_port_suspend(struct device *dev)
-{
 	if (pm_runtime_suspended(dev))
 		return 0;
 
-	return ata_port_suspend_common(dev, PMSG_SUSPEND);
+	ata_port_suspend(ap, PMSG_SUSPEND);
+	return 0;
 }
 
-static int ata_port_do_freeze(struct device *dev)
-{
-	if (pm_runtime_suspended(dev))
-		return 0;
-
-	return ata_port_suspend_common(dev, PMSG_FREEZE);
-}
-
-static int ata_port_poweroff(struct device *dev)
-{
-	return ata_port_suspend_common(dev, PMSG_HIBERNATE);
-}
-
-static int __ata_port_resume_common(struct ata_port *ap, pm_message_t mesg,
-				    int *async)
-{
-	int rc;
-
-	rc = ata_port_request_pm(ap, mesg, ATA_EH_RESET,
-		ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET, async);
-	return rc;
-}
-
-static int ata_port_resume_common(struct device *dev, pm_message_t mesg)
+static int ata_port_pm_freeze(struct device *dev)
 {
 	struct ata_port *ap = to_ata_port(dev);
 
-	return __ata_port_resume_common(ap, mesg, NULL);
+	if (pm_runtime_suspended(dev))
+		return 0;
+
+	ata_port_suspend(ap, PMSG_FREEZE);
+	return 0;
 }
 
-static int ata_port_resume(struct device *dev)
+static int ata_port_pm_poweroff(struct device *dev)
 {
-	int rc;
+	ata_port_suspend(to_ata_port(dev), PMSG_HIBERNATE);
+	return 0;
+}
 
-	rc = ata_port_resume_common(dev, PMSG_RESUME);
-	if (!rc) {
-		pm_runtime_disable(dev);
-		pm_runtime_set_active(dev);
-		pm_runtime_enable(dev);
-	}
+static const unsigned int ata_port_resume_ehi = ATA_EHI_NO_AUTOPSY
+						| ATA_EHI_QUIET;
 
-	return rc;
+static void ata_port_resume(struct ata_port *ap, pm_message_t mesg)
+{
+	ata_port_request_pm(ap, mesg, ATA_EH_RESET, ata_port_resume_ehi, false);
+}
+
+static void ata_port_resume_async(struct ata_port *ap, pm_message_t mesg)
+{
+	ata_port_request_pm(ap, mesg, ATA_EH_RESET, ata_port_resume_ehi, true);
+}
+
+static int ata_port_pm_resume(struct device *dev)
+{
+	ata_port_resume_async(to_ata_port(dev), PMSG_RESUME);
+	pm_runtime_disable(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+	return 0;
 }
 
 /*
@@ -5499,21 +5484,23 @@
 
 static int ata_port_runtime_suspend(struct device *dev)
 {
-	return ata_port_suspend_common(dev, PMSG_AUTO_SUSPEND);
+	ata_port_suspend(to_ata_port(dev), PMSG_AUTO_SUSPEND);
+	return 0;
 }
 
 static int ata_port_runtime_resume(struct device *dev)
 {
-	return ata_port_resume_common(dev, PMSG_AUTO_RESUME);
+	ata_port_resume(to_ata_port(dev), PMSG_AUTO_RESUME);
+	return 0;
 }
 
 static const struct dev_pm_ops ata_port_pm_ops = {
-	.suspend = ata_port_suspend,
-	.resume = ata_port_resume,
-	.freeze = ata_port_do_freeze,
-	.thaw = ata_port_resume,
-	.poweroff = ata_port_poweroff,
-	.restore = ata_port_resume,
+	.suspend = ata_port_pm_suspend,
+	.resume = ata_port_pm_resume,
+	.freeze = ata_port_pm_freeze,
+	.thaw = ata_port_pm_resume,
+	.poweroff = ata_port_pm_poweroff,
+	.restore = ata_port_pm_resume,
 
 	.runtime_suspend = ata_port_runtime_suspend,
 	.runtime_resume = ata_port_runtime_resume,
@@ -5525,18 +5512,17 @@
  * level. sas suspend/resume is async to allow parallel port recovery
  * since sas has multiple ata_port instances per Scsi_Host.
  */
-int ata_sas_port_async_suspend(struct ata_port *ap, int *async)
+void ata_sas_port_suspend(struct ata_port *ap)
 {
-	return __ata_port_suspend_common(ap, PMSG_SUSPEND, async);
+	ata_port_suspend_async(ap, PMSG_SUSPEND);
 }
-EXPORT_SYMBOL_GPL(ata_sas_port_async_suspend);
+EXPORT_SYMBOL_GPL(ata_sas_port_suspend);
 
-int ata_sas_port_async_resume(struct ata_port *ap, int *async)
+void ata_sas_port_resume(struct ata_port *ap)
 {
-	return __ata_port_resume_common(ap, PMSG_RESUME, async);
+	ata_port_resume_async(ap, PMSG_RESUME);
 }
-EXPORT_SYMBOL_GPL(ata_sas_port_async_resume);
-
+EXPORT_SYMBOL_GPL(ata_sas_port_resume);
 
 /**
  *	ata_host_suspend - suspend host
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 6d87570..6760fc4 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -95,12 +95,13 @@
  * represents timeout for that try.  The first try can be soft or
  * hardreset.  All others are hardreset if available.  In most cases
  * the first reset w/ 10sec timeout should succeed.  Following entries
- * are mostly for error handling, hotplug and retarded devices.
+ * are mostly for error handling, hotplug and those outlier devices that
+ * take an exceptionally long time to recover from reset.
  */
 static const unsigned long ata_eh_reset_timeouts[] = {
 	10000,	/* most drives spin up by 10sec */
 	10000,	/* > 99% working drives spin up before 20sec */
-	35000,	/* give > 30 secs of idleness for retarded devices */
+	35000,	/* give > 30 secs of idleness for outlier devices */
 	 5000,	/* and sweet one last chance */
 	ULONG_MAX, /* > 1 min has elapsed, give up */
 };
@@ -4069,7 +4070,7 @@
 
 	ata_acpi_set_state(ap, ap->pm_mesg);
  out:
-	/* report result */
+	/* update the flags */
 	spin_lock_irqsave(ap->lock, flags);
 
 	ap->pflags &= ~ATA_PFLAG_PM_PENDING;
@@ -4078,11 +4079,6 @@
 	else if (ap->pflags & ATA_PFLAG_FROZEN)
 		ata_port_schedule_eh(ap);
 
-	if (ap->pm_result) {
-		*ap->pm_result = rc;
-		ap->pm_result = NULL;
-	}
-
 	spin_unlock_irqrestore(ap->lock, flags);
 
 	return;
@@ -4134,13 +4130,9 @@
 	/* tell ACPI that we're resuming */
 	ata_acpi_on_resume(ap);
 
-	/* report result */
+	/* update the flags */
 	spin_lock_irqsave(ap->lock, flags);
 	ap->pflags &= ~(ATA_PFLAG_PM_PENDING | ATA_PFLAG_SUSPENDED);
-	if (ap->pm_result) {
-		*ap->pm_result = rc;
-		ap->pm_result = NULL;
-	}
 	spin_unlock_irqrestore(ap->lock, flags);
 }
 #endif /* CONFIG_PM */
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 20fd337..7ccc084 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -447,8 +447,11 @@
 		 * otherwise.  Don't try hard to recover it.
 		 */
 		ap->pmp_link[ap->nr_pmp_links - 1].flags |= ATA_LFLAG_NO_RETRY;
-	} else if (vendor == 0x197b && devid == 0x2352) {
-		/* chip found in Thermaltake BlackX Duet, jmicron JMB350? */
+	} else if (vendor == 0x197b && (devid == 0x2352 || devid == 0x0325)) {
+		/*
+		 * 0x2352: found in Thermaltake BlackX Duet, jmicron JMB350?
+		 * 0x0325: jmicron JMB394.
+		 */
 		ata_for_each_link(link, ap, EDGE) {
 			/* SRST breaks detection and disks get misclassified
 			 * LPM disabled to avoid potential problems
diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c
index 88949c6..f3a65a3 100644
--- a/drivers/ata/libata-zpodd.c
+++ b/drivers/ata/libata-zpodd.c
@@ -85,21 +85,6 @@
 		return ODD_MECH_TYPE_UNSUPPORTED;
 }
 
-static bool odd_can_poweroff(struct ata_device *ata_dev)
-{
-	acpi_handle handle;
-	struct acpi_device *acpi_dev;
-
-	handle = ata_dev_acpi_handle(ata_dev);
-	if (!handle)
-		return false;
-
-	if (acpi_bus_get_device(handle, &acpi_dev))
-		return false;
-
-	return acpi_device_can_poweroff(acpi_dev);
-}
-
 /* Test if ODD is zero power ready by sense code */
 static bool zpready(struct ata_device *dev)
 {
@@ -267,13 +252,11 @@
 
 void zpodd_init(struct ata_device *dev)
 {
+	struct acpi_device *adev = ACPI_COMPANION(&dev->tdev);
 	enum odd_mech_type mech_type;
 	struct zpodd *zpodd;
 
-	if (dev->zpodd)
-		return;
-
-	if (!odd_can_poweroff(dev))
+	if (dev->zpodd || !adev || !acpi_device_can_poweroff(adev))
 		return;
 
 	mech_type = zpodd_get_mech_type(dev);
diff --git a/drivers/ata/pata_acpi.c b/drivers/ata/pata_acpi.c
index 62c9ac8..5108b87 100644
--- a/drivers/ata/pata_acpi.c
+++ b/drivers/ata/pata_acpi.c
@@ -7,7 +7,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_amd.c b/drivers/ata/pata_amd.c
index d23e2b3..1206fa6 100644
--- a/drivers/ata/pata_amd.c
+++ b/drivers/ata/pata_amd.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index 73492dd..6fac524 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -356,7 +356,7 @@
 
 static void dma_callback(void *dev)
 {
-	struct arasan_cf_dev *acdev = (struct arasan_cf_dev *) dev;
+	struct arasan_cf_dev *acdev = dev;
 
 	complete(&acdev->dma_completion);
 }
diff --git a/drivers/ata/pata_artop.c b/drivers/ata/pata_artop.c
index 1581dee..3aa4e65 100644
--- a/drivers/ata/pata_artop.c
+++ b/drivers/ata/pata_artop.c
@@ -19,7 +19,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_at91.c b/drivers/ata/pata_at91.c
index d63ee8f..e9c8727 100644
--- a/drivers/ata/pata_at91.c
+++ b/drivers/ata/pata_at91.c
@@ -18,7 +18,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/gfp.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c
index 24e5105..30fa4ca 100644
--- a/drivers/ata/pata_atiixp.c
+++ b/drivers/ata/pata_atiixp.c
@@ -15,7 +15,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_atp867x.c b/drivers/ata/pata_atp867x.c
index 2ca5026..7e73a0f 100644
--- a/drivers/ata/pata_atp867x.c
+++ b/drivers/ata/pata_atp867x.c
@@ -29,7 +29,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_cmd640.c b/drivers/ata/pata_cmd640.c
index 8fb69e5..57f1be6 100644
--- a/drivers/ata/pata_cmd640.c
+++ b/drivers/ata/pata_cmd640.c
@@ -15,7 +15,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/gfp.h>
diff --git a/drivers/ata/pata_cmd64x.c b/drivers/ata/pata_cmd64x.c
index 1275a8d..6bca350 100644
--- a/drivers/ata/pata_cmd64x.c
+++ b/drivers/ata/pata_cmd64x.c
@@ -26,7 +26,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_cs5520.c b/drivers/ata/pata_cs5520.c
index f10baab..bcde4b7 100644
--- a/drivers/ata/pata_cs5520.c
+++ b/drivers/ata/pata_cs5520.c
@@ -34,7 +34,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_cs5530.c b/drivers/ata/pata_cs5530.c
index f07f229..8afe854 100644
--- a/drivers/ata/pata_cs5530.c
+++ b/drivers/ata/pata_cs5530.c
@@ -26,7 +26,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_cs5535.c b/drivers/ata/pata_cs5535.c
index 997e16a..2c0986f 100644
--- a/drivers/ata/pata_cs5535.c
+++ b/drivers/ata/pata_cs5535.c
@@ -31,7 +31,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_cs5536.c b/drivers/ata/pata_cs5536.c
index 0448860..32ddcae 100644
--- a/drivers/ata/pata_cs5536.c
+++ b/drivers/ata/pata_cs5536.c
@@ -33,7 +33,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/libata.h>
diff --git a/drivers/ata/pata_cypress.c b/drivers/ata/pata_cypress.c
index 810bc99..3435bd6 100644
--- a/drivers/ata/pata_cypress.c
+++ b/drivers/ata/pata_cypress.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_efar.c b/drivers/ata/pata_efar.c
index 3c12fd7..f440892 100644
--- a/drivers/ata/pata_efar.c
+++ b/drivers/ata/pata_efar.c
@@ -14,7 +14,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c
index 980b88e..cad9d45 100644
--- a/drivers/ata/pata_ep93xx.c
+++ b/drivers/ata/pata_ep93xx.c
@@ -34,7 +34,6 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <scsi/scsi_host.h>
 #include <linux/ata.h>
diff --git a/drivers/ata/pata_hpt366.c b/drivers/ata/pata_hpt366.c
index 35b5213..8e76f79 100644
--- a/drivers/ata/pata_hpt366.c
+++ b/drivers/ata/pata_hpt366.c
@@ -19,7 +19,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_hpt37x.c b/drivers/ata/pata_hpt37x.c
index a9d74ef..3ba843f 100644
--- a/drivers/ata/pata_hpt37x.c
+++ b/drivers/ata/pata_hpt37x.c
@@ -19,7 +19,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_hpt3x2n.c b/drivers/ata/pata_hpt3x2n.c
index 4be0398..b93c0f0 100644
--- a/drivers/ata/pata_hpt3x2n.c
+++ b/drivers/ata/pata_hpt3x2n.c
@@ -20,7 +20,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_hpt3x3.c b/drivers/ata/pata_hpt3x3.c
index 85cf286..255c5aa 100644
--- a/drivers/ata/pata_hpt3x3.c
+++ b/drivers/ata/pata_hpt3x3.c
@@ -16,7 +16,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_imx.c b/drivers/ata/pata_imx.c
index 26386f0..e0872db 100644
--- a/drivers/ata/pata_imx.c
+++ b/drivers/ata/pata_imx.c
@@ -15,7 +15,6 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <scsi/scsi_host.h>
 #include <linux/ata.h>
@@ -100,13 +99,9 @@
 	struct resource *io_res;
 	int ret;
 
-	io_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (io_res == NULL)
-		return -EINVAL;
-
 	irq = platform_get_irq(pdev, 0);
-	if (irq <= 0)
-		return -EINVAL;
+	if (irq < 0)
+		return irq;
 
 	priv = devm_kzalloc(&pdev->dev,
 				sizeof(struct pata_imx_priv), GFP_KERNEL);
@@ -119,7 +114,9 @@
 		return PTR_ERR(priv->clk);
 	}
 
-	clk_prepare_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return ret;
 
 	host = ata_host_alloc(&pdev->dev, 1);
 	if (!host) {
@@ -134,11 +131,10 @@
 	ap->pio_mask = ATA_PIO0;
 	ap->flags |= ATA_FLAG_SLAVE_POSS;
 
-	priv->host_regs = devm_ioremap(&pdev->dev, io_res->start,
-		resource_size(io_res));
-	if (!priv->host_regs) {
-		dev_err(&pdev->dev, "failed to map IO/CTL base\n");
-		ret = -EBUSY;
+	io_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->host_regs = devm_ioremap_resource(&pdev->dev, io_res);
+	if (IS_ERR(priv->host_regs)) {
+		ret = PTR_ERR(priv->host_regs);
 		goto err;
 	}
 
@@ -212,7 +208,9 @@
 	struct ata_host *host = dev_get_drvdata(dev);
 	struct pata_imx_priv *priv = host->private_data;
 
-	clk_prepare_enable(priv->clk);
+	int ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return ret;
 
 	__raw_writel(priv->ata_ctl, priv->host_regs + PATA_IMX_ATA_CONTROL);
 
diff --git a/drivers/ata/pata_it8213.c b/drivers/ata/pata_it8213.c
index 2a8dd95..81369d1 100644
--- a/drivers/ata/pata_it8213.c
+++ b/drivers/ata/pata_it8213.c
@@ -10,7 +10,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_it821x.c b/drivers/ata/pata_it821x.c
index 581e04d..dc3d787 100644
--- a/drivers/ata/pata_it821x.c
+++ b/drivers/ata/pata_it821x.c
@@ -72,7 +72,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
diff --git a/drivers/ata/pata_jmicron.c b/drivers/ata/pata_jmicron.c
index 76e739b0..b1cfa02 100644
--- a/drivers/ata/pata_jmicron.c
+++ b/drivers/ata/pata_jmicron.c
@@ -10,7 +10,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c
index be81642..bce2a8c 100644
--- a/drivers/ata/pata_legacy.c
+++ b/drivers/ata/pata_legacy.c
@@ -916,7 +916,6 @@
 			local_irq_restore(flags);
 			return BIOS;
 		}
-		local_irq_restore(flags);
 	}
 
 	if (ht6560a & mask)
diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c
index a4f5e78..6bad3df 100644
--- a/drivers/ata/pata_marvell.c
+++ b/drivers/ata/pata_marvell.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_mpiix.c b/drivers/ata/pata_mpiix.c
index 1f5f28b..f39a537 100644
--- a/drivers/ata/pata_mpiix.c
+++ b/drivers/ata/pata_mpiix.c
@@ -28,7 +28,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_netcell.c b/drivers/ata/pata_netcell.c
index ad1a0fe..e3b9709 100644
--- a/drivers/ata/pata_netcell.c
+++ b/drivers/ata/pata_netcell.c
@@ -7,7 +7,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_ninja32.c b/drivers/ata/pata_ninja32.c
index 9513e07..56201a6 100644
--- a/drivers/ata/pata_ninja32.c
+++ b/drivers/ata/pata_ninja32.c
@@ -37,7 +37,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_ns87410.c b/drivers/ata/pata_ns87410.c
index 0c424da..6154c3e 100644
--- a/drivers/ata/pata_ns87410.c
+++ b/drivers/ata/pata_ns87410.c
@@ -20,7 +20,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_ns87415.c b/drivers/ata/pata_ns87415.c
index 16dc3a6..d44df7c 100644
--- a/drivers/ata/pata_ns87415.c
+++ b/drivers/ata/pata_ns87415.c
@@ -25,7 +25,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_oldpiix.c b/drivers/ata/pata_oldpiix.c
index d77b2e1..319b644 100644
--- a/drivers/ata/pata_oldpiix.c
+++ b/drivers/ata/pata_oldpiix.c
@@ -16,7 +16,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_opti.c b/drivers/ata/pata_opti.c
index 4ea70cd..fb042e0 100644
--- a/drivers/ata/pata_opti.c
+++ b/drivers/ata/pata_opti.c
@@ -26,7 +26,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_optidma.c b/drivers/ata/pata_optidma.c
index 78ede3f..bb71ea2 100644
--- a/drivers/ata/pata_optidma.c
+++ b/drivers/ata/pata_optidma.c
@@ -25,7 +25,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_pcmcia.c b/drivers/ata/pata_pcmcia.c
index 40254f4..bcc4b96 100644
--- a/drivers/ata/pata_pcmcia.c
+++ b/drivers/ata/pata_pcmcia.c
@@ -26,7 +26,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c
index 9d874c8..1151f23 100644
--- a/drivers/ata/pata_pdc2027x.c
+++ b/drivers/ata/pata_pdc2027x.c
@@ -25,7 +25,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_pdc202xx_old.c b/drivers/ata/pata_pdc202xx_old.c
index c34fc50..defa050 100644
--- a/drivers/ata/pata_pdc202xx_old.c
+++ b/drivers/ata/pata_pdc202xx_old.c
@@ -15,7 +15,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_piccolo.c b/drivers/ata/pata_piccolo.c
index 2beb6b5..0b46be1 100644
--- a/drivers/ata/pata_piccolo.c
+++ b/drivers/ata/pata_piccolo.c
@@ -18,7 +18,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c
index 0279488..a5579b5 100644
--- a/drivers/ata/pata_platform.c
+++ b/drivers/ata/pata_platform.c
@@ -13,7 +13,6 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <scsi/scsi_host.h>
 #include <linux/ata.h>
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index a6f05ac..73259bf 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -20,7 +20,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/ata.h>
 #include <linux/libata.h>
diff --git a/drivers/ata/pata_radisys.c b/drivers/ata/pata_radisys.c
index f582ba1..be3f102 100644
--- a/drivers/ata/pata_radisys.c
+++ b/drivers/ata/pata_radisys.c
@@ -15,7 +15,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_rdc.c b/drivers/ata/pata_rdc.c
index 79a970f..521b213 100644
--- a/drivers/ata/pata_rdc.c
+++ b/drivers/ata/pata_rdc.c
@@ -24,7 +24,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_rz1000.c b/drivers/ata/pata_rz1000.c
index 040b093..caedc90 100644
--- a/drivers/ata/pata_rz1000.c
+++ b/drivers/ata/pata_rz1000.c
@@ -14,7 +14,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_sc1200.c b/drivers/ata/pata_sc1200.c
index ce2f828..96a232f 100644
--- a/drivers/ata/pata_sc1200.c
+++ b/drivers/ata/pata_sc1200.c
@@ -32,7 +32,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c
index f35f15f..f1f5b5a 100644
--- a/drivers/ata/pata_scc.c
+++ b/drivers/ata/pata_scc.c
@@ -35,7 +35,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_sch.c b/drivers/ata/pata_sch.c
index d3830c4..5a1cde0 100644
--- a/drivers/ata/pata_sch.c
+++ b/drivers/ata/pata_sch.c
@@ -27,7 +27,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c
index 96c6a79..e27f31f 100644
--- a/drivers/ata/pata_serverworks.c
+++ b/drivers/ata/pata_serverworks.c
@@ -34,7 +34,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_sil680.c b/drivers/ata/pata_sil680.c
index c4b0b07..73fe362 100644
--- a/drivers/ata/pata_sil680.c
+++ b/drivers/ata/pata_sil680.c
@@ -25,7 +25,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_sis.c b/drivers/ata/pata_sis.c
index 1e83636..78d913a 100644
--- a/drivers/ata/pata_sis.c
+++ b/drivers/ata/pata_sis.c
@@ -26,7 +26,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/pata_sl82c105.c b/drivers/ata/pata_sl82c105.c
index 6816911..900f0e4 100644
--- a/drivers/ata/pata_sl82c105.c
+++ b/drivers/ata/pata_sl82c105.c
@@ -19,7 +19,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_triflex.c b/drivers/ata/pata_triflex.c
index 94473da..7bc78e2 100644
--- a/drivers/ata/pata_triflex.c
+++ b/drivers/ata/pata_triflex.c
@@ -36,7 +36,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index c3ab9a6..f6c9632 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -55,7 +55,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/gfp.h>
diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c
index 8ea6e6a..f10631b 100644
--- a/drivers/ata/pdc_adma.c
+++ b/drivers/ata/pdc_adma.c
@@ -36,7 +36,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 523524b..0bb2cab 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -29,7 +29,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/device.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -462,8 +461,7 @@
 	int chan;
 	u32 tfr_reg, err_reg;
 	unsigned long flags;
-	struct sata_dwc_device *hsdev =
-		(struct sata_dwc_device *)hsdev_instance;
+	struct sata_dwc_device *hsdev = hsdev_instance;
 	struct ata_host *host = (struct ata_host *)hsdev->host;
 	struct ata_port *ap;
 	struct sata_dwc_device_port *hsdevp;
diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c
index 870b11e..65965cf 100644
--- a/drivers/ata/sata_highbank.c
+++ b/drivers/ata/sata_highbank.c
@@ -19,7 +19,6 @@
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/err.h>
 #include <linux/io.h>
@@ -142,7 +141,7 @@
 					ssize_t size)
 {
 	struct ahci_host_priv *hpriv =  ap->host->private_data;
-	struct ecx_plat_data *pdata = (struct ecx_plat_data *) hpriv->plat_data;
+	struct ecx_plat_data *pdata = hpriv->plat_data;
 	struct ahci_port_priv *pp = ap->private_data;
 	unsigned long flags;
 	int pmp, i;
@@ -403,6 +402,7 @@
 	static const unsigned long timing[] = { 5, 100, 500};
 	struct ata_port *ap = link->ap;
 	struct ahci_port_priv *pp = ap->private_data;
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	u8 *d2h_fis = pp->rx_fis + RX_FIS_D2H_REG;
 	struct ata_taskfile tf;
 	bool online;
@@ -431,7 +431,7 @@
 			break;
 	} while (!online && retry--);
 
-	ahci_start_engine(ap);
+	hpriv->start_engine(ap);
 
 	if (online)
 		*class = ahci_dev_classify(ap);
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 20a7517..05c8a44 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -4104,7 +4104,6 @@
 	if (!hpriv->port_phys)
 		return -ENOMEM;
 	host->private_data = hpriv;
-	hpriv->n_ports = n_ports;
 	hpriv->board_idx = chip_soc;
 
 	host->iomap = NULL;
@@ -4126,17 +4125,24 @@
 			clk_prepare_enable(hpriv->port_clks[port]);
 
 		sprintf(port_number, "port%d", port);
-		hpriv->port_phys[port] = devm_phy_get(&pdev->dev, port_number);
+		hpriv->port_phys[port] = devm_phy_optional_get(&pdev->dev,
+							       port_number);
 		if (IS_ERR(hpriv->port_phys[port])) {
 			rc = PTR_ERR(hpriv->port_phys[port]);
 			hpriv->port_phys[port] = NULL;
-			if ((rc != -EPROBE_DEFER) && (rc != -ENODEV))
-				dev_warn(&pdev->dev, "error getting phy");
+			if (rc != -EPROBE_DEFER)
+				dev_warn(&pdev->dev, "error getting phy %d", rc);
+
+			/* Cleanup only the initialized ports */
+			hpriv->n_ports = port;
 			goto err;
 		} else
 			phy_power_on(hpriv->port_phys[port]);
 	}
 
+	/* All the ports have been initialized */
+	hpriv->n_ports = n_ports;
+
 	/*
 	 * (Re-)program MBUS remapping windows if we are asked to.
 	 */
@@ -4174,7 +4180,7 @@
 		clk_disable_unprepare(hpriv->clk);
 		clk_put(hpriv->clk);
 	}
-	for (port = 0; port < n_ports; port++) {
+	for (port = 0; port < hpriv->n_ports; port++) {
 		if (!IS_ERR(hpriv->port_clks[port])) {
 			clk_disable_unprepare(hpriv->port_clks[port]);
 			clk_put(hpriv->port_clks[port]);
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index d74def8..ba5f271 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -40,7 +40,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index 97f4acb..3638887 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -35,7 +35,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c
index 3b0dd57..9a6bd4c 100644
--- a/drivers/ata/sata_qstor.c
+++ b/drivers/ata/sata_qstor.c
@@ -31,7 +31,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index d67fc35..3062f86 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -37,7 +37,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
@@ -157,6 +156,7 @@
 	{ "ST380011ASL",	SIL_QUIRK_MOD15WRITE },
 	{ "ST3120022ASL",	SIL_QUIRK_MOD15WRITE },
 	{ "ST3160021ASL",	SIL_QUIRK_MOD15WRITE },
+	{ "TOSHIBA MK2561GSYN",	SIL_QUIRK_MOD15WRITE },
 	{ "Maxtor 4D060H3",	SIL_QUIRK_UDMA5MAX },
 	{ }
 };
diff --git a/drivers/ata/sata_sis.c b/drivers/ata/sata_sis.c
index 1ad2f62..b513428 100644
--- a/drivers/ata/sata_sis.c
+++ b/drivers/ata/sata_sis.c
@@ -33,7 +33,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
diff --git a/drivers/ata/sata_svw.c b/drivers/ata/sata_svw.c
index dc4f701..c630fa8 100644
--- a/drivers/ata/sata_svw.c
+++ b/drivers/ata/sata_svw.c
@@ -39,7 +39,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index 9947010..39b5de6 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -82,7 +82,6 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
@@ -1021,8 +1020,7 @@
 	idx++;
 	dist = ((long) (window_size - (offset + size))) >= 0 ? size :
 		(long) (window_size - offset);
-	memcpy_fromio((char *) psource, (char *) (dimm_mmio + offset / 4),
-		      dist);
+	memcpy_fromio(psource, dimm_mmio + offset / 4, dist);
 
 	psource += dist;
 	size -= dist;
@@ -1031,8 +1029,7 @@
 		readl(mmio + PDC_GENERAL_CTLR);
 		writel(((idx) << page_mask), mmio + PDC_DIMM_WINDOW_CTLR);
 		readl(mmio + PDC_DIMM_WINDOW_CTLR);
-		memcpy_fromio((char *) psource, (char *) (dimm_mmio),
-			      window_size / 4);
+		memcpy_fromio(psource, dimm_mmio, window_size / 4);
 		psource += window_size;
 		size -= window_size;
 		idx++;
@@ -1043,8 +1040,7 @@
 		readl(mmio + PDC_GENERAL_CTLR);
 		writel(((idx) << page_mask), mmio + PDC_DIMM_WINDOW_CTLR);
 		readl(mmio + PDC_DIMM_WINDOW_CTLR);
-		memcpy_fromio((char *) psource, (char *) (dimm_mmio),
-			      size / 4);
+		memcpy_fromio(psource, dimm_mmio, size / 4);
 	}
 }
 #endif
diff --git a/drivers/ata/sata_uli.c b/drivers/ata/sata_uli.c
index 6d64891..08f98c3 100644
--- a/drivers/ata/sata_uli.c
+++ b/drivers/ata/sata_uli.c
@@ -28,7 +28,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c
index 87f056e..f72e842 100644
--- a/drivers/ata/sata_via.c
+++ b/drivers/ata/sata_via.c
@@ -36,7 +36,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/drivers/ata/sata_vsc.c b/drivers/ata/sata_vsc.c
index 44f304b..29e847a 100644
--- a/drivers/ata/sata_vsc.c
+++ b/drivers/ata/sata_vsc.c
@@ -37,7 +37,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
diff --git a/drivers/base/component.c b/drivers/base/component.c
index c53efe6..c477899 100644
--- a/drivers/base/component.c
+++ b/drivers/base/component.c
@@ -133,9 +133,16 @@
 			goto out;
 		}
 
+		if (!devres_open_group(master->dev, NULL, GFP_KERNEL)) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
 		/* Found all components */
 		ret = master->ops->bind(master->dev);
 		if (ret < 0) {
+			devres_release_group(master->dev, NULL);
+			dev_info(master->dev, "master bind failed: %d\n", ret);
 			master_remove_components(master);
 			goto out;
 		}
@@ -166,6 +173,7 @@
 {
 	if (master->bound) {
 		master->ops->unbind(master->dev);
+		devres_release_group(master->dev, NULL);
 		master->bound = false;
 	}
 
diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c
index 1e16cbd..61d6d62 100644
--- a/drivers/base/dma-buf.c
+++ b/drivers/base/dma-buf.c
@@ -616,36 +616,35 @@
 	if (ret)
 		return ret;
 
-	seq_printf(s, "\nDma-buf Objects:\n");
-	seq_printf(s, "\texp_name\tsize\tflags\tmode\tcount\n");
+	seq_puts(s, "\nDma-buf Objects:\n");
+	seq_puts(s, "size\tflags\tmode\tcount\texp_name\n");
 
 	list_for_each_entry(buf_obj, &db_list.head, list_node) {
 		ret = mutex_lock_interruptible(&buf_obj->lock);
 
 		if (ret) {
-			seq_printf(s,
-				  "\tERROR locking buffer object: skipping\n");
+			seq_puts(s,
+				 "\tERROR locking buffer object: skipping\n");
 			continue;
 		}
 
-		seq_printf(s, "\t");
-
-		seq_printf(s, "\t%s\t%08zu\t%08x\t%08x\t%08ld\n",
-				buf_obj->exp_name, buf_obj->size,
+		seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\n",
+				buf_obj->size,
 				buf_obj->file->f_flags, buf_obj->file->f_mode,
-				(long)(buf_obj->file->f_count.counter));
+				(long)(buf_obj->file->f_count.counter),
+				buf_obj->exp_name);
 
-		seq_printf(s, "\t\tAttached Devices:\n");
+		seq_puts(s, "\tAttached Devices:\n");
 		attach_count = 0;
 
 		list_for_each_entry(attach_obj, &buf_obj->attachments, node) {
-			seq_printf(s, "\t\t");
+			seq_puts(s, "\t");
 
-			seq_printf(s, "%s\n", attach_obj->dev->init_name);
+			seq_printf(s, "%s\n", dev_name(attach_obj->dev));
 			attach_count++;
 		}
 
-		seq_printf(s, "\n\t\tTotal %d devices attached\n",
+		seq_printf(s, "Total %d devices attached\n\n",
 				attach_count);
 
 		count++;
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 8a97ddf..c30df50e 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -1580,6 +1580,7 @@
 	switch (mode) {
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
+	case PM_RESTORE_PREPARE:
 		kill_requests_without_uevent();
 		device_cache_fw_images();
 		break;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 8184451..422b7d8 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -874,7 +874,7 @@
 		/* Non-zero page count for non-head members of
 		 * compound pages is no longer allowed by the kernel.
 		 */
-		page = compound_trans_head(bv.bv_page);
+		page = compound_head(bv.bv_page);
 		atomic_inc(&page->_count);
 	}
 }
@@ -887,7 +887,7 @@
 	struct bvec_iter iter;
 
 	bio_for_each_segment(bv, bio, iter) {
-		page = compound_trans_head(bv.bv_page);
+		page = compound_head(bv.bv_page);
 		atomic_dec(&page->_count);
 	}
 }
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 2023043..8f5565b 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -961,17 +961,31 @@
 {
 }
 
-static DECLARE_WORK(floppy_work, NULL);
+static void (*floppy_work_fn)(void);
+
+static void floppy_work_workfn(struct work_struct *work)
+{
+	floppy_work_fn();
+}
+
+static DECLARE_WORK(floppy_work, floppy_work_workfn);
 
 static void schedule_bh(void (*handler)(void))
 {
 	WARN_ON(work_pending(&floppy_work));
 
-	PREPARE_WORK(&floppy_work, (work_func_t)handler);
+	floppy_work_fn = handler;
 	queue_work(floppy_wq, &floppy_work);
 }
 
-static DECLARE_DELAYED_WORK(fd_timer, NULL);
+static void (*fd_timer_fn)(void) = NULL;
+
+static void fd_timer_workfn(struct work_struct *work)
+{
+	fd_timer_fn();
+}
+
+static DECLARE_DELAYED_WORK(fd_timer, fd_timer_workfn);
 
 static void cancel_activity(void)
 {
@@ -982,7 +996,7 @@
 
 /* this function makes sure that the disk stays in the drive during the
  * transfer */
-static void fd_watchdog(struct work_struct *arg)
+static void fd_watchdog(void)
 {
 	debug_dcl(DP->flags, "calling disk change from watchdog\n");
 
@@ -993,7 +1007,7 @@
 		reset_fdc();
 	} else {
 		cancel_delayed_work(&fd_timer);
-		PREPARE_DELAYED_WORK(&fd_timer, fd_watchdog);
+		fd_timer_fn = fd_watchdog;
 		queue_delayed_work(floppy_wq, &fd_timer, HZ / 10);
 	}
 }
@@ -1005,7 +1019,8 @@
 }
 
 /* waits for a delay (spinup or select) to pass */
-static int fd_wait_for_completion(unsigned long expires, work_func_t function)
+static int fd_wait_for_completion(unsigned long expires,
+				  void (*function)(void))
 {
 	if (FDCS->reset) {
 		reset_fdc();	/* do the reset during sleep to win time
@@ -1016,7 +1031,7 @@
 
 	if (time_before(jiffies, expires)) {
 		cancel_delayed_work(&fd_timer);
-		PREPARE_DELAYED_WORK(&fd_timer, function);
+		fd_timer_fn = function;
 		queue_delayed_work(floppy_wq, &fd_timer, expires - jiffies);
 		return 1;
 	}
@@ -1334,8 +1349,7 @@
 	 * Pause 5 msec to avoid trouble. (Needs to be 2 jiffies)
 	 */
 	FDCS->dtr = raw_cmd->rate & 3;
-	return fd_wait_for_completion(jiffies + 2UL * HZ / 100,
-				      (work_func_t)floppy_ready);
+	return fd_wait_for_completion(jiffies + 2UL * HZ / 100, floppy_ready);
 }				/* fdc_dtr */
 
 static void tell_sector(void)
@@ -1440,7 +1454,7 @@
 	int flags;
 	int dflags;
 	unsigned long ready_date;
-	work_func_t function;
+	void (*function)(void);
 
 	flags = raw_cmd->flags;
 	if (flags & (FD_RAW_READ | FD_RAW_WRITE))
@@ -1454,9 +1468,9 @@
 		 */
 		if (time_after(ready_date, jiffies + DP->select_delay)) {
 			ready_date -= DP->select_delay;
-			function = (work_func_t)floppy_start;
+			function = floppy_start;
 		} else
-			function = (work_func_t)setup_rw_floppy;
+			function = setup_rw_floppy;
 
 		/* wait until the floppy is spinning fast enough */
 		if (fd_wait_for_completion(ready_date, function))
@@ -1486,7 +1500,7 @@
 		inr = result();
 		cont->interrupt();
 	} else if (flags & FD_RAW_NEED_DISK)
-		fd_watchdog(NULL);
+		fd_watchdog();
 }
 
 static int blind_seek;
@@ -1863,7 +1877,7 @@
 
 	/* wait_for_completion also schedules reset if needed. */
 	return fd_wait_for_completion(DRS->select_date + DP->select_delay,
-				      (work_func_t)function);
+				      function);
 }
 
 static void floppy_ready(void)
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 5160269..d777bb7 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -4498,7 +4498,7 @@
 	}
 	dev_info(&pdev->dev, "NUMA node %d (closest: %d,%d, probe on %d:%d)\n",
 		my_node, pcibus_to_node(pdev->bus), dev_to_node(&pdev->dev),
-		cpu_to_node(smp_processor_id()), smp_processor_id());
+		cpu_to_node(raw_smp_processor_id()), raw_smp_processor_id());
 
 	dd = kzalloc_node(sizeof(struct driver_data), GFP_KERNEL, my_node);
 	if (dd == NULL) {
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index b52e9a6..54174cb 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -53,7 +53,7 @@
 #define MTIP_FTL_REBUILD_TIMEOUT_MS	2400000
 
 /* unaligned IO handling */
-#define MTIP_MAX_UNALIGNED_SLOTS	8
+#define MTIP_MAX_UNALIGNED_SLOTS	2
 
 /* Macro to extract the tag bit number from a tag value. */
 #define MTIP_TAG_BIT(tag)	(tag & 0x1F)
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 3107282..091b9ea 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -60,7 +60,9 @@
 	NULL_IRQ_NONE		= 0,
 	NULL_IRQ_SOFTIRQ	= 1,
 	NULL_IRQ_TIMER		= 2,
+};
 
+enum {
 	NULL_Q_BIO		= 0,
 	NULL_Q_RQ		= 1,
 	NULL_Q_MQ		= 2,
@@ -172,18 +174,20 @@
 
 static void end_cmd(struct nullb_cmd *cmd)
 {
-	if (cmd->rq) {
-		if (queue_mode == NULL_Q_MQ)
-			blk_mq_end_io(cmd->rq, 0);
-		else {
-			INIT_LIST_HEAD(&cmd->rq->queuelist);
-			blk_end_request_all(cmd->rq, 0);
-		}
-	} else if (cmd->bio)
+	switch (queue_mode)  {
+	case NULL_Q_MQ:
+		blk_mq_end_io(cmd->rq, 0);
+		return;
+	case NULL_Q_RQ:
+		INIT_LIST_HEAD(&cmd->rq->queuelist);
+		blk_end_request_all(cmd->rq, 0);
+		break;
+	case NULL_Q_BIO:
 		bio_endio(cmd->bio, 0);
+		break;
+	}
 
-	if (queue_mode != NULL_Q_MQ)
-		free_cmd(cmd);
+	free_cmd(cmd);
 }
 
 static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
@@ -195,6 +199,7 @@
 	cq = &per_cpu(completion_queues, smp_processor_id());
 
 	while ((entry = llist_del_all(&cq->list)) != NULL) {
+		entry = llist_reverse_order(entry);
 		do {
 			cmd = container_of(entry, struct nullb_cmd, ll_list);
 			end_cmd(cmd);
@@ -221,62 +226,32 @@
 
 static void null_softirq_done_fn(struct request *rq)
 {
-	blk_end_request_all(rq, 0);
+	end_cmd(rq->special);
 }
 
-#ifdef CONFIG_SMP
-
-static void null_ipi_cmd_end_io(void *data)
-{
-	struct completion_queue *cq;
-	struct llist_node *entry, *next;
-	struct nullb_cmd *cmd;
-
-	cq = &per_cpu(completion_queues, smp_processor_id());
-
-	entry = llist_del_all(&cq->list);
-
-	while (entry) {
-		next = entry->next;
-		cmd = llist_entry(entry, struct nullb_cmd, ll_list);
-		end_cmd(cmd);
-		entry = next;
-	}
-}
-
-static void null_cmd_end_ipi(struct nullb_cmd *cmd)
-{
-	struct call_single_data *data = &cmd->csd;
-	int cpu = get_cpu();
-	struct completion_queue *cq = &per_cpu(completion_queues, cpu);
-
-	cmd->ll_list.next = NULL;
-
-	if (llist_add(&cmd->ll_list, &cq->list)) {
-		data->func = null_ipi_cmd_end_io;
-		data->flags = 0;
-		__smp_call_function_single(cpu, data, 0);
-	}
-
-	put_cpu();
-}
-
-#endif /* CONFIG_SMP */
-
 static inline void null_handle_cmd(struct nullb_cmd *cmd)
 {
 	/* Complete IO by inline, softirq or timer */
 	switch (irqmode) {
+	case NULL_IRQ_SOFTIRQ:
+		switch (queue_mode)  {
+		case NULL_Q_MQ:
+			blk_mq_complete_request(cmd->rq);
+			break;
+		case NULL_Q_RQ:
+			blk_complete_request(cmd->rq);
+			break;
+		case NULL_Q_BIO:
+			/*
+			 * XXX: no proper submitting cpu information available.
+			 */
+			end_cmd(cmd);
+			break;
+		}
+		break;
 	case NULL_IRQ_NONE:
 		end_cmd(cmd);
 		break;
-	case NULL_IRQ_SOFTIRQ:
-#ifdef CONFIG_SMP
-		null_cmd_end_ipi(cmd);
-#else
-		end_cmd(cmd);
-#endif
-		break;
 	case NULL_IRQ_TIMER:
 		null_cmd_end_timer(cmd);
 		break;
@@ -411,6 +386,7 @@
 	.queue_rq       = null_queue_rq,
 	.map_queue      = blk_mq_map_queue,
 	.init_hctx	= null_init_hctx,
+	.complete	= null_softirq_done_fn,
 };
 
 static struct blk_mq_reg null_mq_reg = {
@@ -609,13 +585,6 @@
 {
 	unsigned int i;
 
-#if !defined(CONFIG_SMP)
-	if (irqmode == NULL_IRQ_SOFTIRQ) {
-		pr_warn("null_blk: softirq completions not available.\n");
-		pr_warn("null_blk: using direct completions.\n");
-		irqmode = NULL_IRQ_NONE;
-	}
-#endif
 	if (bs > PAGE_SIZE) {
 		pr_warn("null_blk: invalid block size\n");
 		pr_warn("null_blk: defaults block size to %lu\n", PAGE_SIZE);
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 1f14ac4..8459e4e 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -46,7 +46,6 @@
 #define NVME_Q_DEPTH 1024
 #define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
 #define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
-#define NVME_MINORS 64
 #define ADMIN_TIMEOUT	(60 * HZ)
 
 static int nvme_major;
@@ -58,6 +57,17 @@
 static DEFINE_SPINLOCK(dev_list_lock);
 static LIST_HEAD(dev_list);
 static struct task_struct *nvme_thread;
+static struct workqueue_struct *nvme_workq;
+
+static void nvme_reset_failed_dev(struct work_struct *ws);
+
+struct async_cmd_info {
+	struct kthread_work work;
+	struct kthread_worker *worker;
+	u32 result;
+	int status;
+	void *ctx;
+};
 
 /*
  * An NVM Express queue.  Each device has at least two (one for admin
@@ -66,6 +76,7 @@
 struct nvme_queue {
 	struct device *q_dmadev;
 	struct nvme_dev *dev;
+	char irqname[24];	/* nvme4294967295-65535\0 */
 	spinlock_t q_lock;
 	struct nvme_command *sq_cmds;
 	volatile struct nvme_completion *cqes;
@@ -80,9 +91,11 @@
 	u16 sq_head;
 	u16 sq_tail;
 	u16 cq_head;
+	u16 qid;
 	u8 cq_phase;
 	u8 cqe_seen;
 	u8 q_suspended;
+	struct async_cmd_info cmdinfo;
 	unsigned long cmdid_data[];
 };
 
@@ -97,6 +110,7 @@
 	BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != 4096);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != 4096);
@@ -111,6 +125,7 @@
 	nvme_completion_fn fn;
 	void *ctx;
 	unsigned long timeout;
+	int aborted;
 };
 
 static struct nvme_cmd_info *nvme_cmd_info(struct nvme_queue *nvmeq)
@@ -154,6 +169,7 @@
 	info[cmdid].fn = handler;
 	info[cmdid].ctx = ctx;
 	info[cmdid].timeout = jiffies + timeout;
+	info[cmdid].aborted = 0;
 	return cmdid;
 }
 
@@ -172,6 +188,7 @@
 #define CMD_CTX_COMPLETED	(0x310 + CMD_CTX_BASE)
 #define CMD_CTX_INVALID		(0x314 + CMD_CTX_BASE)
 #define CMD_CTX_FLUSH		(0x318 + CMD_CTX_BASE)
+#define CMD_CTX_ABORT		(0x31C + CMD_CTX_BASE)
 
 static void special_completion(struct nvme_dev *dev, void *ctx,
 						struct nvme_completion *cqe)
@@ -180,6 +197,10 @@
 		return;
 	if (ctx == CMD_CTX_FLUSH)
 		return;
+	if (ctx == CMD_CTX_ABORT) {
+		++dev->abort_limit;
+		return;
+	}
 	if (ctx == CMD_CTX_COMPLETED) {
 		dev_warn(&dev->pci_dev->dev,
 				"completed id %d twice on queue %d\n",
@@ -196,6 +217,15 @@
 	dev_warn(&dev->pci_dev->dev, "Unknown special completion %p\n", ctx);
 }
 
+static void async_completion(struct nvme_dev *dev, void *ctx,
+						struct nvme_completion *cqe)
+{
+	struct async_cmd_info *cmdinfo = ctx;
+	cmdinfo->result = le32_to_cpup(&cqe->result);
+	cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
+	queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
+}
+
 /*
  * Called with local interrupts disabled and the q_lock held.  May not sleep.
  */
@@ -693,7 +723,7 @@
 	if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
 		return 0;
 
-	writel(head, nvmeq->q_db + (1 << nvmeq->dev->db_stride));
+	writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
 	nvmeq->cq_head = head;
 	nvmeq->cq_phase = phase;
 
@@ -804,12 +834,34 @@
 	return cmdinfo.status;
 }
 
+static int nvme_submit_async_cmd(struct nvme_queue *nvmeq,
+			struct nvme_command *cmd,
+			struct async_cmd_info *cmdinfo, unsigned timeout)
+{
+	int cmdid;
+
+	cmdid = alloc_cmdid_killable(nvmeq, cmdinfo, async_completion, timeout);
+	if (cmdid < 0)
+		return cmdid;
+	cmdinfo->status = -EINTR;
+	cmd->common.command_id = cmdid;
+	nvme_submit_cmd(nvmeq, cmd);
+	return 0;
+}
+
 int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
 								u32 *result)
 {
 	return nvme_submit_sync_cmd(dev->queues[0], cmd, result, ADMIN_TIMEOUT);
 }
 
+static int nvme_submit_admin_cmd_async(struct nvme_dev *dev,
+		struct nvme_command *cmd, struct async_cmd_info *cmdinfo)
+{
+	return nvme_submit_async_cmd(dev->queues[0], cmd, cmdinfo,
+								ADMIN_TIMEOUT);
+}
+
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
 {
 	int status;
@@ -920,6 +972,56 @@
 }
 
 /**
+ * nvme_abort_cmd - Attempt aborting a command
+ * @cmdid: Command id of a timed out IO
+ * @queue: The queue with timed out IO
+ *
+ * Schedule controller reset if the command was already aborted once before and
+ * still hasn't been returned to the driver, or if this is the admin queue.
+ */
+static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq)
+{
+	int a_cmdid;
+	struct nvme_command cmd;
+	struct nvme_dev *dev = nvmeq->dev;
+	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
+
+	if (!nvmeq->qid || info[cmdid].aborted) {
+		if (work_busy(&dev->reset_work))
+			return;
+		list_del_init(&dev->node);
+		dev_warn(&dev->pci_dev->dev,
+			"I/O %d QID %d timeout, reset controller\n", cmdid,
+								nvmeq->qid);
+		dev->reset_workfn = nvme_reset_failed_dev;
+		queue_work(nvme_workq, &dev->reset_work);
+		return;
+	}
+
+	if (!dev->abort_limit)
+		return;
+
+	a_cmdid = alloc_cmdid(dev->queues[0], CMD_CTX_ABORT, special_completion,
+								ADMIN_TIMEOUT);
+	if (a_cmdid < 0)
+		return;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.abort.opcode = nvme_admin_abort_cmd;
+	cmd.abort.cid = cmdid;
+	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
+	cmd.abort.command_id = a_cmdid;
+
+	--dev->abort_limit;
+	info[cmdid].aborted = 1;
+	info[cmdid].timeout = jiffies + ADMIN_TIMEOUT;
+
+	dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", cmdid,
+							nvmeq->qid);
+	nvme_submit_cmd(dev->queues[0], &cmd);
+}
+
+/**
  * nvme_cancel_ios - Cancel outstanding I/Os
  * @queue: The queue to cancel I/Os on
  * @timeout: True to only cancel I/Os which have timed out
@@ -942,7 +1044,12 @@
 			continue;
 		if (info[cmdid].ctx == CMD_CTX_CANCELLED)
 			continue;
-		dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d\n", cmdid);
+		if (timeout && nvmeq->dev->initialized) {
+			nvme_abort_cmd(cmdid, nvmeq);
+			continue;
+		}
+		dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n", cmdid,
+								nvmeq->qid);
 		ctx = cancel_cmdid(nvmeq, cmdid, &fn);
 		fn(nvmeq->dev, ctx, &cqe);
 	}
@@ -964,26 +1071,31 @@
 	kfree(nvmeq);
 }
 
-static void nvme_free_queues(struct nvme_dev *dev)
+static void nvme_free_queues(struct nvme_dev *dev, int lowest)
 {
 	int i;
 
-	for (i = dev->queue_count - 1; i >= 0; i--) {
+	for (i = dev->queue_count - 1; i >= lowest; i--) {
 		nvme_free_queue(dev->queues[i]);
 		dev->queue_count--;
 		dev->queues[i] = NULL;
 	}
 }
 
-static void nvme_disable_queue(struct nvme_dev *dev, int qid)
+/**
+ * nvme_suspend_queue - put queue into suspended state
+ * @nvmeq - queue to suspend
+ *
+ * Returns 1 if already suspended, 0 otherwise.
+ */
+static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 {
-	struct nvme_queue *nvmeq = dev->queues[qid];
-	int vector = dev->entry[nvmeq->cq_vector].vector;
+	int vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
 
 	spin_lock_irq(&nvmeq->q_lock);
 	if (nvmeq->q_suspended) {
 		spin_unlock_irq(&nvmeq->q_lock);
-		return;
+		return 1;
 	}
 	nvmeq->q_suspended = 1;
 	spin_unlock_irq(&nvmeq->q_lock);
@@ -991,18 +1103,35 @@
 	irq_set_affinity_hint(vector, NULL);
 	free_irq(vector, nvmeq);
 
-	/* Don't tell the adapter to delete the admin queue */
-	if (qid) {
-		adapter_delete_sq(dev, qid);
-		adapter_delete_cq(dev, qid);
-	}
+	return 0;
+}
 
+static void nvme_clear_queue(struct nvme_queue *nvmeq)
+{
 	spin_lock_irq(&nvmeq->q_lock);
 	nvme_process_cq(nvmeq);
 	nvme_cancel_ios(nvmeq, false);
 	spin_unlock_irq(&nvmeq->q_lock);
 }
 
+static void nvme_disable_queue(struct nvme_dev *dev, int qid)
+{
+	struct nvme_queue *nvmeq = dev->queues[qid];
+
+	if (!nvmeq)
+		return;
+	if (nvme_suspend_queue(nvmeq))
+		return;
+
+	/* Don't tell the adapter to delete the admin queue.
+	 * Don't tell a removed adapter to delete IO queues. */
+	if (qid && readl(&dev->bar->csts) != -1) {
+		adapter_delete_sq(dev, qid);
+		adapter_delete_cq(dev, qid);
+	}
+	nvme_clear_queue(nvmeq);
+}
+
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 							int depth, int vector)
 {
@@ -1025,15 +1154,18 @@
 
 	nvmeq->q_dmadev = dmadev;
 	nvmeq->dev = dev;
+	snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
+			dev->instance, qid);
 	spin_lock_init(&nvmeq->q_lock);
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
 	init_waitqueue_head(&nvmeq->sq_full);
 	init_waitqueue_entry(&nvmeq->sq_cong_wait, nvme_thread);
 	bio_list_init(&nvmeq->sq_cong);
-	nvmeq->q_db = &dev->dbs[qid << (dev->db_stride + 1)];
+	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
 	nvmeq->q_depth = depth;
 	nvmeq->cq_vector = vector;
+	nvmeq->qid = qid;
 	nvmeq->q_suspended = 1;
 	dev->queue_count++;
 
@@ -1052,11 +1184,10 @@
 {
 	if (use_threaded_interrupts)
 		return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector,
-					nvme_irq_check, nvme_irq,
-					IRQF_DISABLED | IRQF_SHARED,
+					nvme_irq_check, nvme_irq, IRQF_SHARED,
 					name, nvmeq);
 	return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq,
-				IRQF_DISABLED | IRQF_SHARED, name, nvmeq);
+				IRQF_SHARED, name, nvmeq);
 }
 
 static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
@@ -1067,7 +1198,7 @@
 	nvmeq->sq_tail = 0;
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
-	nvmeq->q_db = &dev->dbs[qid << (dev->db_stride + 1)];
+	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
 	memset(nvmeq->cmdid_data, 0, extra);
 	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
 	nvme_cancel_ios(nvmeq, false);
@@ -1087,13 +1218,13 @@
 	if (result < 0)
 		goto release_cq;
 
-	result = queue_request_irq(dev, nvmeq, "nvme");
+	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
 	if (result < 0)
 		goto release_sq;
 
-	spin_lock(&nvmeq->q_lock);
+	spin_lock_irq(&nvmeq->q_lock);
 	nvme_init_queue(nvmeq, qid);
-	spin_unlock(&nvmeq->q_lock);
+	spin_unlock_irq(&nvmeq->q_lock);
 
 	return result;
 
@@ -1205,13 +1336,13 @@
 	if (result)
 		return result;
 
-	result = queue_request_irq(dev, nvmeq, "nvme admin");
+	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
 	if (result)
 		return result;
 
-	spin_lock(&nvmeq->q_lock);
+	spin_lock_irq(&nvmeq->q_lock);
 	nvme_init_queue(nvmeq, 0);
-	spin_unlock(&nvmeq->q_lock);
+	spin_unlock_irq(&nvmeq->q_lock);
 	return result;
 }
 
@@ -1487,10 +1618,47 @@
 	}
 }
 
+#ifdef CONFIG_COMPAT
+static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
+					unsigned int cmd, unsigned long arg)
+{
+	struct nvme_ns *ns = bdev->bd_disk->private_data;
+
+	switch (cmd) {
+	case SG_IO:
+		return nvme_sg_io32(ns, arg);
+	}
+	return nvme_ioctl(bdev, mode, cmd, arg);
+}
+#else
+#define nvme_compat_ioctl	NULL
+#endif
+
+static int nvme_open(struct block_device *bdev, fmode_t mode)
+{
+	struct nvme_ns *ns = bdev->bd_disk->private_data;
+	struct nvme_dev *dev = ns->dev;
+
+	kref_get(&dev->kref);
+	return 0;
+}
+
+static void nvme_free_dev(struct kref *kref);
+
+static void nvme_release(struct gendisk *disk, fmode_t mode)
+{
+	struct nvme_ns *ns = disk->private_data;
+	struct nvme_dev *dev = ns->dev;
+
+	kref_put(&dev->kref, nvme_free_dev);
+}
+
 static const struct block_device_operations nvme_fops = {
 	.owner		= THIS_MODULE,
 	.ioctl		= nvme_ioctl,
-	.compat_ioctl	= nvme_ioctl,
+	.compat_ioctl	= nvme_compat_ioctl,
+	.open		= nvme_open,
+	.release	= nvme_release,
 };
 
 static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
@@ -1514,13 +1682,24 @@
 
 static int nvme_kthread(void *data)
 {
-	struct nvme_dev *dev;
+	struct nvme_dev *dev, *next;
 
 	while (!kthread_should_stop()) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		spin_lock(&dev_list_lock);
-		list_for_each_entry(dev, &dev_list, node) {
+		list_for_each_entry_safe(dev, next, &dev_list, node) {
 			int i;
+			if (readl(&dev->bar->csts) & NVME_CSTS_CFS &&
+							dev->initialized) {
+				if (work_busy(&dev->reset_work))
+					continue;
+				list_del_init(&dev->node);
+				dev_warn(&dev->pci_dev->dev,
+					"Failed status, reset controller\n");
+				dev->reset_workfn = nvme_reset_failed_dev;
+				queue_work(nvme_workq, &dev->reset_work);
+				continue;
+			}
 			for (i = 0; i < dev->queue_count; i++) {
 				struct nvme_queue *nvmeq = dev->queues[i];
 				if (!nvmeq)
@@ -1541,33 +1720,6 @@
 	return 0;
 }
 
-static DEFINE_IDA(nvme_index_ida);
-
-static int nvme_get_ns_idx(void)
-{
-	int index, error;
-
-	do {
-		if (!ida_pre_get(&nvme_index_ida, GFP_KERNEL))
-			return -1;
-
-		spin_lock(&dev_list_lock);
-		error = ida_get_new(&nvme_index_ida, &index);
-		spin_unlock(&dev_list_lock);
-	} while (error == -EAGAIN);
-
-	if (error)
-		index = -1;
-	return index;
-}
-
-static void nvme_put_ns_idx(int index)
-{
-	spin_lock(&dev_list_lock);
-	ida_remove(&nvme_index_ida, index);
-	spin_unlock(&dev_list_lock);
-}
-
 static void nvme_config_discard(struct nvme_ns *ns)
 {
 	u32 logical_block_size = queue_logical_block_size(ns->queue);
@@ -1601,7 +1753,7 @@
 	ns->dev = dev;
 	ns->queue->queuedata = ns;
 
-	disk = alloc_disk(NVME_MINORS);
+	disk = alloc_disk(0);
 	if (!disk)
 		goto out_free_queue;
 	ns->ns_id = nsid;
@@ -1614,12 +1766,12 @@
 		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
 
 	disk->major = nvme_major;
-	disk->minors = NVME_MINORS;
-	disk->first_minor = NVME_MINORS * nvme_get_ns_idx();
+	disk->first_minor = 0;
 	disk->fops = &nvme_fops;
 	disk->private_data = ns;
 	disk->queue = ns->queue;
 	disk->driverfs_dev = &dev->pci_dev->dev;
+	disk->flags = GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "nvme%dn%d", dev->instance, nsid);
 	set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
 
@@ -1635,15 +1787,6 @@
 	return NULL;
 }
 
-static void nvme_ns_free(struct nvme_ns *ns)
-{
-	int index = ns->disk->first_minor / NVME_MINORS;
-	put_disk(ns->disk);
-	nvme_put_ns_idx(index);
-	blk_cleanup_queue(ns->queue);
-	kfree(ns);
-}
-
 static int set_queue_count(struct nvme_dev *dev, int count)
 {
 	int status;
@@ -1659,11 +1802,12 @@
 
 static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
 {
-	return 4096 + ((nr_io_queues + 1) << (dev->db_stride + 3));
+	return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
 }
 
 static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
+	struct nvme_queue *adminq = dev->queues[0];
 	struct pci_dev *pdev = dev->pci_dev;
 	int result, cpu, i, vecs, nr_io_queues, size, q_depth;
 
@@ -1690,7 +1834,7 @@
 	}
 
 	/* Deregister the admin queue's interrupt */
-	free_irq(dev->entry[0].vector, dev->queues[0]);
+	free_irq(dev->entry[0].vector, adminq);
 
 	vecs = nr_io_queues;
 	for (i = 0; i < vecs; i++)
@@ -1728,9 +1872,9 @@
 	 */
 	nr_io_queues = vecs;
 
-	result = queue_request_irq(dev, dev->queues[0], "nvme admin");
+	result = queue_request_irq(dev, adminq, adminq->irqname);
 	if (result) {
-		dev->queues[0]->q_suspended = 1;
+		adminq->q_suspended = 1;
 		goto free_queues;
 	}
 
@@ -1739,9 +1883,9 @@
 	for (i = dev->queue_count - 1; i > nr_io_queues; i--) {
 		struct nvme_queue *nvmeq = dev->queues[i];
 
-		spin_lock(&nvmeq->q_lock);
+		spin_lock_irq(&nvmeq->q_lock);
 		nvme_cancel_ios(nvmeq, false);
-		spin_unlock(&nvmeq->q_lock);
+		spin_unlock_irq(&nvmeq->q_lock);
 
 		nvme_free_queue(nvmeq);
 		dev->queue_count--;
@@ -1782,7 +1926,7 @@
 	return 0;
 
  free_queues:
-	nvme_free_queues(dev);
+	nvme_free_queues(dev, 1);
 	return result;
 }
 
@@ -1794,6 +1938,7 @@
  */
 static int nvme_dev_add(struct nvme_dev *dev)
 {
+	struct pci_dev *pdev = dev->pci_dev;
 	int res;
 	unsigned nn, i;
 	struct nvme_ns *ns;
@@ -1803,8 +1948,7 @@
 	dma_addr_t dma_addr;
 	int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
 
-	mem = dma_alloc_coherent(&dev->pci_dev->dev, 8192, &dma_addr,
-								GFP_KERNEL);
+	mem = dma_alloc_coherent(&pdev->dev, 8192, &dma_addr, GFP_KERNEL);
 	if (!mem)
 		return -ENOMEM;
 
@@ -1817,13 +1961,14 @@
 	ctrl = mem;
 	nn = le32_to_cpup(&ctrl->nn);
 	dev->oncs = le16_to_cpup(&ctrl->oncs);
+	dev->abort_limit = ctrl->acl + 1;
 	memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
 	memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
 	memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
 	if (ctrl->mdts)
 		dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9);
-	if ((dev->pci_dev->vendor == PCI_VENDOR_ID_INTEL) &&
-			(dev->pci_dev->device == 0x0953) && ctrl->vs[3])
+	if ((pdev->vendor == PCI_VENDOR_ID_INTEL) &&
+			(pdev->device == 0x0953) && ctrl->vs[3])
 		dev->stripe_size = 1 << (ctrl->vs[3] + shift);
 
 	id_ns = mem;
@@ -1871,16 +2016,21 @@
 	    dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)))
 		goto disable;
 
-	pci_set_drvdata(pdev, dev);
 	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
 	if (!dev->bar)
 		goto disable;
-
-	dev->db_stride = NVME_CAP_STRIDE(readq(&dev->bar->cap));
+	if (readl(&dev->bar->csts) == -1) {
+		result = -ENODEV;
+		goto unmap;
+	}
+	dev->db_stride = 1 << NVME_CAP_STRIDE(readq(&dev->bar->cap));
 	dev->dbs = ((void __iomem *)dev->bar) + 4096;
 
 	return 0;
 
+ unmap:
+	iounmap(dev->bar);
+	dev->bar = NULL;
  disable:
 	pci_release_regions(pdev);
  disable_pci:
@@ -1898,37 +2048,183 @@
 	if (dev->bar) {
 		iounmap(dev->bar);
 		dev->bar = NULL;
+		pci_release_regions(dev->pci_dev);
 	}
 
-	pci_release_regions(dev->pci_dev);
 	if (pci_is_enabled(dev->pci_dev))
 		pci_disable_device(dev->pci_dev);
 }
 
+struct nvme_delq_ctx {
+	struct task_struct *waiter;
+	struct kthread_worker *worker;
+	atomic_t refcount;
+};
+
+static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev *dev)
+{
+	dq->waiter = current;
+	mb();
+
+	for (;;) {
+		set_current_state(TASK_KILLABLE);
+		if (!atomic_read(&dq->refcount))
+			break;
+		if (!schedule_timeout(ADMIN_TIMEOUT) ||
+					fatal_signal_pending(current)) {
+			set_current_state(TASK_RUNNING);
+
+			nvme_disable_ctrl(dev, readq(&dev->bar->cap));
+			nvme_disable_queue(dev, 0);
+
+			send_sig(SIGKILL, dq->worker->task, 1);
+			flush_kthread_worker(dq->worker);
+			return;
+		}
+	}
+	set_current_state(TASK_RUNNING);
+}
+
+static void nvme_put_dq(struct nvme_delq_ctx *dq)
+{
+	atomic_dec(&dq->refcount);
+	if (dq->waiter)
+		wake_up_process(dq->waiter);
+}
+
+static struct nvme_delq_ctx *nvme_get_dq(struct nvme_delq_ctx *dq)
+{
+	atomic_inc(&dq->refcount);
+	return dq;
+}
+
+static void nvme_del_queue_end(struct nvme_queue *nvmeq)
+{
+	struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx;
+
+	nvme_clear_queue(nvmeq);
+	nvme_put_dq(dq);
+}
+
+static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode,
+						kthread_work_func_t fn)
+{
+	struct nvme_command c;
+
+	memset(&c, 0, sizeof(c));
+	c.delete_queue.opcode = opcode;
+	c.delete_queue.qid = cpu_to_le16(nvmeq->qid);
+
+	init_kthread_work(&nvmeq->cmdinfo.work, fn);
+	return nvme_submit_admin_cmd_async(nvmeq->dev, &c, &nvmeq->cmdinfo);
+}
+
+static void nvme_del_cq_work_handler(struct kthread_work *work)
+{
+	struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
+							cmdinfo.work);
+	nvme_del_queue_end(nvmeq);
+}
+
+static int nvme_delete_cq(struct nvme_queue *nvmeq)
+{
+	return adapter_async_del_queue(nvmeq, nvme_admin_delete_cq,
+						nvme_del_cq_work_handler);
+}
+
+static void nvme_del_sq_work_handler(struct kthread_work *work)
+{
+	struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
+							cmdinfo.work);
+	int status = nvmeq->cmdinfo.status;
+
+	if (!status)
+		status = nvme_delete_cq(nvmeq);
+	if (status)
+		nvme_del_queue_end(nvmeq);
+}
+
+static int nvme_delete_sq(struct nvme_queue *nvmeq)
+{
+	return adapter_async_del_queue(nvmeq, nvme_admin_delete_sq,
+						nvme_del_sq_work_handler);
+}
+
+static void nvme_del_queue_start(struct kthread_work *work)
+{
+	struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
+							cmdinfo.work);
+	allow_signal(SIGKILL);
+	if (nvme_delete_sq(nvmeq))
+		nvme_del_queue_end(nvmeq);
+}
+
+static void nvme_disable_io_queues(struct nvme_dev *dev)
+{
+	int i;
+	DEFINE_KTHREAD_WORKER_ONSTACK(worker);
+	struct nvme_delq_ctx dq;
+	struct task_struct *kworker_task = kthread_run(kthread_worker_fn,
+					&worker, "nvme%d", dev->instance);
+
+	if (IS_ERR(kworker_task)) {
+		dev_err(&dev->pci_dev->dev,
+			"Failed to create queue del task\n");
+		for (i = dev->queue_count - 1; i > 0; i--)
+			nvme_disable_queue(dev, i);
+		return;
+	}
+
+	dq.waiter = NULL;
+	atomic_set(&dq.refcount, 0);
+	dq.worker = &worker;
+	for (i = dev->queue_count - 1; i > 0; i--) {
+		struct nvme_queue *nvmeq = dev->queues[i];
+
+		if (nvme_suspend_queue(nvmeq))
+			continue;
+		nvmeq->cmdinfo.ctx = nvme_get_dq(&dq);
+		nvmeq->cmdinfo.worker = dq.worker;
+		init_kthread_work(&nvmeq->cmdinfo.work, nvme_del_queue_start);
+		queue_kthread_work(dq.worker, &nvmeq->cmdinfo.work);
+	}
+	nvme_wait_dq(&dq, dev);
+	kthread_stop(kworker_task);
+}
+
 static void nvme_dev_shutdown(struct nvme_dev *dev)
 {
 	int i;
 
-	for (i = dev->queue_count - 1; i >= 0; i--)
-		nvme_disable_queue(dev, i);
+	dev->initialized = 0;
 
 	spin_lock(&dev_list_lock);
 	list_del_init(&dev->node);
 	spin_unlock(&dev_list_lock);
 
-	if (dev->bar)
+	if (!dev->bar || (dev->bar && readl(&dev->bar->csts) == -1)) {
+		for (i = dev->queue_count - 1; i >= 0; i--) {
+			struct nvme_queue *nvmeq = dev->queues[i];
+			nvme_suspend_queue(nvmeq);
+			nvme_clear_queue(nvmeq);
+		}
+	} else {
+		nvme_disable_io_queues(dev);
 		nvme_shutdown_ctrl(dev);
+		nvme_disable_queue(dev, 0);
+	}
 	nvme_dev_unmap(dev);
 }
 
 static void nvme_dev_remove(struct nvme_dev *dev)
 {
-	struct nvme_ns *ns, *next;
+	struct nvme_ns *ns;
 
-	list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
-		list_del(&ns->list);
-		del_gendisk(ns->disk);
-		nvme_ns_free(ns);
+	list_for_each_entry(ns, &dev->namespaces, list) {
+		if (ns->disk->flags & GENHD_FL_UP)
+			del_gendisk(ns->disk);
+		if (!blk_queue_dying(ns->queue))
+			blk_cleanup_queue(ns->queue);
 	}
 }
 
@@ -1985,14 +2281,22 @@
 	spin_unlock(&dev_list_lock);
 }
 
+static void nvme_free_namespaces(struct nvme_dev *dev)
+{
+	struct nvme_ns *ns, *next;
+
+	list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
+		list_del(&ns->list);
+		put_disk(ns->disk);
+		kfree(ns);
+	}
+}
+
 static void nvme_free_dev(struct kref *kref)
 {
 	struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
-	nvme_dev_remove(dev);
-	nvme_dev_shutdown(dev);
-	nvme_free_queues(dev);
-	nvme_release_instance(dev);
-	nvme_release_prp_pools(dev);
+
+	nvme_free_namespaces(dev);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
@@ -2056,6 +2360,7 @@
 	return result;
 
  disable:
+	nvme_disable_queue(dev, 0);
 	spin_lock(&dev_list_lock);
 	list_del_init(&dev->node);
 	spin_unlock(&dev_list_lock);
@@ -2064,6 +2369,77 @@
 	return result;
 }
 
+static int nvme_remove_dead_ctrl(void *arg)
+{
+	struct nvme_dev *dev = (struct nvme_dev *)arg;
+	struct pci_dev *pdev = dev->pci_dev;
+
+	if (pci_get_drvdata(pdev))
+		pci_stop_and_remove_bus_device(pdev);
+	kref_put(&dev->kref, nvme_free_dev);
+	return 0;
+}
+
+static void nvme_remove_disks(struct work_struct *ws)
+{
+	int i;
+	struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
+
+	nvme_dev_remove(dev);
+	spin_lock(&dev_list_lock);
+	for (i = dev->queue_count - 1; i > 0; i--) {
+		BUG_ON(!dev->queues[i] || !dev->queues[i]->q_suspended);
+		nvme_free_queue(dev->queues[i]);
+		dev->queue_count--;
+		dev->queues[i] = NULL;
+	}
+	spin_unlock(&dev_list_lock);
+}
+
+static int nvme_dev_resume(struct nvme_dev *dev)
+{
+	int ret;
+
+	ret = nvme_dev_start(dev);
+	if (ret && ret != -EBUSY)
+		return ret;
+	if (ret == -EBUSY) {
+		spin_lock(&dev_list_lock);
+		dev->reset_workfn = nvme_remove_disks;
+		queue_work(nvme_workq, &dev->reset_work);
+		spin_unlock(&dev_list_lock);
+	}
+	dev->initialized = 1;
+	return 0;
+}
+
+static void nvme_dev_reset(struct nvme_dev *dev)
+{
+	nvme_dev_shutdown(dev);
+	if (nvme_dev_resume(dev)) {
+		dev_err(&dev->pci_dev->dev, "Device failed to resume\n");
+		kref_get(&dev->kref);
+		if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
+							dev->instance))) {
+			dev_err(&dev->pci_dev->dev,
+				"Failed to start controller remove task\n");
+			kref_put(&dev->kref, nvme_free_dev);
+		}
+	}
+}
+
+static void nvme_reset_failed_dev(struct work_struct *ws)
+{
+	struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
+	nvme_dev_reset(dev);
+}
+
+static void nvme_reset_workfn(struct work_struct *work)
+{
+	struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work);
+	dev->reset_workfn(work);
+}
+
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	int result = -ENOMEM;
@@ -2082,8 +2458,10 @@
 		goto free;
 
 	INIT_LIST_HEAD(&dev->namespaces);
+	dev->reset_workfn = nvme_reset_failed_dev;
+	INIT_WORK(&dev->reset_work, nvme_reset_workfn);
 	dev->pci_dev = pdev;
-
+	pci_set_drvdata(pdev, dev);
 	result = nvme_set_instance(dev);
 	if (result)
 		goto free;
@@ -2099,6 +2477,7 @@
 		goto release_pools;
 	}
 
+	kref_init(&dev->kref);
 	result = nvme_dev_add(dev);
 	if (result)
 		goto shutdown;
@@ -2113,15 +2492,16 @@
 	if (result)
 		goto remove;
 
-	kref_init(&dev->kref);
+	dev->initialized = 1;
 	return 0;
 
  remove:
 	nvme_dev_remove(dev);
+	nvme_free_namespaces(dev);
  shutdown:
 	nvme_dev_shutdown(dev);
  release_pools:
-	nvme_free_queues(dev);
+	nvme_free_queues(dev, 0);
 	nvme_release_prp_pools(dev);
  release:
 	nvme_release_instance(dev);
@@ -2132,10 +2512,28 @@
 	return result;
 }
 
+static void nvme_shutdown(struct pci_dev *pdev)
+{
+	struct nvme_dev *dev = pci_get_drvdata(pdev);
+	nvme_dev_shutdown(dev);
+}
+
 static void nvme_remove(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
+
+	spin_lock(&dev_list_lock);
+	list_del_init(&dev->node);
+	spin_unlock(&dev_list_lock);
+
+	pci_set_drvdata(pdev, NULL);
+	flush_work(&dev->reset_work);
 	misc_deregister(&dev->miscdev);
+	nvme_dev_remove(dev);
+	nvme_dev_shutdown(dev);
+	nvme_free_queues(dev, 0);
+	nvme_release_instance(dev);
+	nvme_release_prp_pools(dev);
 	kref_put(&dev->kref, nvme_free_dev);
 }
 
@@ -2159,13 +2557,12 @@
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct nvme_dev *ndev = pci_get_drvdata(pdev);
-	int ret;
 
-	ret = nvme_dev_start(ndev);
-	/* XXX: should remove gendisks if resume fails */
-	if (ret)
-		nvme_free_queues(ndev);
-	return ret;
+	if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) {
+		ndev->reset_workfn = nvme_reset_failed_dev;
+		queue_work(nvme_workq, &ndev->reset_work);
+	}
+	return 0;
 }
 
 static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume);
@@ -2192,6 +2589,7 @@
 	.id_table	= nvme_id_table,
 	.probe		= nvme_probe,
 	.remove		= nvme_remove,
+	.shutdown	= nvme_shutdown,
 	.driver		= {
 		.pm	= &nvme_dev_pm_ops,
 	},
@@ -2206,9 +2604,14 @@
 	if (IS_ERR(nvme_thread))
 		return PTR_ERR(nvme_thread);
 
+	result = -ENOMEM;
+	nvme_workq = create_singlethread_workqueue("nvme");
+	if (!nvme_workq)
+		goto kill_kthread;
+
 	result = register_blkdev(nvme_major, "nvme");
 	if (result < 0)
-		goto kill_kthread;
+		goto kill_workq;
 	else if (result > 0)
 		nvme_major = result;
 
@@ -2219,6 +2622,8 @@
 
  unregister_blkdev:
 	unregister_blkdev(nvme_major, "nvme");
+ kill_workq:
+	destroy_workqueue(nvme_workq);
  kill_kthread:
 	kthread_stop(nvme_thread);
 	return result;
@@ -2228,6 +2633,7 @@
 {
 	pci_unregister_driver(&nvme_driver);
 	unregister_blkdev(nvme_major, "nvme");
+	destroy_workqueue(nvme_workq);
 	kthread_stop(nvme_thread);
 }
 
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index 4a4ff4e..4a0ceb6 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -25,6 +25,7 @@
 #include <linux/bio.h>
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
+#include <linux/compat.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -3038,6 +3039,152 @@
 	return retcode;
 }
 
+#ifdef CONFIG_COMPAT
+typedef struct sg_io_hdr32 {
+	compat_int_t interface_id;	/* [i] 'S' for SCSI generic (required) */
+	compat_int_t dxfer_direction;	/* [i] data transfer direction  */
+	unsigned char cmd_len;		/* [i] SCSI command length ( <= 16 bytes) */
+	unsigned char mx_sb_len;		/* [i] max length to write to sbp */
+	unsigned short iovec_count;	/* [i] 0 implies no scatter gather */
+	compat_uint_t dxfer_len;		/* [i] byte count of data transfer */
+	compat_uint_t dxferp;		/* [i], [*io] points to data transfer memory
+					      or scatter gather list */
+	compat_uptr_t cmdp;		/* [i], [*i] points to command to perform */
+	compat_uptr_t sbp;		/* [i], [*o] points to sense_buffer memory */
+	compat_uint_t timeout;		/* [i] MAX_UINT->no timeout (unit: millisec) */
+	compat_uint_t flags;		/* [i] 0 -> default, see SG_FLAG... */
+	compat_int_t pack_id;		/* [i->o] unused internally (normally) */
+	compat_uptr_t usr_ptr;		/* [i->o] unused internally */
+	unsigned char status;		/* [o] scsi status */
+	unsigned char masked_status;	/* [o] shifted, masked scsi status */
+	unsigned char msg_status;		/* [o] messaging level data (optional) */
+	unsigned char sb_len_wr;		/* [o] byte count actually written to sbp */
+	unsigned short host_status;	/* [o] errors from host adapter */
+	unsigned short driver_status;	/* [o] errors from software driver */
+	compat_int_t resid;		/* [o] dxfer_len - actual_transferred */
+	compat_uint_t duration;		/* [o] time taken by cmd (unit: millisec) */
+	compat_uint_t info;		/* [o] auxiliary information */
+} sg_io_hdr32_t;  /* 64 bytes long (on sparc32) */
+
+typedef struct sg_iovec32 {
+	compat_uint_t iov_base;
+	compat_uint_t iov_len;
+} sg_iovec32_t;
+
+static int sg_build_iovec(sg_io_hdr_t __user *sgio, void __user *dxferp, u16 iovec_count)
+{
+	sg_iovec_t __user *iov = (sg_iovec_t __user *) (sgio + 1);
+	sg_iovec32_t __user *iov32 = dxferp;
+	int i;
+
+	for (i = 0; i < iovec_count; i++) {
+		u32 base, len;
+
+		if (get_user(base, &iov32[i].iov_base) ||
+		    get_user(len, &iov32[i].iov_len) ||
+		    put_user(compat_ptr(base), &iov[i].iov_base) ||
+		    put_user(len, &iov[i].iov_len))
+			return -EFAULT;
+	}
+
+	if (put_user(iov, &sgio->dxferp))
+		return -EFAULT;
+	return 0;
+}
+
+int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg)
+{
+	sg_io_hdr32_t __user *sgio32 = (sg_io_hdr32_t __user *)arg;
+	sg_io_hdr_t __user *sgio;
+	u16 iovec_count;
+	u32 data;
+	void __user *dxferp;
+	int err;
+	int interface_id;
+
+	if (get_user(interface_id, &sgio32->interface_id))
+		return -EFAULT;
+	if (interface_id != 'S')
+		return -EINVAL;
+
+	if (get_user(iovec_count, &sgio32->iovec_count))
+		return -EFAULT;
+
+	{
+		void __user *top = compat_alloc_user_space(0);
+		void __user *new = compat_alloc_user_space(sizeof(sg_io_hdr_t) +
+				       (iovec_count * sizeof(sg_iovec_t)));
+		if (new > top)
+			return -EINVAL;
+
+		sgio = new;
+	}
+
+	/* Ok, now construct.  */
+	if (copy_in_user(&sgio->interface_id, &sgio32->interface_id,
+			 (2 * sizeof(int)) +
+			 (2 * sizeof(unsigned char)) +
+			 (1 * sizeof(unsigned short)) +
+			 (1 * sizeof(unsigned int))))
+		return -EFAULT;
+
+	if (get_user(data, &sgio32->dxferp))
+		return -EFAULT;
+	dxferp = compat_ptr(data);
+	if (iovec_count) {
+		if (sg_build_iovec(sgio, dxferp, iovec_count))
+			return -EFAULT;
+	} else {
+		if (put_user(dxferp, &sgio->dxferp))
+			return -EFAULT;
+	}
+
+	{
+		unsigned char __user *cmdp;
+		unsigned char __user *sbp;
+
+		if (get_user(data, &sgio32->cmdp))
+			return -EFAULT;
+		cmdp = compat_ptr(data);
+
+		if (get_user(data, &sgio32->sbp))
+			return -EFAULT;
+		sbp = compat_ptr(data);
+
+		if (put_user(cmdp, &sgio->cmdp) ||
+		    put_user(sbp, &sgio->sbp))
+			return -EFAULT;
+	}
+
+	if (copy_in_user(&sgio->timeout, &sgio32->timeout,
+			 3 * sizeof(int)))
+		return -EFAULT;
+
+	if (get_user(data, &sgio32->usr_ptr))
+		return -EFAULT;
+	if (put_user(compat_ptr(data), &sgio->usr_ptr))
+		return -EFAULT;
+
+	err = nvme_sg_io(ns, sgio);
+	if (err >= 0) {
+		void __user *datap;
+
+		if (copy_in_user(&sgio32->pack_id, &sgio->pack_id,
+				 sizeof(int)) ||
+		    get_user(datap, &sgio->usr_ptr) ||
+		    put_user((u32)(unsigned long)datap,
+			     &sgio32->usr_ptr) ||
+		    copy_in_user(&sgio32->status, &sgio->status,
+				 (4 * sizeof(unsigned char)) +
+				 (2 * sizeof(unsigned short)) +
+				 (3 * sizeof(int))))
+			err = -EFAULT;
+	}
+
+	return err;
+}
+#endif
+
 int nvme_sg_get_version_num(int __user *ip)
 {
 	return put_user(sg_version_num, ip);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index b365e0d..34898d5 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -2109,7 +2109,6 @@
 	rbd_assert(img_request->obj_request_count > 0);
 	rbd_assert(which != BAD_WHICH);
 	rbd_assert(which < img_request->obj_request_count);
-	rbd_assert(which >= img_request->next_completion);
 
 	spin_lock_irq(&img_request->completion_lock);
 	if (which != img_request->next_completion)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6a680d4..b1cb3f4 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -110,9 +110,9 @@
 	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
 }
 
-static inline void virtblk_request_done(struct virtblk_req *vbr)
+static inline void virtblk_request_done(struct request *req)
 {
-	struct request *req = vbr->req;
+	struct virtblk_req *vbr = req->special;
 	int error = virtblk_result(vbr);
 
 	if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
@@ -138,7 +138,7 @@
 	do {
 		virtqueue_disable_cb(vq);
 		while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) {
-			virtblk_request_done(vbr);
+			blk_mq_complete_request(vbr->req);
 			req_done = true;
 		}
 		if (unlikely(virtqueue_is_broken(vq)))
@@ -479,6 +479,7 @@
 	.map_queue	= blk_mq_map_queue,
 	.alloc_hctx	= blk_mq_alloc_single_hw_queue,
 	.free_hctx	= blk_mq_free_single_hw_queue,
+	.complete	= virtblk_request_done,
 };
 
 static struct blk_mq_reg virtio_mq_reg = {
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index da18046..64c60ed 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -285,7 +285,8 @@
 
 		if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST ||
 			!rb_next(&persistent_gnt->node)) {
-			ret = gnttab_unmap_refs(unmap, pages, segs_to_unmap);
+			ret = gnttab_unmap_refs(unmap, NULL, pages,
+				segs_to_unmap);
 			BUG_ON(ret);
 			put_free_pages(blkif, pages, segs_to_unmap);
 			segs_to_unmap = 0;
@@ -298,7 +299,7 @@
 	BUG_ON(num != 0);
 }
 
-static void unmap_purged_grants(struct work_struct *work)
+void xen_blkbk_unmap_purged_grants(struct work_struct *work)
 {
 	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
@@ -320,7 +321,8 @@
 		pages[segs_to_unmap] = persistent_gnt->page;
 
 		if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
-			ret = gnttab_unmap_refs(unmap, pages, segs_to_unmap);
+			ret = gnttab_unmap_refs(unmap, NULL, pages,
+				segs_to_unmap);
 			BUG_ON(ret);
 			put_free_pages(blkif, pages, segs_to_unmap);
 			segs_to_unmap = 0;
@@ -328,7 +330,7 @@
 		kfree(persistent_gnt);
 	}
 	if (segs_to_unmap > 0) {
-		ret = gnttab_unmap_refs(unmap, pages, segs_to_unmap);
+		ret = gnttab_unmap_refs(unmap, NULL, pages, segs_to_unmap);
 		BUG_ON(ret);
 		put_free_pages(blkif, pages, segs_to_unmap);
 	}
@@ -373,7 +375,7 @@
 
 	pr_debug(DRV_PFX "Going to purge %u persistent grants\n", num_clean);
 
-	INIT_LIST_HEAD(&blkif->persistent_purge_list);
+	BUG_ON(!list_empty(&blkif->persistent_purge_list));
 	root = &blkif->persistent_gnts;
 purge_list:
 	foreach_grant_safe(persistent_gnt, n, root, node) {
@@ -418,7 +420,6 @@
 	blkif->vbd.overflow_max_grants = 0;
 
 	/* We can defer this work */
-	INIT_WORK(&blkif->persistent_purge_work, unmap_purged_grants);
 	schedule_work(&blkif->persistent_purge_work);
 	pr_debug(DRV_PFX "Purged %u/%u\n", (total - num_clean), total);
 	return;
@@ -623,16 +624,8 @@
 			print_stats(blkif);
 	}
 
-	/* Since we are shutting down remove all pages from the buffer */
-	shrink_free_pagepool(blkif, 0 /* All */);
-
-	/* Free all persistent grant pages */
-	if (!RB_EMPTY_ROOT(&blkif->persistent_gnts))
-		free_persistent_gnts(blkif, &blkif->persistent_gnts,
-			blkif->persistent_gnt_c);
-
-	BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
-	blkif->persistent_gnt_c = 0;
+	/* Drain pending purge work */
+	flush_work(&blkif->persistent_purge_work);
 
 	if (log_stats)
 		print_stats(blkif);
@@ -644,6 +637,23 @@
 }
 
 /*
+ * Remove persistent grants and empty the pool of free pages
+ */
+void xen_blkbk_free_caches(struct xen_blkif *blkif)
+{
+	/* Free all persistent grant pages */
+	if (!RB_EMPTY_ROOT(&blkif->persistent_gnts))
+		free_persistent_gnts(blkif, &blkif->persistent_gnts,
+			blkif->persistent_gnt_c);
+
+	BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
+	blkif->persistent_gnt_c = 0;
+
+	/* Since we are shutting down remove all pages from the buffer */
+	shrink_free_pagepool(blkif, 0 /* All */);
+}
+
+/*
  * Unmap the grant references, and also remove the M2P over-rides
  * used in the 'pending_req'.
  */
@@ -668,14 +678,15 @@
 				    GNTMAP_host_map, pages[i]->handle);
 		pages[i]->handle = BLKBACK_INVALID_HANDLE;
 		if (++invcount == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
-			ret = gnttab_unmap_refs(unmap, unmap_pages, invcount);
+			ret = gnttab_unmap_refs(unmap, NULL, unmap_pages,
+			                        invcount);
 			BUG_ON(ret);
 			put_free_pages(blkif, unmap_pages, invcount);
 			invcount = 0;
 		}
 	}
 	if (invcount) {
-		ret = gnttab_unmap_refs(unmap, unmap_pages, invcount);
+		ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount);
 		BUG_ON(ret);
 		put_free_pages(blkif, unmap_pages, invcount);
 	}
@@ -737,7 +748,7 @@
 	}
 
 	if (segs_to_map) {
-		ret = gnttab_map_refs(map, pages_to_gnt, segs_to_map);
+		ret = gnttab_map_refs(map, NULL, pages_to_gnt, segs_to_map);
 		BUG_ON(ret);
 	}
 
@@ -835,7 +846,7 @@
 	struct grant_page **pages = pending_req->indirect_pages;
 	struct xen_blkif *blkif = pending_req->blkif;
 	int indirect_grefs, rc, n, nseg, i;
-	struct blkif_request_segment_aligned *segments = NULL;
+	struct blkif_request_segment *segments = NULL;
 
 	nseg = pending_req->nr_pages;
 	indirect_grefs = INDIRECT_PAGES(nseg);
@@ -931,9 +942,7 @@
 {
 	atomic_set(&blkif->drain, 1);
 	do {
-		/* The initial value is one, and one refcnt taken at the
-		 * start of the xen_blkif_schedule thread. */
-		if (atomic_read(&blkif->refcnt) <= 2)
+		if (atomic_read(&blkif->inflight) == 0)
 			break;
 		wait_for_completion_interruptible_timeout(
 				&blkif->drain_complete, HZ);
@@ -973,17 +982,30 @@
 	 * the proper response on the ring.
 	 */
 	if (atomic_dec_and_test(&pending_req->pendcnt)) {
-		xen_blkbk_unmap(pending_req->blkif,
+		struct xen_blkif *blkif = pending_req->blkif;
+
+		xen_blkbk_unmap(blkif,
 		                pending_req->segments,
 		                pending_req->nr_pages);
-		make_response(pending_req->blkif, pending_req->id,
+		make_response(blkif, pending_req->id,
 			      pending_req->operation, pending_req->status);
-		xen_blkif_put(pending_req->blkif);
-		if (atomic_read(&pending_req->blkif->refcnt) <= 2) {
-			if (atomic_read(&pending_req->blkif->drain))
-				complete(&pending_req->blkif->drain_complete);
+		free_req(blkif, pending_req);
+		/*
+		 * Make sure the request is freed before releasing blkif,
+		 * or there could be a race between free_req and the
+		 * cleanup done in xen_blkif_free during shutdown.
+		 *
+		 * NB: The fact that we might try to wake up pending_free_wq
+		 * before drain_complete (in case there's a drain going on)
+		 * it's not a problem with our current implementation
+		 * because we can assure there's no thread waiting on
+		 * pending_free_wq if there's a drain going on, but it has
+		 * to be taken into account if the current model is changed.
+		 */
+		if (atomic_dec_and_test(&blkif->inflight) && atomic_read(&blkif->drain)) {
+			complete(&blkif->drain_complete);
 		}
-		free_req(pending_req->blkif, pending_req);
+		xen_blkif_put(blkif);
 	}
 }
 
@@ -1237,6 +1259,7 @@
 	 * below (in "!bio") if we are handling a BLKIF_OP_DISCARD.
 	 */
 	xen_blkif_get(blkif);
+	atomic_inc(&blkif->inflight);
 
 	for (i = 0; i < nseg; i++) {
 		while ((bio == NULL) ||
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 8d88075..be05277 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -57,7 +57,7 @@
 #define MAX_INDIRECT_SEGMENTS 256
 
 #define SEGS_PER_INDIRECT_FRAME \
-	(PAGE_SIZE/sizeof(struct blkif_request_segment_aligned))
+	(PAGE_SIZE/sizeof(struct blkif_request_segment))
 #define MAX_INDIRECT_PAGES \
 	((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
 #define INDIRECT_PAGES(_segs) \
@@ -278,6 +278,7 @@
 	/* for barrier (drain) requests */
 	struct completion	drain_complete;
 	atomic_t		drain;
+	atomic_t		inflight;
 	/* One thread per one blkif. */
 	struct task_struct	*xenblkd;
 	unsigned int		waiting_reqs;
@@ -376,6 +377,7 @@
 irqreturn_t xen_blkif_be_int(int irq, void *dev_id);
 int xen_blkif_schedule(void *arg);
 int xen_blkif_purge_persistent(void *arg);
+void xen_blkbk_free_caches(struct xen_blkif *blkif);
 
 int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
 			      struct backend_info *be, int state);
@@ -383,6 +385,7 @@
 int xen_blkbk_barrier(struct xenbus_transaction xbt,
 		      struct backend_info *be, int state);
 struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be);
+void xen_blkbk_unmap_purged_grants(struct work_struct *work);
 
 static inline void blkif_get_x86_32_req(struct blkif_request *dst,
 					struct blkif_x86_32_request *src)
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index c2014a0..9a547e6 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -125,8 +125,11 @@
 	blkif->persistent_gnts.rb_node = NULL;
 	spin_lock_init(&blkif->free_pages_lock);
 	INIT_LIST_HEAD(&blkif->free_pages);
+	INIT_LIST_HEAD(&blkif->persistent_purge_list);
 	blkif->free_pages_num = 0;
 	atomic_set(&blkif->persistent_gnt_in_use, 0);
+	atomic_set(&blkif->inflight, 0);
+	INIT_WORK(&blkif->persistent_purge_work, xen_blkbk_unmap_purged_grants);
 
 	INIT_LIST_HEAD(&blkif->pending_free);
 
@@ -259,6 +262,17 @@
 	if (!atomic_dec_and_test(&blkif->refcnt))
 		BUG();
 
+	/* Remove all persistent grants and the cache of ballooned pages. */
+	xen_blkbk_free_caches(blkif);
+
+	/* Make sure everything is drained before shutting down */
+	BUG_ON(blkif->persistent_gnt_c != 0);
+	BUG_ON(atomic_read(&blkif->persistent_gnt_in_use) != 0);
+	BUG_ON(blkif->free_pages_num != 0);
+	BUG_ON(!list_empty(&blkif->persistent_purge_list));
+	BUG_ON(!list_empty(&blkif->free_pages));
+	BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
+
 	/* Check that there is no request in use */
 	list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
 		list_del(&req->free_list);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 8dcfb54..efe1b47 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -162,7 +162,7 @@
 #define DEV_NAME	"xvd"	/* name in /dev */
 
 #define SEGS_PER_INDIRECT_FRAME \
-	(PAGE_SIZE/sizeof(struct blkif_request_segment_aligned))
+	(PAGE_SIZE/sizeof(struct blkif_request_segment))
 #define INDIRECT_GREFS(_segs) \
 	((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
 
@@ -393,7 +393,7 @@
 	unsigned long id;
 	unsigned int fsect, lsect;
 	int i, ref, n;
-	struct blkif_request_segment_aligned *segments = NULL;
+	struct blkif_request_segment *segments = NULL;
 
 	/*
 	 * Used to store if we are able to queue the request by just using
@@ -550,7 +550,7 @@
 			} else {
 				n = i % SEGS_PER_INDIRECT_FRAME;
 				segments[n] =
-					(struct blkif_request_segment_aligned) {
+					(struct blkif_request_segment) {
 							.gref       = ref,
 							.first_sect = fsect,
 							.last_sect  = lsect };
@@ -1904,13 +1904,16 @@
 	case XenbusStateReconfiguring:
 	case XenbusStateReconfigured:
 	case XenbusStateUnknown:
-	case XenbusStateClosed:
 		break;
 
 	case XenbusStateConnected:
 		blkfront_connect(info);
 		break;
 
+	case XenbusStateClosed:
+		if (dev->state == XenbusStateClosed)
+			break;
+		/* Missed the backend's Closing state -- fallthrough */
 	case XenbusStateClosing:
 		blkfront_closing(info);
 		break;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 011e55d..51c557c 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -612,6 +612,8 @@
 
 	disksize = PAGE_ALIGN(disksize);
 	meta = zram_meta_alloc(disksize);
+	if (!meta)
+		return -ENOMEM;
 	down_write(&zram->init_lock);
 	if (zram->init_done) {
 		up_write(&zram->init_lock);
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index b6739cb..962fd35 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -979,7 +979,7 @@
 
 	nb_cci_ports = cci_config->nb_ace + cci_config->nb_ace_lite;
 
-	ports = kcalloc(sizeof(*ports), nb_cci_ports, GFP_KERNEL);
+	ports = kcalloc(nb_cci_ports, sizeof(*ports), GFP_KERNEL);
 	if (!ports)
 		return -ENOMEM;
 
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index fa3243d..1386749 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -499,6 +499,7 @@
 config MAX_RAW_DEVS
 	int "Maximum number of RAW devices to support (1-65536)"
 	depends on RAW_DRIVER
+	range 1 65536
 	default "256"
 	help
 	  The maximum number of RAW devices that are supported.
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index f3223aa..6e8d65e 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -190,7 +190,7 @@
 	struct raw_device_data *rawdev;
 	struct block_device *bdev;
 
-	if (number <= 0 || number >= MAX_RAW_MINORS)
+	if (number <= 0 || number >= max_raw_minors)
 		return -EINVAL;
 
 	rawdev = &raw_devices[number];
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index feea87c..6928d09 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -890,12 +890,10 @@
 	} else {
 		/* Failback to copying a page */
 		struct page *page = alloc_page(GFP_KERNEL);
-		char *src = buf->ops->map(pipe, buf, 1);
-		char *dst;
+		char *src;
 
 		if (!page)
 			return -ENOMEM;
-		dst = kmap(page);
 
 		offset = sd->pos & ~PAGE_MASK;
 
@@ -903,9 +901,8 @@
 		if (len + offset > PAGE_SIZE)
 			len = PAGE_SIZE - offset;
 
-		memcpy(dst + offset, src + buf->offset, len);
-
-		kunmap(page);
+		src = buf->ops->map(pipe, buf, 1);
+		memcpy(page_address(page) + offset, src + buf->offset, len);
 		buf->ops->unmap(pipe, buf, src);
 
 		sg_set_page(&(sgl->sg[sgl->n]), page, len, offset);
diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index bd313f7..c1af80b 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -242,7 +242,7 @@
 
 	irq = irq_of_parse_and_map(np, 0);
 	if (!irq)
-		return;
+		goto out_free_characteristics;
 
 	clk = at91_clk_register_master(pmc, irq, name, num_parents,
 				       parent_names, layout,
diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c
index 6a934a5..05e04ce 100644
--- a/drivers/clk/clk-nomadik.c
+++ b/drivers/clk/clk-nomadik.c
@@ -494,6 +494,9 @@
 
 static int __init nomadik_src_clk_init_debugfs(void)
 {
+	/* Vital for multiplatform */
+	if (!src_base)
+		return -ENODEV;
 	src_pcksr0_boot = readl(src_base + SRC_PCKSR0);
 	src_pcksr1_boot = readl(src_base + SRC_PCKSR1);
 	debugfs_create_file("nomadik-src-clk", S_IFREG | S_IRUGO,
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 5517944..c42e608 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -2226,24 +2226,25 @@
  */
 int __clk_get(struct clk *clk)
 {
-	if (clk && !try_module_get(clk->owner))
-		return 0;
+	if (clk) {
+		if (!try_module_get(clk->owner))
+			return 0;
 
-	kref_get(&clk->ref);
+		kref_get(&clk->ref);
+	}
 	return 1;
 }
 
 void __clk_put(struct clk *clk)
 {
-	if (WARN_ON_ONCE(IS_ERR(clk)))
+	if (!clk || WARN_ON_ONCE(IS_ERR(clk)))
 		return;
 
 	clk_prepare_lock();
 	kref_put(&clk->ref, __clk_release);
 	clk_prepare_unlock();
 
-	if (clk)
-		module_put(clk->owner);
+	module_put(clk->owner);
 }
 
 /***        clk rate change notifiers        ***/
diff --git a/drivers/clk/keystone/gate.c b/drivers/clk/keystone/gate.c
index 17a5983..86f1e36 100644
--- a/drivers/clk/keystone/gate.c
+++ b/drivers/clk/keystone/gate.c
@@ -179,6 +179,7 @@
 
 	init.name = name;
 	init.ops = &clk_psc_ops;
+	init.flags = 0;
 	init.parent_names = (parent_name ? &parent_name : NULL);
 	init.num_parents = (parent_name ? 1 : 0);
 
diff --git a/drivers/clk/mvebu/armada-370.c b/drivers/clk/mvebu/armada-370.c
index 81a202d..bef198a 100644
--- a/drivers/clk/mvebu/armada-370.c
+++ b/drivers/clk/mvebu/armada-370.c
@@ -141,13 +141,6 @@
 	.num_ratios = ARRAY_SIZE(a370_coreclk_ratios),
 };
 
-static void __init a370_coreclk_init(struct device_node *np)
-{
-	mvebu_coreclk_setup(np, &a370_coreclks);
-}
-CLK_OF_DECLARE(a370_core_clk, "marvell,armada-370-core-clock",
-	       a370_coreclk_init);
-
 /*
  * Clock Gating Control
  */
@@ -168,9 +161,15 @@
 	{ }
 };
 
-static void __init a370_clk_gating_init(struct device_node *np)
+static void __init a370_clk_init(struct device_node *np)
 {
-	mvebu_clk_gating_setup(np, a370_gating_desc);
+	struct device_node *cgnp =
+		of_find_compatible_node(NULL, NULL, "marvell,armada-370-gating-clock");
+
+	mvebu_coreclk_setup(np, &a370_coreclks);
+
+	if (cgnp)
+		mvebu_clk_gating_setup(cgnp, a370_gating_desc);
 }
-CLK_OF_DECLARE(a370_clk_gating, "marvell,armada-370-gating-clock",
-	       a370_clk_gating_init);
+CLK_OF_DECLARE(a370_clk, "marvell,armada-370-core-clock", a370_clk_init);
+
diff --git a/drivers/clk/mvebu/armada-xp.c b/drivers/clk/mvebu/armada-xp.c
index 9922c44..b309431 100644
--- a/drivers/clk/mvebu/armada-xp.c
+++ b/drivers/clk/mvebu/armada-xp.c
@@ -158,13 +158,6 @@
 	.num_ratios = ARRAY_SIZE(axp_coreclk_ratios),
 };
 
-static void __init axp_coreclk_init(struct device_node *np)
-{
-	mvebu_coreclk_setup(np, &axp_coreclks);
-}
-CLK_OF_DECLARE(axp_core_clk, "marvell,armada-xp-core-clock",
-	       axp_coreclk_init);
-
 /*
  * Clock Gating Control
  */
@@ -202,9 +195,14 @@
 	{ }
 };
 
-static void __init axp_clk_gating_init(struct device_node *np)
+static void __init axp_clk_init(struct device_node *np)
 {
-	mvebu_clk_gating_setup(np, axp_gating_desc);
+	struct device_node *cgnp =
+		of_find_compatible_node(NULL, NULL, "marvell,armada-xp-gating-clock");
+
+	mvebu_coreclk_setup(np, &axp_coreclks);
+
+	if (cgnp)
+		mvebu_clk_gating_setup(cgnp, axp_gating_desc);
 }
-CLK_OF_DECLARE(axp_clk_gating, "marvell,armada-xp-gating-clock",
-	       axp_clk_gating_init);
+CLK_OF_DECLARE(axp_clk, "marvell,armada-xp-core-clock", axp_clk_init);
diff --git a/drivers/clk/mvebu/dove.c b/drivers/clk/mvebu/dove.c
index 38aee1e..b8c2424 100644
--- a/drivers/clk/mvebu/dove.c
+++ b/drivers/clk/mvebu/dove.c
@@ -154,12 +154,6 @@
 	.num_ratios = ARRAY_SIZE(dove_coreclk_ratios),
 };
 
-static void __init dove_coreclk_init(struct device_node *np)
-{
-	mvebu_coreclk_setup(np, &dove_coreclks);
-}
-CLK_OF_DECLARE(dove_core_clk, "marvell,dove-core-clock", dove_coreclk_init);
-
 /*
  * Clock Gating Control
  */
@@ -186,9 +180,14 @@
 	{ }
 };
 
-static void __init dove_clk_gating_init(struct device_node *np)
+static void __init dove_clk_init(struct device_node *np)
 {
-	mvebu_clk_gating_setup(np, dove_gating_desc);
+	struct device_node *cgnp =
+		of_find_compatible_node(NULL, NULL, "marvell,dove-gating-clock");
+
+	mvebu_coreclk_setup(np, &dove_coreclks);
+
+	if (cgnp)
+		mvebu_clk_gating_setup(cgnp, dove_gating_desc);
 }
-CLK_OF_DECLARE(dove_clk_gating, "marvell,dove-gating-clock",
-	       dove_clk_gating_init);
+CLK_OF_DECLARE(dove_clk, "marvell,dove-core-clock", dove_clk_init);
diff --git a/drivers/clk/mvebu/kirkwood.c b/drivers/clk/mvebu/kirkwood.c
index 2636a55..ddb666a 100644
--- a/drivers/clk/mvebu/kirkwood.c
+++ b/drivers/clk/mvebu/kirkwood.c
@@ -193,13 +193,6 @@
 	.num_ratios = ARRAY_SIZE(kirkwood_coreclk_ratios),
 };
 
-static void __init kirkwood_coreclk_init(struct device_node *np)
-{
-	mvebu_coreclk_setup(np, &kirkwood_coreclks);
-}
-CLK_OF_DECLARE(kirkwood_core_clk, "marvell,kirkwood-core-clock",
-	       kirkwood_coreclk_init);
-
 static const struct coreclk_soc_desc mv88f6180_coreclks = {
 	.get_tclk_freq = kirkwood_get_tclk_freq,
 	.get_cpu_freq = mv88f6180_get_cpu_freq,
@@ -208,13 +201,6 @@
 	.num_ratios = ARRAY_SIZE(kirkwood_coreclk_ratios),
 };
 
-static void __init mv88f6180_coreclk_init(struct device_node *np)
-{
-	mvebu_coreclk_setup(np, &mv88f6180_coreclks);
-}
-CLK_OF_DECLARE(mv88f6180_core_clk, "marvell,mv88f6180-core-clock",
-	       mv88f6180_coreclk_init);
-
 /*
  * Clock Gating Control
  */
@@ -239,9 +225,21 @@
 	{ }
 };
 
-static void __init kirkwood_clk_gating_init(struct device_node *np)
+static void __init kirkwood_clk_init(struct device_node *np)
 {
-	mvebu_clk_gating_setup(np, kirkwood_gating_desc);
+	struct device_node *cgnp =
+		of_find_compatible_node(NULL, NULL, "marvell,kirkwood-gating-clock");
+
+
+	if (of_device_is_compatible(np, "marvell,mv88f6180-core-clock"))
+		mvebu_coreclk_setup(np, &mv88f6180_coreclks);
+	else
+		mvebu_coreclk_setup(np, &kirkwood_coreclks);
+
+	if (cgnp)
+		mvebu_clk_gating_setup(cgnp, kirkwood_gating_desc);
 }
-CLK_OF_DECLARE(kirkwood_clk_gating, "marvell,kirkwood-gating-clock",
-	       kirkwood_clk_gating_init);
+CLK_OF_DECLARE(kirkwood_clk, "marvell,kirkwood-core-clock",
+	       kirkwood_clk_init);
+CLK_OF_DECLARE(mv88f6180_clk, "marvell,mv88f6180-core-clock",
+	       kirkwood_clk_init);
diff --git a/drivers/clk/shmobile/clk-rcar-gen2.c b/drivers/clk/shmobile/clk-rcar-gen2.c
index a59ec21..99c27b1 100644
--- a/drivers/clk/shmobile/clk-rcar-gen2.c
+++ b/drivers/clk/shmobile/clk-rcar-gen2.c
@@ -26,6 +26,8 @@
 	void __iomem *reg;
 };
 
+#define CPG_FRQCRB			0x00000004
+#define CPG_FRQCRB_KICK			BIT(31)
 #define CPG_SDCKCR			0x00000074
 #define CPG_PLL0CR			0x000000d8
 #define CPG_FRQCRC			0x000000e0
@@ -45,6 +47,7 @@
 struct cpg_z_clk {
 	struct clk_hw hw;
 	void __iomem *reg;
+	void __iomem *kick_reg;
 };
 
 #define to_z_clk(_hw)	container_of(_hw, struct cpg_z_clk, hw)
@@ -83,17 +86,45 @@
 {
 	struct cpg_z_clk *zclk = to_z_clk(hw);
 	unsigned int mult;
-	u32 val;
+	u32 val, kick;
+	unsigned int i;
 
 	mult = div_u64((u64)rate * 32, parent_rate);
 	mult = clamp(mult, 1U, 32U);
 
+	if (clk_readl(zclk->kick_reg) & CPG_FRQCRB_KICK)
+		return -EBUSY;
+
 	val = clk_readl(zclk->reg);
 	val &= ~CPG_FRQCRC_ZFC_MASK;
 	val |= (32 - mult) << CPG_FRQCRC_ZFC_SHIFT;
 	clk_writel(val, zclk->reg);
 
-	return 0;
+	/*
+	 * Set KICK bit in FRQCRB to update hardware setting and wait for
+	 * clock change completion.
+	 */
+	kick = clk_readl(zclk->kick_reg);
+	kick |= CPG_FRQCRB_KICK;
+	clk_writel(kick, zclk->kick_reg);
+
+	/*
+	 * Note: There is no HW information about the worst case latency.
+	 *
+	 * Using experimental measurements, it seems that no more than
+	 * ~10 iterations are needed, independently of the CPU rate.
+	 * Since this value might be dependant of external xtal rate, pll1
+	 * rate or even the other emulation clocks rate, use 1000 as a
+	 * "super" safe value.
+	 */
+	for (i = 1000; i; i--) {
+		if (!(clk_readl(zclk->kick_reg) & CPG_FRQCRB_KICK))
+			return 0;
+
+		cpu_relax();
+	}
+
+	return -ETIMEDOUT;
 }
 
 static const struct clk_ops cpg_z_clk_ops = {
@@ -120,6 +151,7 @@
 	init.num_parents = 1;
 
 	zclk->reg = cpg->reg + CPG_FRQCRC;
+	zclk->kick_reg = cpg->reg + CPG_FRQCRB;
 	zclk->hw.init = &init;
 
 	clk = clk_register(NULL, &zclk->hw);
@@ -186,7 +218,7 @@
 			     const char *name)
 {
 	const struct clk_div_table *table = NULL;
-	const char *parent_name = "main";
+	const char *parent_name;
 	unsigned int shift;
 	unsigned int mult = 1;
 	unsigned int div = 1;
@@ -201,23 +233,31 @@
 		 * the multiplier value.
 		 */
 		u32 value = clk_readl(cpg->reg + CPG_PLL0CR);
+		parent_name = "main";
 		mult = ((value >> 24) & ((1 << 7) - 1)) + 1;
 	} else if (!strcmp(name, "pll1")) {
+		parent_name = "main";
 		mult = config->pll1_mult / 2;
 	} else if (!strcmp(name, "pll3")) {
+		parent_name = "main";
 		mult = config->pll3_mult;
 	} else if (!strcmp(name, "lb")) {
+		parent_name = "pll1_div2";
 		div = cpg_mode & BIT(18) ? 36 : 24;
 	} else if (!strcmp(name, "qspi")) {
+		parent_name = "pll1_div2";
 		div = (cpg_mode & (BIT(3) | BIT(2) | BIT(1))) == BIT(2)
-		    ? 16 : 20;
+		    ? 8 : 10;
 	} else if (!strcmp(name, "sdh")) {
+		parent_name = "pll1_div2";
 		table = cpg_sdh_div_table;
 		shift = 8;
 	} else if (!strcmp(name, "sd0")) {
+		parent_name = "pll1_div2";
 		table = cpg_sd01_div_table;
 		shift = 4;
 	} else if (!strcmp(name, "sd1")) {
+		parent_name = "pll1_div2";
 		table = cpg_sd01_div_table;
 		shift = 0;
 	} else if (!strcmp(name, "z")) {
diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c
index 4d75b1f..290f9c1 100644
--- a/drivers/clk/tegra/clk-divider.c
+++ b/drivers/clk/tegra/clk-divider.c
@@ -59,7 +59,7 @@
 		return 0;
 
 	if (divider_ux1 > get_max_div(divider))
-		return -EINVAL;
+		return get_max_div(divider);
 
 	return divider_ux1;
 }
diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h
index cf0c323..c39613c 100644
--- a/drivers/clk/tegra/clk-id.h
+++ b/drivers/clk/tegra/clk-id.h
@@ -180,9 +180,13 @@
 	tegra_clk_sbc6_8,
 	tegra_clk_sclk,
 	tegra_clk_sdmmc1,
+	tegra_clk_sdmmc1_8,
 	tegra_clk_sdmmc2,
+	tegra_clk_sdmmc2_8,
 	tegra_clk_sdmmc3,
+	tegra_clk_sdmmc3_8,
 	tegra_clk_sdmmc4,
+	tegra_clk_sdmmc4_8,
 	tegra_clk_se,
 	tegra_clk_soc_therm,
 	tegra_clk_sor0,
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 5c35885..1fa5c3f 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -371,9 +371,7 @@
 static const char *mux_pllm_pllc_pllp_plla_pllc2_c3_clkm[] = {
 	"pll_m", "pll_c", "pll_p", "pll_a", "pll_c2", "pll_c3", "clk_m"
 };
-static u32 mux_pllm_pllc_pllp_plla_pllc2_c3_clkm_idx[] = {
-	[0] = 0, [1] = 1, [2] = 2, [3] = 3, [4] = 4, [5] = 6,
-};
+#define mux_pllm_pllc_pllp_plla_pllc2_c3_clkm_idx NULL
 
 static const char *mux_pllm_pllc2_c_c3_pllp_plla_pllc4[] = {
 	"pll_m", "pll_c2", "pll_c", "pll_c3", "pll_p", "pll_a_out0", "pll_c4",
@@ -465,6 +463,10 @@
 	MUX("adx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_ADX1, 180, TEGRA_PERIPH_ON_APB, tegra_clk_adx1),
 	MUX("amx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_AMX1, 185, TEGRA_PERIPH_ON_APB, tegra_clk_amx1),
 	MUX("vi_sensor2", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR2, 20, TEGRA_PERIPH_NO_RESET, tegra_clk_vi_sensor2),
+	MUX8("sdmmc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC1, 14, 0, tegra_clk_sdmmc1_8),
+	MUX8("sdmmc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC2, 9, 0, tegra_clk_sdmmc2_8),
+	MUX8("sdmmc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC3, 69, 0, tegra_clk_sdmmc3_8),
+	MUX8("sdmmc4", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC4, 15, 0, tegra_clk_sdmmc4_8),
 	MUX8("sbc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC1, 41, TEGRA_PERIPH_ON_APB, tegra_clk_sbc1_8),
 	MUX8("sbc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC2, 44, TEGRA_PERIPH_ON_APB, tegra_clk_sbc2_8),
 	MUX8("sbc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC3, 46, TEGRA_PERIPH_ON_APB, tegra_clk_sbc3_8),
@@ -492,7 +494,7 @@
 	UART("uartb", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTB, 7, tegra_clk_uartb),
 	UART("uartc", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTC, 55, tegra_clk_uartc),
 	UART("uartd", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTD, 65, tegra_clk_uartd),
-	UART("uarte", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTE, 65, tegra_clk_uarte),
+	UART("uarte", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTE, 66, tegra_clk_uarte),
 	XUSB("xusb_host_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_HOST_SRC, 143, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_host_src),
 	XUSB("xusb_falcon_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_FALCON_SRC, 143, TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_falcon_src),
 	XUSB("xusb_fs_src", mux_clkm_48M_pllp_480M, CLK_SOURCE_XUSB_FS_SRC, 143, TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_fs_src),
diff --git a/drivers/clk/tegra/clk-tegra-super-gen4.c b/drivers/clk/tegra/clk-tegra-super-gen4.c
index 05dce4a..feb3201 100644
--- a/drivers/clk/tegra/clk-tegra-super-gen4.c
+++ b/drivers/clk/tegra/clk-tegra-super-gen4.c
@@ -120,7 +120,7 @@
 					ARRAY_SIZE(cclk_lp_parents),
 					CLK_SET_RATE_PARENT,
 					clk_base + CCLKLP_BURST_POLICY,
-					0, 4, 8, 9, NULL);
+					TEGRA_DIVIDER_2, 4, 8, 9, NULL);
 		*dt_clk = clk;
 	}
 
diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c
index 90d9d25..80431f0 100644
--- a/drivers/clk/tegra/clk-tegra114.c
+++ b/drivers/clk/tegra/clk-tegra114.c
@@ -682,12 +682,12 @@
 	[tegra_clk_timer] = { .dt_id = TEGRA114_CLK_TIMER, .present = true },
 	[tegra_clk_uarta] = { .dt_id = TEGRA114_CLK_UARTA, .present = true },
 	[tegra_clk_uartd] = { .dt_id = TEGRA114_CLK_UARTD, .present = true },
-	[tegra_clk_sdmmc2] = { .dt_id = TEGRA114_CLK_SDMMC2, .present = true },
+	[tegra_clk_sdmmc2_8] = { .dt_id = TEGRA114_CLK_SDMMC2, .present = true },
 	[tegra_clk_i2s1] = { .dt_id = TEGRA114_CLK_I2S1, .present = true },
 	[tegra_clk_i2c1] = { .dt_id = TEGRA114_CLK_I2C1, .present = true },
 	[tegra_clk_ndflash] = { .dt_id = TEGRA114_CLK_NDFLASH, .present = true },
-	[tegra_clk_sdmmc1] = { .dt_id = TEGRA114_CLK_SDMMC1, .present = true },
-	[tegra_clk_sdmmc4] = { .dt_id = TEGRA114_CLK_SDMMC4, .present = true },
+	[tegra_clk_sdmmc1_8] = { .dt_id = TEGRA114_CLK_SDMMC1, .present = true },
+	[tegra_clk_sdmmc4_8] = { .dt_id = TEGRA114_CLK_SDMMC4, .present = true },
 	[tegra_clk_pwm] = { .dt_id = TEGRA114_CLK_PWM, .present = true },
 	[tegra_clk_i2s0] = { .dt_id = TEGRA114_CLK_I2S0, .present = true },
 	[tegra_clk_i2s2] = { .dt_id = TEGRA114_CLK_I2S2, .present = true },
@@ -723,7 +723,7 @@
 	[tegra_clk_bsev] = { .dt_id = TEGRA114_CLK_BSEV, .present = true },
 	[tegra_clk_i2c3] = { .dt_id = TEGRA114_CLK_I2C3, .present = true },
 	[tegra_clk_sbc4_8] = { .dt_id = TEGRA114_CLK_SBC4, .present = true },
-	[tegra_clk_sdmmc3] = { .dt_id = TEGRA114_CLK_SDMMC3, .present = true },
+	[tegra_clk_sdmmc3_8] = { .dt_id = TEGRA114_CLK_SDMMC3, .present = true },
 	[tegra_clk_owr] = { .dt_id = TEGRA114_CLK_OWR, .present = true },
 	[tegra_clk_csite] = { .dt_id = TEGRA114_CLK_CSITE, .present = true },
 	[tegra_clk_la] = { .dt_id = TEGRA114_CLK_LA, .present = true },
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index aff86b5..166e02f 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -516,11 +516,11 @@
 };
 
 static struct tegra_clk_pll_freq_table pll_p_freq_table[] = {
-	{12000000, 216000000, 432, 12, 1, 8},
-	{13000000, 216000000, 432, 13, 1, 8},
-	{16800000, 216000000, 360, 14, 1, 8},
-	{19200000, 216000000, 360, 16, 1, 8},
-	{26000000, 216000000, 432, 26, 1, 8},
+	{12000000, 408000000, 408, 12, 0, 8},
+	{13000000, 408000000, 408, 13, 0, 8},
+	{16800000, 408000000, 340, 14, 0, 8},
+	{19200000, 408000000, 340, 16, 0, 8},
+	{26000000, 408000000, 408, 26, 0, 8},
 	{0, 0, 0, 0, 0, 0},
 };
 
@@ -570,6 +570,15 @@
 	.flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_USE_LOCK,
 };
 
+static struct div_nmp plld_nmp = {
+	.divm_shift = 0,
+	.divm_width = 5,
+	.divn_shift = 8,
+	.divn_width = 11,
+	.divp_shift = 20,
+	.divp_width = 3,
+};
+
 static struct tegra_clk_pll_freq_table pll_d_freq_table[] = {
 	{12000000, 216000000, 864, 12, 4, 12},
 	{13000000, 216000000, 864, 13, 4, 12},
@@ -603,19 +612,18 @@
 	.lock_mask = PLL_BASE_LOCK,
 	.lock_enable_bit_idx = PLLDU_MISC_LOCK_ENABLE,
 	.lock_delay = 1000,
-	.div_nmp = &pllp_nmp,
+	.div_nmp = &plld_nmp,
 	.freq_table = pll_d_freq_table,
 	.flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_SET_LFCON |
 		 TEGRA_PLL_USE_LOCK,
 };
 
 static struct tegra_clk_pll_freq_table tegra124_pll_d2_freq_table[] = {
-	{ 12000000, 148500000,  99, 1, 8},
-	{ 12000000, 594000000,  99, 1, 1},
-	{ 13000000, 594000000,  91, 1, 1},      /* actual: 591.5 MHz */
-	{ 16800000, 594000000,  71, 1, 1},      /* actual: 596.4 MHz */
-	{ 19200000, 594000000,  62, 1, 1},      /* actual: 595.2 MHz */
-	{ 26000000, 594000000,  91, 2, 1},      /* actual: 591.5 MHz */
+	{ 12000000, 594000000,  99, 1, 2},
+	{ 13000000, 594000000,  91, 1, 2},      /* actual: 591.5 MHz */
+	{ 16800000, 594000000,  71, 1, 2},      /* actual: 596.4 MHz */
+	{ 19200000, 594000000,  62, 1, 2},      /* actual: 595.2 MHz */
+	{ 26000000, 594000000,  91, 2, 2},      /* actual: 591.5 MHz */
 	{ 0, 0, 0, 0, 0, 0 },
 };
 
@@ -753,21 +761,19 @@
 	[tegra_clk_rtc] = { .dt_id = TEGRA124_CLK_RTC, .present = true },
 	[tegra_clk_timer] = { .dt_id = TEGRA124_CLK_TIMER, .present = true },
 	[tegra_clk_uarta] = { .dt_id = TEGRA124_CLK_UARTA, .present = true },
-	[tegra_clk_sdmmc2] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true },
+	[tegra_clk_sdmmc2_8] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true },
 	[tegra_clk_i2s1] = { .dt_id = TEGRA124_CLK_I2S1, .present = true },
 	[tegra_clk_i2c1] = { .dt_id = TEGRA124_CLK_I2C1, .present = true },
 	[tegra_clk_ndflash] = { .dt_id = TEGRA124_CLK_NDFLASH, .present = true },
-	[tegra_clk_sdmmc1] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true },
-	[tegra_clk_sdmmc4] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true },
+	[tegra_clk_sdmmc1_8] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true },
+	[tegra_clk_sdmmc4_8] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true },
 	[tegra_clk_pwm] = { .dt_id = TEGRA124_CLK_PWM, .present = true },
 	[tegra_clk_i2s2] = { .dt_id = TEGRA124_CLK_I2S2, .present = true },
-	[tegra_clk_gr2d] = { .dt_id = TEGRA124_CLK_GR_2D, .present = true },
 	[tegra_clk_usbd] = { .dt_id = TEGRA124_CLK_USBD, .present = true },
 	[tegra_clk_isp_8] = { .dt_id = TEGRA124_CLK_ISP, .present = true },
-	[tegra_clk_gr3d] = { .dt_id = TEGRA124_CLK_GR_3D, .present = true },
 	[tegra_clk_disp2] = { .dt_id = TEGRA124_CLK_DISP2, .present = true },
 	[tegra_clk_disp1] = { .dt_id = TEGRA124_CLK_DISP1, .present = true },
-	[tegra_clk_host1x] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true },
+	[tegra_clk_host1x_8] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true },
 	[tegra_clk_vcp] = { .dt_id = TEGRA124_CLK_VCP, .present = true },
 	[tegra_clk_i2s0] = { .dt_id = TEGRA124_CLK_I2S0, .present = true },
 	[tegra_clk_apbdma] = { .dt_id = TEGRA124_CLK_APBDMA, .present = true },
@@ -794,7 +800,7 @@
 	[tegra_clk_uartd] = { .dt_id = TEGRA124_CLK_UARTD, .present = true },
 	[tegra_clk_i2c3] = { .dt_id = TEGRA124_CLK_I2C3, .present = true },
 	[tegra_clk_sbc4] = { .dt_id = TEGRA124_CLK_SBC4, .present = true },
-	[tegra_clk_sdmmc3] = { .dt_id = TEGRA124_CLK_SDMMC3, .present = true },
+	[tegra_clk_sdmmc3_8] = { .dt_id = TEGRA124_CLK_SDMMC3, .present = true },
 	[tegra_clk_pcie] = { .dt_id = TEGRA124_CLK_PCIE, .present = true },
 	[tegra_clk_owr] = { .dt_id = TEGRA124_CLK_OWR, .present = true },
 	[tegra_clk_afi] = { .dt_id = TEGRA124_CLK_AFI, .present = true },
@@ -1286,9 +1292,9 @@
 	clk_register_clkdev(clk, "pll_d2", NULL);
 	clks[TEGRA124_CLK_PLL_D2] = clk;
 
-	/* PLLD2_OUT0 ?? */
+	/* PLLD2_OUT0 */
 	clk = clk_register_fixed_factor(NULL, "pll_d2_out0", "pll_d2",
-					CLK_SET_RATE_PARENT, 1, 2);
+					CLK_SET_RATE_PARENT, 1, 1);
 	clk_register_clkdev(clk, "pll_d2_out0", NULL);
 	clks[TEGRA124_CLK_PLL_D2_OUT0] = clk;
 
diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c
index dbace15..dace2b1 100644
--- a/drivers/clk/tegra/clk-tegra20.c
+++ b/drivers/clk/tegra/clk-tegra20.c
@@ -574,6 +574,8 @@
 	[tegra_clk_tvdac] = { .dt_id = TEGRA20_CLK_TVDAC, .present = true },
 	[tegra_clk_vi_sensor] = { .dt_id = TEGRA20_CLK_VI_SENSOR, .present = true },
 	[tegra_clk_afi] = { .dt_id = TEGRA20_CLK_AFI, .present = true },
+	[tegra_clk_fuse] = { .dt_id = TEGRA20_CLK_FUSE, .present = true },
+	[tegra_clk_kfuse] = { .dt_id = TEGRA20_CLK_KFUSE, .present = true },
 };
 
 static unsigned long tegra20_clk_measure_input_freq(void)
diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c
index 5176e76..0595dc6 100644
--- a/drivers/clocksource/bcm_kona_timer.c
+++ b/drivers/clocksource/bcm_kona_timer.c
@@ -17,6 +17,7 @@
 #include <linux/jiffies.h>
 #include <linux/clockchips.h>
 #include <linux/types.h>
+#include <linux/clk.h>
 
 #include <linux/io.h>
 #include <asm/mach/time.h>
@@ -98,24 +99,6 @@
 	return;
 }
 
-static void __init kona_timers_init(struct device_node *node)
-{
-	u32 freq;
-
-	if (!of_property_read_u32(node, "clock-frequency", &freq))
-		arch_timer_rate = freq;
-	else
-		panic("clock-frequency not set in the .dts file");
-
-	/* Setup IRQ numbers */
-	timers.tmr_irq = irq_of_parse_and_map(node, 0);
-
-	/* Setup IO addresses */
-	timers.tmr_regs = of_iomap(node, 0);
-
-	kona_timer_disable_and_clear(timers.tmr_regs);
-}
-
 static int kona_timer_set_next_event(unsigned long clc,
 				  struct clock_event_device *unused)
 {
@@ -190,7 +173,34 @@
 
 static void __init kona_timer_init(struct device_node *node)
 {
-	kona_timers_init(node);
+	u32 freq;
+	struct clk *external_clk;
+
+	if (!of_device_is_available(node)) {
+		pr_info("Kona Timer v1 marked as disabled in device tree\n");
+		return;
+	}
+
+	external_clk = of_clk_get_by_name(node, NULL);
+
+	if (!IS_ERR(external_clk)) {
+		arch_timer_rate = clk_get_rate(external_clk);
+		clk_prepare_enable(external_clk);
+	} else if (!of_property_read_u32(node, "clock-frequency", &freq)) {
+		arch_timer_rate = freq;
+	} else {
+		pr_err("Kona Timer v1 unable to determine clock-frequency");
+		return;
+	}
+
+	/* Setup IRQ numbers */
+	timers.tmr_irq = irq_of_parse_and_map(node, 0);
+
+	/* Setup IO addresses */
+	timers.tmr_regs = of_iomap(node, 0);
+
+	kona_timer_disable_and_clear(timers.tmr_regs);
+
 	kona_timer_clockevents_init();
 	setup_irq(timers.tmr_irq, &kona_timer_irq);
 	kona_timer_set_next_event((arch_timer_rate / HZ), NULL);
diff --git a/drivers/clocksource/vf_pit_timer.c b/drivers/clocksource/vf_pit_timer.c
index 02821b0..a918bc4 100644
--- a/drivers/clocksource/vf_pit_timer.c
+++ b/drivers/clocksource/vf_pit_timer.c
@@ -54,7 +54,7 @@
 
 static u64 pit_read_sched_clock(void)
 {
-	return __raw_readl(clksrc_base + PITCVAL);
+	return ~__raw_readl(clksrc_base + PITCVAL);
 }
 
 static int __init pit_clocksource_init(unsigned long rate)
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 4b029c0..1fbe11f 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -200,7 +200,7 @@
 endmenu
 
 menu "ARM CPU frequency scaling drivers"
-depends on ARM
+depends on ARM || ARM64
 source "drivers/cpufreq/Kconfig.arm"
 endmenu
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 08ca8c9..199b52b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1109,12 +1109,27 @@
 		goto err_set_policy_cpu;
 	}
 
+	/* related cpus should atleast have policy->cpus */
+	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
+
+	/*
+	 * affected cpus must always be the one, which are online. We aren't
+	 * managing offline cpus here.
+	 */
+	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
+
+	if (!frozen) {
+		policy->user_policy.min = policy->min;
+		policy->user_policy.max = policy->max;
+	}
+
+	down_write(&policy->rwsem);
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	for_each_cpu(j, policy->cpus)
 		per_cpu(cpufreq_cpu_data, j) = policy;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	if (cpufreq_driver->get) {
+	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
 		policy->cur = cpufreq_driver->get(policy->cpu);
 		if (!policy->cur) {
 			pr_err("%s: ->get() failed\n", __func__);
@@ -1162,20 +1177,6 @@
 		}
 	}
 
-	/* related cpus should atleast have policy->cpus */
-	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
-
-	/*
-	 * affected cpus must always be the one, which are online. We aren't
-	 * managing offline cpus here.
-	 */
-	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
-
-	if (!frozen) {
-		policy->user_policy.min = policy->min;
-		policy->user_policy.max = policy->max;
-	}
-
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				     CPUFREQ_START, policy);
 
@@ -1206,6 +1207,7 @@
 		policy->user_policy.policy = policy->policy;
 		policy->user_policy.governor = policy->governor;
 	}
+	up_write(&policy->rwsem);
 
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
 	up_read(&cpufreq_rwsem);
@@ -1323,8 +1325,7 @@
 	up_read(&policy->rwsem);
 
 	if (cpu != policy->cpu) {
-		if (!frozen)
-			sysfs_remove_link(&dev->kobj, "cpufreq");
+		sysfs_remove_link(&dev->kobj, "cpufreq");
 	} else if (cpus > 1) {
 		new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu);
 		if (new_cpu >= 0) {
@@ -1547,23 +1548,16 @@
  */
 unsigned int cpufreq_get(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 	unsigned int ret_freq = 0;
 
-	if (cpufreq_disabled() || !cpufreq_driver)
-		return -ENOENT;
+	if (policy) {
+		down_read(&policy->rwsem);
+		ret_freq = __cpufreq_get(cpu);
+		up_read(&policy->rwsem);
 
-	BUG_ON(!policy);
-
-	if (!down_read_trylock(&cpufreq_rwsem))
-		return 0;
-
-	down_read(&policy->rwsem);
-
-	ret_freq = __cpufreq_get(cpu);
-
-	up_read(&policy->rwsem);
-	up_read(&cpufreq_rwsem);
+		cpufreq_cpu_put(policy);
+	}
 
 	return ret_freq;
 }
@@ -2149,7 +2143,7 @@
 	 * BIOS might change freq behind our back
 	 * -> ask driver for current freq and notify governors about a change
 	 */
-	if (cpufreq_driver->get) {
+	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
 		new_policy.cur = cpufreq_driver->get(cpu);
 		if (!policy->cur) {
 			pr_debug("Driver did not initialize current freq");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 7e257b2..2cd36b9 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -34,12 +34,15 @@
 
 #define SAMPLE_COUNT		3
 
-#define BYT_RATIOS	0x66a
-#define BYT_VIDS        0x66b
+#define BYT_RATIOS		0x66a
+#define BYT_VIDS		0x66b
+#define BYT_TURBO_RATIOS	0x66c
 
-#define FRAC_BITS 8
+
+#define FRAC_BITS 6
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
 #define fp_toint(X) ((X) >> FRAC_BITS)
+#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS)
 
 static inline int32_t mul_fp(int32_t x, int32_t y)
 {
@@ -51,12 +54,11 @@
 	return div_s64((int64_t)x << FRAC_BITS, (int64_t)y);
 }
 
-static u64 energy_divisor;
-
 struct sample {
 	int32_t core_pct_busy;
 	u64 aperf;
 	u64 mperf;
+	unsigned long long tsc;
 	int freq;
 };
 
@@ -96,6 +98,7 @@
 
 	u64	prev_aperf;
 	u64	prev_mperf;
+	unsigned long long prev_tsc;
 	int	sample_ptr;
 	struct sample samples[SAMPLE_COUNT];
 };
@@ -357,7 +360,7 @@
 {
 	u64 value;
 	rdmsrl(BYT_RATIOS, value);
-	return value & 0xFF;
+	return (value >> 8) & 0xFF;
 }
 
 static int byt_get_max_pstate(void)
@@ -367,6 +370,13 @@
 	return (value >> 16) & 0xFF;
 }
 
+static int byt_get_turbo_pstate(void)
+{
+	u64 value;
+	rdmsrl(BYT_TURBO_RATIOS, value);
+	return value & 0x3F;
+}
+
 static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
@@ -469,7 +479,7 @@
 	.funcs = {
 		.get_max = byt_get_max_pstate,
 		.get_min = byt_get_min_pstate,
-		.get_turbo = byt_get_max_pstate,
+		.get_turbo = byt_get_turbo_pstate,
 		.set = byt_set_pstate,
 		.get_vid = byt_get_vid,
 	},
@@ -547,31 +557,48 @@
 static inline void intel_pstate_calc_busy(struct cpudata *cpu,
 					struct sample *sample)
 {
-	u64 core_pct;
-	core_pct = div64_u64(int_tofp(sample->aperf * 100),
-			     sample->mperf);
-	sample->freq = fp_toint(cpu->pstate.max_pstate * core_pct * 1000);
+	int32_t core_pct;
+	int32_t c0_pct;
 
-	sample->core_pct_busy = core_pct;
+	core_pct = div_fp(int_tofp((sample->aperf)),
+			int_tofp((sample->mperf)));
+	core_pct = mul_fp(core_pct, int_tofp(100));
+	FP_ROUNDUP(core_pct);
+
+	c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc));
+
+	sample->freq = fp_toint(
+		mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct));
+
+	sample->core_pct_busy = mul_fp(core_pct, c0_pct);
 }
 
 static inline void intel_pstate_sample(struct cpudata *cpu)
 {
 	u64 aperf, mperf;
+	unsigned long long tsc;
 
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
+	tsc = native_read_tsc();
+
+	aperf = aperf >> FRAC_BITS;
+	mperf = mperf >> FRAC_BITS;
+	tsc = tsc >> FRAC_BITS;
 
 	cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
 	cpu->samples[cpu->sample_ptr].aperf = aperf;
 	cpu->samples[cpu->sample_ptr].mperf = mperf;
+	cpu->samples[cpu->sample_ptr].tsc = tsc;
 	cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
 	cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;
+	cpu->samples[cpu->sample_ptr].tsc -= cpu->prev_tsc;
 
 	intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);
 
 	cpu->prev_aperf = aperf;
 	cpu->prev_mperf = mperf;
+	cpu->prev_tsc = tsc;
 }
 
 static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
@@ -590,7 +617,8 @@
 	core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy;
 	max_pstate = int_tofp(cpu->pstate.max_pstate);
 	current_pstate = int_tofp(cpu->pstate.current_pstate);
-	return mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+	core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+	return FP_ROUNDUP(core_busy);
 }
 
 static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
@@ -617,12 +645,10 @@
 {
 	struct cpudata *cpu = (struct cpudata *) __data;
 	struct sample *sample;
-	u64 energy;
 
 	intel_pstate_sample(cpu);
 
 	sample = &cpu->samples[cpu->sample_ptr];
-	rdmsrl(MSR_PKG_ENERGY_STATUS, energy);
 
 	intel_pstate_adjust_busy_pstate(cpu);
 
@@ -631,7 +657,6 @@
 			cpu->pstate.current_pstate,
 			sample->mperf,
 			sample->aperf,
-			div64_u64(energy, energy_divisor),
 			sample->freq);
 
 	intel_pstate_set_sample_time(cpu);
@@ -913,7 +938,6 @@
 	int cpu, rc = 0;
 	const struct x86_cpu_id *id;
 	struct cpu_defaults *cpu_info;
-	u64 units;
 
 	if (no_load)
 		return -ENODEV;
@@ -947,9 +971,6 @@
 	if (rc)
 		goto out;
 
-	rdmsrl(MSR_RAPL_POWER_UNIT, units);
-	energy_divisor = 1 << ((units >> 8) & 0x1f); /* bits{12:8} */
-
 	intel_pstate_debug_expose_params();
 	intel_pstate_sysfs_expose_params();
 
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index e10b646..6684e03 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1076,7 +1076,7 @@
 {
 	struct powernow_k8_data *data;
 	struct init_on_cpu init_on_cpu;
-	int rc;
+	int rc, cpu;
 
 	smp_call_function_single(pol->cpu, check_supported_cpu, &rc, 1);
 	if (rc)
@@ -1140,7 +1140,9 @@
 	pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n",
 		 data->currfid, data->currvid);
 
-	per_cpu(powernow_data, pol->cpu) = data;
+	/* Point all the CPUs in this policy to the same data */
+	for_each_cpu(cpu, pol->cpus)
+		per_cpu(powernow_data, cpu) = data;
 
 	return 0;
 
@@ -1155,6 +1157,7 @@
 static int powernowk8_cpu_exit(struct cpufreq_policy *pol)
 {
 	struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
+	int cpu;
 
 	if (!data)
 		return -EINVAL;
@@ -1165,7 +1168,8 @@
 
 	kfree(data->powernow_table);
 	kfree(data);
-	per_cpu(powernow_data, pol->cpu) = NULL;
+	for_each_cpu(cpu, pol->cpus)
+		per_cpu(powernow_data, cpu) = NULL;
 
 	return 0;
 }
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 78fd174..f48607c 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -14,6 +14,7 @@
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
+#include <asm/runlatch.h>
 
 struct cpuidle_driver powernv_idle_driver = {
 	.name             = "powernv_idle",
@@ -30,12 +31,14 @@
 	local_irq_enable();
 	set_thread_flag(TIF_POLLING_NRFLAG);
 
+	ppc64_runlatch_off();
 	while (!need_resched()) {
 		HMT_low();
 		HMT_very_low();
 	}
 
 	HMT_medium();
+	ppc64_runlatch_on();
 	clear_thread_flag(TIF_POLLING_NRFLAG);
 	smp_mb();
 	return index;
@@ -45,7 +48,9 @@
 			struct cpuidle_driver *drv,
 			int index)
 {
+	ppc64_runlatch_off();
 	power7_idle();
+	ppc64_runlatch_on();
 	return index;
 }
 
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 7ab564a..6f7b019 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -17,6 +17,7 @@
 #include <asm/reg.h>
 #include <asm/machdep.h>
 #include <asm/firmware.h>
+#include <asm/runlatch.h>
 #include <asm/plpar_wrappers.h>
 
 struct cpuidle_driver pseries_idle_driver = {
@@ -29,6 +30,7 @@
 
 static inline void idle_loop_prolog(unsigned long *in_purr)
 {
+	ppc64_runlatch_off();
 	*in_purr = mfspr(SPRN_PURR);
 	/*
 	 * Indicate to the HV that we are idle. Now would be
@@ -45,6 +47,10 @@
 	wait_cycles += mfspr(SPRN_PURR) - in_purr;
 	get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
 	get_lppaca()->idle = 0;
+
+	if (irqs_disabled())
+		local_irq_enable();
+	ppc64_runlatch_on();
 }
 
 static int snooze_loop(struct cpuidle_device *dev,
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 6c4c000..1e5481d 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -158,6 +158,15 @@
 	return sl->entry_nr * sizeof(struct nx842_slentry);
 }
 
+static inline unsigned long nx842_get_pa(void *addr)
+{
+	if (is_vmalloc_addr(addr))
+		return page_to_phys(vmalloc_to_page(addr))
+		       + offset_in_page(addr);
+	else
+		return __pa(addr);
+}
+
 static int nx842_build_scatterlist(unsigned long buf, int len,
 			struct nx842_scatterlist *sl)
 {
@@ -168,7 +177,7 @@
 
 	entry = sl->entries;
 	while (len) {
-		entry->ptr = __pa(buf);
+		entry->ptr = nx842_get_pa((void *)buf);
 		nextpage = ALIGN(buf + 1, NX842_HW_PAGE_SIZE);
 		if (nextpage < buf + len) {
 			/* we aren't at the end yet */
@@ -370,8 +379,8 @@
 	op.flags = NX842_OP_COMPRESS;
 	csbcpb = &workmem->csbcpb;
 	memset(csbcpb, 0, sizeof(*csbcpb));
-	op.csbcpb = __pa(csbcpb);
-	op.out = __pa(slout.entries);
+	op.csbcpb = nx842_get_pa(csbcpb);
+	op.out = nx842_get_pa(slout.entries);
 
 	for (i = 0; i < hdr->blocks_nr; i++) {
 		/*
@@ -401,13 +410,13 @@
 		 */
 		if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) {
 			/* Create direct DDE */
-			op.in = __pa(inbuf);
+			op.in = nx842_get_pa((void *)inbuf);
 			op.inlen = max_sync_size;
 
 		} else {
 			/* Create indirect DDE (scatterlist) */
 			nx842_build_scatterlist(inbuf, max_sync_size, &slin);
-			op.in = __pa(slin.entries);
+			op.in = nx842_get_pa(slin.entries);
 			op.inlen = -nx842_get_scatterlist_size(&slin);
 		}
 
@@ -565,7 +574,7 @@
 	op.flags = NX842_OP_DECOMPRESS;
 	csbcpb = &workmem->csbcpb;
 	memset(csbcpb, 0, sizeof(*csbcpb));
-	op.csbcpb = __pa(csbcpb);
+	op.csbcpb = nx842_get_pa(csbcpb);
 
 	/*
 	 * max_sync_size may have changed since compression,
@@ -597,12 +606,12 @@
 		if (likely((inbuf & NX842_HW_PAGE_MASK) ==
 			((inbuf + hdr->sizes[i] - 1) & NX842_HW_PAGE_MASK))) {
 			/* Create direct DDE */
-			op.in = __pa(inbuf);
+			op.in = nx842_get_pa((void *)inbuf);
 			op.inlen = hdr->sizes[i];
 		} else {
 			/* Create indirect DDE (scatterlist) */
 			nx842_build_scatterlist(inbuf, hdr->sizes[i] , &slin);
-			op.in = __pa(slin.entries);
+			op.in = nx842_get_pa(slin.entries);
 			op.inlen = -nx842_get_scatterlist_size(&slin);
 		}
 
@@ -613,12 +622,12 @@
 		 */
 		if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) {
 			/* Create direct DDE */
-			op.out = __pa(outbuf);
+			op.out = nx842_get_pa((void *)outbuf);
 			op.outlen = max_sync_size;
 		} else {
 			/* Create indirect DDE (scatterlist) */
 			nx842_build_scatterlist(outbuf, max_sync_size, &slout);
-			op.out = __pa(slout.entries);
+			op.out = nx842_get_pa(slout.entries);
 			op.outlen = -nx842_get_scatterlist_size(&slout);
 		}
 
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 9bed1a2..605b016 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -346,6 +346,7 @@
 	tristate "MOXART DMA support"
 	depends on ARCH_MOXART
 	select DMA_ENGINE
+	select DMA_OF
 	select DMA_VIRTUAL_CHANNELS
 	help
 	  Enable support for the MOXA ART SoC DMA controller.
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 4e79183..19041ce 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -449,6 +449,7 @@
 	{ .compatible = "fsl,imx51-sdma", .data = &sdma_imx51, },
 	{ .compatible = "fsl,imx35-sdma", .data = &sdma_imx35, },
 	{ .compatible = "fsl,imx31-sdma", .data = &sdma_imx31, },
+	{ .compatible = "fsl,imx25-sdma", .data = &sdma_imx25, },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sdma_dt_ids);
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 8752918..4e3549a 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -77,7 +77,8 @@
 	attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET);
 	for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) {
 		chan = ioat_chan_by_index(instance, bit);
-		tasklet_schedule(&chan->cleanup_task);
+		if (test_bit(IOAT_RUN, &chan->state))
+			tasklet_schedule(&chan->cleanup_task);
 	}
 
 	writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
@@ -93,7 +94,8 @@
 {
 	struct ioat_chan_common *chan = data;
 
-	tasklet_schedule(&chan->cleanup_task);
+	if (test_bit(IOAT_RUN, &chan->state))
+		tasklet_schedule(&chan->cleanup_task);
 
 	return IRQ_HANDLED;
 }
@@ -116,7 +118,6 @@
 	chan->timer.function = device->timer_fn;
 	chan->timer.data = data;
 	tasklet_init(&chan->cleanup_task, device->cleanup_fn, data);
-	tasklet_disable(&chan->cleanup_task);
 }
 
 /**
@@ -354,13 +355,49 @@
 	writel(((u64) chan->completion_dma) >> 32,
 	       chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
 
-	tasklet_enable(&chan->cleanup_task);
+	set_bit(IOAT_RUN, &chan->state);
 	ioat1_dma_start_null_desc(ioat);  /* give chain to dma device */
 	dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
 		__func__, ioat->desccount);
 	return ioat->desccount;
 }
 
+void ioat_stop(struct ioat_chan_common *chan)
+{
+	struct ioatdma_device *device = chan->device;
+	struct pci_dev *pdev = device->pdev;
+	int chan_id = chan_num(chan);
+	struct msix_entry *msix;
+
+	/* 1/ stop irq from firing tasklets
+	 * 2/ stop the tasklet from re-arming irqs
+	 */
+	clear_bit(IOAT_RUN, &chan->state);
+
+	/* flush inflight interrupts */
+	switch (device->irq_mode) {
+	case IOAT_MSIX:
+		msix = &device->msix_entries[chan_id];
+		synchronize_irq(msix->vector);
+		break;
+	case IOAT_MSI:
+	case IOAT_INTX:
+		synchronize_irq(pdev->irq);
+		break;
+	default:
+		break;
+	}
+
+	/* flush inflight timers */
+	del_timer_sync(&chan->timer);
+
+	/* flush inflight tasklet runs */
+	tasklet_kill(&chan->cleanup_task);
+
+	/* final cleanup now that everything is quiesced and can't re-arm */
+	device->cleanup_fn((unsigned long) &chan->common);
+}
+
 /**
  * ioat1_dma_free_chan_resources - release all the descriptors
  * @chan: the channel to be cleaned
@@ -379,9 +416,7 @@
 	if (ioat->desccount == 0)
 		return;
 
-	tasklet_disable(&chan->cleanup_task);
-	del_timer_sync(&chan->timer);
-	ioat1_cleanup(ioat);
+	ioat_stop(chan);
 
 	/* Delay 100ms after reset to allow internal DMA logic to quiesce
 	 * before removing DMA descriptor resources.
@@ -526,8 +561,11 @@
 static void ioat1_cleanup_event(unsigned long data)
 {
 	struct ioat_dma_chan *ioat = to_ioat_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat1_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 11fb877..e982f00 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -356,6 +356,7 @@
 void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
 void ioat_kobject_del(struct ioatdma_device *device);
 int ioat_dma_setup_interrupts(struct ioatdma_device *device);
+void ioat_stop(struct ioat_chan_common *chan);
 extern const struct sysfs_ops ioat_sysfs_ops;
 extern struct ioat_sysfs_entry ioat_version_attr;
 extern struct ioat_sysfs_entry ioat_cap_attr;
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 5d3affe..8d10580 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -190,8 +190,11 @@
 void ioat2_cleanup_event(unsigned long data)
 {
 	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat2_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
@@ -553,10 +556,10 @@
 	ioat->issued = 0;
 	ioat->tail = 0;
 	ioat->alloc_order = order;
+	set_bit(IOAT_RUN, &chan->state);
 	spin_unlock_bh(&ioat->prep_lock);
 	spin_unlock_bh(&chan->cleanup_lock);
 
-	tasklet_enable(&chan->cleanup_task);
 	ioat2_start_null_desc(ioat);
 
 	/* check that we got off the ground */
@@ -566,7 +569,6 @@
 	} while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status));
 
 	if (is_ioat_active(status) || is_ioat_idle(status)) {
-		set_bit(IOAT_RUN, &chan->state);
 		return 1 << ioat->alloc_order;
 	} else {
 		u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
@@ -809,11 +811,8 @@
 	if (!ioat->ring)
 		return;
 
-	tasklet_disable(&chan->cleanup_task);
-	del_timer_sync(&chan->timer);
-	device->cleanup_fn((unsigned long) c);
+	ioat_stop(chan);
 	device->reset_hw(chan);
-	clear_bit(IOAT_RUN, &chan->state);
 
 	spin_lock_bh(&chan->cleanup_lock);
 	spin_lock_bh(&ioat->prep_lock);
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index 820817e9..b9b38a1 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -464,8 +464,11 @@
 static void ioat3_cleanup_event(unsigned long data)
 {
 	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat3_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 53fb0c8..766b68e 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -497,8 +497,8 @@
 		if (!mv_can_chain(grp_start))
 			goto submit_done;
 
-		dev_dbg(mv_chan_to_devp(mv_chan), "Append to last desc %x\n",
-			old_chain_tail->async_tx.phys);
+		dev_dbg(mv_chan_to_devp(mv_chan), "Append to last desc %pa\n",
+			&old_chain_tail->async_tx.phys);
 
 		/* fix up the hardware chain */
 		mv_desc_set_next_desc(old_chain_tail, grp_start->async_tx.phys);
@@ -527,7 +527,8 @@
 /* returns the number of allocated descriptors */
 static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 {
-	char *hw_desc;
+	void *virt_desc;
+	dma_addr_t dma_desc;
 	int idx;
 	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
 	struct mv_xor_desc_slot *slot = NULL;
@@ -542,17 +543,16 @@
 				" %d descriptor slots", idx);
 			break;
 		}
-		hw_desc = (char *) mv_chan->dma_desc_pool_virt;
-		slot->hw_desc = (void *) &hw_desc[idx * MV_XOR_SLOT_SIZE];
+		virt_desc = mv_chan->dma_desc_pool_virt;
+		slot->hw_desc = virt_desc + idx * MV_XOR_SLOT_SIZE;
 
 		dma_async_tx_descriptor_init(&slot->async_tx, chan);
 		slot->async_tx.tx_submit = mv_xor_tx_submit;
 		INIT_LIST_HEAD(&slot->chain_node);
 		INIT_LIST_HEAD(&slot->slot_node);
 		INIT_LIST_HEAD(&slot->tx_list);
-		hw_desc = (char *) mv_chan->dma_desc_pool;
-		slot->async_tx.phys =
-			(dma_addr_t) &hw_desc[idx * MV_XOR_SLOT_SIZE];
+		dma_desc = mv_chan->dma_desc_pool;
+		slot->async_tx.phys = dma_desc + idx * MV_XOR_SLOT_SIZE;
 		slot->idx = idx++;
 
 		spin_lock_bh(&mv_chan->lock);
@@ -582,8 +582,8 @@
 	int slot_cnt;
 
 	dev_dbg(mv_chan_to_devp(mv_chan),
-		"%s dest: %x src %x len: %u flags: %ld\n",
-		__func__, dest, src, len, flags);
+		"%s dest: %pad src %pad len: %u flags: %ld\n",
+		__func__, &dest, &src, len, flags);
 	if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
 		return NULL;
 
@@ -626,8 +626,8 @@
 	BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
 
 	dev_dbg(mv_chan_to_devp(mv_chan),
-		"%s src_cnt: %d len: dest %x %u flags: %ld\n",
-		__func__, src_cnt, len, dest, flags);
+		"%s src_cnt: %d len: %u dest %pad flags: %ld\n",
+		__func__, src_cnt, len, &dest, flags);
 
 	spin_lock_bh(&mv_chan->lock);
 	slot_cnt = mv_chan_xor_slot_count(len, src_cnt);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 00a2de9..bf18c78 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -1641,6 +1641,7 @@
 	struct d40_chan *d40c = (struct d40_chan *) data;
 	struct d40_desc *d40d;
 	unsigned long flags;
+	bool callback_active;
 	dma_async_tx_callback callback;
 	void *callback_param;
 
@@ -1668,6 +1669,7 @@
 	}
 
 	/* Callback to client */
+	callback_active = !!(d40d->txd.flags & DMA_PREP_INTERRUPT);
 	callback = d40d->txd.callback;
 	callback_param = d40d->txd.callback_param;
 
@@ -1690,7 +1692,7 @@
 
 	spin_unlock_irqrestore(&d40c->lock, flags);
 
-	if (callback && (d40d->txd.flags & DMA_PREP_INTERRUPT))
+	if (callback_active && callback)
 		callback(callback_param);
 
 	return;
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index e8c9ef0..33edd67 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -559,7 +559,8 @@
  *
  *		called with the mem_ctls_mutex held
  */
-static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec)
+static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec,
+				bool init)
 {
 	edac_dbg(0, "\n");
 
@@ -567,7 +568,9 @@
 	if (mci->op_state != OP_RUNNING_POLL)
 		return;
 
-	INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
+	if (init)
+		INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
+
 	mod_delayed_work(edac_workqueue, &mci->work, msecs_to_jiffies(msec));
 }
 
@@ -601,7 +604,7 @@
  *	user space has updated our poll period value, need to
  *	reset our workq delays
  */
-void edac_mc_reset_delay_period(int value)
+void edac_mc_reset_delay_period(unsigned long value)
 {
 	struct mem_ctl_info *mci;
 	struct list_head *item;
@@ -611,7 +614,7 @@
 	list_for_each(item, &mc_devices) {
 		mci = list_entry(item, struct mem_ctl_info, link);
 
-		edac_mc_workq_setup(mci, (unsigned long) value);
+		edac_mc_workq_setup(mci, value, false);
 	}
 
 	mutex_unlock(&mem_ctls_mutex);
@@ -782,7 +785,7 @@
 		/* This instance is NOW RUNNING */
 		mci->op_state = OP_RUNNING_POLL;
 
-		edac_mc_workq_setup(mci, edac_mc_get_poll_msec());
+		edac_mc_workq_setup(mci, edac_mc_get_poll_msec(), true);
 	} else {
 		mci->op_state = OP_RUNNING_INTERRUPT;
 	}
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 51c0362..b335c6a 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -52,18 +52,20 @@
 
 static int edac_set_poll_msec(const char *val, struct kernel_param *kp)
 {
-	long l;
+	unsigned long l;
 	int ret;
 
 	if (!val)
 		return -EINVAL;
 
-	ret = kstrtol(val, 0, &l);
+	ret = kstrtoul(val, 0, &l);
 	if (ret)
 		return ret;
-	if ((int)l != l)
+
+	if (l < 1000)
 		return -EINVAL;
-	*((int *)kp->arg) = l;
+
+	*((unsigned long *)kp->arg) = l;
 
 	/* notify edac_mc engine to reset the poll period */
 	edac_mc_reset_delay_period(l);
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index 3d139c6..f2118bf 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -52,7 +52,7 @@
 extern void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev);
 extern void edac_device_reset_delay_period(struct edac_device_ctl_info
 					   *edac_dev, unsigned long value);
-extern void edac_mc_reset_delay_period(int value);
+extern void edac_mc_reset_delay_period(unsigned long value);
 
 extern void *edac_align_ptr(void **p, unsigned size, int n_elems);
 
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index d63f479..57e96a3 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -943,33 +943,35 @@
 
 	/* Attempt to 'get' the MCH register we want */
 	pdev = NULL;
-	while (!pvt->pci_dev_16_1_fsb_addr_map ||
-	       !pvt->pci_dev_16_2_fsb_err_regs) {
-		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
-				      PCI_DEVICE_ID_INTEL_I7300_MCH_ERR, pdev);
-		if (!pdev) {
-			/* End of list, leave */
-			i7300_printk(KERN_ERR,
-				"'system address,Process Bus' "
-				"device not found:"
-				"vendor 0x%x device 0x%x ERR funcs "
-				"(broken BIOS?)\n",
-				PCI_VENDOR_ID_INTEL,
-				PCI_DEVICE_ID_INTEL_I7300_MCH_ERR);
-			goto error;
-		}
-
+	while ((pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+				      PCI_DEVICE_ID_INTEL_I7300_MCH_ERR,
+				      pdev))) {
 		/* Store device 16 funcs 1 and 2 */
 		switch (PCI_FUNC(pdev->devfn)) {
 		case 1:
-			pvt->pci_dev_16_1_fsb_addr_map = pdev;
+			if (!pvt->pci_dev_16_1_fsb_addr_map)
+				pvt->pci_dev_16_1_fsb_addr_map =
+							pci_dev_get(pdev);
 			break;
 		case 2:
-			pvt->pci_dev_16_2_fsb_err_regs = pdev;
+			if (!pvt->pci_dev_16_2_fsb_err_regs)
+				pvt->pci_dev_16_2_fsb_err_regs =
+							pci_dev_get(pdev);
 			break;
 		}
 	}
 
+	if (!pvt->pci_dev_16_1_fsb_addr_map ||
+	    !pvt->pci_dev_16_2_fsb_err_regs) {
+		/* At least one device was not found */
+		i7300_printk(KERN_ERR,
+			"'system address,Process Bus' device not found:"
+			"vendor 0x%x device 0x%x ERR funcs (broken BIOS?)\n",
+			PCI_VENDOR_ID_INTEL,
+			PCI_DEVICE_ID_INTEL_I7300_MCH_ERR);
+		goto error;
+	}
+
 	edac_dbg(1, "System Address, processor bus- PCI Bus ID: %s  %x:%x\n",
 		 pci_name(pvt->pci_dev_16_0_fsb_ctlr),
 		 pvt->pci_dev_16_0_fsb_ctlr->vendor,
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 87533ca..d871275 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1334,14 +1334,19 @@
 	 * is at addr 8086:2c40, instead of 8086:2c41. So, we need
 	 * to probe for the alternate address in case of failure
 	 */
-	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev)
+	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev) {
+		pci_dev_get(*prev);	/* pci_get_device will put it */
 		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
 				      PCI_DEVICE_ID_INTEL_I7_NONCORE_ALT, *prev);
+	}
 
-	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE && !pdev)
+	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE &&
+	    !pdev) {
+		pci_dev_get(*prev);	/* pci_get_device will put it */
 		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
 				      PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_ALT,
 				      *prev);
+	}
 
 	if (!pdev) {
 		if (*prev) {
diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c
index c20602f..98a14f6 100644
--- a/drivers/extcon/extcon-arizona.c
+++ b/drivers/extcon/extcon-arizona.c
@@ -222,27 +222,19 @@
 	struct snd_soc_dapm_context *dapm = arizona->dapm;
 	int ret;
 
-	mutex_lock(&dapm->card->dapm_mutex);
-
 	ret = snd_soc_dapm_force_enable_pin(dapm, widget);
 	if (ret != 0)
 		dev_warn(arizona->dev, "Failed to enable %s: %d\n",
 			 widget, ret);
 
-	mutex_unlock(&dapm->card->dapm_mutex);
-
 	snd_soc_dapm_sync(dapm);
 
 	if (!arizona->pdata.micd_force_micbias) {
-		mutex_lock(&dapm->card->dapm_mutex);
-
 		ret = snd_soc_dapm_disable_pin(arizona->dapm, widget);
 		if (ret != 0)
 			dev_warn(arizona->dev, "Failed to disable %s: %d\n",
 				 widget, ret);
 
-		mutex_unlock(&dapm->card->dapm_mutex);
-
 		snd_soc_dapm_sync(dapm);
 	}
 }
@@ -304,16 +296,12 @@
 				 ARIZONA_MICD_ENA, 0,
 				 &change);
 
-	mutex_lock(&dapm->card->dapm_mutex);
-
 	ret = snd_soc_dapm_disable_pin(dapm, widget);
 	if (ret != 0)
 		dev_warn(arizona->dev,
 			 "Failed to disable %s: %d\n",
 			 widget, ret);
 
-	mutex_unlock(&dapm->card->dapm_mutex);
-
 	snd_soc_dapm_sync(dapm);
 
 	if (info->micd_reva) {
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index de4aa40..2c6d5e1 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -916,7 +916,7 @@
 		old->config_rom_retries = 0;
 		fw_notice(card, "rediscovered device %s\n", dev_name(dev));
 
-		PREPARE_DELAYED_WORK(&old->work, fw_device_update);
+		old->workfn = fw_device_update;
 		fw_schedule_device_work(old, 0);
 
 		if (current_node == card->root_node)
@@ -1075,7 +1075,7 @@
 	if (atomic_cmpxchg(&device->state,
 			   FW_DEVICE_INITIALIZING,
 			   FW_DEVICE_RUNNING) == FW_DEVICE_GONE) {
-		PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+		device->workfn = fw_device_shutdown;
 		fw_schedule_device_work(device, SHUTDOWN_DELAY);
 	} else {
 		fw_notice(card, "created device %s: GUID %08x%08x, S%d00\n",
@@ -1196,13 +1196,20 @@
 		  dev_name(&device->device), fw_rcode_string(ret));
  gone:
 	atomic_set(&device->state, FW_DEVICE_GONE);
-	PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+	device->workfn = fw_device_shutdown;
 	fw_schedule_device_work(device, SHUTDOWN_DELAY);
  out:
 	if (node_id == card->root_node->node_id)
 		fw_schedule_bm_work(card, 0);
 }
 
+static void fw_device_workfn(struct work_struct *work)
+{
+	struct fw_device *device = container_of(to_delayed_work(work),
+						struct fw_device, work);
+	device->workfn(work);
+}
+
 void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 {
 	struct fw_device *device;
@@ -1252,7 +1259,8 @@
 		 * power-up after getting plugged in.  We schedule the
 		 * first config rom scan half a second after bus reset.
 		 */
-		INIT_DELAYED_WORK(&device->work, fw_device_init);
+		device->workfn = fw_device_init;
+		INIT_DELAYED_WORK(&device->work, fw_device_workfn);
 		fw_schedule_device_work(device, INITIAL_DELAY);
 		break;
 
@@ -1268,7 +1276,7 @@
 		if (atomic_cmpxchg(&device->state,
 			    FW_DEVICE_RUNNING,
 			    FW_DEVICE_INITIALIZING) == FW_DEVICE_RUNNING) {
-			PREPARE_DELAYED_WORK(&device->work, fw_device_refresh);
+			device->workfn = fw_device_refresh;
 			fw_schedule_device_work(device,
 				device->is_local ? 0 : INITIAL_DELAY);
 		}
@@ -1283,7 +1291,7 @@
 		smp_wmb();  /* update node_id before generation */
 		device->generation = card->generation;
 		if (atomic_read(&device->state) == FW_DEVICE_RUNNING) {
-			PREPARE_DELAYED_WORK(&device->work, fw_device_update);
+			device->workfn = fw_device_update;
 			fw_schedule_device_work(device, 0);
 		}
 		break;
@@ -1308,7 +1316,7 @@
 		device = node->data;
 		if (atomic_xchg(&device->state,
 				FW_DEVICE_GONE) == FW_DEVICE_RUNNING) {
-			PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+			device->workfn = fw_device_shutdown;
 			fw_schedule_device_work(device,
 				list_empty(&card->link) ? 0 : SHUTDOWN_DELAY);
 		}
diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index 6b89598..4af0a7b 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -929,8 +929,6 @@
 	if (rcode == RCODE_COMPLETE) {
 		fwnet_transmit_packet_done(ptask);
 	} else {
-		fwnet_transmit_packet_failed(ptask);
-
 		if (printk_timed_ratelimit(&j,  1000) || rcode != last_rcode) {
 			dev_err(&ptask->dev->netdev->dev,
 				"fwnet_write_complete failed: %x (skipped %d)\n",
@@ -938,8 +936,10 @@
 
 			errors_skipped = 0;
 			last_rcode = rcode;
-		} else
+		} else {
 			errors_skipped++;
+		}
+		fwnet_transmit_packet_failed(ptask);
 	}
 }
 
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 6f74d8d..8db6632 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -290,7 +290,6 @@
 #define QUIRK_NO_MSI			0x10
 #define QUIRK_TI_SLLZ059		0x20
 #define QUIRK_IR_WAKE			0x40
-#define QUIRK_PHY_LCTRL_TIMEOUT		0x80
 
 /* In case of multiple matches in ohci_quirks[], only the first one is used. */
 static const struct {
@@ -303,10 +302,7 @@
 		QUIRK_BE_HEADERS},
 
 	{PCI_VENDOR_ID_ATT, PCI_DEVICE_ID_AGERE_FW643, 6,
-		QUIRK_PHY_LCTRL_TIMEOUT | QUIRK_NO_MSI},
-
-	{PCI_VENDOR_ID_ATT, PCI_ANY_ID, PCI_ANY_ID,
-		QUIRK_PHY_LCTRL_TIMEOUT},
+		QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_CREATIVE, PCI_DEVICE_ID_CREATIVE_SB1394, PCI_ANY_ID,
 		QUIRK_RESET_PACKET},
@@ -353,7 +349,6 @@
 	", disable MSI = "		__stringify(QUIRK_NO_MSI)
 	", TI SLLZ059 erratum = "	__stringify(QUIRK_TI_SLLZ059)
 	", IR wake unreliable = "	__stringify(QUIRK_IR_WAKE)
-	", phy LCtrl timeout = "	__stringify(QUIRK_PHY_LCTRL_TIMEOUT)
 	")");
 
 #define OHCI_PARAM_DEBUG_AT_AR		1
@@ -2299,9 +2294,6 @@
 	 * TI TSB82AA2 + TSB81BA3(A) cards signal LPS enabled early but
 	 * cannot actually use the phy at that time.  These need tens of
 	 * millisecods pause between LPS write and first phy access too.
-	 *
-	 * But do not wait for 50msec on Agere/LSI cards.  Their phy
-	 * arbitration state machine may time out during such a long wait.
 	 */
 
 	reg_write(ohci, OHCI1394_HCControlSet,
@@ -2309,11 +2301,8 @@
 		  OHCI1394_HCControl_postedWriteEnable);
 	flush_writes(ohci);
 
-	if (!(ohci->quirks & QUIRK_PHY_LCTRL_TIMEOUT))
+	for (lps = 0, i = 0; !lps && i < 3; i++) {
 		msleep(50);
-
-	for (lps = 0, i = 0; !lps && i < 150; i++) {
-		msleep(1);
 		lps = reg_read(ohci, OHCI1394_HCControlSet) &
 		      OHCI1394_HCControl_LPS;
 	}
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 281029d..7aef911 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -146,6 +146,7 @@
 	 */
 	int generation;
 	int retries;
+	work_func_t workfn;
 	struct delayed_work work;
 	bool has_sdev;
 	bool blocked;
@@ -864,7 +865,7 @@
 	/* set appropriate retry limit(s) in BUSY_TIMEOUT register */
 	sbp2_set_busy_timeout(lu);
 
-	PREPARE_DELAYED_WORK(&lu->work, sbp2_reconnect);
+	lu->workfn = sbp2_reconnect;
 	sbp2_agent_reset(lu);
 
 	/* This was a re-login. */
@@ -918,7 +919,7 @@
 	 * If a bus reset happened, sbp2_update will have requeued
 	 * lu->work already.  Reset the work from reconnect to login.
 	 */
-	PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
+	lu->workfn = sbp2_login;
 }
 
 static void sbp2_reconnect(struct work_struct *work)
@@ -952,7 +953,7 @@
 		    lu->retries++ >= 5) {
 			dev_err(tgt_dev(tgt), "failed to reconnect\n");
 			lu->retries = 0;
-			PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
+			lu->workfn = sbp2_login;
 		}
 		sbp2_queue_work(lu, DIV_ROUND_UP(HZ, 5));
 
@@ -972,6 +973,13 @@
 	sbp2_conditionally_unblock(lu);
 }
 
+static void sbp2_lu_workfn(struct work_struct *work)
+{
+	struct sbp2_logical_unit *lu = container_of(to_delayed_work(work),
+						struct sbp2_logical_unit, work);
+	lu->workfn(work);
+}
+
 static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry)
 {
 	struct sbp2_logical_unit *lu;
@@ -998,7 +1006,8 @@
 	lu->blocked  = false;
 	++tgt->dont_block;
 	INIT_LIST_HEAD(&lu->orb_list);
-	INIT_DELAYED_WORK(&lu->work, sbp2_login);
+	lu->workfn = sbp2_login;
+	INIT_DELAYED_WORK(&lu->work, sbp2_lu_workfn);
 
 	list_add_tail(&lu->link, &tgt->lu_list);
 	return 0;
diff --git a/drivers/firmware/dcdbas.c b/drivers/firmware/dcdbas.c
index 1b5e8e4..7160c43 100644
--- a/drivers/firmware/dcdbas.c
+++ b/drivers/firmware/dcdbas.c
@@ -584,7 +584,7 @@
 	.remove		= dcdbas_remove,
 };
 
-static const struct platform_device_info dcdbas_dev_info __initdata = {
+static const struct platform_device_info dcdbas_dev_info __initconst = {
 	.name		= DRIVER_NAME,
 	.id		= -1,
 	.dma_mask	= DMA_BIT_MASK(32),
diff --git a/drivers/firmware/efi/efi-stub-helper.c b/drivers/firmware/efi/efi-stub-helper.c
index b6bffbf..ff50aee 100644
--- a/drivers/firmware/efi/efi-stub-helper.c
+++ b/drivers/firmware/efi/efi-stub-helper.c
@@ -16,18 +16,6 @@
 	u64 size;
 };
 
-
-
-
-static void efi_char16_printk(efi_system_table_t *sys_table_arg,
-			      efi_char16_t *str)
-{
-	struct efi_simple_text_output_protocol *out;
-
-	out = (struct efi_simple_text_output_protocol *)sys_table_arg->con_out;
-	efi_call_phys2(out->output_string, out, str);
-}
-
 static void efi_printk(efi_system_table_t *sys_table_arg, char *str)
 {
 	char *s8;
@@ -65,20 +53,23 @@
 	 * allocation which may be in a new descriptor region.
 	 */
 	*map_size += sizeof(*m);
-	status = efi_call_phys3(sys_table_arg->boottime->allocate_pool,
-				EFI_LOADER_DATA, *map_size, (void **)&m);
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				*map_size, (void **)&m);
 	if (status != EFI_SUCCESS)
 		goto fail;
 
-	status = efi_call_phys5(sys_table_arg->boottime->get_memory_map,
-				map_size, m, &key, desc_size, &desc_version);
+	*desc_size = 0;
+	key = 0;
+	status = efi_call_early(get_memory_map, map_size, m,
+				&key, desc_size, &desc_version);
 	if (status == EFI_BUFFER_TOO_SMALL) {
-		efi_call_phys1(sys_table_arg->boottime->free_pool, m);
+		efi_call_early(free_pool, m);
 		goto again;
 	}
 
 	if (status != EFI_SUCCESS)
-		efi_call_phys1(sys_table_arg->boottime->free_pool, m);
+		efi_call_early(free_pool, m);
+
 	if (key_ptr && status == EFI_SUCCESS)
 		*key_ptr = key;
 	if (desc_ver && status == EFI_SUCCESS)
@@ -158,7 +149,7 @@
 	if (!max_addr)
 		status = EFI_NOT_FOUND;
 	else {
-		status = efi_call_phys4(sys_table_arg->boottime->allocate_pages,
+		status = efi_call_early(allocate_pages,
 					EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
 					nr_pages, &max_addr);
 		if (status != EFI_SUCCESS) {
@@ -170,8 +161,7 @@
 		*addr = max_addr;
 	}
 
-	efi_call_phys1(sys_table_arg->boottime->free_pool, map);
-
+	efi_call_early(free_pool, map);
 fail:
 	return status;
 }
@@ -231,7 +221,7 @@
 		if ((start + size) > end)
 			continue;
 
-		status = efi_call_phys4(sys_table_arg->boottime->allocate_pages,
+		status = efi_call_early(allocate_pages,
 					EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
 					nr_pages, &start);
 		if (status == EFI_SUCCESS) {
@@ -243,7 +233,7 @@
 	if (i == map_size / desc_size)
 		status = EFI_NOT_FOUND;
 
-	efi_call_phys1(sys_table_arg->boottime->free_pool, map);
+	efi_call_early(free_pool, map);
 fail:
 	return status;
 }
@@ -257,7 +247,7 @@
 		return;
 
 	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
-	efi_call_phys2(sys_table_arg->boottime->free_pages, addr, nr_pages);
+	efi_call_early(free_pages, addr, nr_pages);
 }
 
 
@@ -276,9 +266,7 @@
 {
 	struct file_info *files;
 	unsigned long file_addr;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
 	u64 file_size_total;
-	efi_file_io_interface_t *io;
 	efi_file_handle_t *fh;
 	efi_status_t status;
 	int nr_files;
@@ -319,10 +307,8 @@
 	if (!nr_files)
 		return EFI_SUCCESS;
 
-	status = efi_call_phys3(sys_table_arg->boottime->allocate_pool,
-				EFI_LOADER_DATA,
-				nr_files * sizeof(*files),
-				(void **)&files);
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				nr_files * sizeof(*files), (void **)&files);
 	if (status != EFI_SUCCESS) {
 		efi_printk(sys_table_arg, "Failed to alloc mem for file handle list\n");
 		goto fail;
@@ -331,13 +317,8 @@
 	str = cmd_line;
 	for (i = 0; i < nr_files; i++) {
 		struct file_info *file;
-		efi_file_handle_t *h;
-		efi_file_info_t *info;
 		efi_char16_t filename_16[256];
-		unsigned long info_sz;
-		efi_guid_t info_guid = EFI_FILE_INFO_ID;
 		efi_char16_t *p;
-		u64 file_sz;
 
 		str = strstr(str, option_string);
 		if (!str)
@@ -368,71 +349,18 @@
 
 		/* Only open the volume once. */
 		if (!i) {
-			efi_boot_services_t *boottime;
-
-			boottime = sys_table_arg->boottime;
-
-			status = efi_call_phys3(boottime->handle_protocol,
-					image->device_handle, &fs_proto,
-						(void **)&io);
-			if (status != EFI_SUCCESS) {
-				efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
+			status = efi_open_volume(sys_table_arg, image,
+						 (void **)&fh);
+			if (status != EFI_SUCCESS)
 				goto free_files;
-			}
-
-			status = efi_call_phys2(io->open_volume, io, &fh);
-			if (status != EFI_SUCCESS) {
-				efi_printk(sys_table_arg, "Failed to open volume\n");
-				goto free_files;
-			}
 		}
 
-		status = efi_call_phys5(fh->open, fh, &h, filename_16,
-					EFI_FILE_MODE_READ, (u64)0);
-		if (status != EFI_SUCCESS) {
-			efi_printk(sys_table_arg, "Failed to open file: ");
-			efi_char16_printk(sys_table_arg, filename_16);
-			efi_printk(sys_table_arg, "\n");
+		status = efi_file_size(sys_table_arg, fh, filename_16,
+				       (void **)&file->handle, &file->size);
+		if (status != EFI_SUCCESS)
 			goto close_handles;
-		}
 
-		file->handle = h;
-
-		info_sz = 0;
-		status = efi_call_phys4(h->get_info, h, &info_guid,
-					&info_sz, NULL);
-		if (status != EFI_BUFFER_TOO_SMALL) {
-			efi_printk(sys_table_arg, "Failed to get file info size\n");
-			goto close_handles;
-		}
-
-grow:
-		status = efi_call_phys3(sys_table_arg->boottime->allocate_pool,
-					EFI_LOADER_DATA, info_sz,
-					(void **)&info);
-		if (status != EFI_SUCCESS) {
-			efi_printk(sys_table_arg, "Failed to alloc mem for file info\n");
-			goto close_handles;
-		}
-
-		status = efi_call_phys4(h->get_info, h, &info_guid,
-					&info_sz, info);
-		if (status == EFI_BUFFER_TOO_SMALL) {
-			efi_call_phys1(sys_table_arg->boottime->free_pool,
-				       info);
-			goto grow;
-		}
-
-		file_sz = info->file_size;
-		efi_call_phys1(sys_table_arg->boottime->free_pool, info);
-
-		if (status != EFI_SUCCESS) {
-			efi_printk(sys_table_arg, "Failed to get file info\n");
-			goto close_handles;
-		}
-
-		file->size = file_sz;
-		file_size_total += file_sz;
+		file_size_total += file->size;
 	}
 
 	if (file_size_total) {
@@ -468,10 +396,10 @@
 					chunksize = EFI_READ_CHUNK_SIZE;
 				else
 					chunksize = size;
-				status = efi_call_phys3(fh->read,
-							files[j].handle,
-							&chunksize,
-							(void *)addr);
+
+				status = efi_file_read(fh, files[j].handle,
+						       &chunksize,
+						       (void *)addr);
 				if (status != EFI_SUCCESS) {
 					efi_printk(sys_table_arg, "Failed to read file\n");
 					goto free_file_total;
@@ -480,12 +408,12 @@
 				size -= chunksize;
 			}
 
-			efi_call_phys1(fh->close, files[j].handle);
+			efi_file_close(fh, files[j].handle);
 		}
 
 	}
 
-	efi_call_phys1(sys_table_arg->boottime->free_pool, files);
+	efi_call_early(free_pool, files);
 
 	*load_addr = file_addr;
 	*load_size = file_size_total;
@@ -497,9 +425,9 @@
 
 close_handles:
 	for (k = j; k < i; k++)
-		efi_call_phys1(fh->close, files[k].handle);
+		efi_file_close(fh, files[k].handle);
 free_files:
-	efi_call_phys1(sys_table_arg->boottime->free_pool, files);
+	efi_call_early(free_pool, files);
 fail:
 	*load_addr = 0;
 	*load_size = 0;
@@ -545,7 +473,7 @@
 	 * as possible while respecting the required alignment.
 	 */
 	nr_pages = round_up(alloc_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
-	status = efi_call_phys4(sys_table_arg->boottime->allocate_pages,
+	status = efi_call_early(allocate_pages,
 				EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
 				nr_pages, &efi_addr);
 	new_addr = efi_addr;
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 4753bac..af20f17 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -233,7 +233,7 @@
 	{SAL_SYSTEM_TABLE_GUID, "SALsystab", &efi.sal_systab},
 	{SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios},
 	{UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga},
-	{NULL_GUID, NULL, 0},
+	{NULL_GUID, NULL, NULL},
 };
 
 static __init int match_config_table(efi_guid_t *guid,
@@ -313,5 +313,8 @@
 	}
 	pr_cont("\n");
 	early_iounmap(config_tables, efi.systab->nr_tables * sz);
+
+	set_bit(EFI_CONFIG_TABLES, &efi.flags);
+
 	return 0;
 }
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 3dc2482..50ea412 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -227,7 +227,7 @@
 	memcpy(&entry->var, new_var, count);
 
 	err = efivar_entry_set(entry, new_var->Attributes,
-			       new_var->DataSize, new_var->Data, false);
+			       new_var->DataSize, new_var->Data, NULL);
 	if (err) {
 		printk(KERN_WARNING "efivars: set_variable() failed: status=%d\n", err);
 		return -EIO;
diff --git a/drivers/fmc/fmc-write-eeprom.c b/drivers/fmc/fmc-write-eeprom.c
index ee5b479..9bb2cbd 100644
--- a/drivers/fmc/fmc-write-eeprom.c
+++ b/drivers/fmc/fmc-write-eeprom.c
@@ -27,7 +27,7 @@
 /* The "file=" is like the generic "gateware=" used elsewhere */
 static char *fwe_file[FMC_MAX_CARDS];
 static int fwe_file_n;
-module_param_array_named(file, fwe_file, charp, &fwe_file_n, 444);
+module_param_array_named(file, fwe_file, charp, &fwe_file_n, 0444);
 
 static int fwe_run_tlv(struct fmc_device *fmc, const struct firmware *fw,
 	int write)
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 6973387..903f24d 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -403,6 +403,7 @@
 
 config GPIO_TB10X
 	bool
+	select GENERIC_IRQ_CHIP
 	select OF_GPIO
 
 comment "I2C GPIO expanders:"
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 233d088..f32357e 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2012-2013 Broadcom Corporation
+ * Copyright (C) 2012-2014 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
@@ -657,6 +657,6 @@
 
 module_platform_driver(bcm_kona_gpio_driver);
 
-MODULE_AUTHOR("Broadcom");
+MODULE_AUTHOR("Broadcom Corporation <bcm-kernel-feedback-list@broadcom.com>");
 MODULE_DESCRIPTION("Broadcom Kona GPIO Driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-clps711x.c b/drivers/gpio/gpio-clps711x.c
index d355027..3c2ba2ad 100644
--- a/drivers/gpio/gpio-clps711x.c
+++ b/drivers/gpio/gpio-clps711x.c
@@ -97,3 +97,4 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Alexander Shiyan <shc_work@mail.ru>");
 MODULE_DESCRIPTION("CLPS711X GPIO driver");
+MODULE_ALIAS("platform:clps711x-gpio");
diff --git a/drivers/gpio/gpio-intel-mid.c b/drivers/gpio/gpio-intel-mid.c
index d1b50ef..e585163 100644
--- a/drivers/gpio/gpio-intel-mid.c
+++ b/drivers/gpio/gpio-intel-mid.c
@@ -394,8 +394,8 @@
 
 static int intel_gpio_runtime_idle(struct device *dev)
 {
-	pm_schedule_suspend(dev, 500);
-	return -EBUSY;
+	int err = pm_schedule_suspend(dev, 500);
+	return err ?: -EBUSY;
 }
 
 static const struct dev_pm_ops intel_gpio_pm_ops = {
diff --git a/drivers/gpio/gpio-xtensa.c b/drivers/gpio/gpio-xtensa.c
index 1d136ec..7081304 100644
--- a/drivers/gpio/gpio-xtensa.c
+++ b/drivers/gpio/gpio-xtensa.c
@@ -40,6 +40,8 @@
 #error GPIO32 option is not enabled for your xtensa core variant
 #endif
 
+#if XCHAL_HAVE_CP
+
 static inline unsigned long enable_cp(unsigned long *cpenable)
 {
 	unsigned long flags;
@@ -57,6 +59,20 @@
 	local_irq_restore(flags);
 }
 
+#else
+
+static inline unsigned long enable_cp(unsigned long *cpenable)
+{
+	*cpenable = 0; /* avoid uninitialized value warning */
+	return 0;
+}
+
+static inline void disable_cp(unsigned long flags, unsigned long cpenable)
+{
+}
+
+#endif /* XCHAL_HAVE_CP */
+
 static int xtensa_impwire_get_direction(struct gpio_chip *gc, unsigned offset)
 {
 	return 1; /* input only */
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index acf3a36..32982da 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -68,15 +68,7 @@
 {
 	struct armada_private *priv = dev->dev_private;
 
-	/*
-	 * Yes, we really must jump through these hoops just to store a
-	 * _pointer_ to something into the kfifo.  This is utterly insane
-	 * and idiotic, because it kfifo requires the _data_ pointed to by
-	 * the pointer const, not the pointer itself.  Not only that, but
-	 * you have to pass a pointer _to_ the pointer you want stored.
-	 */
-	const struct drm_framebuffer *silly_api_alert = fb;
-	WARN_ON(!kfifo_put(&priv->fb_unref, &silly_api_alert));
+	WARN_ON(!kfifo_put(&priv->fb_unref, fb));
 	schedule_work(&priv->fb_unref_work);
 }
 
diff --git a/drivers/gpu/drm/ast/ast_fb.c b/drivers/gpu/drm/ast/ast_fb.c
index 3f65dd6..a28640f 100644
--- a/drivers/gpu/drm/ast/ast_fb.c
+++ b/drivers/gpu/drm/ast/ast_fb.c
@@ -65,7 +65,7 @@
 	 * then the BO is being moved and we should
 	 * store up the damage until later.
 	 */
-	if (!drm_can_sleep())
+	if (drm_can_sleep())
 		ret = ast_bo_reserve(bo, true);
 	if (ret) {
 		if (ret != -EBUSY)
diff --git a/drivers/gpu/drm/bochs/Kconfig b/drivers/gpu/drm/bochs/Kconfig
index c8fcf12..5f8b0c2 100644
--- a/drivers/gpu/drm/bochs/Kconfig
+++ b/drivers/gpu/drm/bochs/Kconfig
@@ -2,6 +2,7 @@
 	tristate "DRM Support for bochs dispi vga interface (qemu stdvga)"
 	depends on DRM && PCI
 	select DRM_KMS_HELPER
+	select DRM_KMS_FB_HELPER
 	select FB_SYS_FILLRECT
 	select FB_SYS_COPYAREA
 	select FB_SYS_IMAGEBLIT
diff --git a/drivers/gpu/drm/cirrus/cirrus_fbdev.c b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
index 2fd4a92..32bbba0 100644
--- a/drivers/gpu/drm/cirrus/cirrus_fbdev.c
+++ b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
@@ -39,7 +39,7 @@
 	 * then the BO is being moved and we should
 	 * store up the damage until later.
 	 */
-	if (!drm_can_sleep())
+	if (drm_can_sleep())
 		ret = cirrus_bo_reserve(bo, true);
 	if (ret) {
 		if (ret != -EBUSY)
diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c
index bb8f580..534cb89 100644
--- a/drivers/gpu/drm/drm_cache.c
+++ b/drivers/gpu/drm/drm_cache.c
@@ -32,6 +32,12 @@
 #include <drm/drmP.h>
 
 #if defined(CONFIG_X86)
+
+/*
+ * clflushopt is an unordered instruction which needs fencing with mfence or
+ * sfence to avoid ordering issues.  For drm_clflush_page this fencing happens
+ * in the caller.
+ */
 static void
 drm_clflush_page(struct page *page)
 {
@@ -44,7 +50,7 @@
 
 	page_virtual = kmap_atomic(page);
 	for (i = 0; i < PAGE_SIZE; i += size)
-		clflush(page_virtual + i);
+		clflushopt(page_virtual + i);
 	kunmap_atomic(page_virtual);
 }
 
@@ -133,7 +139,7 @@
 		mb();
 		for (; addr < end; addr += boot_cpu_data.x86_clflush_size)
 			clflush(addr);
-		clflush(end - 1);
+		clflushopt(end - 1);
 		mb();
 		return;
 	}
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index dffc836..f4dc9b7 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -296,6 +296,18 @@
 	case DRM_CAP_ASYNC_PAGE_FLIP:
 		req->value = dev->mode_config.async_page_flip;
 		break;
+	case DRM_CAP_CURSOR_WIDTH:
+		if (dev->mode_config.cursor_width)
+			req->value = dev->mode_config.cursor_width;
+		else
+			req->value = 64;
+		break;
+	case DRM_CAP_CURSOR_HEIGHT:
+		if (dev->mode_config.cursor_height)
+			req->value = dev->mode_config.cursor_height;
+		else
+			req->value = 64;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 5736aaa..f7af69b 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -468,8 +468,8 @@
 	} else {
 		list_for_each_entry_safe(dev, tmp, &driver->legacy_dev_list,
 					 legacy_dev_list) {
-			drm_put_dev(dev);
 			list_del(&dev->legacy_dev_list);
+			drm_put_dev(dev);
 		}
 	}
 	DRM_INFO("Module unloaded\n");
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index f227f54..6e1a1a2 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -51,7 +51,7 @@
 
 config DRM_EXYNOS_IPP
 	bool "Exynos DRM IPP"
-	depends on DRM_EXYNOS && !ARCH_MULTIPLATFORM
+	depends on DRM_EXYNOS
 	help
 	  Choose this option if you want to use IPP feature for DRM.
 
@@ -69,6 +69,6 @@
 
 config DRM_EXYNOS_GSC
 	bool "Exynos DRM GSC"
-	depends on DRM_EXYNOS_IPP && ARCH_EXYNOS5
+	depends on DRM_EXYNOS_IPP && ARCH_EXYNOS5 && !ARCH_MULTIPLATFORM
 	help
 	  Choose this option if you want to use Exynos GSC for DRM.
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 9d096a0..c204b4e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -171,22 +171,28 @@
 	file->driver_priv = file_priv;
 
 	ret = exynos_drm_subdrv_open(dev, file);
-	if (ret) {
-		kfree(file_priv);
-		file->driver_priv = NULL;
-	}
+	if (ret)
+		goto err_file_priv_free;
 
 	anon_filp = anon_inode_getfile("exynos_gem", &exynos_drm_gem_fops,
 					NULL, 0);
 	if (IS_ERR(anon_filp)) {
-		kfree(file_priv);
-		return PTR_ERR(anon_filp);
+		ret = PTR_ERR(anon_filp);
+		goto err_subdrv_close;
 	}
 
 	anon_filp->f_mode = FMODE_READ | FMODE_WRITE;
 	file_priv->anon_filp = anon_filp;
 
 	return ret;
+
+err_subdrv_close:
+	exynos_drm_subdrv_close(dev, file);
+
+err_file_priv_free:
+	kfree(file_priv);
+	file->driver_priv = NULL;
+	return ret;
 }
 
 static void exynos_drm_preclose(struct drm_device *dev,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 380aec2..6c1885e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -607,7 +607,7 @@
 		reg_type = REG_TYPE_NONE;
 		DRM_ERROR("Unknown register offset![%d]\n", reg_offset);
 		break;
-	};
+	}
 
 	return reg_type;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index d519a4e..09312b8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -16,7 +16,6 @@
 #include <linux/types.h>
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
-#include <plat/map-base.h>
 
 #include <drm/drmP.h>
 #include <drm/exynos_drm.h>
@@ -826,7 +825,7 @@
 		DRM_DEBUG_KMS("count[%d]e[0x%x]\n", count++, (int)e);
 
 		/*
-		 * quf == NULL condition means all event deletion.
+		 * qbuf == NULL condition means all event deletion.
 		 * stop operations want to delete all event list.
 		 * another case delete only same buf id.
 		 */
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index a0e10ae..c021ddc 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -34,6 +34,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
+#include <linux/hdmi.h>
 
 #include <drm/exynos_drm.h>
 
@@ -59,19 +60,6 @@
 #define HDMI_AUI_VERSION	0x01
 #define HDMI_AUI_LENGTH	0x0A
 
-/* HDMI infoframe to configure HDMI out packet header, AUI and AVI */
-enum HDMI_PACKET_TYPE {
-	/* refer to Table 5-8 Packet Type in HDMI specification v1.4a */
-	/* InfoFrame packet type */
-	HDMI_PACKET_TYPE_INFOFRAME = 0x80,
-	/* Vendor-Specific InfoFrame */
-	HDMI_PACKET_TYPE_VSI = HDMI_PACKET_TYPE_INFOFRAME + 1,
-	/* Auxiliary Video information InfoFrame */
-	HDMI_PACKET_TYPE_AVI = HDMI_PACKET_TYPE_INFOFRAME + 2,
-	/* Audio information InfoFrame */
-	HDMI_PACKET_TYPE_AUI = HDMI_PACKET_TYPE_INFOFRAME + 4
-};
-
 enum hdmi_type {
 	HDMI_TYPE13,
 	HDMI_TYPE14,
@@ -379,12 +367,6 @@
 	},
 };
 
-struct hdmi_infoframe {
-	enum HDMI_PACKET_TYPE type;
-	u8 ver;
-	u8 len;
-};
-
 static inline u32 hdmi_reg_read(struct hdmi_context *hdata, u32 reg_id)
 {
 	return readl(hdata->regs + reg_id);
@@ -682,7 +664,7 @@
 }
 
 static void hdmi_reg_infoframe(struct hdmi_context *hdata,
-			struct hdmi_infoframe *infoframe)
+			union hdmi_infoframe *infoframe)
 {
 	u32 hdr_sum;
 	u8 chksum;
@@ -700,13 +682,15 @@
 		return;
 	}
 
-	switch (infoframe->type) {
-	case HDMI_PACKET_TYPE_AVI:
+	switch (infoframe->any.type) {
+	case HDMI_INFOFRAME_TYPE_AVI:
 		hdmi_reg_writeb(hdata, HDMI_AVI_CON, HDMI_AVI_CON_EVERY_VSYNC);
-		hdmi_reg_writeb(hdata, HDMI_AVI_HEADER0, infoframe->type);
-		hdmi_reg_writeb(hdata, HDMI_AVI_HEADER1, infoframe->ver);
-		hdmi_reg_writeb(hdata, HDMI_AVI_HEADER2, infoframe->len);
-		hdr_sum = infoframe->type + infoframe->ver + infoframe->len;
+		hdmi_reg_writeb(hdata, HDMI_AVI_HEADER0, infoframe->any.type);
+		hdmi_reg_writeb(hdata, HDMI_AVI_HEADER1,
+				infoframe->any.version);
+		hdmi_reg_writeb(hdata, HDMI_AVI_HEADER2, infoframe->any.length);
+		hdr_sum = infoframe->any.type + infoframe->any.version +
+			  infoframe->any.length;
 
 		/* Output format zero hardcoded ,RGB YBCR selection */
 		hdmi_reg_writeb(hdata, HDMI_AVI_BYTE(1), 0 << 5 |
@@ -722,18 +706,20 @@
 		hdmi_reg_writeb(hdata, HDMI_AVI_BYTE(4), vic);
 
 		chksum = hdmi_chksum(hdata, HDMI_AVI_BYTE(1),
-					infoframe->len, hdr_sum);
+					infoframe->any.length, hdr_sum);
 		DRM_DEBUG_KMS("AVI checksum = 0x%x\n", chksum);
 		hdmi_reg_writeb(hdata, HDMI_AVI_CHECK_SUM, chksum);
 		break;
-	case HDMI_PACKET_TYPE_AUI:
+	case HDMI_INFOFRAME_TYPE_AUDIO:
 		hdmi_reg_writeb(hdata, HDMI_AUI_CON, 0x02);
-		hdmi_reg_writeb(hdata, HDMI_AUI_HEADER0, infoframe->type);
-		hdmi_reg_writeb(hdata, HDMI_AUI_HEADER1, infoframe->ver);
-		hdmi_reg_writeb(hdata, HDMI_AUI_HEADER2, infoframe->len);
-		hdr_sum = infoframe->type + infoframe->ver + infoframe->len;
+		hdmi_reg_writeb(hdata, HDMI_AUI_HEADER0, infoframe->any.type);
+		hdmi_reg_writeb(hdata, HDMI_AUI_HEADER1,
+				infoframe->any.version);
+		hdmi_reg_writeb(hdata, HDMI_AUI_HEADER2, infoframe->any.length);
+		hdr_sum = infoframe->any.type + infoframe->any.version +
+			  infoframe->any.length;
 		chksum = hdmi_chksum(hdata, HDMI_AUI_BYTE(1),
-					infoframe->len, hdr_sum);
+					infoframe->any.length, hdr_sum);
 		DRM_DEBUG_KMS("AUI checksum = 0x%x\n", chksum);
 		hdmi_reg_writeb(hdata, HDMI_AUI_CHECK_SUM, chksum);
 		break;
@@ -985,7 +971,7 @@
 
 static void hdmi_conf_init(struct hdmi_context *hdata)
 {
-	struct hdmi_infoframe infoframe;
+	union hdmi_infoframe infoframe;
 
 	/* disable HPD interrupts from HDMI IP block, use GPIO instead */
 	hdmi_reg_writemask(hdata, HDMI_INTC_CON, 0, HDMI_INTC_EN_GLOBAL |
@@ -1021,14 +1007,14 @@
 		hdmi_reg_writeb(hdata, HDMI_V13_AUI_CON, 0x02);
 		hdmi_reg_writeb(hdata, HDMI_V13_ACR_CON, 0x04);
 	} else {
-		infoframe.type = HDMI_PACKET_TYPE_AVI;
-		infoframe.ver = HDMI_AVI_VERSION;
-		infoframe.len = HDMI_AVI_LENGTH;
+		infoframe.any.type = HDMI_INFOFRAME_TYPE_AVI;
+		infoframe.any.version = HDMI_AVI_VERSION;
+		infoframe.any.length = HDMI_AVI_LENGTH;
 		hdmi_reg_infoframe(hdata, &infoframe);
 
-		infoframe.type = HDMI_PACKET_TYPE_AUI;
-		infoframe.ver = HDMI_AUI_VERSION;
-		infoframe.len = HDMI_AUI_LENGTH;
+		infoframe.any.type = HDMI_INFOFRAME_TYPE_AUDIO;
+		infoframe.any.version = HDMI_AUI_VERSION;
+		infoframe.any.length = HDMI_AUI_LENGTH;
 		hdmi_reg_infoframe(hdata, &infoframe);
 
 		/* enable AVI packet every vsync, fixes purple line problem */
diff --git a/drivers/gpu/drm/gma500/mmu.c b/drivers/gpu/drm/gma500/mmu.c
index 49bac41..c3e67ba 100644
--- a/drivers/gpu/drm/gma500/mmu.c
+++ b/drivers/gpu/drm/gma500/mmu.c
@@ -520,7 +520,7 @@
 
 	driver->has_clflush = 0;
 
-	if (boot_cpu_has(X86_FEATURE_CLFLSH)) {
+	if (boot_cpu_has(X86_FEATURE_CLFLUSH)) {
 		uint32_t tfms, misc, cap0, cap4, clflush_size;
 
 		/*
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 400b0c4..faa77f5 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -208,7 +208,7 @@
 # define PLL_SERIAL_1_SRL_IZ(x)   (((x) & 3) << 1)
 # define PLL_SERIAL_1_SRL_MAN_IZ  (1 << 6)
 #define REG_PLL_SERIAL_2          REG(0x02, 0x01)     /* read/write */
-# define PLL_SERIAL_2_SRL_NOSC(x) (((x) & 3) << 0)
+# define PLL_SERIAL_2_SRL_NOSC(x) ((x) << 0)
 # define PLL_SERIAL_2_SRL_PR(x)   (((x) & 0xf) << 4)
 #define REG_PLL_SERIAL_3          REG(0x02, 0x02)     /* read/write */
 # define PLL_SERIAL_3_SRL_CCIR    (1 << 0)
@@ -528,10 +528,10 @@
 {
 	uint8_t buf[PB(5) + 1];
 
+	memset(buf, 0, sizeof(buf));
 	buf[HB(0)] = 0x84;
 	buf[HB(1)] = 0x01;
 	buf[HB(2)] = 10;
-	buf[PB(0)] = 0;
 	buf[PB(1)] = p->audio_frame[1] & 0x07; /* CC */
 	buf[PB(2)] = p->audio_frame[2] & 0x1c; /* SF */
 	buf[PB(4)] = p->audio_frame[4];
@@ -824,6 +824,11 @@
 	}
 
 	div = 148500 / mode->clock;
+	if (div != 0) {
+		div--;
+		if (div > 3)
+			div = 3;
+	}
 
 	/* mute the audio FIFO: */
 	reg_set(encoder, REG_AIP_CNTRL_0, AIP_CNTRL_0_RST_FIFO);
@@ -913,7 +918,7 @@
 
 	if (priv->rev == TDA19988) {
 		/* let incoming pixels fill the active space (if any) */
-		reg_write(encoder, REG_ENABLE_SPACE, 0x01);
+		reg_write(encoder, REG_ENABLE_SPACE, 0x00);
 	}
 
 	/* must be last register set: */
@@ -1094,6 +1099,8 @@
 {
 	struct tda998x_priv *priv = to_tda998x_priv(encoder);
 	drm_i2c_encoder_destroy(encoder);
+	if (priv->cec)
+		i2c_unregister_device(priv->cec);
 	kfree(priv);
 }
 
@@ -1142,8 +1149,12 @@
 	priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(0) | VIP_CNTRL_1_SWAP_D(1);
 	priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(4) | VIP_CNTRL_2_SWAP_F(5);
 
-	priv->current_page = 0;
+	priv->current_page = 0xff;
 	priv->cec = i2c_new_dummy(client->adapter, 0x34);
+	if (!priv->cec) {
+		kfree(priv);
+		return -ENODEV;
+	}
 	priv->dpms = DRM_MODE_DPMS_OFF;
 
 	encoder_slave->slave_priv = priv;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 04f1f02..ec7bb0f 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -403,7 +403,7 @@
 void intel_detect_pch(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct pci_dev *pch;
+	struct pci_dev *pch = NULL;
 
 	/* In all current cases, num_pipes is equivalent to the PCH_NOP setting
 	 * (which really amounts to a PCH but no South Display).
@@ -424,12 +424,9 @@
 	 * all the ISA bridge devices and check for the first match, instead
 	 * of only checking the first one.
 	 */
-	pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL);
-	while (pch) {
-		struct pci_dev *curr = pch;
+	while ((pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, pch))) {
 		if (pch->vendor == PCI_VENDOR_ID_INTEL) {
-			unsigned short id;
-			id = pch->device & INTEL_PCH_DEVICE_ID_MASK;
+			unsigned short id = pch->device & INTEL_PCH_DEVICE_ID_MASK;
 			dev_priv->pch_id = id;
 
 			if (id == INTEL_PCH_IBX_DEVICE_ID_TYPE) {
@@ -461,18 +458,16 @@
 				DRM_DEBUG_KMS("Found LynxPoint LP PCH\n");
 				WARN_ON(!IS_HASWELL(dev));
 				WARN_ON(!IS_ULT(dev));
-			} else {
-				goto check_next;
-			}
-			pci_dev_put(pch);
+			} else
+				continue;
+
 			break;
 		}
-check_next:
-		pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, curr);
-		pci_dev_put(curr);
 	}
 	if (!pch)
-		DRM_DEBUG_KMS("No PCH found?\n");
+		DRM_DEBUG_KMS("No PCH found.\n");
+
+	pci_dev_put(pch);
 }
 
 bool i915_semaphore_is_enabled(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4a2bf8e..df77e20 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1831,6 +1831,14 @@
 
 /* Early gen2 have a totally busted CS tlb and require pinned batches. */
 #define HAS_BROKEN_CS_TLB(dev)		(IS_I830(dev) || IS_845G(dev))
+/*
+ * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
+ * even when in MSI mode. This results in spurious interrupt warnings if the
+ * legacy irq no. is shared with another device. The kernel then disables that
+ * interrupt source and so prevents the other device from working properly.
+ */
+#define HAS_AUX_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
+#define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
 
 /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
  * rows, which changed the alignment requirements and fence programming.
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 40a2b36..d278be1 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -842,7 +842,7 @@
 	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
 				       dev_priv->gtt.base.start / PAGE_SIZE,
 				       dev_priv->gtt.base.total / PAGE_SIZE,
-				       false);
+				       true);
 }
 
 void i915_gem_restore_gtt_mappings(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 1a24e84..28d24ca 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -82,9 +82,22 @@
 	r = devm_request_mem_region(dev->dev, base, dev_priv->gtt.stolen_size,
 				    "Graphics Stolen Memory");
 	if (r == NULL) {
-		DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n",
-			  base, base + (uint32_t)dev_priv->gtt.stolen_size);
-		base = 0;
+		/*
+		 * One more attempt but this time requesting region from
+		 * base + 1, as we have seen that this resolves the region
+		 * conflict with the PCI Bus.
+		 * This is a BIOS w/a: Some BIOS wrap stolen in the root
+		 * PCI bus, but have an off-by-one error. Hence retry the
+		 * reservation starting from 1 instead of 0.
+		 */
+		r = devm_request_mem_region(dev->dev, base + 1,
+					    dev_priv->gtt.stolen_size - 1,
+					    "Graphics Stolen Memory");
+		if (r == NULL) {
+			DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n",
+				  base, base + (uint32_t)dev_priv->gtt.stolen_size);
+			base = 0;
+		}
 	}
 
 	return base;
@@ -201,6 +214,13 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int bios_reserved = 0;
 
+#ifdef CONFIG_INTEL_IOMMU
+	if (intel_iommu_gfx_mapped) {
+		DRM_INFO("DMAR active, disabling use of stolen memory\n");
+		return 0;
+	}
+#endif
+
 	if (dev_priv->gtt.stolen_size == 0)
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index d7fd2fd..990cf8f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -146,7 +146,10 @@
 		va_list tmp;
 
 		va_copy(tmp, args);
-		if (!__i915_error_seek(e, vsnprintf(NULL, 0, f, tmp)))
+		len = vsnprintf(NULL, 0, f, tmp);
+		va_end(tmp);
+
+		if (!__i915_error_seek(e, len))
 			return;
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 17d8fcb..d554169 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -567,8 +567,7 @@
 
 		vbl_start = mode->crtc_vblank_start * mode->crtc_htotal;
 	} else {
-		enum transcoder cpu_transcoder =
-			intel_pipe_to_cpu_transcoder(dev_priv, pipe);
+		enum transcoder cpu_transcoder = (enum transcoder) pipe;
 		u32 htotal;
 
 		htotal = ((I915_READ(HTOTAL(cpu_transcoder)) >> 16) & 0x1fff) + 1;
@@ -619,33 +618,25 @@
 
 /* raw reads, only for fast reads of display block, no need for forcewake etc. */
 #define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__))
-#define __raw_i915_read16(dev_priv__, reg__) readw((dev_priv__)->regs + (reg__))
 
 static bool ilk_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t status;
+	int reg;
 
-	if (INTEL_INFO(dev)->gen < 7) {
-		status = pipe == PIPE_A ?
-			DE_PIPEA_VBLANK :
-			DE_PIPEB_VBLANK;
+	if (INTEL_INFO(dev)->gen >= 8) {
+		status = GEN8_PIPE_VBLANK;
+		reg = GEN8_DE_PIPE_ISR(pipe);
+	} else if (INTEL_INFO(dev)->gen >= 7) {
+		status = DE_PIPE_VBLANK_IVB(pipe);
+		reg = DEISR;
 	} else {
-		switch (pipe) {
-		default:
-		case PIPE_A:
-			status = DE_PIPEA_VBLANK_IVB;
-			break;
-		case PIPE_B:
-			status = DE_PIPEB_VBLANK_IVB;
-			break;
-		case PIPE_C:
-			status = DE_PIPEC_VBLANK_IVB;
-			break;
-		}
+		status = DE_PIPE_VBLANK(pipe);
+		reg = DEISR;
 	}
 
-	return __raw_i915_read32(dev_priv, DEISR) & status;
+	return __raw_i915_read32(dev_priv, reg) & status;
 }
 
 static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
@@ -703,7 +694,28 @@
 		else
 			position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
 
-		if (HAS_PCH_SPLIT(dev)) {
+		if (HAS_DDI(dev)) {
+			/*
+			 * On HSW HDMI outputs there seems to be a 2 line
+			 * difference, whereas eDP has the normal 1 line
+			 * difference that earlier platforms have. External
+			 * DP is unknown. For now just check for the 2 line
+			 * difference case on all output types on HSW+.
+			 *
+			 * This might misinterpret the scanline counter being
+			 * one line too far along on eDP, but that's less
+			 * dangerous than the alternative since that would lead
+			 * the vblank timestamp code astray when it sees a
+			 * scanline count before vblank_start during a vblank
+			 * interrupt.
+			 */
+			in_vbl = ilk_pipe_in_vblank_locked(dev, pipe);
+			if ((in_vbl && (position == vbl_start - 2 ||
+					position == vbl_start - 1)) ||
+			    (!in_vbl && (position == vbl_end - 2 ||
+					 position == vbl_end - 1)))
+				position = (position + 2) % vtotal;
+		} else if (HAS_PCH_SPLIT(dev)) {
 			/*
 			 * The scanline counter increments at the leading edge
 			 * of hsync, ie. it completely misses the active portion
@@ -2770,10 +2782,9 @@
 		return;
 
 	if (HAS_PCH_IBX(dev)) {
-		mask = SDE_GMBUS | SDE_AUX_MASK | SDE_TRANSB_FIFO_UNDER |
-		       SDE_TRANSA_FIFO_UNDER | SDE_POISON;
+		mask = SDE_GMBUS | SDE_AUX_MASK | SDE_POISON;
 	} else {
-		mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT | SDE_ERROR_CPT;
+		mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT;
 
 		I915_WRITE(SERR_INT, I915_READ(SERR_INT));
 	}
@@ -2833,20 +2844,19 @@
 		display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE_IVB |
 				DE_PCH_EVENT_IVB | DE_PLANEC_FLIP_DONE_IVB |
 				DE_PLANEB_FLIP_DONE_IVB |
-				DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB |
-				DE_ERR_INT_IVB);
+				DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB);
 		extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB |
-			      DE_PIPEA_VBLANK_IVB);
+			      DE_PIPEA_VBLANK_IVB | DE_ERR_INT_IVB);
 
 		I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT));
 	} else {
 		display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT |
 				DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE |
 				DE_AUX_CHANNEL_A |
-				DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN |
 				DE_PIPEB_CRC_DONE | DE_PIPEA_CRC_DONE |
 				DE_POISON);
-		extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT;
+		extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT |
+				DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN;
 	}
 
 	dev_priv->irq_mask = ~display_mask;
@@ -2962,9 +2972,9 @@
 	struct drm_device *dev = dev_priv->dev;
 	uint32_t de_pipe_masked = GEN8_PIPE_FLIP_DONE |
 		GEN8_PIPE_CDCLK_CRC_DONE |
-		GEN8_PIPE_FIFO_UNDERRUN |
 		GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
-	uint32_t de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK;
+	uint32_t de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK |
+		GEN8_PIPE_FIFO_UNDERRUN;
 	int pipe;
 	dev_priv->de_irq_mask[PIPE_A] = ~de_pipe_masked;
 	dev_priv->de_irq_mask[PIPE_B] = ~de_pipe_masked;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index e06b9e0..234ac5f 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1244,6 +1244,7 @@
 	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+		ironlake_edp_panel_vdd_on(intel_dp);
 		ironlake_edp_panel_off(intel_dp);
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 9fa2434..9b8a7c7 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1092,12 +1092,12 @@
 	struct drm_device *dev = dev_priv->dev;
 	bool cur_state;
 
-	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-		cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE;
-	else if (IS_845G(dev) || IS_I865G(dev))
+	if (IS_845G(dev) || IS_I865G(dev))
 		cur_state = I915_READ(_CURACNTR) & CURSOR_ENABLE;
-	else
+	else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev))
 		cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
+	else
+		cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE;
 
 	WARN(cur_state != state,
 	     "cursor on pipe %c assertion failure (expected %s, current %s)\n",
@@ -8586,6 +8586,20 @@
 	if (ring->id == RCS)
 		len += 6;
 
+	/*
+	 * BSpec MI_DISPLAY_FLIP for IVB:
+	 * "The full packet must be contained within the same cache line."
+	 *
+	 * Currently the LRI+SRM+MI_DISPLAY_FLIP all fit within the same
+	 * cacheline, if we ever start emitting more commands before
+	 * the MI_DISPLAY_FLIP we may need to first emit everything else,
+	 * then do the cacheline alignment, and finally emit the
+	 * MI_DISPLAY_FLIP.
+	 */
+	ret = intel_ring_cacheline_align(ring);
+	if (ret)
+		goto err_unpin;
+
 	ret = intel_ring_begin(ring, len);
 	if (ret)
 		goto err_unpin;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 5ede4e8..2688f6d 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -404,7 +404,7 @@
 	int i, ret, recv_bytes;
 	uint32_t status;
 	int try, precharge, clock = 0;
-	bool has_aux_irq = true;
+	bool has_aux_irq = HAS_AUX_IRQ(dev);
 	uint32_t timeout;
 
 	/* dp aux is extremely sensitive to irq latency, hence request the
@@ -537,6 +537,7 @@
 	uint8_t	msg[20];
 	int msg_bytes;
 	uint8_t	ack;
+	int retry;
 
 	if (WARN_ON(send_bytes > 16))
 		return -E2BIG;
@@ -548,19 +549,21 @@
 	msg[3] = send_bytes - 1;
 	memcpy(&msg[4], send, send_bytes);
 	msg_bytes = send_bytes + 4;
-	for (;;) {
+	for (retry = 0; retry < 7; retry++) {
 		ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes, &ack, 1);
 		if (ret < 0)
 			return ret;
 		ack >>= 4;
 		if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_ACK)
-			break;
+			return send_bytes;
 		else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
-			udelay(100);
+			usleep_range(400, 500);
 		else
 			return -EIO;
 	}
-	return send_bytes;
+
+	DRM_ERROR("too many retries, giving up\n");
+	return -EIO;
 }
 
 /* Write a single byte to the aux channel in native mode */
@@ -582,6 +585,7 @@
 	int reply_bytes;
 	uint8_t ack;
 	int ret;
+	int retry;
 
 	if (WARN_ON(recv_bytes > 19))
 		return -E2BIG;
@@ -595,7 +599,7 @@
 	msg_bytes = 4;
 	reply_bytes = recv_bytes + 1;
 
-	for (;;) {
+	for (retry = 0; retry < 7; retry++) {
 		ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes,
 				      reply, reply_bytes);
 		if (ret == 0)
@@ -608,10 +612,13 @@
 			return ret - 1;
 		}
 		else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
-			udelay(100);
+			usleep_range(400, 500);
 		else
 			return -EIO;
 	}
+
+	DRM_ERROR("too many retries, giving up\n");
+	return -EIO;
 }
 
 static int
@@ -1242,17 +1249,24 @@
 
 	DRM_DEBUG_KMS("Turn eDP power off\n");
 
+	WARN(!intel_dp->want_panel_vdd, "Need VDD to turn off panel\n");
+
 	pp = ironlake_get_pp_control(intel_dp);
 	/* We need to switch off panel power _and_ force vdd, for otherwise some
 	 * panels get very unhappy and cease to work. */
-	pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+	pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE);
 
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 
 	I915_WRITE(pp_ctrl_reg, pp);
 	POSTING_READ(pp_ctrl_reg);
 
+	intel_dp->want_panel_vdd = false;
+
 	ironlake_wait_panel_off(intel_dp);
+
+	/* We got a reference when we enabled the VDD. */
+	intel_runtime_pm_put(dev_priv);
 }
 
 void ironlake_edp_backlight_on(struct intel_dp *intel_dp)
@@ -1632,7 +1646,7 @@
 		val |= EDP_PSR_LINK_DISABLE;
 
 	I915_WRITE(EDP_PSR_CTL(dev), val |
-		   IS_BROADWELL(dev) ? 0 : link_entry_time |
+		   (IS_BROADWELL(dev) ? 0 : link_entry_time) |
 		   max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT |
 		   idle_frames << EDP_PSR_IDLE_FRAME_SHIFT |
 		   EDP_PSR_ENABLE);
@@ -1777,6 +1791,7 @@
 
 	/* Make sure the panel is off before trying to change the mode. But also
 	 * ensure that we have vdd while we switch off the panel. */
+	ironlake_edp_panel_vdd_on(intel_dp);
 	ironlake_edp_backlight_off(intel_dp);
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
 	ironlake_edp_panel_off(intel_dp);
@@ -1869,10 +1884,12 @@
 
 	mutex_unlock(&dev_priv->dpio_lock);
 
-	/* init power sequencer on this pipe and port */
-	intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
-	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
-						      &power_seq);
+	if (is_edp(intel_dp)) {
+		/* init power sequencer on this pipe and port */
+		intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
+		intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
+							      &power_seq);
+	}
 
 	intel_enable_dp(encoder);
 
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 6db0d9d..ee3181e 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -845,7 +845,7 @@
 {
 	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
 
-	if (IS_G4X(dev))
+	if (!hdmi->has_hdmi_sink || IS_G4X(dev))
 		return 165000;
 	else if (IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8)
 		return 300000;
@@ -899,8 +899,8 @@
 	 * outputs. We also need to check that the higher clock still fits
 	 * within limits.
 	 */
-	if (pipe_config->pipe_bpp > 8*3 && clock_12bpc <= portclock_limit
-	    && HAS_PCH_SPLIT(dev)) {
+	if (pipe_config->pipe_bpp > 8*3 && intel_hdmi->has_hdmi_sink &&
+	    clock_12bpc <= portclock_limit && HAS_PCH_SPLIT(dev)) {
 		DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
 		desired_bpp = 12*3;
 
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index b1dc33f..d33b61d 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -258,13 +258,6 @@
 	algo->data = bus;
 }
 
-/*
- * gmbus on gen4 seems to be able to generate legacy interrupts even when in MSI
- * mode. This results in spurious interrupt warnings if the legacy irq no. is
- * shared with another device. The kernel then disables that interrupt source
- * and so prevents the other device from working properly.
- */
-#define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
 static int
 gmbus_wait_hw_status(struct drm_i915_private *dev_priv,
 		     u32 gmbus2_status,
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 4e960ec..acde294 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -226,6 +226,8 @@
 #define ACPI_DIGITAL_OUTPUT (3<<8)
 #define ACPI_LVDS_OUTPUT (4<<8)
 
+#define MAX_DSLP	1500
+
 #ifdef CONFIG_ACPI
 static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 {
@@ -260,10 +262,11 @@
 		/* The spec says 2ms should be the default, but it's too small
 		 * for some machines. */
 		dslp = 50;
-	} else if (dslp > 500) {
+	} else if (dslp > MAX_DSLP) {
 		/* Hey bios, trust must be earned. */
-		WARN_ONCE(1, "excessive driver sleep timeout (DSPL) %u\n", dslp);
-		dslp = 500;
+		DRM_INFO_ONCE("ACPI BIOS requests an excessive sleep of %u ms, "
+			      "using %u ms instead\n", dslp, MAX_DSLP);
+		dslp = MAX_DSLP;
 	}
 
 	/* The spec tells us to do this, but we are the only user... */
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 350de35..079ea38 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -698,7 +698,7 @@
 		freq /= 0xff;
 
 	ctl = freq << 17;
-	if (IS_GEN2(dev) && panel->backlight.combination_mode)
+	if (panel->backlight.combination_mode)
 		ctl |= BLM_LEGACY_MODE;
 	if (IS_PINEVIEW(dev) && panel->backlight.active_low_pwm)
 		ctl |= BLM_POLARITY_PNV;
@@ -979,7 +979,7 @@
 
 	ctl = I915_READ(BLC_PWM_CTL);
 
-	if (IS_GEN2(dev))
+	if (IS_GEN2(dev) || IS_I915GM(dev) || IS_I945GM(dev))
 		panel->backlight.combination_mode = ctl & BLM_LEGACY_MODE;
 
 	if (IS_PINEVIEW(dev))
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d77cc81..e1fc35a 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3493,6 +3493,8 @@
 	u32 pcbr;
 	int pctx_size = 24*1024;
 
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
 	pcbr = I915_READ(VLV_PCBR);
 	if (pcbr) {
 		/* BIOS set it up already, grab the pre-alloc'd space */
@@ -3542,8 +3544,6 @@
 		I915_WRITE(GTFIFODBG, gtfifodbg);
 	}
 
-	valleyview_setup_pctx(dev);
-
 	/* If VLV, Forcewake all wells, else re-direct to regular path */
 	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
@@ -4395,6 +4395,8 @@
 		ironlake_enable_rc6(dev);
 		intel_init_emon(dev);
 	} else if (IS_GEN6(dev) || IS_GEN7(dev)) {
+		if (IS_VALLEYVIEW(dev))
+			valleyview_setup_pctx(dev);
 		/*
 		 * PCU communication is slow and this doesn't need to be
 		 * done at any specific time, so do this out of our fast path
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b7f1742..31b36c5 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1653,6 +1653,27 @@
 	return 0;
 }
 
+/* Align the ring tail to a cacheline boundary */
+int intel_ring_cacheline_align(struct intel_ring_buffer *ring)
+{
+	int num_dwords = (64 - (ring->tail & 63)) / sizeof(uint32_t);
+	int ret;
+
+	if (num_dwords == 0)
+		return 0;
+
+	ret = intel_ring_begin(ring, num_dwords);
+	if (ret)
+		return ret;
+
+	while (num_dwords--)
+		intel_ring_emit(ring, MI_NOOP);
+
+	intel_ring_advance(ring);
+
+	return 0;
+}
+
 void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 71a73f4..0b243ce 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -233,6 +233,7 @@
 void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring);
 
 int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n);
+int __must_check intel_ring_cacheline_align(struct intel_ring_buffer *ring);
 static inline void intel_ring_emit(struct intel_ring_buffer *ring,
 				   u32 data)
 {
diff --git a/drivers/gpu/drm/mgag200/mgag200_fb.c b/drivers/gpu/drm/mgag200/mgag200_fb.c
index f9adc27..13b7dd8 100644
--- a/drivers/gpu/drm/mgag200/mgag200_fb.c
+++ b/drivers/gpu/drm/mgag200/mgag200_fb.c
@@ -41,7 +41,7 @@
 	 * then the BO is being moved and we should
 	 * store up the damage until later.
 	 */
-	if (!drm_can_sleep())
+	if (drm_can_sleep())
 		ret = mgag200_bo_reserve(bo, true);
 	if (ret) {
 		if (ret != -EBUSY)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index b8583f2..9683747 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1519,11 +1519,11 @@
 		(mga_vga_calculate_mode_bandwidth(mode, bpp)
 			> (32700 * 1024))) {
 		return MODE_BANDWIDTH;
-	} else if (mode->type == G200_EH &&
+	} else if (mdev->type == G200_EH &&
 		(mga_vga_calculate_mode_bandwidth(mode, bpp)
 			> (37500 * 1024))) {
 		return MODE_BANDWIDTH;
-	} else if (mode->type == G200_ER &&
+	} else if (mdev->type == G200_ER &&
 		(mga_vga_calculate_mode_bandwidth(mode,
 			bpp) > (55000 * 1024))) {
 		return MODE_BANDWIDTH;
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
index 1964f4f..84c5b13 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
@@ -39,6 +39,7 @@
 		spinlock_t lock;
 		bool stale;
 		uint32_t width, height;
+		uint32_t x, y;
 
 		/* next cursor to scan-out: */
 		uint32_t next_iova;
@@ -57,9 +58,16 @@
 #define PENDING_FLIP   0x2
 	atomic_t pending;
 
-	/* the fb that we currently hold a scanout ref to: */
+	/* the fb that we logically (from PoV of KMS API) hold a ref
+	 * to.  Which we may not yet be scanning out (we may still
+	 * be scanning out previous in case of page_flip while waiting
+	 * for gpu rendering to complete:
+	 */
 	struct drm_framebuffer *fb;
 
+	/* the fb that we currently hold a scanout ref to: */
+	struct drm_framebuffer *scanout_fb;
+
 	/* for unref'ing framebuffers after scanout completes: */
 	struct drm_flip_work unref_fb_work;
 
@@ -77,24 +85,73 @@
 	return to_mdp4_kms(to_mdp_kms(priv->kms));
 }
 
-static void update_fb(struct drm_crtc *crtc, bool async,
-		struct drm_framebuffer *new_fb)
+static void request_pending(struct drm_crtc *crtc, uint32_t pending)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+
+	atomic_or(pending, &mdp4_crtc->pending);
+	mdp_irq_register(&get_kms(crtc)->base, &mdp4_crtc->vblank);
+}
+
+static void crtc_flush(struct drm_crtc *crtc)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+	uint32_t i, flush = 0;
+
+	for (i = 0; i < ARRAY_SIZE(mdp4_crtc->planes); i++) {
+		struct drm_plane *plane = mdp4_crtc->planes[i];
+		if (plane) {
+			enum mdp4_pipe pipe_id = mdp4_plane_pipe(plane);
+			flush |= pipe2flush(pipe_id);
+		}
+	}
+	flush |= ovlp2flush(mdp4_crtc->ovlp);
+
+	DBG("%s: flush=%08x", mdp4_crtc->name, flush);
+
+	mdp4_write(mdp4_kms, REG_MDP4_OVERLAY_FLUSH, flush);
+}
+
+static void update_fb(struct drm_crtc *crtc, struct drm_framebuffer *new_fb)
 {
 	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
 	struct drm_framebuffer *old_fb = mdp4_crtc->fb;
 
-	if (old_fb)
-		drm_flip_work_queue(&mdp4_crtc->unref_fb_work, old_fb);
-
 	/* grab reference to incoming scanout fb: */
 	drm_framebuffer_reference(new_fb);
 	mdp4_crtc->base.fb = new_fb;
 	mdp4_crtc->fb = new_fb;
 
-	if (!async) {
-		/* enable vblank to pick up the old_fb */
-		mdp_irq_register(&get_kms(crtc)->base, &mdp4_crtc->vblank);
-	}
+	if (old_fb)
+		drm_flip_work_queue(&mdp4_crtc->unref_fb_work, old_fb);
+}
+
+/* unlike update_fb(), take a ref to the new scanout fb *before* updating
+ * plane, then call this.  Needed to ensure we don't unref the buffer that
+ * is actually still being scanned out.
+ *
+ * Note that this whole thing goes away with atomic.. since we can defer
+ * calling into driver until rendering is done.
+ */
+static void update_scanout(struct drm_crtc *crtc, struct drm_framebuffer *fb)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+
+	/* flush updates, to make sure hw is updated to new scanout fb,
+	 * so that we can safely queue unref to current fb (ie. next
+	 * vblank we know hw is done w/ previous scanout_fb).
+	 */
+	crtc_flush(crtc);
+
+	if (mdp4_crtc->scanout_fb)
+		drm_flip_work_queue(&mdp4_crtc->unref_fb_work,
+				mdp4_crtc->scanout_fb);
+
+	mdp4_crtc->scanout_fb = fb;
+
+	/* enable vblank to complete flip: */
+	request_pending(crtc, PENDING_FLIP);
 }
 
 /* if file!=NULL, this is preclose potential cancel-flip path */
@@ -120,34 +177,6 @@
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
 
-static void crtc_flush(struct drm_crtc *crtc)
-{
-	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
-	struct mdp4_kms *mdp4_kms = get_kms(crtc);
-	uint32_t i, flush = 0;
-
-	for (i = 0; i < ARRAY_SIZE(mdp4_crtc->planes); i++) {
-		struct drm_plane *plane = mdp4_crtc->planes[i];
-		if (plane) {
-			enum mdp4_pipe pipe_id = mdp4_plane_pipe(plane);
-			flush |= pipe2flush(pipe_id);
-		}
-	}
-	flush |= ovlp2flush(mdp4_crtc->ovlp);
-
-	DBG("%s: flush=%08x", mdp4_crtc->name, flush);
-
-	mdp4_write(mdp4_kms, REG_MDP4_OVERLAY_FLUSH, flush);
-}
-
-static void request_pending(struct drm_crtc *crtc, uint32_t pending)
-{
-	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
-
-	atomic_or(pending, &mdp4_crtc->pending);
-	mdp_irq_register(&get_kms(crtc)->base, &mdp4_crtc->vblank);
-}
-
 static void pageflip_cb(struct msm_fence_cb *cb)
 {
 	struct mdp4_crtc *mdp4_crtc =
@@ -158,11 +187,9 @@
 	if (!fb)
 		return;
 
+	drm_framebuffer_reference(fb);
 	mdp4_plane_set_scanout(mdp4_crtc->plane, fb);
-	crtc_flush(crtc);
-
-	/* enable vblank to complete flip: */
-	request_pending(crtc, PENDING_FLIP);
+	update_scanout(crtc, fb);
 }
 
 static void unref_fb_worker(struct drm_flip_work *work, void *val)
@@ -320,6 +347,20 @@
 			mode->vsync_end, mode->vtotal,
 			mode->type, mode->flags);
 
+	/* grab extra ref for update_scanout() */
+	drm_framebuffer_reference(crtc->fb);
+
+	ret = mdp4_plane_mode_set(mdp4_crtc->plane, crtc, crtc->fb,
+			0, 0, mode->hdisplay, mode->vdisplay,
+			x << 16, y << 16,
+			mode->hdisplay << 16, mode->vdisplay << 16);
+	if (ret) {
+		drm_framebuffer_unreference(crtc->fb);
+		dev_err(crtc->dev->dev, "%s: failed to set mode on plane: %d\n",
+				mdp4_crtc->name, ret);
+		return ret;
+	}
+
 	mdp4_write(mdp4_kms, REG_MDP4_DMA_SRC_SIZE(dma),
 			MDP4_DMA_SRC_SIZE_WIDTH(mode->hdisplay) |
 			MDP4_DMA_SRC_SIZE_HEIGHT(mode->vdisplay));
@@ -341,24 +382,15 @@
 
 	mdp4_write(mdp4_kms, REG_MDP4_OVLP_CFG(ovlp), 1);
 
-	update_fb(crtc, false, crtc->fb);
-
-	ret = mdp4_plane_mode_set(mdp4_crtc->plane, crtc, crtc->fb,
-			0, 0, mode->hdisplay, mode->vdisplay,
-			x << 16, y << 16,
-			mode->hdisplay << 16, mode->vdisplay << 16);
-	if (ret) {
-		dev_err(crtc->dev->dev, "%s: failed to set mode on plane: %d\n",
-				mdp4_crtc->name, ret);
-		return ret;
-	}
-
 	if (dma == DMA_E) {
 		mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(0), 0x00ff0000);
 		mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(1), 0x00ff0000);
 		mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(2), 0x00ff0000);
 	}
 
+	update_fb(crtc, crtc->fb);
+	update_scanout(crtc, crtc->fb);
+
 	return 0;
 }
 
@@ -385,13 +417,24 @@
 	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
 	struct drm_plane *plane = mdp4_crtc->plane;
 	struct drm_display_mode *mode = &crtc->mode;
+	int ret;
 
-	update_fb(crtc, false, crtc->fb);
+	/* grab extra ref for update_scanout() */
+	drm_framebuffer_reference(crtc->fb);
 
-	return mdp4_plane_mode_set(plane, crtc, crtc->fb,
+	ret = mdp4_plane_mode_set(plane, crtc, crtc->fb,
 			0, 0, mode->hdisplay, mode->vdisplay,
 			x << 16, y << 16,
 			mode->hdisplay << 16, mode->vdisplay << 16);
+	if (ret) {
+		drm_framebuffer_unreference(crtc->fb);
+		return ret;
+	}
+
+	update_fb(crtc, crtc->fb);
+	update_scanout(crtc, crtc->fb);
+
+	return 0;
 }
 
 static void mdp4_crtc_load_lut(struct drm_crtc *crtc)
@@ -419,7 +462,7 @@
 	mdp4_crtc->event = event;
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 
-	update_fb(crtc, true, new_fb);
+	update_fb(crtc, new_fb);
 
 	return msm_gem_queue_inactive_cb(obj, &mdp4_crtc->pageflip_cb);
 }
@@ -442,12 +485,12 @@
 static void update_cursor(struct drm_crtc *crtc)
 {
 	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct mdp4_kms *mdp4_kms = get_kms(crtc);
 	enum mdp4_dma dma = mdp4_crtc->dma;
 	unsigned long flags;
 
 	spin_lock_irqsave(&mdp4_crtc->cursor.lock, flags);
 	if (mdp4_crtc->cursor.stale) {
-		struct mdp4_kms *mdp4_kms = get_kms(crtc);
 		struct drm_gem_object *next_bo = mdp4_crtc->cursor.next_bo;
 		struct drm_gem_object *prev_bo = mdp4_crtc->cursor.scanout_bo;
 		uint32_t iova = mdp4_crtc->cursor.next_iova;
@@ -479,6 +522,11 @@
 		mdp4_crtc->cursor.scanout_bo = next_bo;
 		mdp4_crtc->cursor.stale = false;
 	}
+
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_POS(dma),
+			MDP4_DMA_CURSOR_POS_X(mdp4_crtc->cursor.x) |
+			MDP4_DMA_CURSOR_POS_Y(mdp4_crtc->cursor.y));
+
 	spin_unlock_irqrestore(&mdp4_crtc->cursor.lock, flags);
 }
 
@@ -530,6 +578,7 @@
 		drm_gem_object_unreference_unlocked(old_bo);
 	}
 
+	crtc_flush(crtc);
 	request_pending(crtc, PENDING_CURSOR);
 
 	return 0;
@@ -542,12 +591,15 @@
 static int mdp4_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 {
 	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
-	struct mdp4_kms *mdp4_kms = get_kms(crtc);
-	enum mdp4_dma dma = mdp4_crtc->dma;
+	unsigned long flags;
 
-	mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_POS(dma),
-			MDP4_DMA_CURSOR_POS_X(x) |
-			MDP4_DMA_CURSOR_POS_Y(y));
+	spin_lock_irqsave(&mdp4_crtc->cursor.lock, flags);
+	mdp4_crtc->cursor.x = x;
+	mdp4_crtc->cursor.y = y;
+	spin_unlock_irqrestore(&mdp4_crtc->cursor.lock, flags);
+
+	crtc_flush(crtc);
+	request_pending(crtc, PENDING_CURSOR);
 
 	return 0;
 }
@@ -713,6 +765,7 @@
 	crtc = &mdp4_crtc->base;
 
 	mdp4_crtc->plane = plane;
+	mdp4_crtc->id = id;
 
 	mdp4_crtc->ovlp = ovlp_id;
 	mdp4_crtc->dma = dma_id;
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
index 2406027..1e893dd 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
@@ -170,8 +170,8 @@
 			MDP4_PIPE_DST_SIZE_HEIGHT(crtc_h));
 
 	mdp4_write(mdp4_kms, REG_MDP4_PIPE_DST_XY(pipe),
-			MDP4_PIPE_SRC_XY_X(crtc_x) |
-			MDP4_PIPE_SRC_XY_Y(crtc_y));
+			MDP4_PIPE_DST_XY_X(crtc_x) |
+			MDP4_PIPE_DST_XY_Y(crtc_y));
 
 	mdp4_plane_set_scanout(plane, fb);
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
index 71a3b23..f279402 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
@@ -296,6 +296,7 @@
 			x << 16, y << 16,
 			mode->hdisplay << 16, mode->vdisplay << 16);
 	if (ret) {
+		drm_framebuffer_unreference(crtc->fb);
 		dev_err(crtc->dev->dev, "%s: failed to set mode on plane: %d\n",
 				mdp5_crtc->name, ret);
 		return ret;
@@ -343,11 +344,15 @@
 			0, 0, mode->hdisplay, mode->vdisplay,
 			x << 16, y << 16,
 			mode->hdisplay << 16, mode->vdisplay << 16);
+	if (ret) {
+		drm_framebuffer_unreference(crtc->fb);
+		return ret;
+	}
 
 	update_fb(crtc, crtc->fb);
 	update_scanout(crtc, crtc->fb);
 
-	return ret;
+	return 0;
 }
 
 static void mdp5_crtc_load_lut(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index d8d60c9..3da8264 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -644,7 +644,7 @@
 
 fail:
 	if (obj)
-		drm_gem_object_unreference_unlocked(obj);
+		drm_gem_object_unreference(obj);
 
 	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 5281d4b..5423e91 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -163,7 +163,7 @@
 
 
 		/* if locking succeeded, pin bo: */
-		ret = msm_gem_get_iova(&msm_obj->base,
+		ret = msm_gem_get_iova_locked(&msm_obj->base,
 				submit->gpu->id, &iova);
 
 		/* this would break the logic in the fail path.. there is no
@@ -247,7 +247,7 @@
 	/* For now, just map the entire thing.  Eventually we probably
 	 * to do it page-by-page, w/ kmap() if not vmap()d..
 	 */
-	ptr = msm_gem_vaddr(&obj->base);
+	ptr = msm_gem_vaddr_locked(&obj->base);
 
 	if (IS_ERR(ptr)) {
 		ret = PTR_ERR(ptr);
@@ -307,14 +307,12 @@
 {
 	unsigned i;
 
-	mutex_lock(&submit->dev->struct_mutex);
 	for (i = 0; i < submit->nr_bos; i++) {
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
 		submit_unlock_unpin_bo(submit, i);
 		list_del_init(&msm_obj->submit_entry);
 		drm_gem_object_unreference(&msm_obj->base);
 	}
-	mutex_unlock(&submit->dev->struct_mutex);
 
 	ww_acquire_fini(&submit->ticket);
 	kfree(submit);
@@ -342,6 +340,8 @@
 	if (args->nr_cmds > MAX_CMDS)
 		return -EINVAL;
 
+	mutex_lock(&dev->struct_mutex);
+
 	submit = submit_create(dev, gpu, args->nr_bos);
 	if (!submit) {
 		ret = -ENOMEM;
@@ -410,5 +410,6 @@
 out:
 	if (submit)
 		submit_cleanup(submit, !!ret);
+	mutex_unlock(&dev->struct_mutex);
 	return ret;
 }
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 4ebce8b..0cfe3f4 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -298,8 +298,6 @@
 	struct msm_drm_private *priv = dev->dev_private;
 	int i, ret;
 
-	mutex_lock(&dev->struct_mutex);
-
 	submit->fence = ++priv->next_fence;
 
 	gpu->submitted_fence = submit->fence;
@@ -331,7 +329,6 @@
 			msm_gem_move_to_active(&msm_obj->base, gpu, true, submit->fence);
 	}
 	hangcheck_timer_reset(gpu);
-	mutex_unlock(&dev->struct_mutex);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile
index e88145b..d310c19 100644
--- a/drivers/gpu/drm/nouveau/Makefile
+++ b/drivers/gpu/drm/nouveau/Makefile
@@ -141,6 +141,7 @@
 nouveau-y += core/subdev/mc/nv04.o
 nouveau-y += core/subdev/mc/nv40.o
 nouveau-y += core/subdev/mc/nv44.o
+nouveau-y += core/subdev/mc/nv4c.o
 nouveau-y += core/subdev/mc/nv50.o
 nouveau-y += core/subdev/mc/nv94.o
 nouveau-y += core/subdev/mc/nv98.o
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nv40.c b/drivers/gpu/drm/nouveau/core/engine/device/nv40.c
index 1b653dd..08b8859 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nv40.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nv40.c
@@ -311,7 +311,7 @@
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
-		device->oclass[NVDEV_SUBDEV_MC     ] =  nv44_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  nv4c_mc_oclass;
 		device->oclass[NVDEV_SUBDEV_BUS    ] =  nv31_bus_oclass;
 		device->oclass[NVDEV_SUBDEV_TIMER  ] = &nv04_timer_oclass;
 		device->oclass[NVDEV_SUBDEV_FB     ] =  nv46_fb_oclass;
@@ -334,7 +334,7 @@
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
-		device->oclass[NVDEV_SUBDEV_MC     ] =  nv44_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  nv4c_mc_oclass;
 		device->oclass[NVDEV_SUBDEV_BUS    ] =  nv31_bus_oclass;
 		device->oclass[NVDEV_SUBDEV_TIMER  ] = &nv04_timer_oclass;
 		device->oclass[NVDEV_SUBDEV_FB     ] =  nv4e_fb_oclass;
@@ -357,7 +357,7 @@
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
-		device->oclass[NVDEV_SUBDEV_MC     ] =  nv44_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  nv4c_mc_oclass;
 		device->oclass[NVDEV_SUBDEV_BUS    ] =  nv31_bus_oclass;
 		device->oclass[NVDEV_SUBDEV_TIMER  ] = &nv04_timer_oclass;
 		device->oclass[NVDEV_SUBDEV_FB     ] =  nv46_fb_oclass;
@@ -380,7 +380,7 @@
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
-		device->oclass[NVDEV_SUBDEV_MC     ] =  nv44_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  nv4c_mc_oclass;
 		device->oclass[NVDEV_SUBDEV_BUS    ] =  nv31_bus_oclass;
 		device->oclass[NVDEV_SUBDEV_TIMER  ] = &nv04_timer_oclass;
 		device->oclass[NVDEV_SUBDEV_FB     ] =  nv46_fb_oclass;
@@ -403,7 +403,7 @@
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
-		device->oclass[NVDEV_SUBDEV_MC     ] =  nv44_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  nv4c_mc_oclass;
 		device->oclass[NVDEV_SUBDEV_BUS    ] =  nv31_bus_oclass;
 		device->oclass[NVDEV_SUBDEV_TIMER  ] = &nv04_timer_oclass;
 		device->oclass[NVDEV_SUBDEV_FB     ] =  nv46_fb_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
index 940eaa5..9ad722e 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
@@ -1142,7 +1142,7 @@
 	if (conf != ~0) {
 		if (outp.location == 0 && outp.type == DCB_OUTPUT_DP) {
 			u32 soff = (ffs(outp.or) - 1) * 0x08;
-			u32 ctrl = nv_rd32(priv, 0x610798 + soff);
+			u32 ctrl = nv_rd32(priv, 0x610794 + soff);
 			u32 datarate;
 
 			switch ((ctrl & 0x000f0000) >> 16) {
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
index 9a850fe..54c1b5b 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
@@ -112,7 +112,7 @@
 
 	nv_wr32(priv, 0x002270, cur->addr >> 12);
 	nv_wr32(priv, 0x002274, (engine << 20) | (p >> 3));
-	if (!nv_wait(priv, 0x002284 + (engine * 4), 0x00100000, 0x00000000))
+	if (!nv_wait(priv, 0x002284 + (engine * 8), 0x00100000, 0x00000000))
 		nv_error(priv, "runlist %d update timeout\n", engine);
 	mutex_unlock(&nv_subdev(priv)->mutex);
 }
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
index 30ed19c..7a367c4 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
@@ -539,7 +539,7 @@
 				ustatus &= ~0x04030000;
 			}
 			if (ustatus && display) {
-				nv_error("%s - TP%d:", name, i);
+				nv_error(priv, "%s - TP%d:", name, i);
 				nouveau_bitfield_print(nv50_mpc_traps, ustatus);
 				pr_cont("\n");
 				ustatus = 0;
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
index adc88b7..3c6738e 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
@@ -47,6 +47,7 @@
 extern struct nouveau_oclass *nv04_mc_oclass;
 extern struct nouveau_oclass *nv40_mc_oclass;
 extern struct nouveau_oclass *nv44_mc_oclass;
+extern struct nouveau_oclass *nv4c_mc_oclass;
 extern struct nouveau_oclass *nv50_mc_oclass;
 extern struct nouveau_oclass *nv94_mc_oclass;
 extern struct nouveau_oclass *nv98_mc_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
index aa0fbbe..ef0c9c4 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
@@ -130,6 +130,10 @@
 	u16 pcir;
 	int i;
 
+	/* there is no prom on nv4x IGP's */
+	if (device->card_type == NV_40 && device->chipset >= 0x4c)
+		return;
+
 	/* enable access to rom */
 	if (device->card_type >= NV_50)
 		pcireg = 0x088050;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c
index 9159a5c..265d125 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c
@@ -36,7 +36,7 @@
 		.fini = _nouveau_fb_fini,
 	},
 	.base.memtype = nv04_fb_memtype_valid,
-	.base.ram = &nv10_ram_oclass,
+	.base.ram = &nv1a_ram_oclass,
 	.tile.regions = 8,
 	.tile.init = nv10_fb_tile_init,
 	.tile.fini = nv10_fb_tile_fini,
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h
index b0d5c31..81a408e 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h
@@ -14,6 +14,7 @@
 extern const struct nouveau_mc_intr nv04_mc_intr[];
 int  nv04_mc_init(struct nouveau_object *);
 void nv40_mc_msi_rearm(struct nouveau_mc *);
+int  nv44_mc_init(struct nouveau_object *object);
 int  nv50_mc_init(struct nouveau_object *);
 extern const struct nouveau_mc_intr nv50_mc_intr[];
 extern const struct nouveau_mc_intr nvc0_mc_intr[];
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
index 3bfee5c..cc4d0d2 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
@@ -24,7 +24,7 @@
 
 #include "nv04.h"
 
-static int
+int
 nv44_mc_init(struct nouveau_object *object)
 {
 	struct nv04_mc_priv *priv = (void *)object;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
new file mode 100644
index 0000000..a75c35c
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2014 Ilia Mirkin
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ilia Mirkin
+ */
+
+#include "nv04.h"
+
+static void
+nv4c_mc_msi_rearm(struct nouveau_mc *pmc)
+{
+	struct nv04_mc_priv *priv = (void *)pmc;
+	nv_wr08(priv, 0x088050, 0xff);
+}
+
+struct nouveau_oclass *
+nv4c_mc_oclass = &(struct nouveau_mc_oclass) {
+	.base.handle = NV_SUBDEV(MC, 0x4c),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = nv04_mc_ctor,
+		.dtor = _nouveau_mc_dtor,
+		.init = nv44_mc_init,
+		.fini = _nouveau_mc_fini,
+	},
+	.intr = nv04_mc_intr,
+	.msi_rearm = nv4c_mc_msi_rearm,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 4ef83df..83face3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -106,6 +106,29 @@
 	return 0;
 }
 
+/*
+ * On some platforms, _DSM(nouveau_op_dsm_muid, func0) has special
+ * requirements on the fourth parameter, so a private implementation
+ * instead of using acpi_check_dsm().
+ */
+static int nouveau_check_optimus_dsm(acpi_handle handle)
+{
+	int result;
+
+	/*
+	 * Function 0 returns a Buffer containing available functions.
+	 * The args parameter is ignored for function 0, so just put 0 in it
+	 */
+	if (nouveau_optimus_dsm(handle, 0, 0, &result))
+		return 0;
+
+	/*
+	 * ACPI Spec v4 9.14.1: if bit 0 is zero, no function is supported.
+	 * If the n-th bit is enabled, function n is supported
+	 */
+	return result & 1 && result & (1 << NOUVEAU_DSM_OPTIMUS_CAPS);
+}
+
 static int nouveau_dsm(acpi_handle handle, int func, int arg)
 {
 	int ret = 0;
@@ -207,8 +230,7 @@
 			   1 << NOUVEAU_DSM_POWER))
 		retval |= NOUVEAU_DSM_HAS_MUX;
 
-	if (acpi_check_dsm(dhandle, nouveau_op_dsm_muid, 0x00000100,
-			   1 << NOUVEAU_DSM_OPTIMUS_CAPS))
+	if (nouveau_check_optimus_dsm(dhandle))
 		retval |= NOUVEAU_DSM_HAS_OPT;
 
 	if (retval & NOUVEAU_DSM_HAS_OPT) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 488686d..4aed171 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1249,7 +1249,7 @@
 			mem->bus.is_iomem = !dev->agp->cant_use_aperture;
 		}
 #endif
-		if (!node->memtype)
+		if (nv_device(drm->device)->card_type < NV_50 || !node->memtype)
 			/* untiled */
 			break;
 		/* fallthrough, tiled memory */
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 78c8e71..4ee702a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -376,6 +376,8 @@
 	if (ret)
 		goto fail_device;
 
+	dev->irq_enabled = true;
+
 	/* workaround an odd issue on nvc1 by disabling the device's
 	 * nosnoop capability.  hopefully won't cause issues until a
 	 * better fix is found - assuming there is one...
@@ -475,6 +477,7 @@
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_object *device;
 
+	dev->irq_enabled = false;
 	device = drm->client.base.device;
 	drm_put_dev(dev);
 
@@ -863,13 +866,16 @@
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	int ret;
 
-	if (nouveau_runtime_pm == 0)
-		return -EINVAL;
+	if (nouveau_runtime_pm == 0) {
+		pm_runtime_forbid(dev);
+		return -EBUSY;
+	}
 
 	/* are we optimus enabled? */
 	if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
 		DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
-		return -EINVAL;
+		pm_runtime_forbid(dev);
+		return -EBUSY;
 	}
 
 	nv_debug_level(SILENT);
@@ -920,12 +926,15 @@
 	struct nouveau_drm *drm = nouveau_drm(drm_dev);
 	struct drm_crtc *crtc;
 
-	if (nouveau_runtime_pm == 0)
+	if (nouveau_runtime_pm == 0) {
+		pm_runtime_forbid(dev);
 		return -EBUSY;
+	}
 
 	/* are we optimus enabled? */
 	if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
 		DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c
index 81638d7..471347e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vga.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vga.c
@@ -14,7 +14,9 @@
 {
 	struct nouveau_device *device = nouveau_dev(priv);
 
-	if (device->chipset >= 0x40)
+	if (device->card_type == NV_40 && device->chipset >= 0x4c)
+		nv_wr32(device, 0x088060, state);
+	else if (device->chipset >= 0x40)
 		nv_wr32(device, 0x088054, state);
 	else
 		nv_wr32(device, 0x001854, state);
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index a9338c8..daa4dd3 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -559,7 +559,7 @@
 	u32 adjusted_clock = mode->clock;
 	int encoder_mode = atombios_get_encoder_mode(encoder);
 	u32 dp_clock = mode->clock;
-	int bpc = radeon_get_monitor_bpc(connector);
+	int bpc = radeon_crtc->bpc;
 	bool is_duallink = radeon_dig_monitor_is_duallink(encoder, mode->clock);
 
 	/* reset the pll flags */
@@ -1176,7 +1176,7 @@
 		evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split);
 
 		/* Set NUM_BANKS. */
-		if (rdev->family >= CHIP_BONAIRE) {
+		if (rdev->family >= CHIP_TAHITI) {
 			unsigned tileb, index, num_banks, tile_split_bytes;
 
 			/* Calculate the macrotile mode index. */
@@ -1194,13 +1194,14 @@
 				return -EINVAL;
 			}
 
-			num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3;
+			if (rdev->family >= CHIP_BONAIRE)
+				num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3;
+			else
+				num_banks = (rdev->config.si.tile_mode_array[index] >> 20) & 0x3;
 			fb_format |= EVERGREEN_GRPH_NUM_BANKS(num_banks);
 		} else {
-			/* SI and older. */
-			if (rdev->family >= CHIP_TAHITI)
-				tmp = rdev->config.si.tile_config;
-			else if (rdev->family >= CHIP_CAYMAN)
+			/* NI and older. */
+			if (rdev->family >= CHIP_CAYMAN)
 				tmp = rdev->config.cayman.tile_config;
 			else
 				tmp = rdev->config.evergreen.tile_config;
@@ -1773,6 +1774,20 @@
 			return ATOM_PPLL1;
 		DRM_ERROR("unable to allocate a PPLL\n");
 		return ATOM_PPLL_INVALID;
+	} else if (ASIC_IS_DCE41(rdev)) {
+		/* Don't share PLLs on DCE4.1 chips */
+		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) {
+			if (rdev->clock.dp_extclk)
+				/* skip PPLL programming if using ext clock */
+				return ATOM_PPLL_INVALID;
+		}
+		pll_in_use = radeon_get_pll_use_mask(crtc);
+		if (!(pll_in_use & (1 << ATOM_PPLL1)))
+			return ATOM_PPLL1;
+		if (!(pll_in_use & (1 << ATOM_PPLL2)))
+			return ATOM_PPLL2;
+		DRM_ERROR("unable to allocate a PPLL\n");
+		return ATOM_PPLL_INVALID;
 	} else if (ASIC_IS_DCE4(rdev)) {
 		/* in DP mode, the DP ref clock can come from PPLL, DCPLL, or ext clock,
 		 * depending on the asic:
@@ -1800,7 +1815,7 @@
 				if (pll != ATOM_PPLL_INVALID)
 					return pll;
 			}
-		} else if (!ASIC_IS_DCE41(rdev)) { /* Don't share PLLs on DCE4.1 chips */
+		} else {
 			/* use the same PPLL for all monitors with the same clock */
 			pll = radeon_get_shared_nondp_ppll(crtc);
 			if (pll != ATOM_PPLL_INVALID)
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index a42d615..607dc14 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -464,11 +464,12 @@
 
 static u8 radeon_atom_get_bpc(struct drm_encoder *encoder)
 {
-	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 	int bpc = 8;
 
-	if (connector)
-		bpc = radeon_get_monitor_bpc(connector);
+	if (encoder->crtc) {
+		struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
+		bpc = radeon_crtc->bpc;
+	}
 
 	switch (bpc) {
 	case 0:
@@ -1313,7 +1314,7 @@
 			}
 			if (is_dp)
 				args.v5.ucLaneNum = dp_lane_count;
-			else if (radeon_encoder->pixel_clock > 165000)
+			else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
 				args.v5.ucLaneNum = 8;
 			else
 				args.v5.ucLaneNum = 4;
diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index 0fbd36f..ea103cc 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -29,6 +29,7 @@
 #include "cypress_dpm.h"
 #include "btc_dpm.h"
 #include "atom.h"
+#include <linux/seq_file.h>
 
 #define MC_CG_ARB_FREQ_F0           0x0a
 #define MC_CG_ARB_FREQ_F1           0x0b
@@ -2756,6 +2757,37 @@
 	r600_free_extended_power_table(rdev);
 }
 
+void btc_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
+						     struct seq_file *m)
+{
+	struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
+	struct radeon_ps *rps = &eg_pi->current_rps;
+	struct rv7xx_ps *ps = rv770_get_ps(rps);
+	struct rv7xx_pl *pl;
+	u32 current_index =
+		(RREG32(TARGET_AND_CURRENT_PROFILE_INDEX) & CURRENT_PROFILE_INDEX_MASK) >>
+		CURRENT_PROFILE_INDEX_SHIFT;
+
+	if (current_index > 2) {
+		seq_printf(m, "invalid dpm profile %d\n", current_index);
+	} else {
+		if (current_index == 0)
+			pl = &ps->low;
+		else if (current_index == 1)
+			pl = &ps->medium;
+		else /* current_index == 2 */
+			pl = &ps->high;
+		seq_printf(m, "uvd    vclk: %d dclk: %d\n", rps->vclk, rps->dclk);
+		if (rdev->family >= CHIP_CEDAR) {
+			seq_printf(m, "power level %d    sclk: %u mclk: %u vddc: %u vddci: %u\n",
+				   current_index, pl->sclk, pl->mclk, pl->vddc, pl->vddci);
+		} else {
+			seq_printf(m, "power level %d    sclk: %u mclk: %u vddc: %u\n",
+				   current_index, pl->sclk, pl->mclk, pl->vddc);
+		}
+	}
+}
+
 u32 btc_dpm_get_sclk(struct radeon_device *rdev, bool low)
 {
 	struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
diff --git a/drivers/gpu/drm/radeon/btcd.h b/drivers/gpu/drm/radeon/btcd.h
index 29e32de..9c65be2 100644
--- a/drivers/gpu/drm/radeon/btcd.h
+++ b/drivers/gpu/drm/radeon/btcd.h
@@ -44,6 +44,10 @@
 #       define DYN_SPREAD_SPECTRUM_EN                   (1 << 23)
 #       define AC_DC_SW                                 (1 << 24)
 
+#define TARGET_AND_CURRENT_PROFILE_INDEX                  0x66c
+#       define CURRENT_PROFILE_INDEX_MASK                 (0xf << 4)
+#       define CURRENT_PROFILE_INDEX_SHIFT                4
+
 #define	CG_BIF_REQ_AND_RSP				0x7f4
 #define		CG_CLIENT_REQ(x)			((x) << 0)
 #define		CG_CLIENT_REQ_MASK			(0xff << 0)
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index e6419ca..bbb1784 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3046,7 +3046,7 @@
 }
 
 /**
- * cik_select_se_sh - select which SE, SH to address
+ * cik_get_rb_disabled - computes the mask of disabled RBs
  *
  * @rdev: radeon_device pointer
  * @max_rb_num: max RBs (render backends) for the asic
@@ -4134,8 +4134,11 @@
 {
 	if (enable)
 		WREG32(CP_MEC_CNTL, 0);
-	else
+	else {
 		WREG32(CP_MEC_CNTL, (MEC_ME1_HALT | MEC_ME2_HALT));
+		rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX].ready = false;
+		rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX].ready = false;
+	}
 	udelay(50);
 }
 
@@ -7902,7 +7905,8 @@
 	/* init golden registers */
 	cik_init_golden_registers(rdev);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = cik_startup(rdev);
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index 1ecb3f1..94626ea 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -264,6 +264,8 @@
 		WREG32(SDMA0_GFX_RB_CNTL + reg_offset, rb_cntl);
 		WREG32(SDMA0_GFX_IB_CNTL + reg_offset, 0);
 	}
+	rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
+	rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX].ready = false;
 }
 
 /**
@@ -291,6 +293,11 @@
 	u32 me_cntl, reg_offset;
 	int i;
 
+	if (enable == false) {
+		cik_sdma_gfx_stop(rdev);
+		cik_sdma_rlc_stop(rdev);
+	}
+
 	for (i = 0; i < 2; i++) {
 		if (i == 0)
 			reg_offset = SDMA0_REGISTER_OFFSET;
@@ -420,10 +427,6 @@
 	if (!rdev->sdma_fw)
 		return -EINVAL;
 
-	/* stop the gfx rings and rlc compute queues */
-	cik_sdma_gfx_stop(rdev);
-	cik_sdma_rlc_stop(rdev);
-
 	/* halt the MEs */
 	cik_sdma_enable(rdev, false);
 
@@ -492,9 +495,6 @@
  */
 void cik_sdma_fini(struct radeon_device *rdev)
 {
-	/* stop the gfx rings and rlc compute queues */
-	cik_sdma_gfx_stop(rdev);
-	cik_sdma_rlc_stop(rdev);
 	/* halt the MEs */
 	cik_sdma_enable(rdev, false);
 	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index 713a5d3..94e8587 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -278,13 +278,15 @@
 	return !ASIC_IS_NODCE(rdev);
 }
 
-static void dce6_audio_enable(struct radeon_device *rdev,
-			      struct r600_audio_pin *pin,
-			      bool enable)
+void dce6_audio_enable(struct radeon_device *rdev,
+		       struct r600_audio_pin *pin,
+		       bool enable)
 {
+	if (!pin)
+		return;
+
 	WREG32_ENDPOINT(pin->offset, AZ_F0_CODEC_PIN_CONTROL_HOTPLUG_CONTROL,
-			AUDIO_ENABLED);
-	DRM_INFO("%s audio %d support\n", enable ? "Enabling" : "Disabling", pin->id);
+			enable ? AUDIO_ENABLED : 0);
 }
 
 static const u32 pin_offsets[7] =
@@ -323,7 +325,8 @@
 		rdev->audio.pin[i].connected = false;
 		rdev->audio.pin[i].offset = pin_offsets[i];
 		rdev->audio.pin[i].id = i;
-		dce6_audio_enable(rdev, &rdev->audio.pin[i], true);
+		/* disable audio.  it will be set up later */
+		dce6_audio_enable(rdev, &rdev->audio.pin[i], false);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index f2b9e21..27b0ff1 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1680,7 +1680,7 @@
 	case RADEON_HPD_6:
 		if (RREG32(DC_HPD6_INT_STATUS) & DC_HPDx_SENSE)
 			connected = true;
-			break;
+		break;
 	default:
 		break;
 	}
@@ -5299,7 +5299,8 @@
 	/* init golden registers */
 	evergreen_init_golden_registers(rdev);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = evergreen_startup(rdev);
@@ -5475,9 +5476,9 @@
 	radeon_wb_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
-	evergreen_pcie_gart_fini(rdev);
 	uvd_v1_0_fini(rdev);
 	radeon_uvd_fini(rdev);
+	evergreen_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
 	radeon_fence_driver_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index 0c6d5ce..05b0c95 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -306,6 +306,15 @@
 		return;
 	offset = dig->afmt->offset;
 
+	/* disable audio prior to setting up hw */
+	if (ASIC_IS_DCE6(rdev)) {
+		dig->afmt->pin = dce6_audio_get_pin(rdev);
+		dce6_audio_enable(rdev, dig->afmt->pin, false);
+	} else {
+		dig->afmt->pin = r600_audio_get_pin(rdev);
+		r600_audio_enable(rdev, dig->afmt->pin, false);
+	}
+
 	evergreen_audio_set_dto(encoder, mode->clock);
 
 	WREG32(HDMI_VBI_PACKET_CONTROL + offset,
@@ -409,12 +418,16 @@
 	WREG32(AFMT_RAMP_CONTROL1 + offset, 0x007FFFFF);
 	WREG32(AFMT_RAMP_CONTROL2 + offset, 0x00000001);
 	WREG32(AFMT_RAMP_CONTROL3 + offset, 0x00000001);
+
+	/* enable audio after to setting up hw */
+	if (ASIC_IS_DCE6(rdev))
+		dce6_audio_enable(rdev, dig->afmt->pin, true);
+	else
+		r600_audio_enable(rdev, dig->afmt->pin, true);
 }
 
 void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable)
 {
-	struct drm_device *dev = encoder->dev;
-	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 
@@ -427,15 +440,6 @@
 	if (!enable && !dig->afmt->enabled)
 		return;
 
-	if (enable) {
-		if (ASIC_IS_DCE6(rdev))
-			dig->afmt->pin = dce6_audio_get_pin(rdev);
-		else
-			dig->afmt->pin = r600_audio_get_pin(rdev);
-	} else {
-		dig->afmt->pin = NULL;
-	}
-
 	dig->afmt->enabled = enable;
 
 	DRM_DEBUG("%sabling HDMI interface @ 0x%04X for encoder 0x%x\n",
diff --git a/drivers/gpu/drm/radeon/evergreen_smc.h b/drivers/gpu/drm/radeon/evergreen_smc.h
index 76ada8c..3a03ba3 100644
--- a/drivers/gpu/drm/radeon/evergreen_smc.h
+++ b/drivers/gpu/drm/radeon/evergreen_smc.h
@@ -57,7 +57,7 @@
 
 #define EVERGREEN_SMC_FIRMWARE_HEADER_LOCATION 0x100
 
-#define EVERGREEN_SMC_FIRMWARE_HEADER_softRegisters   0x0
+#define EVERGREEN_SMC_FIRMWARE_HEADER_softRegisters   0x8
 #define EVERGREEN_SMC_FIRMWARE_HEADER_stateTable      0xC
 #define EVERGREEN_SMC_FIRMWARE_HEADER_mcRegisterTable 0x20
 
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index b6e01d5..351db36 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -1223,7 +1223,7 @@
 
 int kv_dpm_late_enable(struct radeon_device *rdev)
 {
-	int ret;
+	int ret = 0;
 
 	if (rdev->irq.installed &&
 	    r600_is_internal_thermal_sensor(rdev->pm.int_thermal_type)) {
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index ea932ac..bf6300c 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -2105,7 +2105,8 @@
 	/* init golden registers */
 	ni_init_golden_registers(rdev);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = cayman_startup(rdev);
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index c351226..ca81427 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -2588,7 +2588,7 @@
 	if (NISLANDS_DPM2_SQ_RAMP_STI_SIZE > (STI_SIZE_MASK >> STI_SIZE_SHIFT))
 		enable_sq_ramping = false;
 
-	if (NISLANDS_DPM2_SQ_RAMP_LTI_RATIO <= (LTI_RATIO_MASK >> LTI_RATIO_SHIFT))
+	if (NISLANDS_DPM2_SQ_RAMP_LTI_RATIO > (LTI_RATIO_MASK >> LTI_RATIO_SHIFT))
 		enable_sq_ramping = false;
 
 	for (i = 0; i < state->performance_level_count; i++) {
@@ -3945,7 +3945,6 @@
 	struct rv7xx_power_info *pi = rv770_get_pi(rdev);
 	struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
 	struct ni_ps *ps = ni_get_ps(rps);
-	u16 vddc;
 	struct rv7xx_pl *pl = &ps->performance_levels[index];
 
 	ps->performance_level_count = index + 1;
@@ -3961,8 +3960,8 @@
 
 	/* patch up vddc if necessary */
 	if (pl->vddc == 0xff01) {
-		if (radeon_atom_get_max_vddc(rdev, 0, 0, &vddc) == 0)
-			pl->vddc = vddc;
+		if (pi->max_vddc)
+			pl->vddc = pi->max_vddc;
 	}
 
 	if (rps->class & ATOM_PPLIB_CLASSIFICATION_ACPI) {
@@ -4322,7 +4321,8 @@
 void ni_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
 						    struct seq_file *m)
 {
-	struct radeon_ps *rps = rdev->pm.dpm.current_ps;
+	struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
+	struct radeon_ps *rps = &eg_pi->current_rps;
 	struct ni_ps *ps = ni_get_ps(rps);
 	struct rv7xx_pl *pl;
 	u32 current_index =
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index ef024ce..3cc78bb 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -3942,8 +3942,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = r100_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 7c63ef8..0b658b3 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -1430,8 +1430,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = r300_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c
index 3768aab..802b192 100644
--- a/drivers/gpu/drm/radeon/r420.c
+++ b/drivers/gpu/drm/radeon/r420.c
@@ -325,8 +325,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = r420_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c
index e209eb7..98d6053 100644
--- a/drivers/gpu/drm/radeon/r520.c
+++ b/drivers/gpu/drm/radeon/r520.c
@@ -240,8 +240,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = r520_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 56140b4..647ef40 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2968,7 +2968,8 @@
 	/* post card */
 	atom_asic_init(rdev->mode_info.atom_context);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = r600_startup(rdev);
@@ -3991,6 +3992,10 @@
 				break;
 			}
 			break;
+		case 124: /* UVD */
+			DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data);
+			radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX);
+			break;
 		case 176: /* CP_INT in ring buffer */
 		case 177: /* CP_INT in IB1 */
 		case 178: /* CP_INT in IB2 */
diff --git a/drivers/gpu/drm/radeon/r600_audio.c b/drivers/gpu/drm/radeon/r600_audio.c
index 47fc2b8..bffac10 100644
--- a/drivers/gpu/drm/radeon/r600_audio.c
+++ b/drivers/gpu/drm/radeon/r600_audio.c
@@ -142,12 +142,15 @@
 }
 
 /* enable the audio stream */
-static void r600_audio_enable(struct radeon_device *rdev,
-			      struct r600_audio_pin *pin,
-			      bool enable)
+void r600_audio_enable(struct radeon_device *rdev,
+		       struct r600_audio_pin *pin,
+		       bool enable)
 {
 	u32 value = 0;
 
+	if (!pin)
+		return;
+
 	if (ASIC_IS_DCE4(rdev)) {
 		if (enable) {
 			value |= 0x81000000; /* Required to enable audio */
@@ -158,7 +161,6 @@
 		WREG32_P(R600_AUDIO_ENABLE,
 			 enable ? 0x81000000 : 0x0, ~0x81000000);
 	}
-	DRM_INFO("%s audio %d support\n", enable ? "Enabling" : "Disabling", pin->id);
 }
 
 /*
@@ -178,8 +180,8 @@
 	rdev->audio.pin[0].status_bits = 0;
 	rdev->audio.pin[0].category_code = 0;
 	rdev->audio.pin[0].id = 0;
-
-	r600_audio_enable(rdev, &rdev->audio.pin[0], true);
+	/* disable audio.  it will be set up later */
+	r600_audio_enable(rdev, &rdev->audio.pin[0], false);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 7b399dc..2812c7d1a 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -1007,8 +1007,22 @@
 	case R_008C64_SQ_VSTMP_RING_SIZE:
 	case R_0288C8_SQ_GS_VERT_ITEMSIZE:
 		/* get value to populate the IB don't remove */
-		tmp =radeon_get_ib_value(p, idx);
-		ib[idx] = 0;
+		/*tmp =radeon_get_ib_value(p, idx);
+		  ib[idx] = 0;*/
+		break;
+	case SQ_ESGS_RING_BASE:
+	case SQ_GSVS_RING_BASE:
+	case SQ_ESTMP_RING_BASE:
+	case SQ_GSTMP_RING_BASE:
+	case SQ_PSTMP_RING_BASE:
+	case SQ_VSTMP_RING_BASE:
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
+		if (r) {
+			dev_warn(p->dev, "bad SET_CONTEXT_REG "
+					"0x%04X\n", reg);
+			return -EINVAL;
+		}
+		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
 		break;
 	case SQ_CONFIG:
 		track->sq_config = radeon_get_ib_value(p, idx);
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 3016fc1..85a2bb2 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -329,9 +329,6 @@
 	u8 *sadb;
 	int sad_count;
 
-	/* XXX: setting this register causes hangs on some asics */
-	return;
-
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
 		if (connector->encoder == encoder) {
 			radeon_connector = to_radeon_connector(connector);
@@ -460,6 +457,10 @@
 		return;
 	offset = dig->afmt->offset;
 
+	/* disable audio prior to setting up hw */
+	dig->afmt->pin = r600_audio_get_pin(rdev);
+	r600_audio_enable(rdev, dig->afmt->pin, false);
+
 	r600_audio_set_dto(encoder, mode->clock);
 
 	WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
@@ -531,6 +532,9 @@
 	WREG32(HDMI0_RAMP_CONTROL3 + offset, 0x00000001);
 
 	r600_hdmi_audio_workaround(encoder);
+
+	/* enable audio after to setting up hw */
+	r600_audio_enable(rdev, dig->afmt->pin, true);
 }
 
 /*
@@ -651,11 +655,6 @@
 	if (!enable && !dig->afmt->enabled)
 		return;
 
-	if (enable)
-		dig->afmt->pin = r600_audio_get_pin(rdev);
-	else
-		dig->afmt->pin = NULL;
-
 	/* Older chipsets require setting HDMI and routing manually */
 	if (!ASIC_IS_DCE3(rdev)) {
 		if (enable)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 4a8ac1c..e887d02 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -135,6 +135,9 @@
 /* R600+ */
 #define R600_RING_TYPE_UVD_INDEX	5
 
+/* number of hw syncs before falling back on blocking */
+#define RADEON_NUM_SYNCS			4
+
 /* hardcode those limit for now */
 #define RADEON_VA_IB_OFFSET			(1 << 20)
 #define RADEON_VA_RESERVED_SIZE			(8 << 20)
@@ -554,7 +557,6 @@
 /*
  * Semaphores.
  */
-/* everything here is constant */
 struct radeon_semaphore {
 	struct radeon_sa_bo		*sa_bo;
 	signed				waiters;
@@ -2745,6 +2747,12 @@
 void r600_audio_update_hdmi(struct work_struct *work);
 struct r600_audio_pin *r600_audio_get_pin(struct radeon_device *rdev);
 struct r600_audio_pin *dce6_audio_get_pin(struct radeon_device *rdev);
+void r600_audio_enable(struct radeon_device *rdev,
+		       struct r600_audio_pin *pin,
+		       bool enable);
+void dce6_audio_enable(struct radeon_device *rdev,
+		       struct r600_audio_pin *pin,
+		       bool enable);
 
 /*
  * R600 vram scratch functions
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index f74db43..dda02bf 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1555,7 +1555,7 @@
 		.get_sclk = &btc_dpm_get_sclk,
 		.get_mclk = &btc_dpm_get_mclk,
 		.print_power_state = &rv770_dpm_print_power_state,
-		.debugfs_print_current_performance_level = &rv770_dpm_debugfs_print_current_performance_level,
+		.debugfs_print_current_performance_level = &btc_dpm_debugfs_print_current_performance_level,
 		.force_performance_level = &rv770_dpm_force_performance_level,
 		.vblank_too_short = &btc_dpm_vblank_too_short,
 	},
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index b3bc433..ae637cf 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -551,6 +551,8 @@
 u32 btc_dpm_get_sclk(struct radeon_device *rdev, bool low);
 u32 btc_dpm_get_mclk(struct radeon_device *rdev, bool low);
 bool btc_dpm_vblank_too_short(struct radeon_device *rdev);
+void btc_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
+						     struct seq_file *m);
 int sumo_dpm_init(struct radeon_device *rdev);
 int sumo_dpm_enable(struct radeon_device *rdev);
 int sumo_dpm_late_enable(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 485848f..fa9a9c0 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -219,7 +219,8 @@
 	memcpy(&output, info->buffer.pointer, size);
 
 	/* TODO: check version? */
-	printk("ATPX version %u\n", output.version);
+	printk("ATPX version %u, functions 0x%08x\n",
+	       output.version, output.function_bits);
 
 	radeon_atpx_parse_functions(&atpx->functions, output.function_bits);
 
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index b012cbb..044bc98 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1521,13 +1521,16 @@
 	if (r)
 		DRM_ERROR("ib ring test failed (%d).\n", r);
 
-	if (rdev->pm.dpm_enabled) {
+	if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) {
 		/* do dpm late init */
 		r = radeon_pm_late_init(rdev);
 		if (r) {
 			rdev->pm.dpm_enabled = false;
 			DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n");
 		}
+	} else {
+		/* resume old pm late */
+		radeon_pm_resume(rdev);
 	}
 
 	radeon_restore_bios_scratch_regs(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index d680608..fbd8b93 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -571,6 +571,8 @@
 		radeon_crtc->max_cursor_width = CURSOR_WIDTH;
 		radeon_crtc->max_cursor_height = CURSOR_HEIGHT;
 	}
+	dev->mode_config.cursor_width = radeon_crtc->max_cursor_width;
+	dev->mode_config.cursor_height = radeon_crtc->max_cursor_height;
 
 #if 0
 	radeon_crtc->mode_set.crtc = &radeon_crtc->base;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index ec8c388..f633c27 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -78,9 +78,10 @@
  *   2.34.0 - Add CIK tiling mode array query
  *   2.35.0 - Add CIK macrotile mode array query
  *   2.36.0 - Fix CIK DCE tiling setup
+ *   2.37.0 - allow GS ring setup on r6xx/r7xx
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	36
+#define KMS_DRIVER_MINOR	37
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
@@ -402,11 +403,15 @@
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	int ret;
 
-	if (radeon_runtime_pm == 0)
-		return -EINVAL;
+	if (radeon_runtime_pm == 0) {
+		pm_runtime_forbid(dev);
+		return -EBUSY;
+	}
 
-	if (radeon_runtime_pm == -1 && !radeon_is_px())
-		return -EINVAL;
+	if (radeon_runtime_pm == -1 && !radeon_is_px()) {
+		pm_runtime_forbid(dev);
+		return -EBUSY;
+	}
 
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 	drm_kms_helper_poll_disable(drm_dev);
@@ -455,12 +460,15 @@
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	struct drm_crtc *crtc;
 
-	if (radeon_runtime_pm == 0)
+	if (radeon_runtime_pm == 0) {
+		pm_runtime_forbid(dev);
 		return -EBUSY;
+	}
 
 	/* are we PX enabled? */
 	if (radeon_runtime_pm == -1 && !radeon_is_px()) {
 		DRM_DEBUG_DRIVER("failing to power off - not px\n");
+		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 114d167..66ed3ea 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -33,6 +33,13 @@
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
+
+#if defined(CONFIG_VGA_SWITCHEROO)
+bool radeon_is_px(void);
+#else
+static inline bool radeon_is_px(void) { return false; }
+#endif
+
 /**
  * radeon_driver_unload_kms - Main unload function for KMS.
  *
@@ -130,7 +137,8 @@
 				"Error during ACPI methods call\n");
 	}
 
-	if (radeon_runtime_pm != 0) {
+	if ((radeon_runtime_pm == 1) ||
+	    ((radeon_runtime_pm == -1) && radeon_is_px())) {
 		pm_runtime_use_autosuspend(dev->dev);
 		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
 		pm_runtime_set_active(dev->dev);
@@ -537,6 +545,10 @@
 
 		radeon_vm_init(rdev, &fpriv->vm);
 
+		r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
+		if (r)
+			return r;
+
 		/* map the ib pool buffer read only into
 		 * virtual address space */
 		bo_va = radeon_vm_bo_add(rdev, &fpriv->vm,
@@ -544,6 +556,8 @@
 		r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET,
 					  RADEON_VM_PAGE_READABLE |
 					  RADEON_VM_PAGE_SNOOPED);
+
+		radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 		if (r) {
 			radeon_vm_fini(rdev, &fpriv->vm);
 			kfree(fpriv);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 1b783f0..15e44a7 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -139,7 +139,7 @@
 	}
 
 	/* 64 dwords should be enough for fence too */
-	r = radeon_ring_lock(rdev, ring, 64 + RADEON_NUM_RINGS * 8);
+	r = radeon_ring_lock(rdev, ring, 64 + RADEON_NUM_SYNCS * 8);
 	if (r) {
 		dev_err(rdev->dev, "scheduling IB failed (%d).\n", r);
 		return r;
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index 2b42aa1..9006b32 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -34,14 +34,15 @@
 int radeon_semaphore_create(struct radeon_device *rdev,
 			    struct radeon_semaphore **semaphore)
 {
+	uint32_t *cpu_addr;
 	int i, r;
 
 	*semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL);
 	if (*semaphore == NULL) {
 		return -ENOMEM;
 	}
-	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo,
-			     &(*semaphore)->sa_bo, 8, 8, true);
+	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &(*semaphore)->sa_bo,
+			     8 * RADEON_NUM_SYNCS, 8, true);
 	if (r) {
 		kfree(*semaphore);
 		*semaphore = NULL;
@@ -49,7 +50,10 @@
 	}
 	(*semaphore)->waiters = 0;
 	(*semaphore)->gpu_addr = radeon_sa_bo_gpu_addr((*semaphore)->sa_bo);
-	*((uint64_t*)radeon_sa_bo_cpu_addr((*semaphore)->sa_bo)) = 0;
+
+	cpu_addr = radeon_sa_bo_cpu_addr((*semaphore)->sa_bo);
+	for (i = 0; i < RADEON_NUM_SYNCS; ++i)
+		cpu_addr[i] = 0;
 
 	for (i = 0; i < RADEON_NUM_RINGS; ++i)
 		(*semaphore)->sync_to[i] = NULL;
@@ -125,6 +129,7 @@
 				struct radeon_semaphore *semaphore,
 				int ring)
 {
+	unsigned count = 0;
 	int i, r;
 
         for (i = 0; i < RADEON_NUM_RINGS; ++i) {
@@ -140,6 +145,12 @@
 			return -EINVAL;
 		}
 
+		if (++count > RADEON_NUM_SYNCS) {
+			/* not enough room, wait manually */
+			radeon_fence_wait_locked(fence);
+			continue;
+		}
+
 		/* allocate enough space for sync command */
 		r = radeon_ring_alloc(rdev, &rdev->ring[i], 16);
 		if (r) {
@@ -164,6 +175,8 @@
 
 		radeon_ring_commit(rdev, &rdev->ring[i]);
 		radeon_fence_note_sync(fence, ring);
+
+		semaphore->gpu_addr += 8;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 77f5b0c..040a2a1 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -714,6 +714,9 @@
 		DRM_ERROR("Failed initializing VRAM heap.\n");
 		return r;
 	}
+	/* Change the size here instead of the init above so only lpfn is affected */
+	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
+
 	r = radeon_bo_create(rdev, 256 * 1024, PAGE_SIZE, true,
 			     RADEON_GEM_DOMAIN_VRAM,
 			     NULL, &rdev->stollen_vga_memory);
@@ -935,7 +938,7 @@
 	while (size) {
 		loff_t p = *pos / PAGE_SIZE;
 		unsigned off = *pos & ~PAGE_MASK;
-		ssize_t cur_size = min(size, PAGE_SIZE - off);
+		size_t cur_size = min_t(size_t, size, PAGE_SIZE - off);
 		struct page *page;
 		void *ptr;
 
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 6781fee..3e6804b 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -171,6 +171,8 @@
 
 	radeon_bo_unref(&rdev->uvd.vcpu_bo);
 
+	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_UVD_INDEX]);
+
 	release_firmware(rdev->uvd_fw);
 }
 
diff --git a/drivers/gpu/drm/radeon/reg_srcs/r600 b/drivers/gpu/drm/radeon/reg_srcs/r600
index 20bfbda..ec0c682 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/r600
+++ b/drivers/gpu/drm/radeon/reg_srcs/r600
@@ -18,6 +18,7 @@
 0x00028A3C VGT_GROUP_VECT_1_FMT_CNTL
 0x00028A40 VGT_GS_MODE
 0x00028A6C VGT_GS_OUT_PRIM_TYPE
+0x00028B38 VGT_GS_MAX_VERT_OUT
 0x000088C8 VGT_GS_PER_ES
 0x000088E8 VGT_GS_PER_VS
 0x000088D4 VGT_GS_VERTEX_REUSE
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index b5c2369..130d5cc 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -474,8 +474,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = rs400_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index fdcde76..72d3616 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -1048,8 +1048,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = rs600_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 3595073..3462b64 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -756,8 +756,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = rs690_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 98e8138..237dd29 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -586,8 +586,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r =  rv515_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 6c772e5..fef3107 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -1811,7 +1811,8 @@
 	/* init golden registers */
 	rv770_init_golden_registers(rdev);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = rv770_startup(rdev);
@@ -1955,9 +1956,9 @@
 	radeon_wb_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
-	rv770_pcie_gart_fini(rdev);
 	uvd_v1_0_fini(rdev);
 	radeon_uvd_fini(rdev);
+	rv770_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
 	radeon_fence_driver_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index 80c595a..b5f63f5 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -2174,7 +2174,6 @@
 	struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
 	struct rv7xx_ps *ps = rv770_get_ps(rps);
 	u32 sclk, mclk;
-	u16 vddc;
 	struct rv7xx_pl *pl;
 
 	switch (index) {
@@ -2214,8 +2213,8 @@
 
 	/* patch up vddc if necessary */
 	if (pl->vddc == 0xff01) {
-		if (radeon_atom_get_max_vddc(rdev, 0, 0, &vddc) == 0)
-			pl->vddc = vddc;
+		if (pi->max_vddc)
+			pl->vddc = pi->max_vddc;
 	}
 
 	if (rps->class & ATOM_PPLIB_CLASSIFICATION_ACPI) {
@@ -2527,14 +2526,7 @@
 bool rv770_dpm_vblank_too_short(struct radeon_device *rdev)
 {
 	u32 vblank_time = r600_dpm_get_vblank_time(rdev);
-	u32 switch_limit = 300;
-
-	/* quirks */
-	/* ASUS K70AF */
-	if ((rdev->pdev->device == 0x9553) &&
-	    (rdev->pdev->subsystem_vendor == 0x1043) &&
-	    (rdev->pdev->subsystem_device == 0x1c42))
-		switch_limit = 200;
+	u32 switch_limit = 200; /* 300 */
 
 	/* RV770 */
 	/* mclk switching doesn't seem to work reliably on desktop RV770s */
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 09ec4f6..9a124d0 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -6338,6 +6338,10 @@
 				break;
 			}
 			break;
+		case 124: /* UVD */
+			DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data);
+			radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX);
+			break;
 		case 146:
 		case 147:
 			addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR);
@@ -6614,7 +6618,8 @@
 	/* init golden registers */
 	si_init_golden_registers(rdev);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = si_startup(rdev);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 0471501..0a2f5b4 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2395,7 +2395,7 @@
 	if (SISLANDS_DPM2_SQ_RAMP_STI_SIZE > (STI_SIZE_MASK >> STI_SIZE_SHIFT))
 		enable_sq_ramping = false;
 
-	if (SISLANDS_DPM2_SQ_RAMP_LTI_RATIO <= (LTI_RATIO_MASK >> LTI_RATIO_SHIFT))
+	if (SISLANDS_DPM2_SQ_RAMP_LTI_RATIO > (LTI_RATIO_MASK >> LTI_RATIO_SHIFT))
 		enable_sq_ramping = false;
 
 	for (i = 0; i < state->performance_level_count; i++) {
@@ -6472,7 +6472,8 @@
 void si_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
 						    struct seq_file *m)
 {
-	struct radeon_ps *rps = rdev->pm.dpm.current_ps;
+	struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
+	struct radeon_ps *rps = &eg_pi->current_rps;
 	struct ni_ps *ps = ni_get_ps(rps);
 	struct rv7xx_pl *pl;
 	u32 current_index =
diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c
index f121efe..8b47b3cd 100644
--- a/drivers/gpu/drm/radeon/sumo_dpm.c
+++ b/drivers/gpu/drm/radeon/sumo_dpm.c
@@ -1807,7 +1807,7 @@
 						      struct seq_file *m)
 {
 	struct sumo_power_info *pi = sumo_get_pi(rdev);
-	struct radeon_ps *rps = rdev->pm.dpm.current_ps;
+	struct radeon_ps *rps = &pi->current_rps;
 	struct sumo_ps *ps = sumo_get_ps(rps);
 	struct sumo_pl *pl;
 	u32 current_index =
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
index 2d44719..2da0e17 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -1926,7 +1926,8 @@
 void trinity_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
 							 struct seq_file *m)
 {
-	struct radeon_ps *rps = rdev->pm.dpm.current_ps;
+	struct trinity_power_info *pi = trinity_get_pi(rdev);
+	struct radeon_ps *rps = &pi->current_rps;
 	struct trinity_ps *ps = trinity_get_ps(rps);
 	struct trinity_pl *pl;
 	u32 current_index =
diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c
index 824550d..d177100 100644
--- a/drivers/gpu/drm/radeon/uvd_v2_2.c
+++ b/drivers/gpu/drm/radeon/uvd_v2_2.c
@@ -57,7 +57,6 @@
 	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_CMD, 0));
 	radeon_ring_write(ring, 2);
-	return;
 }
 
 /**
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 88a5290..c715947 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -104,7 +104,7 @@
 
 static void tegra_drm_lastclose(struct drm_device *drm)
 {
-#ifdef CONFIG_TEGRA_DRM_FBDEV
+#ifdef CONFIG_DRM_TEGRA_FBDEV
 	struct tegra_drm *tegra = drm->dev_private;
 
 	tegra_fbdev_restore_mode(tegra->fbdev);
diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c
index 338f7f6..0266fb4 100644
--- a/drivers/gpu/drm/tegra/rgb.c
+++ b/drivers/gpu/drm/tegra/rgb.c
@@ -15,6 +15,7 @@
 struct tegra_rgb {
 	struct tegra_output output;
 	struct tegra_dc *dc;
+	bool enabled;
 
 	struct clk *clk_parent;
 	struct clk *clk;
@@ -89,6 +90,9 @@
 	struct tegra_rgb *rgb = to_rgb(output);
 	unsigned long value;
 
+	if (rgb->enabled)
+		return 0;
+
 	tegra_dc_write_regs(rgb->dc, rgb_enable, ARRAY_SIZE(rgb_enable));
 
 	value = DE_SELECT_ACTIVE | DE_CONTROL_NORMAL;
@@ -122,6 +126,8 @@
 	tegra_dc_writel(rgb->dc, GENERAL_ACT_REQ << 8, DC_CMD_STATE_CONTROL);
 	tegra_dc_writel(rgb->dc, GENERAL_ACT_REQ, DC_CMD_STATE_CONTROL);
 
+	rgb->enabled = true;
+
 	return 0;
 }
 
@@ -130,6 +136,9 @@
 	struct tegra_rgb *rgb = to_rgb(output);
 	unsigned long value;
 
+	if (!rgb->enabled)
+		return 0;
+
 	value = tegra_dc_readl(rgb->dc, DC_CMD_DISPLAY_POWER_CONTROL);
 	value &= ~(PW0_ENABLE | PW1_ENABLE | PW2_ENABLE | PW3_ENABLE |
 		   PW4_ENABLE | PM0_ENABLE | PM1_ENABLE);
@@ -144,6 +153,8 @@
 
 	tegra_dc_write_regs(rgb->dc, rgb_disable, ARRAY_SIZE(rgb_disable));
 
+	rgb->enabled = false;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 3302f99e..764be36 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -126,6 +126,7 @@
 	agp_be->ttm.func = &ttm_agp_func;
 
 	if (ttm_tt_init(&agp_be->ttm, bdev, size, page_flags, dummy_read_page)) {
+		kfree(agp_be);
 		return NULL;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index a066513..214b799 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -351,9 +351,11 @@
 
 moved:
 	if (bo->evicted) {
-		ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
-		if (ret)
-			pr_err("Can not flush read caches\n");
+		if (bdev->driver->invalidate_caches) {
+			ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
+			if (ret)
+				pr_err("Can not flush read caches\n");
+		}
 		bo->evicted = false;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 801231c..0ce48e5 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -339,11 +339,13 @@
 	vma->vm_private_data = bo;
 
 	/*
-	 * PFNMAP is faster than MIXEDMAP due to reduced page
-	 * administration. So use MIXEDMAP only if private VMA, where
-	 * we need to support COW.
+	 * We'd like to use VM_PFNMAP on shared mappings, where
+	 * (vma->vm_flags & VM_SHARED) != 0, for performance reasons,
+	 * but for some reason VM_PFNMAP + x86 PAT + write-combine is very
+	 * bad for performance. Until that has been sorted out, use
+	 * VM_MIXEDMAP on all mappings. See freedesktop.org bug #75719
 	 */
-	vma->vm_flags |= (vma->vm_flags & VM_SHARED) ? VM_PFNMAP : VM_MIXEDMAP;
+	vma->vm_flags |= VM_MIXEDMAP;
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	return 0;
 out_unref:
@@ -359,7 +361,7 @@
 
 	vma->vm_ops = &ttm_bo_vm_ops;
 	vma->vm_private_data = ttm_bo_reference(bo);
-	vma->vm_flags |= (vma->vm_flags & VM_SHARED) ? VM_PFNMAP : VM_MIXEDMAP;
+	vma->vm_flags |= VM_MIXEDMAP;
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND;
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c
index 3707985..53b51c4 100644
--- a/drivers/gpu/drm/ttm/ttm_object.c
+++ b/drivers/gpu/drm/ttm/ttm_object.c
@@ -292,7 +292,7 @@
 
 		if (ret == 0) {
 			ref = drm_hash_entry(hash, struct ttm_ref_object, hash);
-			if (!kref_get_unless_zero(&ref->kref)) {
+			if (kref_get_unless_zero(&ref->kref)) {
 				rcu_read_unlock();
 				break;
 			}
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 9af9908..75f3190 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -380,6 +380,9 @@
 	pgoff_t i;
 	struct page **page = ttm->pages;
 
+	if (ttm->page_flags & TTM_PAGE_FLAG_SG)
+		return;
+
 	for (i = 0; i < ttm->num_pages; ++i) {
 		(*page)->mapping = NULL;
 		(*page++)->index = 0;
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 8d67b94..0394811 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -177,8 +177,10 @@
 	if (obj->vmapping)
 		udl_gem_vunmap(obj);
 
-	if (gem_obj->import_attach)
+	if (gem_obj->import_attach) {
 		drm_prime_gem_destroy(gem_obj, obj->sg);
+		put_device(gem_obj->dev->dev);
+	}
 
 	if (obj->pages)
 		udl_gem_put_pages(obj);
@@ -256,9 +258,12 @@
 	int ret;
 
 	/* need to attach */
+	get_device(dev->dev);
 	attach = dma_buf_attach(dma_buf, dev->dev);
-	if (IS_ERR(attach))
+	if (IS_ERR(attach)) {
+		put_device(dev->dev);
 		return ERR_CAST(attach);
+	}
 
 	get_dma_buf(dma_buf);
 
@@ -282,6 +287,6 @@
 fail_detach:
 	dma_buf_detach(dma_buf, attach);
 	dma_buf_put(dma_buf);
-
+	put_device(dev->dev);
 	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/vmwgfx/svga3d_reg.h b/drivers/gpu/drm/vmwgfx/svga3d_reg.h
index d95335c..f58dc7d 100644
--- a/drivers/gpu/drm/vmwgfx/svga3d_reg.h
+++ b/drivers/gpu/drm/vmwgfx/svga3d_reg.h
@@ -261,12 +261,7 @@
    /* Planar video formats. */
    SVGA3D_YV12                         = 121,
 
-   /* Shader constant formats. */
-   SVGA3D_SURFACE_SHADERCONST_FLOAT    = 122,
-   SVGA3D_SURFACE_SHADERCONST_INT      = 123,
-   SVGA3D_SURFACE_SHADERCONST_BOOL     = 124,
-
-   SVGA3D_FORMAT_MAX                   = 125,
+   SVGA3D_FORMAT_MAX                   = 122,
 } SVGA3dSurfaceFormat;
 
 typedef uint32 SVGA3dColor; /* a, r, g, b */
@@ -1223,9 +1218,19 @@
 #define SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL 1129
 
 #define SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE  1130
-
+#define SVGA_3D_CMD_GB_SCREEN_DMA               1131
+#define SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH  1132
+#define SVGA_3D_CMD_GB_MOB_FENCE                1133
+#define SVGA_3D_CMD_DEFINE_GB_SURFACE_V2        1134
 #define SVGA_3D_CMD_DEFINE_GB_MOB64          1135
 #define SVGA_3D_CMD_REDEFINE_GB_MOB64        1136
+#define SVGA_3D_CMD_NOP_ERROR                1137
+
+#define SVGA_3D_CMD_RESERVED1                1138
+#define SVGA_3D_CMD_RESERVED2                1139
+#define SVGA_3D_CMD_RESERVED3                1140
+#define SVGA_3D_CMD_RESERVED4                1141
+#define SVGA_3D_CMD_RESERVED5                1142
 
 #define SVGA_3D_CMD_MAX                      1142
 #define SVGA_3D_CMD_FUTURE_MAX               3000
@@ -1973,8 +1978,7 @@
    uint32 sizeInBytes;
    uint32 validSizeInBytes;
    SVGAMobFormat ptDepth;
-}
-__attribute__((__packed__))
+} __packed
 SVGA3dCmdSetOTableBase;  /* SVGA_3D_CMD_SET_OTABLE_BASE */
 
 typedef
@@ -1984,15 +1988,13 @@
    uint32 sizeInBytes;
    uint32 validSizeInBytes;
    SVGAMobFormat ptDepth;
-}
-__attribute__((__packed__))
+} __packed
 SVGA3dCmdSetOTableBase64;  /* SVGA_3D_CMD_SET_OTABLE_BASE64 */
 
 typedef
 struct {
    SVGAOTableType type;
-}
-__attribute__((__packed__))
+} __packed
 SVGA3dCmdReadbackOTable;  /* SVGA_3D_CMD_READBACK_OTABLE */
 
 /*
@@ -2005,8 +2007,7 @@
    SVGAMobFormat ptDepth;
    PPN base;
    uint32 sizeInBytes;
-}
-__attribute__((__packed__))
+} __packed
 SVGA3dCmdDefineGBMob;   /* SVGA_3D_CMD_DEFINE_GB_MOB */
 
 
@@ -2017,8 +2018,7 @@
 typedef
 struct SVGA3dCmdDestroyGBMob {
    SVGAMobId mobid;
-}
-__attribute__((__packed__))
+} __packed
 SVGA3dCmdDestroyGBMob;   /* SVGA_3D_CMD_DESTROY_GB_MOB */
 
 /*
@@ -2031,8 +2031,7 @@
    SVGAMobFormat ptDepth;
    PPN base;
    uint32 sizeInBytes;
-}
-__attribute__((__packed__))
+} __packed
 SVGA3dCmdRedefineGBMob;   /* SVGA_3D_CMD_REDEFINE_GB_MOB */
 
 /*
@@ -2045,8 +2044,7 @@
    SVGAMobFormat ptDepth;
    PPN64 base;
    uint32 sizeInBytes;
-}
-__attribute__((__packed__))
+} __packed
 SVGA3dCmdDefineGBMob64;   /* SVGA_3D_CMD_DEFINE_GB_MOB64 */
 
 /*
@@ -2059,8 +2057,7 @@
    SVGAMobFormat ptDepth;
    PPN64 base;
    uint32 sizeInBytes;
-}
-__attribute__((__packed__))
+} __packed
 SVGA3dCmdRedefineGBMob64;   /* SVGA_3D_CMD_REDEFINE_GB_MOB64 */
 
 /*
@@ -2070,8 +2067,7 @@
 typedef
 struct SVGA3dCmdUpdateGBMobMapping {
    SVGAMobId mobid;
-}
-__attribute__((__packed__))
+} __packed
 SVGA3dCmdUpdateGBMobMapping;   /* SVGA_3D_CMD_UPDATE_GB_MOB_MAPPING */
 
 /*
@@ -2087,7 +2083,8 @@
    uint32 multisampleCount;
    SVGA3dTextureFilter autogenFilter;
    SVGA3dSize size;
-} SVGA3dCmdDefineGBSurface;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE */
+} __packed
+SVGA3dCmdDefineGBSurface;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE */
 
 /*
  * Destroy a guest-backed surface.
@@ -2096,7 +2093,8 @@
 typedef
 struct SVGA3dCmdDestroyGBSurface {
    uint32 sid;
-} SVGA3dCmdDestroyGBSurface;   /* SVGA_3D_CMD_DESTROY_GB_SURFACE */
+} __packed
+SVGA3dCmdDestroyGBSurface;   /* SVGA_3D_CMD_DESTROY_GB_SURFACE */
 
 /*
  * Bind a guest-backed surface to an object.
@@ -2106,7 +2104,8 @@
 struct SVGA3dCmdBindGBSurface {
    uint32 sid;
    SVGAMobId mobid;
-} SVGA3dCmdBindGBSurface;   /* SVGA_3D_CMD_BIND_GB_SURFACE */
+} __packed
+SVGA3dCmdBindGBSurface;   /* SVGA_3D_CMD_BIND_GB_SURFACE */
 
 /*
  * Conditionally bind a mob to a guest backed surface if testMobid
@@ -2123,7 +2122,7 @@
    SVGAMobId testMobid;
    SVGAMobId mobid;
    uint32 flags;
-}
+} __packed
 SVGA3dCmdCondBindGBSurface;          /* SVGA_3D_CMD_COND_BIND_GB_SURFACE */
 
 /*
@@ -2135,7 +2134,8 @@
 struct SVGA3dCmdUpdateGBImage {
    SVGA3dSurfaceImageId image;
    SVGA3dBox box;
-} SVGA3dCmdUpdateGBImage;   /* SVGA_3D_CMD_UPDATE_GB_IMAGE */
+} __packed
+SVGA3dCmdUpdateGBImage;   /* SVGA_3D_CMD_UPDATE_GB_IMAGE */
 
 /*
  * Update an entire guest-backed surface.
@@ -2145,7 +2145,8 @@
 typedef
 struct SVGA3dCmdUpdateGBSurface {
    uint32 sid;
-} SVGA3dCmdUpdateGBSurface;   /* SVGA_3D_CMD_UPDATE_GB_SURFACE */
+} __packed
+SVGA3dCmdUpdateGBSurface;   /* SVGA_3D_CMD_UPDATE_GB_SURFACE */
 
 /*
  * Readback an image in a guest-backed surface.
@@ -2155,7 +2156,8 @@
 typedef
 struct SVGA3dCmdReadbackGBImage {
    SVGA3dSurfaceImageId image;
-} SVGA3dCmdReadbackGBImage;   /* SVGA_3D_CMD_READBACK_GB_IMAGE*/
+} __packed
+SVGA3dCmdReadbackGBImage;   /* SVGA_3D_CMD_READBACK_GB_IMAGE*/
 
 /*
  * Readback an entire guest-backed surface.
@@ -2165,7 +2167,8 @@
 typedef
 struct SVGA3dCmdReadbackGBSurface {
    uint32 sid;
-} SVGA3dCmdReadbackGBSurface;   /* SVGA_3D_CMD_READBACK_GB_SURFACE */
+} __packed
+SVGA3dCmdReadbackGBSurface;   /* SVGA_3D_CMD_READBACK_GB_SURFACE */
 
 /*
  * Readback a sub rect of an image in a guest-backed surface.  After
@@ -2179,7 +2182,7 @@
    SVGA3dSurfaceImageId image;
    SVGA3dBox box;
    uint32 invertBox;
-}
+} __packed
 SVGA3dCmdReadbackGBImagePartial; /* SVGA_3D_CMD_READBACK_GB_IMAGE_PARTIAL */
 
 /*
@@ -2190,7 +2193,8 @@
 typedef
 struct SVGA3dCmdInvalidateGBImage {
    SVGA3dSurfaceImageId image;
-} SVGA3dCmdInvalidateGBImage;   /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE */
+} __packed
+SVGA3dCmdInvalidateGBImage;   /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE */
 
 /*
  * Invalidate an entire guest-backed surface.
@@ -2200,7 +2204,8 @@
 typedef
 struct SVGA3dCmdInvalidateGBSurface {
    uint32 sid;
-} SVGA3dCmdInvalidateGBSurface; /* SVGA_3D_CMD_INVALIDATE_GB_SURFACE */
+} __packed
+SVGA3dCmdInvalidateGBSurface; /* SVGA_3D_CMD_INVALIDATE_GB_SURFACE */
 
 /*
  * Invalidate a sub rect of an image in a guest-backed surface.  After
@@ -2214,7 +2219,7 @@
    SVGA3dSurfaceImageId image;
    SVGA3dBox box;
    uint32 invertBox;
-}
+} __packed
 SVGA3dCmdInvalidateGBImagePartial; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL */
 
 /*
@@ -2224,7 +2229,8 @@
 typedef
 struct SVGA3dCmdDefineGBContext {
    uint32 cid;
-} SVGA3dCmdDefineGBContext;   /* SVGA_3D_CMD_DEFINE_GB_CONTEXT */
+} __packed
+SVGA3dCmdDefineGBContext;   /* SVGA_3D_CMD_DEFINE_GB_CONTEXT */
 
 /*
  * Destroy a guest-backed context.
@@ -2233,7 +2239,8 @@
 typedef
 struct SVGA3dCmdDestroyGBContext {
    uint32 cid;
-} SVGA3dCmdDestroyGBContext;   /* SVGA_3D_CMD_DESTROY_GB_CONTEXT */
+} __packed
+SVGA3dCmdDestroyGBContext;   /* SVGA_3D_CMD_DESTROY_GB_CONTEXT */
 
 /*
  * Bind a guest-backed context.
@@ -2252,7 +2259,8 @@
    uint32 cid;
    SVGAMobId mobid;
    uint32 validContents;
-} SVGA3dCmdBindGBContext;   /* SVGA_3D_CMD_BIND_GB_CONTEXT */
+} __packed
+SVGA3dCmdBindGBContext;   /* SVGA_3D_CMD_BIND_GB_CONTEXT */
 
 /*
  * Readback a guest-backed context.
@@ -2262,7 +2270,8 @@
 typedef
 struct SVGA3dCmdReadbackGBContext {
    uint32 cid;
-} SVGA3dCmdReadbackGBContext;   /* SVGA_3D_CMD_READBACK_GB_CONTEXT */
+} __packed
+SVGA3dCmdReadbackGBContext;   /* SVGA_3D_CMD_READBACK_GB_CONTEXT */
 
 /*
  * Invalidate a guest-backed context.
@@ -2270,7 +2279,8 @@
 typedef
 struct SVGA3dCmdInvalidateGBContext {
    uint32 cid;
-} SVGA3dCmdInvalidateGBContext;   /* SVGA_3D_CMD_INVALIDATE_GB_CONTEXT */
+} __packed
+SVGA3dCmdInvalidateGBContext;   /* SVGA_3D_CMD_INVALIDATE_GB_CONTEXT */
 
 /*
  * Define a guest-backed shader.
@@ -2281,7 +2291,8 @@
    uint32 shid;
    SVGA3dShaderType type;
    uint32 sizeInBytes;
-} SVGA3dCmdDefineGBShader;   /* SVGA_3D_CMD_DEFINE_GB_SHADER */
+} __packed
+SVGA3dCmdDefineGBShader;   /* SVGA_3D_CMD_DEFINE_GB_SHADER */
 
 /*
  * Bind a guest-backed shader.
@@ -2291,7 +2302,8 @@
    uint32 shid;
    SVGAMobId mobid;
    uint32 offsetInBytes;
-} SVGA3dCmdBindGBShader;   /* SVGA_3D_CMD_BIND_GB_SHADER */
+} __packed
+SVGA3dCmdBindGBShader;   /* SVGA_3D_CMD_BIND_GB_SHADER */
 
 /*
  * Destroy a guest-backed shader.
@@ -2299,7 +2311,8 @@
 
 typedef struct SVGA3dCmdDestroyGBShader {
    uint32 shid;
-} SVGA3dCmdDestroyGBShader;   /* SVGA_3D_CMD_DESTROY_GB_SHADER */
+} __packed
+SVGA3dCmdDestroyGBShader;   /* SVGA_3D_CMD_DESTROY_GB_SHADER */
 
 typedef
 struct {
@@ -2314,14 +2327,16 @@
     * Note that FLOAT and INT constants are 4-dwords in length, while
     * BOOL constants are 1-dword in length.
     */
-} SVGA3dCmdSetGBShaderConstInline;
+} __packed
+SVGA3dCmdSetGBShaderConstInline;
 /* SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE */
 
 typedef
 struct {
    uint32               cid;
    SVGA3dQueryType      type;
-} SVGA3dCmdBeginGBQuery;           /* SVGA_3D_CMD_BEGIN_GB_QUERY */
+} __packed
+SVGA3dCmdBeginGBQuery;           /* SVGA_3D_CMD_BEGIN_GB_QUERY */
 
 typedef
 struct {
@@ -2329,7 +2344,8 @@
    SVGA3dQueryType      type;
    SVGAMobId mobid;
    uint32 offset;
-} SVGA3dCmdEndGBQuery;                  /* SVGA_3D_CMD_END_GB_QUERY */
+} __packed
+SVGA3dCmdEndGBQuery;                  /* SVGA_3D_CMD_END_GB_QUERY */
 
 
 /*
@@ -2346,21 +2362,22 @@
    SVGA3dQueryType      type;
    SVGAMobId mobid;
    uint32 offset;
-} SVGA3dCmdWaitForGBQuery;          /* SVGA_3D_CMD_WAIT_FOR_GB_QUERY */
+} __packed
+SVGA3dCmdWaitForGBQuery;          /* SVGA_3D_CMD_WAIT_FOR_GB_QUERY */
 
 typedef
 struct {
    SVGAMobId mobid;
    uint32 fbOffset;
    uint32 initalized;
-}
+} __packed
 SVGA3dCmdEnableGart;              /* SVGA_3D_CMD_ENABLE_GART */
 
 typedef
 struct {
    SVGAMobId mobid;
    uint32 gartOffset;
-}
+} __packed
 SVGA3dCmdMapMobIntoGart;          /* SVGA_3D_CMD_MAP_MOB_INTO_GART */
 
 
@@ -2368,7 +2385,7 @@
 struct {
    uint32 gartOffset;
    uint32 numPages;
-}
+} __packed
 SVGA3dCmdUnmapGartRange;          /* SVGA_3D_CMD_UNMAP_GART_RANGE */
 
 
@@ -2385,27 +2402,27 @@
    int32 xRoot;
    int32 yRoot;
    uint32 flags;
-}
+} __packed
 SVGA3dCmdDefineGBScreenTarget;    /* SVGA_3D_CMD_DEFINE_GB_SCREENTARGET */
 
 typedef
 struct {
    uint32 stid;
-}
+} __packed
 SVGA3dCmdDestroyGBScreenTarget;  /* SVGA_3D_CMD_DESTROY_GB_SCREENTARGET */
 
 typedef
 struct {
    uint32 stid;
    SVGA3dSurfaceImageId image;
-}
+} __packed
 SVGA3dCmdBindGBScreenTarget;  /* SVGA_3D_CMD_BIND_GB_SCREENTARGET */
 
 typedef
 struct {
    uint32 stid;
    SVGA3dBox box;
-}
+} __packed
 SVGA3dCmdUpdateGBScreenTarget;  /* SVGA_3D_CMD_UPDATE_GB_SCREENTARGET */
 
 /*
@@ -2583,4 +2600,28 @@
    float  f;
 } SVGA3dDevCapResult;
 
+typedef enum {
+   SVGA3DCAPS_RECORD_UNKNOWN        = 0,
+   SVGA3DCAPS_RECORD_DEVCAPS_MIN    = 0x100,
+   SVGA3DCAPS_RECORD_DEVCAPS        = 0x100,
+   SVGA3DCAPS_RECORD_DEVCAPS_MAX    = 0x1ff,
+} SVGA3dCapsRecordType;
+
+typedef
+struct SVGA3dCapsRecordHeader {
+   uint32 length;
+   SVGA3dCapsRecordType type;
+}
+SVGA3dCapsRecordHeader;
+
+typedef
+struct SVGA3dCapsRecord {
+   SVGA3dCapsRecordHeader header;
+   uint32 data[1];
+}
+SVGA3dCapsRecord;
+
+
+typedef uint32 SVGA3dCapPair[2];
+
 #endif /* _SVGA3D_REG_H_ */
diff --git a/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h
index 8369c3b..ef33850 100644
--- a/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h
+++ b/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h
@@ -38,8 +38,11 @@
 
 #define DIV_ROUND_UP(x, y)  (((x) + (y) - 1) / (y))
 #define max_t(type, x, y)  ((x) > (y) ? (x) : (y))
+#define min_t(type, x, y)  ((x) < (y) ? (x) : (y))
 #define surf_size_struct SVGA3dSize
 #define u32 uint32
+#define u64 uint64_t
+#define U32_MAX ((u32)~0U)
 
 #endif /* __KERNEL__ */
 
@@ -704,8 +707,8 @@
 
 static inline u32 clamped_umul32(u32 a, u32 b)
 {
-	uint64_t tmp = (uint64_t) a*b;
-	return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp;
+	u64 tmp = (u64) a*b;
+	return (tmp > (u64) U32_MAX) ? U32_MAX : tmp;
 }
 
 static inline const struct svga3d_surface_desc *
@@ -834,7 +837,7 @@
 				  bool cubemap)
 {
 	const struct svga3d_surface_desc *desc = svga3dsurface_get_desc(format);
-	u32 total_size = 0;
+	u64 total_size = 0;
 	u32 mip;
 
 	for (mip = 0; mip < num_mip_levels; mip++) {
@@ -847,7 +850,7 @@
 	if (cubemap)
 		total_size *= SVGA3D_MAX_SURFACE_FACES;
 
-	return total_size;
+	return (u32) min_t(u64, total_size, (u64) U32_MAX);
 }
 
 
diff --git a/drivers/gpu/drm/vmwgfx/svga_reg.h b/drivers/gpu/drm/vmwgfx/svga_reg.h
index 71defa4..11323dd 100644
--- a/drivers/gpu/drm/vmwgfx/svga_reg.h
+++ b/drivers/gpu/drm/vmwgfx/svga_reg.h
@@ -169,10 +169,17 @@
    SVGA_REG_TRACES = 45,            /* Enable trace-based updates even when FIFO is on */
    SVGA_REG_GMRS_MAX_PAGES = 46,    /* Maximum number of 4KB pages for all GMRs */
    SVGA_REG_MEMORY_SIZE = 47,       /* Total dedicated device memory excluding FIFO */
+   SVGA_REG_COMMAND_LOW = 48,       /* Lower 32 bits and submits commands */
+   SVGA_REG_COMMAND_HIGH = 49,      /* Upper 32 bits of command buffer PA */
    SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50,   /* Max primary memory */
    SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51, /* Suggested limit on mob mem */
    SVGA_REG_DEV_CAP = 52,           /* Write dev cap index, read value */
-   SVGA_REG_TOP = 53,               /* Must be 1 more than the last register */
+   SVGA_REG_CMD_PREPEND_LOW = 53,
+   SVGA_REG_CMD_PREPEND_HIGH = 54,
+   SVGA_REG_SCREENTARGET_MAX_WIDTH = 55,
+   SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56,
+   SVGA_REG_MOB_MAX_SIZE = 57,
+   SVGA_REG_TOP = 58,               /* Must be 1 more than the last register */
 
    SVGA_PALETTE_BASE = 1024,        /* Base of SVGA color map */
    /* Next 768 (== 256*3) registers exist for colormap */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
index 82c41da..1e80152 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
@@ -37,7 +37,7 @@
 
 
 
-typedef int (*vmw_scrub_func)(struct vmw_ctx_bindinfo *);
+typedef int (*vmw_scrub_func)(struct vmw_ctx_bindinfo *, bool);
 
 static void vmw_user_context_free(struct vmw_resource *res);
 static struct vmw_resource *
@@ -50,9 +50,11 @@
 				 bool readback,
 				 struct ttm_validate_buffer *val_buf);
 static int vmw_gb_context_destroy(struct vmw_resource *res);
-static int vmw_context_scrub_shader(struct vmw_ctx_bindinfo *bi);
-static int vmw_context_scrub_render_target(struct vmw_ctx_bindinfo *bi);
-static int vmw_context_scrub_texture(struct vmw_ctx_bindinfo *bi);
+static int vmw_context_scrub_shader(struct vmw_ctx_bindinfo *bi, bool rebind);
+static int vmw_context_scrub_render_target(struct vmw_ctx_bindinfo *bi,
+					   bool rebind);
+static int vmw_context_scrub_texture(struct vmw_ctx_bindinfo *bi, bool rebind);
+static void vmw_context_binding_state_scrub(struct vmw_ctx_binding_state *cbs);
 static void vmw_context_binding_state_kill(struct vmw_ctx_binding_state *cbs);
 static uint64_t vmw_user_context_size;
 
@@ -111,10 +113,14 @@
 
 	if (res->func->destroy == vmw_gb_context_destroy) {
 		mutex_lock(&dev_priv->cmdbuf_mutex);
+		mutex_lock(&dev_priv->binding_mutex);
+		(void) vmw_context_binding_state_kill
+			(&container_of(res, struct vmw_user_context, res)->cbs);
 		(void) vmw_gb_context_destroy(res);
 		if (dev_priv->pinned_bo != NULL &&
 		    !dev_priv->query_cid_valid)
 			__vmw_execbuf_release_pinned_bo(dev_priv, NULL);
+		mutex_unlock(&dev_priv->binding_mutex);
 		mutex_unlock(&dev_priv->cmdbuf_mutex);
 		return;
 	}
@@ -328,7 +334,7 @@
 	BUG_ON(bo->mem.mem_type != VMW_PL_MOB);
 
 	mutex_lock(&dev_priv->binding_mutex);
-	vmw_context_binding_state_kill(&uctx->cbs);
+	vmw_context_binding_state_scrub(&uctx->cbs);
 
 	submit_size = sizeof(*cmd2) + (readback ? sizeof(*cmd1) : 0);
 
@@ -378,10 +384,6 @@
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDestroyGBContext body;
 	} *cmd;
-	struct vmw_user_context *uctx =
-		container_of(res, struct vmw_user_context, res);
-
-	BUG_ON(!list_empty(&uctx->cbs.list));
 
 	if (likely(res->id == -1))
 		return 0;
@@ -528,8 +530,9 @@
  * vmw_context_scrub_shader - scrub a shader binding from a context.
  *
  * @bi: single binding information.
+ * @rebind: Whether to issue a bind instead of scrub command.
  */
-static int vmw_context_scrub_shader(struct vmw_ctx_bindinfo *bi)
+static int vmw_context_scrub_shader(struct vmw_ctx_bindinfo *bi, bool rebind)
 {
 	struct vmw_private *dev_priv = bi->ctx->dev_priv;
 	struct {
@@ -548,7 +551,7 @@
 	cmd->header.size = sizeof(cmd->body);
 	cmd->body.cid = bi->ctx->id;
 	cmd->body.type = bi->i1.shader_type;
-	cmd->body.shid = SVGA3D_INVALID_ID;
+	cmd->body.shid = ((rebind) ? bi->res->id : SVGA3D_INVALID_ID);
 	vmw_fifo_commit(dev_priv, sizeof(*cmd));
 
 	return 0;
@@ -559,8 +562,10 @@
  * from a context.
  *
  * @bi: single binding information.
+ * @rebind: Whether to issue a bind instead of scrub command.
  */
-static int vmw_context_scrub_render_target(struct vmw_ctx_bindinfo *bi)
+static int vmw_context_scrub_render_target(struct vmw_ctx_bindinfo *bi,
+					   bool rebind)
 {
 	struct vmw_private *dev_priv = bi->ctx->dev_priv;
 	struct {
@@ -579,7 +584,7 @@
 	cmd->header.size = sizeof(cmd->body);
 	cmd->body.cid = bi->ctx->id;
 	cmd->body.type = bi->i1.rt_type;
-	cmd->body.target.sid = SVGA3D_INVALID_ID;
+	cmd->body.target.sid = ((rebind) ? bi->res->id : SVGA3D_INVALID_ID);
 	cmd->body.target.face = 0;
 	cmd->body.target.mipmap = 0;
 	vmw_fifo_commit(dev_priv, sizeof(*cmd));
@@ -591,11 +596,13 @@
  * vmw_context_scrub_texture - scrub a texture binding from a context.
  *
  * @bi: single binding information.
+ * @rebind: Whether to issue a bind instead of scrub command.
  *
  * TODO: Possibly complement this function with a function that takes
  * a list of texture bindings and combines them to a single command.
  */
-static int vmw_context_scrub_texture(struct vmw_ctx_bindinfo *bi)
+static int vmw_context_scrub_texture(struct vmw_ctx_bindinfo *bi,
+				     bool rebind)
 {
 	struct vmw_private *dev_priv = bi->ctx->dev_priv;
 	struct {
@@ -619,7 +626,7 @@
 	cmd->body.c.cid = bi->ctx->id;
 	cmd->body.s1.stage = bi->i1.texture_stage;
 	cmd->body.s1.name = SVGA3D_TS_BIND_TEXTURE;
-	cmd->body.s1.value = (uint32) SVGA3D_INVALID_ID;
+	cmd->body.s1.value = ((rebind) ? bi->res->id : SVGA3D_INVALID_ID);
 	vmw_fifo_commit(dev_priv, sizeof(*cmd));
 
 	return 0;
@@ -692,6 +699,7 @@
 		vmw_context_binding_drop(loc);
 
 	loc->bi = *bi;
+	loc->bi.scrubbed = false;
 	list_add_tail(&loc->ctx_list, &cbs->list);
 	INIT_LIST_HEAD(&loc->res_list);
 
@@ -727,12 +735,11 @@
 	if (loc->bi.ctx != NULL)
 		vmw_context_binding_drop(loc);
 
-	loc->bi = *bi;
-	list_add_tail(&loc->ctx_list, &cbs->list);
-	if (bi->res != NULL)
+	if (bi->res != NULL) {
+		loc->bi = *bi;
+		list_add_tail(&loc->ctx_list, &cbs->list);
 		list_add_tail(&loc->res_list, &bi->res->binding_head);
-	else
-		INIT_LIST_HEAD(&loc->res_list);
+	}
 }
 
 /**
@@ -746,7 +753,10 @@
  */
 static void vmw_context_binding_kill(struct vmw_ctx_binding *cb)
 {
-	(void) vmw_scrub_funcs[cb->bi.bt](&cb->bi);
+	if (!cb->bi.scrubbed) {
+		(void) vmw_scrub_funcs[cb->bi.bt](&cb->bi, false);
+		cb->bi.scrubbed = true;
+	}
 	vmw_context_binding_drop(cb);
 }
 
@@ -768,6 +778,27 @@
 }
 
 /**
+ * vmw_context_binding_state_scrub - Scrub all bindings associated with a
+ * struct vmw_ctx_binding state structure.
+ *
+ * @cbs: Pointer to the context binding state tracker.
+ *
+ * Emits commands to scrub all bindings associated with the
+ * context binding state tracker.
+ */
+static void vmw_context_binding_state_scrub(struct vmw_ctx_binding_state *cbs)
+{
+	struct vmw_ctx_binding *entry;
+
+	list_for_each_entry(entry, &cbs->list, ctx_list) {
+		if (!entry->bi.scrubbed) {
+			(void) vmw_scrub_funcs[entry->bi.bt](&entry->bi, false);
+			entry->bi.scrubbed = true;
+		}
+	}
+}
+
+/**
  * vmw_context_binding_res_list_kill - Kill all bindings on a
  * resource binding list
  *
@@ -785,6 +816,27 @@
 }
 
 /**
+ * vmw_context_binding_res_list_scrub - Scrub all bindings on a
+ * resource binding list
+ *
+ * @head: list head of resource binding list
+ *
+ * Scrub all bindings associated with a specific resource. Typically
+ * called before the resource is evicted.
+ */
+void vmw_context_binding_res_list_scrub(struct list_head *head)
+{
+	struct vmw_ctx_binding *entry;
+
+	list_for_each_entry(entry, head, res_list) {
+		if (!entry->bi.scrubbed) {
+			(void) vmw_scrub_funcs[entry->bi.bt](&entry->bi, false);
+			entry->bi.scrubbed = true;
+		}
+	}
+}
+
+/**
  * vmw_context_binding_state_transfer - Commit staged binding info
  *
  * @ctx: Pointer to context to commit the staged binding info to.
@@ -803,3 +855,50 @@
 	list_for_each_entry_safe(entry, next, &from->list, ctx_list)
 		vmw_context_binding_transfer(&uctx->cbs, &entry->bi);
 }
+
+/**
+ * vmw_context_rebind_all - Rebind all scrubbed bindings of a context
+ *
+ * @ctx: The context resource
+ *
+ * Walks through the context binding list and rebinds all scrubbed
+ * resources.
+ */
+int vmw_context_rebind_all(struct vmw_resource *ctx)
+{
+	struct vmw_ctx_binding *entry;
+	struct vmw_user_context *uctx =
+		container_of(ctx, struct vmw_user_context, res);
+	struct vmw_ctx_binding_state *cbs = &uctx->cbs;
+	int ret;
+
+	list_for_each_entry(entry, &cbs->list, ctx_list) {
+		if (likely(!entry->bi.scrubbed))
+			continue;
+
+		if (WARN_ON(entry->bi.res == NULL || entry->bi.res->id ==
+			    SVGA3D_INVALID_ID))
+			continue;
+
+		ret = vmw_scrub_funcs[entry->bi.bt](&entry->bi, true);
+		if (unlikely(ret != 0))
+			return ret;
+
+		entry->bi.scrubbed = false;
+	}
+
+	return 0;
+}
+
+/**
+ * vmw_context_binding_list - Return a list of context bindings
+ *
+ * @ctx: The context resource
+ *
+ * Returns the current list of bindings of the given context. Note that
+ * this list becomes stale as soon as the dev_priv::binding_mutex is unlocked.
+ */
+struct list_head *vmw_context_binding_list(struct vmw_resource *ctx)
+{
+	return &(container_of(ctx, struct vmw_user_context, res)->cbs.list);
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 9893328..0083cbf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -667,6 +667,7 @@
 		dev_priv->memory_size = 512*1024*1024;
 	}
 	dev_priv->max_mob_pages = 0;
+	dev_priv->max_mob_size = 0;
 	if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) {
 		uint64_t mem_size =
 			vmw_read(dev_priv,
@@ -676,6 +677,8 @@
 		dev_priv->prim_bb_mem =
 			vmw_read(dev_priv,
 				 SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM);
+		dev_priv->max_mob_size =
+			vmw_read(dev_priv, SVGA_REG_MOB_MAX_SIZE);
 	} else
 		dev_priv->prim_bb_mem = dev_priv->vram_size;
 
@@ -941,6 +944,7 @@
 		drm_master_put(&vmw_fp->locked_master);
 	}
 
+	vmw_compat_shader_man_destroy(vmw_fp->shman);
 	ttm_object_file_release(&vmw_fp->tfile);
 	kfree(vmw_fp);
 }
@@ -960,11 +964,17 @@
 	if (unlikely(vmw_fp->tfile == NULL))
 		goto out_no_tfile;
 
+	vmw_fp->shman = vmw_compat_shader_man_create(dev_priv);
+	if (IS_ERR(vmw_fp->shman))
+		goto out_no_shman;
+
 	file_priv->driver_priv = vmw_fp;
 	dev_priv->bdev.dev_mapping = dev->dev_mapping;
 
 	return 0;
 
+out_no_shman:
+	ttm_object_file_release(&vmw_fp->tfile);
 out_no_tfile:
 	kfree(vmw_fp);
 	return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 554e7fa..0783155 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -40,7 +40,7 @@
 #include <drm/ttm/ttm_module.h>
 #include "vmwgfx_fence.h"
 
-#define VMWGFX_DRIVER_DATE "20121114"
+#define VMWGFX_DRIVER_DATE "20140228"
 #define VMWGFX_DRIVER_MAJOR 2
 #define VMWGFX_DRIVER_MINOR 5
 #define VMWGFX_DRIVER_PATCHLEVEL 0
@@ -75,10 +75,14 @@
 #define VMW_RES_FENCE ttm_driver_type3
 #define VMW_RES_SHADER ttm_driver_type4
 
+struct vmw_compat_shader_manager;
+
 struct vmw_fpriv {
 	struct drm_master *locked_master;
 	struct ttm_object_file *tfile;
 	struct list_head fence_events;
+	bool gb_aware;
+	struct vmw_compat_shader_manager *shman;
 };
 
 struct vmw_dma_buffer {
@@ -272,6 +276,7 @@
 	struct vmw_resource *ctx;
 	struct vmw_resource *res;
 	enum vmw_ctx_binding_type bt;
+	bool scrubbed;
 	union {
 		SVGA3dShaderType shader_type;
 		SVGA3dRenderTargetType rt_type;
@@ -318,7 +323,7 @@
 	struct drm_open_hash res_ht;
 	bool res_ht_initialized;
 	bool kernel; /**< is the called made from the kernel */
-	struct ttm_object_file *tfile;
+	struct vmw_fpriv *fp;
 	struct list_head validate_nodes;
 	struct vmw_relocation relocs[VMWGFX_MAX_RELOCATIONS];
 	uint32_t cur_reloc;
@@ -336,6 +341,7 @@
 	bool needs_post_query_barrier;
 	struct vmw_resource *error_resource;
 	struct vmw_ctx_binding_state staged_bindings;
+	struct list_head staged_shaders;
 };
 
 struct vmw_legacy_display;
@@ -380,6 +386,7 @@
 	uint32_t max_gmr_ids;
 	uint32_t max_gmr_pages;
 	uint32_t max_mob_pages;
+	uint32_t max_mob_size;
 	uint32_t memory_size;
 	bool has_gmr;
 	bool has_mob;
@@ -569,6 +576,8 @@
 
 extern void vmw_resource_unreference(struct vmw_resource **p_res);
 extern struct vmw_resource *vmw_resource_reference(struct vmw_resource *res);
+extern struct vmw_resource *
+vmw_resource_reference_unless_doomed(struct vmw_resource *res);
 extern int vmw_resource_validate(struct vmw_resource *res);
 extern int vmw_resource_reserve(struct vmw_resource *res, bool no_backup);
 extern bool vmw_resource_needs_backup(const struct vmw_resource *res);
@@ -957,6 +966,9 @@
 vmw_context_binding_state_transfer(struct vmw_resource *res,
 				   struct vmw_ctx_binding_state *cbs);
 extern void vmw_context_binding_res_list_kill(struct list_head *head);
+extern void vmw_context_binding_res_list_scrub(struct list_head *head);
+extern int vmw_context_rebind_all(struct vmw_resource *ctx);
+extern struct list_head *vmw_context_binding_list(struct vmw_resource *ctx);
 
 /*
  * Surface management - vmwgfx_surface.c
@@ -991,6 +1003,28 @@
 				   struct drm_file *file_priv);
 extern int vmw_shader_destroy_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *file_priv);
+extern int vmw_compat_shader_lookup(struct vmw_compat_shader_manager *man,
+				    SVGA3dShaderType shader_type,
+				    u32 *user_key);
+extern void vmw_compat_shaders_commit(struct vmw_compat_shader_manager *man,
+				      struct list_head *list);
+extern void vmw_compat_shaders_revert(struct vmw_compat_shader_manager *man,
+				      struct list_head *list);
+extern int vmw_compat_shader_remove(struct vmw_compat_shader_manager *man,
+				    u32 user_key,
+				    SVGA3dShaderType shader_type,
+				    struct list_head *list);
+extern int vmw_compat_shader_add(struct vmw_compat_shader_manager *man,
+				 u32 user_key, const void *bytecode,
+				 SVGA3dShaderType shader_type,
+				 size_t size,
+				 struct ttm_object_file *tfile,
+				 struct list_head *list);
+extern struct vmw_compat_shader_manager *
+vmw_compat_shader_man_create(struct vmw_private *dev_priv);
+extern void
+vmw_compat_shader_man_destroy(struct vmw_compat_shader_manager *man);
+
 
 /**
  * Inline helper functions
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 7a5f1eb..efb575a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -114,8 +114,10 @@
 		 * persistent context binding tracker.
 		 */
 		if (unlikely(val->staged_bindings)) {
-			vmw_context_binding_state_transfer
-				(val->res, val->staged_bindings);
+			if (!backoff) {
+				vmw_context_binding_state_transfer
+					(val->res, val->staged_bindings);
+			}
 			kfree(val->staged_bindings);
 			val->staged_bindings = NULL;
 		}
@@ -178,6 +180,44 @@
 }
 
 /**
+ * vmw_resource_context_res_add - Put resources previously bound to a context on
+ * the validation list
+ *
+ * @dev_priv: Pointer to a device private structure
+ * @sw_context: Pointer to a software context used for this command submission
+ * @ctx: Pointer to the context resource
+ *
+ * This function puts all resources that were previously bound to @ctx on
+ * the resource validation list. This is part of the context state reemission
+ */
+static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
+					struct vmw_sw_context *sw_context,
+					struct vmw_resource *ctx)
+{
+	struct list_head *binding_list;
+	struct vmw_ctx_binding *entry;
+	int ret = 0;
+	struct vmw_resource *res;
+
+	mutex_lock(&dev_priv->binding_mutex);
+	binding_list = vmw_context_binding_list(ctx);
+
+	list_for_each_entry(entry, binding_list, ctx_list) {
+		res = vmw_resource_reference_unless_doomed(entry->bi.res);
+		if (unlikely(res == NULL))
+			continue;
+
+		ret = vmw_resource_val_add(sw_context, entry->bi.res, NULL);
+		vmw_resource_unreference(&res);
+		if (unlikely(ret != 0))
+			break;
+	}
+
+	mutex_unlock(&dev_priv->binding_mutex);
+	return ret;
+}
+
+/**
  * vmw_resource_relocation_add - Add a relocation to the relocation list
  *
  * @list: Pointer to head of relocation list.
@@ -233,8 +273,12 @@
 {
 	struct vmw_resource_relocation *rel;
 
-	list_for_each_entry(rel, list, head)
-		cb[rel->offset] = rel->res->id;
+	list_for_each_entry(rel, list, head) {
+		if (likely(rel->res != NULL))
+			cb[rel->offset] = rel->res->id;
+		else
+			cb[rel->offset] = SVGA_3D_CMD_NOP;
+	}
 }
 
 static int vmw_cmd_invalid(struct vmw_private *dev_priv,
@@ -379,22 +423,27 @@
 }
 
 /**
- * vmw_cmd_res_check - Check that a resource is present and if so, put it
+ * vmw_cmd_compat_res_check - Check that a resource is present and if so, put it
  * on the resource validate list unless it's already there.
  *
  * @dev_priv: Pointer to a device private structure.
  * @sw_context: Pointer to the software context.
  * @res_type: Resource type.
  * @converter: User-space visisble type specific information.
- * @id: Pointer to the location in the command buffer currently being
+ * @id: user-space resource id handle.
+ * @id_loc: Pointer to the location in the command buffer currently being
  * parsed from where the user-space resource id handle is located.
+ * @p_val: Pointer to pointer to resource validalidation node. Populated
+ * on exit.
  */
-static int vmw_cmd_res_check(struct vmw_private *dev_priv,
-			     struct vmw_sw_context *sw_context,
-			     enum vmw_res_type res_type,
-			     const struct vmw_user_resource_conv *converter,
-			     uint32_t *id,
-			     struct vmw_resource_val_node **p_val)
+static int
+vmw_cmd_compat_res_check(struct vmw_private *dev_priv,
+			 struct vmw_sw_context *sw_context,
+			 enum vmw_res_type res_type,
+			 const struct vmw_user_resource_conv *converter,
+			 uint32_t id,
+			 uint32_t *id_loc,
+			 struct vmw_resource_val_node **p_val)
 {
 	struct vmw_res_cache_entry *rcache =
 		&sw_context->res_cache[res_type];
@@ -402,7 +451,7 @@
 	struct vmw_resource_val_node *node;
 	int ret;
 
-	if (*id == SVGA3D_INVALID_ID) {
+	if (id == SVGA3D_INVALID_ID) {
 		if (p_val)
 			*p_val = NULL;
 		if (res_type == vmw_res_context) {
@@ -417,7 +466,7 @@
 	 * resource
 	 */
 
-	if (likely(rcache->valid && *id == rcache->handle)) {
+	if (likely(rcache->valid && id == rcache->handle)) {
 		const struct vmw_resource *res = rcache->res;
 
 		rcache->node->first_usage = false;
@@ -426,28 +475,28 @@
 
 		return vmw_resource_relocation_add
 			(&sw_context->res_relocations, res,
-			 id - sw_context->buf_start);
+			 id_loc - sw_context->buf_start);
 	}
 
 	ret = vmw_user_resource_lookup_handle(dev_priv,
-					      sw_context->tfile,
-					      *id,
+					      sw_context->fp->tfile,
+					      id,
 					      converter,
 					      &res);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use resource 0x%08x.\n",
-			  (unsigned) *id);
+			  (unsigned) id);
 		dump_stack();
 		return ret;
 	}
 
 	rcache->valid = true;
 	rcache->res = res;
-	rcache->handle = *id;
+	rcache->handle = id;
 
 	ret = vmw_resource_relocation_add(&sw_context->res_relocations,
 					  res,
-					  id - sw_context->buf_start);
+					  id_loc - sw_context->buf_start);
 	if (unlikely(ret != 0))
 		goto out_no_reloc;
 
@@ -459,7 +508,11 @@
 	if (p_val)
 		*p_val = node;
 
-	if (node->first_usage && res_type == vmw_res_context) {
+	if (dev_priv->has_mob && node->first_usage &&
+	    res_type == vmw_res_context) {
+		ret = vmw_resource_context_res_add(dev_priv, sw_context, res);
+		if (unlikely(ret != 0))
+			goto out_no_reloc;
 		node->staged_bindings =
 			kzalloc(sizeof(*node->staged_bindings), GFP_KERNEL);
 		if (node->staged_bindings == NULL) {
@@ -481,6 +534,59 @@
 }
 
 /**
+ * vmw_cmd_res_check - Check that a resource is present and if so, put it
+ * on the resource validate list unless it's already there.
+ *
+ * @dev_priv: Pointer to a device private structure.
+ * @sw_context: Pointer to the software context.
+ * @res_type: Resource type.
+ * @converter: User-space visisble type specific information.
+ * @id_loc: Pointer to the location in the command buffer currently being
+ * parsed from where the user-space resource id handle is located.
+ * @p_val: Pointer to pointer to resource validalidation node. Populated
+ * on exit.
+ */
+static int
+vmw_cmd_res_check(struct vmw_private *dev_priv,
+		  struct vmw_sw_context *sw_context,
+		  enum vmw_res_type res_type,
+		  const struct vmw_user_resource_conv *converter,
+		  uint32_t *id_loc,
+		  struct vmw_resource_val_node **p_val)
+{
+	return vmw_cmd_compat_res_check(dev_priv, sw_context, res_type,
+					converter, *id_loc, id_loc, p_val);
+}
+
+/**
+ * vmw_rebind_contexts - Rebind all resources previously bound to
+ * referenced contexts.
+ *
+ * @sw_context: Pointer to the software context.
+ *
+ * Rebind context binding points that have been scrubbed because of eviction.
+ */
+static int vmw_rebind_contexts(struct vmw_sw_context *sw_context)
+{
+	struct vmw_resource_val_node *val;
+	int ret;
+
+	list_for_each_entry(val, &sw_context->resource_list, head) {
+		if (likely(!val->staged_bindings))
+			continue;
+
+		ret = vmw_context_rebind_all(val->res);
+		if (unlikely(ret != 0)) {
+			if (ret != -ERESTARTSYS)
+				DRM_ERROR("Failed to rebind context.\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/**
  * vmw_cmd_cid_check - Check a command header for valid context information.
  *
  * @dev_priv: Pointer to a device private structure.
@@ -496,7 +602,7 @@
 {
 	struct vmw_cid_cmd {
 		SVGA3dCmdHeader header;
-		__le32 cid;
+		uint32_t cid;
 	} *cmd;
 
 	cmd = container_of(header, struct vmw_cid_cmd, header);
@@ -767,7 +873,7 @@
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->tfile, handle, &vmw_bo);
+	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use MOB buffer.\n");
 		return -EINVAL;
@@ -828,7 +934,7 @@
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->tfile, handle, &vmw_bo);
+	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use GMR region.\n");
 		return -EINVAL;
@@ -1127,7 +1233,8 @@
 
 	srf = vmw_res_to_srf(sw_context->res_cache[vmw_res_surface].res);
 
-	vmw_kms_cursor_snoop(srf, sw_context->tfile, &vmw_bo->base, header);
+	vmw_kms_cursor_snoop(srf, sw_context->fp->tfile, &vmw_bo->base,
+			     header);
 
 out_no_surface:
 	vmw_dmabuf_unreference(&vmw_bo);
@@ -1478,6 +1585,98 @@
 				 &cmd->body.sid, NULL);
 }
 
+
+/**
+ * vmw_cmd_shader_define - Validate an SVGA_3D_CMD_SHADER_DEFINE
+ * command
+ *
+ * @dev_priv: Pointer to a device private struct.
+ * @sw_context: The software context being used for this batch.
+ * @header: Pointer to the command header in the command stream.
+ */
+static int vmw_cmd_shader_define(struct vmw_private *dev_priv,
+				 struct vmw_sw_context *sw_context,
+				 SVGA3dCmdHeader *header)
+{
+	struct vmw_shader_define_cmd {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdDefineShader body;
+	} *cmd;
+	int ret;
+	size_t size;
+
+	cmd = container_of(header, struct vmw_shader_define_cmd,
+			   header);
+
+	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_context,
+				user_context_converter, &cmd->body.cid,
+				NULL);
+	if (unlikely(ret != 0))
+		return ret;
+
+	if (unlikely(!dev_priv->has_mob))
+		return 0;
+
+	size = cmd->header.size - sizeof(cmd->body);
+	ret = vmw_compat_shader_add(sw_context->fp->shman,
+				    cmd->body.shid, cmd + 1,
+				    cmd->body.type, size,
+				    sw_context->fp->tfile,
+				    &sw_context->staged_shaders);
+	if (unlikely(ret != 0))
+		return ret;
+
+	return vmw_resource_relocation_add(&sw_context->res_relocations,
+					   NULL, &cmd->header.id -
+					   sw_context->buf_start);
+
+	return 0;
+}
+
+/**
+ * vmw_cmd_shader_destroy - Validate an SVGA_3D_CMD_SHADER_DESTROY
+ * command
+ *
+ * @dev_priv: Pointer to a device private struct.
+ * @sw_context: The software context being used for this batch.
+ * @header: Pointer to the command header in the command stream.
+ */
+static int vmw_cmd_shader_destroy(struct vmw_private *dev_priv,
+				  struct vmw_sw_context *sw_context,
+				  SVGA3dCmdHeader *header)
+{
+	struct vmw_shader_destroy_cmd {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdDestroyShader body;
+	} *cmd;
+	int ret;
+
+	cmd = container_of(header, struct vmw_shader_destroy_cmd,
+			   header);
+
+	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_context,
+				user_context_converter, &cmd->body.cid,
+				NULL);
+	if (unlikely(ret != 0))
+		return ret;
+
+	if (unlikely(!dev_priv->has_mob))
+		return 0;
+
+	ret = vmw_compat_shader_remove(sw_context->fp->shman,
+				       cmd->body.shid,
+				       cmd->body.type,
+				       &sw_context->staged_shaders);
+	if (unlikely(ret != 0))
+		return ret;
+
+	return vmw_resource_relocation_add(&sw_context->res_relocations,
+					   NULL, &cmd->header.id -
+					   sw_context->buf_start);
+
+	return 0;
+}
+
 /**
  * vmw_cmd_set_shader - Validate an SVGA_3D_CMD_SET_SHADER
  * command
@@ -1509,10 +1708,18 @@
 	if (dev_priv->has_mob) {
 		struct vmw_ctx_bindinfo bi;
 		struct vmw_resource_val_node *res_node;
+		u32 shid = cmd->body.shid;
 
-		ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_shader,
-					user_shader_converter,
-					&cmd->body.shid, &res_node);
+		if (shid != SVGA3D_INVALID_ID)
+			(void) vmw_compat_shader_lookup(sw_context->fp->shman,
+							cmd->body.type,
+							&shid);
+
+		ret = vmw_cmd_compat_res_check(dev_priv, sw_context,
+					       vmw_res_shader,
+					       user_shader_converter,
+					       shid,
+					       &cmd->body.shid, &res_node);
 		if (unlikely(ret != 0))
 			return ret;
 
@@ -1527,6 +1734,39 @@
 }
 
 /**
+ * vmw_cmd_set_shader_const - Validate an SVGA_3D_CMD_SET_SHADER_CONST
+ * command
+ *
+ * @dev_priv: Pointer to a device private struct.
+ * @sw_context: The software context being used for this batch.
+ * @header: Pointer to the command header in the command stream.
+ */
+static int vmw_cmd_set_shader_const(struct vmw_private *dev_priv,
+				    struct vmw_sw_context *sw_context,
+				    SVGA3dCmdHeader *header)
+{
+	struct vmw_set_shader_const_cmd {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdSetShaderConst body;
+	} *cmd;
+	int ret;
+
+	cmd = container_of(header, struct vmw_set_shader_const_cmd,
+			   header);
+
+	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_context,
+				user_context_converter, &cmd->body.cid,
+				NULL);
+	if (unlikely(ret != 0))
+		return ret;
+
+	if (dev_priv->has_mob)
+		header->id = SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE;
+
+	return 0;
+}
+
+/**
  * vmw_cmd_bind_gb_shader - Validate an SVGA_3D_CMD_BIND_GB_SHADER
  * command
  *
@@ -1595,7 +1835,7 @@
 	return 0;
 }
 
-static const struct vmw_cmd_entry const vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
+static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
 	VMW_CMD_DEF(SVGA_3D_CMD_SURFACE_DEFINE, &vmw_cmd_invalid,
 		    false, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_SURFACE_DESTROY, &vmw_cmd_invalid,
@@ -1634,14 +1874,14 @@
 		    true, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_PRESENT, &vmw_cmd_present_check,
 		    false, false, false),
-	VMW_CMD_DEF(SVGA_3D_CMD_SHADER_DEFINE, &vmw_cmd_cid_check,
-		    true, true, false),
-	VMW_CMD_DEF(SVGA_3D_CMD_SHADER_DESTROY, &vmw_cmd_cid_check,
-		    true, true, false),
+	VMW_CMD_DEF(SVGA_3D_CMD_SHADER_DEFINE, &vmw_cmd_shader_define,
+		    true, false, false),
+	VMW_CMD_DEF(SVGA_3D_CMD_SHADER_DESTROY, &vmw_cmd_shader_destroy,
+		    true, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_SET_SHADER, &vmw_cmd_set_shader,
 		    true, false, false),
-	VMW_CMD_DEF(SVGA_3D_CMD_SET_SHADER_CONST, &vmw_cmd_cid_check,
-		    true, true, false),
+	VMW_CMD_DEF(SVGA_3D_CMD_SET_SHADER_CONST, &vmw_cmd_set_shader_const,
+		    true, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_DRAW_PRIMITIVES, &vmw_cmd_draw,
 		    true, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_SETSCISSORRECT, &vmw_cmd_cid_check,
@@ -1792,6 +2032,9 @@
 		goto out_invalid;
 
 	entry = &vmw_cmd_entries[cmd_id];
+	if (unlikely(!entry->func))
+		goto out_invalid;
+
 	if (unlikely(!entry->user_allow && !sw_context->kernel))
 		goto out_privileged;
 
@@ -2171,7 +2414,7 @@
 	} else
 		sw_context->kernel = true;
 
-	sw_context->tfile = vmw_fpriv(file_priv)->tfile;
+	sw_context->fp = vmw_fpriv(file_priv);
 	sw_context->cur_reloc = 0;
 	sw_context->cur_val_buf = 0;
 	sw_context->fence_flags = 0;
@@ -2188,16 +2431,17 @@
 			goto out_unlock;
 		sw_context->res_ht_initialized = true;
 	}
+	INIT_LIST_HEAD(&sw_context->staged_shaders);
 
 	INIT_LIST_HEAD(&resource_list);
 	ret = vmw_cmd_check_all(dev_priv, sw_context, kernel_commands,
 				command_size);
 	if (unlikely(ret != 0))
-		goto out_err;
+		goto out_err_nores;
 
 	ret = vmw_resources_reserve(sw_context);
 	if (unlikely(ret != 0))
-		goto out_err;
+		goto out_err_nores;
 
 	ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes);
 	if (unlikely(ret != 0))
@@ -2225,6 +2469,12 @@
 		goto out_err;
 	}
 
+	if (dev_priv->has_mob) {
+		ret = vmw_rebind_contexts(sw_context);
+		if (unlikely(ret != 0))
+			goto out_unlock_binding;
+	}
+
 	cmd = vmw_fifo_reserve(dev_priv, command_size);
 	if (unlikely(cmd == NULL)) {
 		DRM_ERROR("Failed reserving fifo space for commands.\n");
@@ -2276,6 +2526,8 @@
 	}
 
 	list_splice_init(&sw_context->resource_list, &resource_list);
+	vmw_compat_shaders_commit(sw_context->fp->shman,
+				  &sw_context->staged_shaders);
 	mutex_unlock(&dev_priv->cmdbuf_mutex);
 
 	/*
@@ -2289,10 +2541,11 @@
 out_unlock_binding:
 	mutex_unlock(&dev_priv->binding_mutex);
 out_err:
+	ttm_eu_backoff_reservation(&ticket, &sw_context->validate_nodes);
+out_err_nores:
+	vmw_resource_list_unreserve(&sw_context->resource_list, true);
 	vmw_resource_relocations_free(&sw_context->res_relocations);
 	vmw_free_relocations(sw_context);
-	ttm_eu_backoff_reservation(&ticket, &sw_context->validate_nodes);
-	vmw_resource_list_unreserve(&sw_context->resource_list, true);
 	vmw_clear_validations(sw_context);
 	if (unlikely(dev_priv->pinned_bo != NULL &&
 		     !dev_priv->query_cid_valid))
@@ -2301,6 +2554,8 @@
 	list_splice_init(&sw_context->resource_list, &resource_list);
 	error_resource = sw_context->error_resource;
 	sw_context->error_resource = NULL;
+	vmw_compat_shaders_revert(sw_context->fp->shman,
+				  &sw_context->staged_shaders);
 	mutex_unlock(&dev_priv->cmdbuf_mutex);
 
 	/*
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index 116c497..47b7094 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -29,12 +29,18 @@
 #include <drm/vmwgfx_drm.h>
 #include "vmwgfx_kms.h"
 
+struct svga_3d_compat_cap {
+	SVGA3dCapsRecordHeader header;
+	SVGA3dCapPair pairs[SVGA3D_DEVCAP_MAX];
+};
+
 int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv)
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
 	struct drm_vmw_getparam_arg *param =
 	    (struct drm_vmw_getparam_arg *)data;
+	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
 
 	switch (param->param) {
 	case DRM_VMW_PARAM_NUM_STREAMS:
@@ -60,6 +66,11 @@
 		__le32 __iomem *fifo_mem = dev_priv->mmio_virt;
 		const struct vmw_fifo_state *fifo = &dev_priv->fifo;
 
+		if ((dev_priv->capabilities & SVGA_CAP_GBOBJECTS)) {
+			param->value = SVGA3D_HWVERSION_WS8_B1;
+			break;
+		}
+
 		param->value =
 			ioread32(fifo_mem +
 				 ((fifo->capabilities &
@@ -69,19 +80,31 @@
 		break;
 	}
 	case DRM_VMW_PARAM_MAX_SURF_MEMORY:
-		param->value = dev_priv->memory_size;
+		if ((dev_priv->capabilities & SVGA_CAP_GBOBJECTS) &&
+		    !vmw_fp->gb_aware)
+			param->value = dev_priv->max_mob_pages * PAGE_SIZE / 2;
+		else
+			param->value = dev_priv->memory_size;
 		break;
 	case DRM_VMW_PARAM_3D_CAPS_SIZE:
-		if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS)
-			param->value = SVGA3D_DEVCAP_MAX;
+		if ((dev_priv->capabilities & SVGA_CAP_GBOBJECTS) &&
+		    vmw_fp->gb_aware)
+			param->value = SVGA3D_DEVCAP_MAX * sizeof(uint32_t);
+		else if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS)
+			param->value = sizeof(struct svga_3d_compat_cap) +
+				sizeof(uint32_t);
 		else
 			param->value = (SVGA_FIFO_3D_CAPS_LAST -
-					SVGA_FIFO_3D_CAPS + 1);
-		param->value *= sizeof(uint32_t);
+					SVGA_FIFO_3D_CAPS + 1) *
+				sizeof(uint32_t);
 		break;
 	case DRM_VMW_PARAM_MAX_MOB_MEMORY:
+		vmw_fp->gb_aware = true;
 		param->value = dev_priv->max_mob_pages * PAGE_SIZE;
 		break;
+	case DRM_VMW_PARAM_MAX_MOB_SIZE:
+		param->value = dev_priv->max_mob_size;
+		break;
 	default:
 		DRM_ERROR("Illegal vmwgfx get param request: %d\n",
 			  param->param);
@@ -91,6 +114,38 @@
 	return 0;
 }
 
+static int vmw_fill_compat_cap(struct vmw_private *dev_priv, void *bounce,
+			       size_t size)
+{
+	struct svga_3d_compat_cap *compat_cap =
+		(struct svga_3d_compat_cap *) bounce;
+	unsigned int i;
+	size_t pair_offset = offsetof(struct svga_3d_compat_cap, pairs);
+	unsigned int max_size;
+
+	if (size < pair_offset)
+		return -EINVAL;
+
+	max_size = (size - pair_offset) / sizeof(SVGA3dCapPair);
+
+	if (max_size > SVGA3D_DEVCAP_MAX)
+		max_size = SVGA3D_DEVCAP_MAX;
+
+	compat_cap->header.length =
+		(pair_offset + max_size * sizeof(SVGA3dCapPair)) / sizeof(u32);
+	compat_cap->header.type = SVGA3DCAPS_RECORD_DEVCAPS;
+
+	mutex_lock(&dev_priv->hw_mutex);
+	for (i = 0; i < max_size; ++i) {
+		vmw_write(dev_priv, SVGA_REG_DEV_CAP, i);
+		compat_cap->pairs[i][0] = i;
+		compat_cap->pairs[i][1] = vmw_read(dev_priv, SVGA_REG_DEV_CAP);
+	}
+	mutex_unlock(&dev_priv->hw_mutex);
+
+	return 0;
+}
+
 
 int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv)
@@ -104,41 +159,49 @@
 	void *bounce;
 	int ret;
 	bool gb_objects = !!(dev_priv->capabilities & SVGA_CAP_GBOBJECTS);
+	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
 
 	if (unlikely(arg->pad64 != 0)) {
 		DRM_ERROR("Illegal GET_3D_CAP argument.\n");
 		return -EINVAL;
 	}
 
-	if (gb_objects)
-		size = SVGA3D_DEVCAP_MAX;
+	if (gb_objects && vmw_fp->gb_aware)
+		size = SVGA3D_DEVCAP_MAX * sizeof(uint32_t);
+	else if (gb_objects)
+		size = sizeof(struct svga_3d_compat_cap) + sizeof(uint32_t);
 	else
-		size = (SVGA_FIFO_3D_CAPS_LAST - SVGA_FIFO_3D_CAPS + 1);
-
-	size *= sizeof(uint32_t);
+		size = (SVGA_FIFO_3D_CAPS_LAST - SVGA_FIFO_3D_CAPS + 1) *
+			sizeof(uint32_t);
 
 	if (arg->max_size < size)
 		size = arg->max_size;
 
-	bounce = vmalloc(size);
+	bounce = vzalloc(size);
 	if (unlikely(bounce == NULL)) {
 		DRM_ERROR("Failed to allocate bounce buffer for 3D caps.\n");
 		return -ENOMEM;
 	}
 
-	if (gb_objects) {
-		int i;
+	if (gb_objects && vmw_fp->gb_aware) {
+		int i, num;
 		uint32_t *bounce32 = (uint32_t *) bounce;
 
+		num = size / sizeof(uint32_t);
+		if (num > SVGA3D_DEVCAP_MAX)
+			num = SVGA3D_DEVCAP_MAX;
+
 		mutex_lock(&dev_priv->hw_mutex);
-		for (i = 0; i < SVGA3D_DEVCAP_MAX; ++i) {
+		for (i = 0; i < num; ++i) {
 			vmw_write(dev_priv, SVGA_REG_DEV_CAP, i);
 			*bounce32++ = vmw_read(dev_priv, SVGA_REG_DEV_CAP);
 		}
 		mutex_unlock(&dev_priv->hw_mutex);
-
+	} else if (gb_objects) {
+		ret = vmw_fill_compat_cap(dev_priv, bounce, size);
+		if (unlikely(ret != 0))
+			goto out_err;
 	} else {
-
 		fifo_mem = dev_priv->mmio_virt;
 		memcpy_fromio(bounce, &fifo_mem[SVGA_FIFO_3D_CAPS], size);
 	}
@@ -146,6 +209,7 @@
 	ret = copy_to_user(buffer, bounce, size);
 	if (ret)
 		ret = -EFAULT;
+out_err:
 	vfree(bounce);
 
 	if (unlikely(ret != 0))
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index 4910e7b..04a64b8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -134,6 +134,7 @@
 	cmd = vmw_fifo_reserve(dev_priv, sizeof(*cmd));
 	if (unlikely(cmd == NULL)) {
 		DRM_ERROR("Failed reserving FIFO space for OTable setup.\n");
+		ret = -ENOMEM;
 		goto out_no_fifo;
 	}
 
@@ -187,18 +188,20 @@
 
 	bo = otable->page_table->pt_bo;
 	cmd = vmw_fifo_reserve(dev_priv, sizeof(*cmd));
-	if (unlikely(cmd == NULL))
-		DRM_ERROR("Failed reserving FIFO space for OTable setup.\n");
-
-	memset(cmd, 0, sizeof(*cmd));
-	cmd->header.id = SVGA_3D_CMD_SET_OTABLE_BASE;
-	cmd->header.size = sizeof(cmd->body);
-	cmd->body.type = type;
-	cmd->body.baseAddress = 0;
-	cmd->body.sizeInBytes = 0;
-	cmd->body.validSizeInBytes = 0;
-	cmd->body.ptDepth = SVGA3D_MOBFMT_INVALID;
-	vmw_fifo_commit(dev_priv, sizeof(*cmd));
+	if (unlikely(cmd == NULL)) {
+		DRM_ERROR("Failed reserving FIFO space for OTable "
+			  "takedown.\n");
+	} else {
+		memset(cmd, 0, sizeof(*cmd));
+		cmd->header.id = SVGA_3D_CMD_SET_OTABLE_BASE;
+		cmd->header.size = sizeof(cmd->body);
+		cmd->body.type = type;
+		cmd->body.baseAddress = 0;
+		cmd->body.sizeInBytes = 0;
+		cmd->body.validSizeInBytes = 0;
+		cmd->body.ptDepth = SVGA3D_MOBFMT_INVALID;
+		vmw_fifo_commit(dev_priv, sizeof(*cmd));
+	}
 
 	if (bo) {
 		int ret;
@@ -561,11 +564,12 @@
 	if (unlikely(cmd == NULL)) {
 		DRM_ERROR("Failed reserving FIFO space for Memory "
 			  "Object unbinding.\n");
+	} else {
+		cmd->header.id = SVGA_3D_CMD_DESTROY_GB_MOB;
+		cmd->header.size = sizeof(cmd->body);
+		cmd->body.mobid = mob->id;
+		vmw_fifo_commit(dev_priv, sizeof(*cmd));
 	}
-	cmd->header.id = SVGA_3D_CMD_DESTROY_GB_MOB;
-	cmd->header.size = sizeof(cmd->body);
-	cmd->body.mobid = mob->id;
-	vmw_fifo_commit(dev_priv, sizeof(*cmd));
 	if (bo) {
 		vmw_fence_single_bo(bo, NULL);
 		ttm_bo_unreserve(bo);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 6fdd82d..9757b57 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -88,6 +88,11 @@
 	return res;
 }
 
+struct vmw_resource *
+vmw_resource_reference_unless_doomed(struct vmw_resource *res)
+{
+	return kref_get_unless_zero(&res->kref) ? res : NULL;
+}
 
 /**
  * vmw_resource_release_id - release a resource id to the id manager.
@@ -136,8 +141,12 @@
 		vmw_dmabuf_unreference(&res->backup);
 	}
 
-	if (likely(res->hw_destroy != NULL))
+	if (likely(res->hw_destroy != NULL)) {
 		res->hw_destroy(res);
+		mutex_lock(&dev_priv->binding_mutex);
+		vmw_context_binding_res_list_kill(&res->binding_head);
+		mutex_unlock(&dev_priv->binding_mutex);
+	}
 
 	id = res->id;
 	if (res->res_free != NULL)
@@ -418,8 +427,7 @@
 	INIT_LIST_HEAD(&vmw_bo->res_list);
 
 	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
-			  (user) ? ttm_bo_type_device :
-			  ttm_bo_type_kernel, placement,
+			  ttm_bo_type_device, placement,
 			  0, interruptible,
 			  NULL, acc_size, NULL, bo_free);
 	return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index 1457ec4b..ee38565 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -29,6 +29,8 @@
 #include "vmwgfx_resource_priv.h"
 #include "ttm/ttm_placement.h"
 
+#define VMW_COMPAT_SHADER_HT_ORDER 12
+
 struct vmw_shader {
 	struct vmw_resource res;
 	SVGA3dShaderType type;
@@ -40,6 +42,50 @@
 	struct vmw_shader shader;
 };
 
+/**
+ * enum vmw_compat_shader_state - Staging state for compat shaders
+ */
+enum vmw_compat_shader_state {
+	VMW_COMPAT_COMMITED,
+	VMW_COMPAT_ADD,
+	VMW_COMPAT_DEL
+};
+
+/**
+ * struct vmw_compat_shader - Metadata for compat shaders.
+ *
+ * @handle: The TTM handle of the guest backed shader.
+ * @tfile: The struct ttm_object_file the guest backed shader is registered
+ * with.
+ * @hash: Hash item for lookup.
+ * @head: List head for staging lists or the compat shader manager list.
+ * @state: Staging state.
+ *
+ * The structure is protected by the cmdbuf lock.
+ */
+struct vmw_compat_shader {
+	u32 handle;
+	struct ttm_object_file *tfile;
+	struct drm_hash_item hash;
+	struct list_head head;
+	enum vmw_compat_shader_state state;
+};
+
+/**
+ * struct vmw_compat_shader_manager - Compat shader manager.
+ *
+ * @shaders: Hash table containing staged and commited compat shaders
+ * @list: List of commited shaders.
+ * @dev_priv: Pointer to a device private structure.
+ *
+ * @shaders and @list are protected by the cmdbuf mutex for now.
+ */
+struct vmw_compat_shader_manager {
+	struct drm_open_hash shaders;
+	struct list_head list;
+	struct vmw_private *dev_priv;
+};
+
 static void vmw_user_shader_free(struct vmw_resource *res);
 static struct vmw_resource *
 vmw_user_shader_base_to_res(struct ttm_base_object *base);
@@ -258,7 +304,7 @@
 		return 0;
 
 	mutex_lock(&dev_priv->binding_mutex);
-	vmw_context_binding_res_list_kill(&res->binding_head);
+	vmw_context_binding_res_list_scrub(&res->binding_head);
 
 	cmd = vmw_fifo_reserve(dev_priv, sizeof(*cmd));
 	if (unlikely(cmd == NULL)) {
@@ -325,13 +371,81 @@
 					 TTM_REF_USAGE);
 }
 
+static int vmw_shader_alloc(struct vmw_private *dev_priv,
+			    struct vmw_dma_buffer *buffer,
+			    size_t shader_size,
+			    size_t offset,
+			    SVGA3dShaderType shader_type,
+			    struct ttm_object_file *tfile,
+			    u32 *handle)
+{
+	struct vmw_user_shader *ushader;
+	struct vmw_resource *res, *tmp;
+	int ret;
+
+	/*
+	 * Approximate idr memory usage with 128 bytes. It will be limited
+	 * by maximum number_of shaders anyway.
+	 */
+	if (unlikely(vmw_user_shader_size == 0))
+		vmw_user_shader_size =
+			ttm_round_pot(sizeof(struct vmw_user_shader)) + 128;
+
+	ret = ttm_mem_global_alloc(vmw_mem_glob(dev_priv),
+				   vmw_user_shader_size,
+				   false, true);
+	if (unlikely(ret != 0)) {
+		if (ret != -ERESTARTSYS)
+			DRM_ERROR("Out of graphics memory for shader "
+				  "creation.\n");
+		goto out;
+	}
+
+	ushader = kzalloc(sizeof(*ushader), GFP_KERNEL);
+	if (unlikely(ushader == NULL)) {
+		ttm_mem_global_free(vmw_mem_glob(dev_priv),
+				    vmw_user_shader_size);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	res = &ushader->shader.res;
+	ushader->base.shareable = false;
+	ushader->base.tfile = NULL;
+
+	/*
+	 * From here on, the destructor takes over resource freeing.
+	 */
+
+	ret = vmw_gb_shader_init(dev_priv, res, shader_size,
+				 offset, shader_type, buffer,
+				 vmw_user_shader_free);
+	if (unlikely(ret != 0))
+		goto out;
+
+	tmp = vmw_resource_reference(res);
+	ret = ttm_base_object_init(tfile, &ushader->base, false,
+				   VMW_RES_SHADER,
+				   &vmw_user_shader_base_release, NULL);
+
+	if (unlikely(ret != 0)) {
+		vmw_resource_unreference(&tmp);
+		goto out_err;
+	}
+
+	if (handle)
+		*handle = ushader->base.hash.key;
+out_err:
+	vmw_resource_unreference(&res);
+out:
+	return ret;
+}
+
+
 int vmw_shader_define_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv)
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_user_shader *ushader;
-	struct vmw_resource *res;
-	struct vmw_resource *tmp;
 	struct drm_vmw_shader_create_arg *arg =
 		(struct drm_vmw_shader_create_arg *)data;
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
@@ -373,69 +487,326 @@
 		goto out_bad_arg;
 	}
 
-	/*
-	 * Approximate idr memory usage with 128 bytes. It will be limited
-	 * by maximum number_of shaders anyway.
-	 */
-
-	if (unlikely(vmw_user_shader_size == 0))
-		vmw_user_shader_size = ttm_round_pot(sizeof(*ushader))
-			+ 128;
-
 	ret = ttm_read_lock(&vmaster->lock, true);
 	if (unlikely(ret != 0))
-		return ret;
+		goto out_bad_arg;
 
-	ret = ttm_mem_global_alloc(vmw_mem_glob(dev_priv),
-				   vmw_user_shader_size,
-				   false, true);
-	if (unlikely(ret != 0)) {
-		if (ret != -ERESTARTSYS)
-			DRM_ERROR("Out of graphics memory for shader"
-				  " creation.\n");
-		goto out_unlock;
-	}
+	ret = vmw_shader_alloc(dev_priv, buffer, arg->size, arg->offset,
+			       shader_type, tfile, &arg->shader_handle);
 
-	ushader = kzalloc(sizeof(*ushader), GFP_KERNEL);
-	if (unlikely(ushader == NULL)) {
-		ttm_mem_global_free(vmw_mem_glob(dev_priv),
-				    vmw_user_shader_size);
-		ret = -ENOMEM;
-		goto out_unlock;
-	}
-
-	res = &ushader->shader.res;
-	ushader->base.shareable = false;
-	ushader->base.tfile = NULL;
-
-	/*
-	 * From here on, the destructor takes over resource freeing.
-	 */
-
-	ret = vmw_gb_shader_init(dev_priv, res, arg->size,
-				 arg->offset, shader_type, buffer,
-				 vmw_user_shader_free);
-	if (unlikely(ret != 0))
-		goto out_unlock;
-
-	tmp = vmw_resource_reference(res);
-	ret = ttm_base_object_init(tfile, &ushader->base, false,
-				   VMW_RES_SHADER,
-				   &vmw_user_shader_base_release, NULL);
-
-	if (unlikely(ret != 0)) {
-		vmw_resource_unreference(&tmp);
-		goto out_err;
-	}
-
-	arg->shader_handle = ushader->base.hash.key;
-out_err:
-	vmw_resource_unreference(&res);
-out_unlock:
 	ttm_read_unlock(&vmaster->lock);
 out_bad_arg:
 	vmw_dmabuf_unreference(&buffer);
-
 	return ret;
+}
 
+/**
+ * vmw_compat_shader_lookup - Look up a compat shader
+ *
+ * @man: Pointer to the compat shader manager.
+ * @shader_type: The shader type, that combined with the user_key identifies
+ * the shader.
+ * @user_key: On entry, this should be a pointer to the user_key.
+ * On successful exit, it will contain the guest-backed shader's TTM handle.
+ *
+ * Returns 0 on success. Non-zero on failure, in which case the value pointed
+ * to by @user_key is unmodified.
+ */
+int vmw_compat_shader_lookup(struct vmw_compat_shader_manager *man,
+			     SVGA3dShaderType shader_type,
+			     u32 *user_key)
+{
+	struct drm_hash_item *hash;
+	int ret;
+	unsigned long key = *user_key | (shader_type << 24);
+
+	ret = drm_ht_find_item(&man->shaders, key, &hash);
+	if (unlikely(ret != 0))
+		return ret;
+
+	*user_key = drm_hash_entry(hash, struct vmw_compat_shader,
+				   hash)->handle;
+
+	return 0;
+}
+
+/**
+ * vmw_compat_shader_free - Free a compat shader.
+ *
+ * @man: Pointer to the compat shader manager.
+ * @entry: Pointer to a struct vmw_compat_shader.
+ *
+ * Frees a struct vmw_compat_shder entry and drops its reference to the
+ * guest backed shader.
+ */
+static void vmw_compat_shader_free(struct vmw_compat_shader_manager *man,
+				   struct vmw_compat_shader *entry)
+{
+	list_del(&entry->head);
+	WARN_ON(drm_ht_remove_item(&man->shaders, &entry->hash));
+	WARN_ON(ttm_ref_object_base_unref(entry->tfile, entry->handle,
+					  TTM_REF_USAGE));
+	kfree(entry);
+}
+
+/**
+ * vmw_compat_shaders_commit - Commit a list of compat shader actions.
+ *
+ * @man: Pointer to the compat shader manager.
+ * @list: Caller's list of compat shader actions.
+ *
+ * This function commits a list of compat shader additions or removals.
+ * It is typically called when the execbuf ioctl call triggering these
+ * actions has commited the fifo contents to the device.
+ */
+void vmw_compat_shaders_commit(struct vmw_compat_shader_manager *man,
+			       struct list_head *list)
+{
+	struct vmw_compat_shader *entry, *next;
+
+	list_for_each_entry_safe(entry, next, list, head) {
+		list_del(&entry->head);
+		switch (entry->state) {
+		case VMW_COMPAT_ADD:
+			entry->state = VMW_COMPAT_COMMITED;
+			list_add_tail(&entry->head, &man->list);
+			break;
+		case VMW_COMPAT_DEL:
+			ttm_ref_object_base_unref(entry->tfile, entry->handle,
+						  TTM_REF_USAGE);
+			kfree(entry);
+			break;
+		default:
+			BUG();
+			break;
+		}
+	}
+}
+
+/**
+ * vmw_compat_shaders_revert - Revert a list of compat shader actions
+ *
+ * @man: Pointer to the compat shader manager.
+ * @list: Caller's list of compat shader actions.
+ *
+ * This function reverts a list of compat shader additions or removals.
+ * It is typically called when the execbuf ioctl call triggering these
+ * actions failed for some reason, and the command stream was never
+ * submitted.
+ */
+void vmw_compat_shaders_revert(struct vmw_compat_shader_manager *man,
+			       struct list_head *list)
+{
+	struct vmw_compat_shader *entry, *next;
+	int ret;
+
+	list_for_each_entry_safe(entry, next, list, head) {
+		switch (entry->state) {
+		case VMW_COMPAT_ADD:
+			vmw_compat_shader_free(man, entry);
+			break;
+		case VMW_COMPAT_DEL:
+			ret = drm_ht_insert_item(&man->shaders, &entry->hash);
+			list_del(&entry->head);
+			list_add_tail(&entry->head, &man->list);
+			entry->state = VMW_COMPAT_COMMITED;
+			break;
+		default:
+			BUG();
+			break;
+		}
+	}
+}
+
+/**
+ * vmw_compat_shader_remove - Stage a compat shader for removal.
+ *
+ * @man: Pointer to the compat shader manager
+ * @user_key: The key that is used to identify the shader. The key is
+ * unique to the shader type.
+ * @shader_type: Shader type.
+ * @list: Caller's list of staged shader actions.
+ *
+ * This function stages a compat shader for removal and removes the key from
+ * the shader manager's hash table. If the shader was previously only staged
+ * for addition it is completely removed (But the execbuf code may keep a
+ * reference if it was bound to a context between addition and removal). If
+ * it was previously commited to the manager, it is staged for removal.
+ */
+int vmw_compat_shader_remove(struct vmw_compat_shader_manager *man,
+			     u32 user_key, SVGA3dShaderType shader_type,
+			     struct list_head *list)
+{
+	struct vmw_compat_shader *entry;
+	struct drm_hash_item *hash;
+	int ret;
+
+	ret = drm_ht_find_item(&man->shaders, user_key | (shader_type << 24),
+			       &hash);
+	if (likely(ret != 0))
+		return -EINVAL;
+
+	entry = drm_hash_entry(hash, struct vmw_compat_shader, hash);
+
+	switch (entry->state) {
+	case VMW_COMPAT_ADD:
+		vmw_compat_shader_free(man, entry);
+		break;
+	case VMW_COMPAT_COMMITED:
+		(void) drm_ht_remove_item(&man->shaders, &entry->hash);
+		list_del(&entry->head);
+		entry->state = VMW_COMPAT_DEL;
+		list_add_tail(&entry->head, list);
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * vmw_compat_shader_add - Create a compat shader and add the
+ * key to the manager
+ *
+ * @man: Pointer to the compat shader manager
+ * @user_key: The key that is used to identify the shader. The key is
+ * unique to the shader type.
+ * @bytecode: Pointer to the bytecode of the shader.
+ * @shader_type: Shader type.
+ * @tfile: Pointer to a struct ttm_object_file that the guest-backed shader is
+ * to be created with.
+ * @list: Caller's list of staged shader actions.
+ *
+ * Note that only the key is added to the shader manager's hash table.
+ * The shader is not yet added to the shader manager's list of shaders.
+ */
+int vmw_compat_shader_add(struct vmw_compat_shader_manager *man,
+			  u32 user_key, const void *bytecode,
+			  SVGA3dShaderType shader_type,
+			  size_t size,
+			  struct ttm_object_file *tfile,
+			  struct list_head *list)
+{
+	struct vmw_dma_buffer *buf;
+	struct ttm_bo_kmap_obj map;
+	bool is_iomem;
+	struct vmw_compat_shader *compat;
+	u32 handle;
+	int ret;
+
+	if (user_key > ((1 << 24) - 1) || (unsigned) shader_type > 16)
+		return -EINVAL;
+
+	/* Allocate and pin a DMA buffer */
+	buf = kzalloc(sizeof(*buf), GFP_KERNEL);
+	if (unlikely(buf == NULL))
+		return -ENOMEM;
+
+	ret = vmw_dmabuf_init(man->dev_priv, buf, size, &vmw_sys_ne_placement,
+			      true, vmw_dmabuf_bo_free);
+	if (unlikely(ret != 0))
+		goto out;
+
+	ret = ttm_bo_reserve(&buf->base, false, true, false, NULL);
+	if (unlikely(ret != 0))
+		goto no_reserve;
+
+	/* Map and copy shader bytecode. */
+	ret = ttm_bo_kmap(&buf->base, 0, PAGE_ALIGN(size) >> PAGE_SHIFT,
+			  &map);
+	if (unlikely(ret != 0)) {
+		ttm_bo_unreserve(&buf->base);
+		goto no_reserve;
+	}
+
+	memcpy(ttm_kmap_obj_virtual(&map, &is_iomem), bytecode, size);
+	WARN_ON(is_iomem);
+
+	ttm_bo_kunmap(&map);
+	ret = ttm_bo_validate(&buf->base, &vmw_sys_placement, false, true);
+	WARN_ON(ret != 0);
+	ttm_bo_unreserve(&buf->base);
+
+	/* Create a guest-backed shader container backed by the dma buffer */
+	ret = vmw_shader_alloc(man->dev_priv, buf, size, 0, shader_type,
+			       tfile, &handle);
+	vmw_dmabuf_unreference(&buf);
+	if (unlikely(ret != 0))
+		goto no_reserve;
+	/*
+	 * Create a compat shader structure and stage it for insertion
+	 * in the manager
+	 */
+	compat = kzalloc(sizeof(*compat), GFP_KERNEL);
+	if (compat == NULL)
+		goto no_compat;
+
+	compat->hash.key = user_key |  (shader_type << 24);
+	ret = drm_ht_insert_item(&man->shaders, &compat->hash);
+	if (unlikely(ret != 0))
+		goto out_invalid_key;
+
+	compat->state = VMW_COMPAT_ADD;
+	compat->handle = handle;
+	compat->tfile = tfile;
+	list_add_tail(&compat->head, list);
+
+	return 0;
+
+out_invalid_key:
+	kfree(compat);
+no_compat:
+	ttm_ref_object_base_unref(tfile, handle, TTM_REF_USAGE);
+no_reserve:
+out:
+	return ret;
+}
+
+/**
+ * vmw_compat_shader_man_create - Create a compat shader manager
+ *
+ * @dev_priv: Pointer to a device private structure.
+ *
+ * Typically done at file open time. If successful returns a pointer to a
+ * compat shader manager. Otherwise returns an error pointer.
+ */
+struct vmw_compat_shader_manager *
+vmw_compat_shader_man_create(struct vmw_private *dev_priv)
+{
+	struct vmw_compat_shader_manager *man;
+	int ret;
+
+	man = kzalloc(sizeof(*man), GFP_KERNEL);
+	if (man == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	man->dev_priv = dev_priv;
+	INIT_LIST_HEAD(&man->list);
+	ret = drm_ht_create(&man->shaders, VMW_COMPAT_SHADER_HT_ORDER);
+	if (ret == 0)
+		return man;
+
+	kfree(man);
+	return ERR_PTR(ret);
+}
+
+/**
+ * vmw_compat_shader_man_destroy - Destroy a compat shader manager
+ *
+ * @man: Pointer to the shader manager to destroy.
+ *
+ * Typically done at file close time.
+ */
+void vmw_compat_shader_man_destroy(struct vmw_compat_shader_manager *man)
+{
+	struct vmw_compat_shader *entry, *next;
+
+	mutex_lock(&man->dev_priv->cmdbuf_mutex);
+	list_for_each_entry_safe(entry, next, &man->list, head)
+		vmw_compat_shader_free(man, entry);
+
+	mutex_unlock(&man->dev_priv->cmdbuf_mutex);
+	kfree(man);
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 979da1c..e7af580 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -830,6 +830,24 @@
 	if (unlikely(ret != 0))
 		goto out_unlock;
 
+	/*
+	 * A gb-aware client referencing a shared surface will
+	 * expect a backup buffer to be present.
+	 */
+	if (dev_priv->has_mob && req->shareable) {
+		uint32_t backup_handle;
+
+		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
+					    res->backup_size,
+					    true,
+					    &backup_handle,
+					    &res->backup);
+		if (unlikely(ret != 0)) {
+			vmw_resource_unreference(&res);
+			goto out_unlock;
+		}
+	}
+
 	tmp = vmw_resource_reference(&srf->res);
 	ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime,
 				    req->shareable, VMW_RES_SURFACE,
@@ -908,8 +926,8 @@
 	    rep->size_addr;
 
 	if (user_sizes)
-		ret = copy_to_user(user_sizes, srf->sizes,
-				   srf->num_sizes * sizeof(*srf->sizes));
+		ret = copy_to_user(user_sizes, &srf->base_size,
+				   sizeof(srf->base_size));
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("copy_to_user failed %p %u\n",
 			  user_sizes, srf->num_sizes);
@@ -1111,7 +1129,7 @@
 		return 0;
 
 	mutex_lock(&dev_priv->binding_mutex);
-	vmw_context_binding_res_list_kill(&res->binding_head);
+	vmw_context_binding_res_list_scrub(&res->binding_head);
 
 	cmd = vmw_fifo_reserve(dev_priv, sizeof(*cmd));
 	if (unlikely(cmd == NULL)) {
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index 1146e3b..112f27e 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -538,7 +538,7 @@
 
 		g->base = job->gather_addr_phys[i];
 
-		for (j = 0; j < job->num_gathers; j++)
+		for (j = i + 1; j < job->num_gathers; j++)
 			if (job->gathers[j].bo == g->bo)
 				job->gathers[j].handled = true;
 
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 4975581..f822fd2 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -469,6 +469,9 @@
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
 				USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI),
 		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
+				USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS),
+		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_JIS),
 		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ANSI),
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 3bfac3a..cc32a6f 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1679,6 +1679,7 @@
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO) },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AUREAL, USB_DEVICE_ID_AUREAL_W01RN) },
@@ -1779,6 +1780,8 @@
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_USB) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_WIRELESS_OPTICAL_DESKTOP_3_0) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_1) },
diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c
index 8fae6d1..c24908f 100644
--- a/drivers/hid/hid-hyperv.c
+++ b/drivers/hid/hid-hyperv.c
@@ -157,6 +157,7 @@
 	u32			report_desc_size;
 	struct hv_input_dev_info hid_dev_info;
 	struct hid_device       *hid_device;
+	u8			input_buf[HID_MAX_BUFFER_SIZE];
 };
 
 
@@ -256,6 +257,7 @@
 	struct synthhid_msg *hid_msg;
 	struct mousevsc_dev *input_dev = hv_get_drvdata(device);
 	struct synthhid_input_report *input_report;
+	size_t len;
 
 	pipe_msg = (struct pipe_prt_msg *)((unsigned long)packet +
 						(packet->offset8 << 3));
@@ -300,9 +302,12 @@
 			(struct synthhid_input_report *)pipe_msg->data;
 		if (!input_dev->init_complete)
 			break;
-		hid_input_report(input_dev->hid_device,
-				HID_INPUT_REPORT, input_report->buffer,
-				input_report->header.size, 1);
+
+		len = min(input_report->header.size,
+			  (u32)sizeof(input_dev->input_buf));
+		memcpy(input_dev->input_buf, input_report->buffer, len);
+		hid_input_report(input_dev->hid_device, HID_INPUT_REPORT,
+				 input_dev->input_buf, len, 1);
 		break;
 	default:
 		pr_err("unsupported hid msg type - type %d len %d",
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 5a5248f..22f28d6 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -135,6 +135,7 @@
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS   0x023b
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI  0x0255
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO   0x0256
+#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS   0x0257
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI	0x0290
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO	0x0291
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS	0x0292
@@ -240,6 +241,7 @@
 
 #define USB_VENDOR_ID_CYGNAL		0x10c4
 #define USB_DEVICE_ID_CYGNAL_RADIO_SI470X	0x818a
+#define USB_DEVICE_ID_FOCALTECH_FTXXXX_MULTITOUCH	0x81b9
 
 #define USB_DEVICE_ID_CYGNAL_RADIO_SI4713       0x8244
 
@@ -451,6 +453,9 @@
 #define USB_VENDOR_ID_INTEL_1		0x8087
 #define USB_DEVICE_ID_INTEL_HID_SENSOR	0x09fa
 
+#define USB_VENDOR_ID_STM_0             0x0483
+#define USB_DEVICE_ID_STM_HID_SENSOR    0x91d1
+
 #define USB_VENDOR_ID_ION		0x15e4
 #define USB_DEVICE_ID_ICADE		0x0132
 
@@ -619,6 +624,8 @@
 #define USB_DEVICE_ID_MS_PRESENTER_8K_USB	0x0713
 #define USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K	0x0730
 #define USB_DEVICE_ID_MS_COMFORT_MOUSE_4500	0x076c
+#define USB_DEVICE_ID_MS_TOUCH_COVER_2	0x07a7
+#define USB_DEVICE_ID_MS_TYPE_COVER_2	0x07a9
 
 #define USB_VENDOR_ID_MOJO		0x8282
 #define USB_DEVICE_ID_RETRO_ADAPTER	0x3201
@@ -644,6 +651,7 @@
 
 #define USB_VENDOR_ID_NEXIO		0x1870
 #define USB_DEVICE_ID_NEXIO_MULTITOUCH_420	0x010d
+#define USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750	0x0110
 
 #define USB_VENDOR_ID_NEXTWINDOW	0x1926
 #define USB_DEVICE_ID_NEXTWINDOW_TOUCHSCREEN	0x0003
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index d50e731..a713e62 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1178,7 +1178,7 @@
 
 	/* fall back to generic raw-output-report */
 	len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
-	buf = kmalloc(len, GFP_KERNEL);
+	buf = hid_alloc_report_buf(report, GFP_KERNEL);
 	if (!buf)
 		return;
 
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index befe0e3..24883b4 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -43,6 +43,7 @@
 #define G25_REV_MIN 0x22
 #define G27_REV_MAJ 0x12
 #define G27_REV_MIN 0x38
+#define G27_2_REV_MIN 0x39
 
 #define to_hid_device(pdev) container_of(pdev, struct hid_device, dev)
 
@@ -130,6 +131,7 @@
 	{DFP_REV_MAJ,  DFP_REV_MIN,  &native_dfp},	/* Driving Force Pro */
 	{G25_REV_MAJ,  G25_REV_MIN,  &native_g25},	/* G25 */
 	{G27_REV_MAJ,  G27_REV_MIN,  &native_g27},	/* G27 */
+	{G27_REV_MAJ,  G27_2_REV_MIN,  &native_g27},	/* G27 v2 */
 };
 
 /* Recalculates X axis value accordingly to currently selected range */
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index c6ef6ee..404a3a8 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -208,6 +208,10 @@
 		.driver_data = MS_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_COMFORT_MOUSE_4500),
 		.driver_data = MS_DUPLICATE_USAGES },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2),
+		.driver_data = 0 },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2),
+		.driver_data = 0 },
 
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_BT),
 		.driver_data = MS_PRESENTER },
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index f134d73..221d503 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1166,6 +1166,11 @@
 		MT_USB_DEVICE(USB_VENDOR_ID_FLATFROG,
 			USB_DEVICE_ID_MULTITOUCH_3200) },
 
+	/* FocalTech Panels */
+	{ .driver_data = MT_CLS_SERIAL,
+		MT_USB_DEVICE(USB_VENDOR_ID_CYGNAL,
+			USB_DEVICE_ID_FOCALTECH_FTXXXX_MULTITOUCH) },
+
 	/* GeneralTouch panel */
 	{ .driver_data = MT_CLS_GENERALTOUCH_TWOFINGERS,
 		MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index 46f4480..9c22e14 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -665,6 +665,9 @@
 	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, USB_VENDOR_ID_INTEL_1,
 			USB_DEVICE_ID_INTEL_HID_SENSOR),
 			.driver_data = HID_SENSOR_HUB_ENUM_QUIRK},
+	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, USB_VENDOR_ID_STM_0,
+			USB_DEVICE_ID_STM_HID_SENSOR),
+			.driver_data = HID_SENSOR_HUB_ENUM_QUIRK},
 	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, HID_ANY_ID,
 		     HID_ANY_ID) },
 	{ }
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 1235405..2f19b15 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -42,6 +42,7 @@
 #define DUALSHOCK4_CONTROLLER_BT  BIT(6)
 
 #define SONY_LED_SUPPORT (SIXAXIS_CONTROLLER_USB | BUZZ_CONTROLLER | DUALSHOCK4_CONTROLLER_USB)
+#define SONY_FF_SUPPORT (SIXAXIS_CONTROLLER_USB | DUALSHOCK4_CONTROLLER_USB)
 
 #define MAX_LEDS 4
 
@@ -499,6 +500,7 @@
 	__u8 right;
 #endif
 
+	__u8 worker_initialized;
 	__u8 led_state[MAX_LEDS];
 	__u8 led_count;
 };
@@ -993,22 +995,11 @@
 	return input_ff_create_memless(input_dev, NULL, sony_play_effect);
 }
 
-static void sony_destroy_ff(struct hid_device *hdev)
-{
-	struct sony_sc *sc = hid_get_drvdata(hdev);
-
-	cancel_work_sync(&sc->state_worker);
-}
-
 #else
 static int sony_init_ff(struct hid_device *hdev)
 {
 	return 0;
 }
-
-static void sony_destroy_ff(struct hid_device *hdev)
-{
-}
 #endif
 
 static int sony_set_output_report(struct sony_sc *sc, int req_id, int req_size)
@@ -1077,6 +1068,8 @@
 	if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
 		hdev->hid_output_raw_report = sixaxis_usb_output_raw_report;
 		ret = sixaxis_set_operational_usb(hdev);
+
+		sc->worker_initialized = 1;
 		INIT_WORK(&sc->state_worker, sixaxis_state_worker);
 	}
 	else if (sc->quirks & SIXAXIS_CONTROLLER_BT)
@@ -1087,6 +1080,7 @@
 		if (ret < 0)
 			goto err_stop;
 
+		sc->worker_initialized = 1;
 		INIT_WORK(&sc->state_worker, dualshock4_state_worker);
 	} else {
 		ret = 0;
@@ -1101,9 +1095,11 @@
 			goto err_stop;
 	}
 
-	ret = sony_init_ff(hdev);
-	if (ret < 0)
-		goto err_stop;
+	if (sc->quirks & SONY_FF_SUPPORT) {
+		ret = sony_init_ff(hdev);
+		if (ret < 0)
+			goto err_stop;
+	}
 
 	return 0;
 err_stop:
@@ -1120,7 +1116,8 @@
 	if (sc->quirks & SONY_LED_SUPPORT)
 		sony_leds_remove(hdev);
 
-	sony_destroy_ff(hdev);
+	if (sc->worker_initialized)
+		cancel_work_sync(&sc->state_worker);
 
 	hid_hw_stop(hdev);
 }
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index cb0137b..ab24ce2 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -320,13 +320,13 @@
 			hid_hw_close(hidraw->hid);
 			wake_up_interruptible(&hidraw->wait);
 		}
+		device_destroy(hidraw_class,
+			       MKDEV(hidraw_major, hidraw->minor));
 	} else {
 		--hidraw->open;
 	}
 	if (!hidraw->open) {
 		if (!hidraw->exist) {
-			device_destroy(hidraw_class,
-					MKDEV(hidraw_major, hidraw->minor));
 			hidraw_table[hidraw->minor] = NULL;
 			kfree(hidraw);
 		} else {
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index d1f81f5..42eebd1 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -582,7 +582,7 @@
 	int ret;
 	int len = i2c_hid_get_report_length(rep) - 2;
 
-	buf = kzalloc(len, GFP_KERNEL);
+	buf = hid_alloc_report_buf(rep, GFP_KERNEL);
 	if (!buf)
 		return;
 
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 175ec0a..dbd8387 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -74,6 +74,7 @@
 	{ USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GX680R_LED_PANEL, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_NEXIO, USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_NOVATEK, USB_DEVICE_ID_NOVATEK_MOUSE, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN1, HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index af6edf9..f2d7bf9 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -67,7 +67,6 @@
 	int ret = 0;
 	struct vmbus_channel_initiate_contact *msg;
 	unsigned long flags;
-	int t;
 
 	init_completion(&msginfo->waitevent);
 
@@ -78,6 +77,8 @@
 	msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
 	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
 	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
+	if (version == VERSION_WIN8)
+		msg->target_vcpu = hv_context.vp_index[smp_processor_id()];
 
 	/*
 	 * Add to list before we send the request since we may
@@ -100,15 +101,7 @@
 	}
 
 	/* Wait for the connection response */
-	t =  wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
-	if (t == 0) {
-		spin_lock_irqsave(&vmbus_connection.channelmsg_lock,
-				flags);
-		list_del(&msginfo->msglistentry);
-		spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock,
-					flags);
-		return -ETIMEDOUT;
-	}
+	wait_for_completion(&msginfo->waitevent);
 
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&msginfo->msglistentry);
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index f6ca3b2..5ce43d8 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -650,6 +650,7 @@
 config SENSORS_LM75
 	tristate "National Semiconductor LM75 and compatibles"
 	depends on I2C
+	depends on THERMAL || !THERMAL_OF
 	help
 	  If you say yes here you get support for one common type of
 	  temperature sensor chip, with models including:
@@ -1285,6 +1286,7 @@
 config SENSORS_TMP102
 	tristate "Texas Instruments TMP102"
 	depends on I2C
+	depends on THERMAL || !THERMAL_OF
 	help
 	  If you say yes here you get support for Texas Instruments TMP102
 	  sensor chips.
diff --git a/drivers/hwmon/da9055-hwmon.c b/drivers/hwmon/da9055-hwmon.c
index 029ecab..73b3865 100644
--- a/drivers/hwmon/da9055-hwmon.c
+++ b/drivers/hwmon/da9055-hwmon.c
@@ -278,10 +278,6 @@
 	if (hwmon_irq < 0)
 		return hwmon_irq;
 
-	hwmon_irq = regmap_irq_get_virq(hwmon->da9055->irq_data, hwmon_irq);
-	if (hwmon_irq < 0)
-		return hwmon_irq;
-
 	ret = devm_request_threaded_irq(&pdev->dev, hwmon_irq,
 					NULL, da9055_auxadc_irq,
 					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
diff --git a/drivers/hwmon/max1668.c b/drivers/hwmon/max1668.c
index a762635..029b65e 100644
--- a/drivers/hwmon/max1668.c
+++ b/drivers/hwmon/max1668.c
@@ -243,7 +243,7 @@
 	data->temp_min[index] = clamp_val(temp/1000, -128, 127);
 	if (i2c_smbus_write_byte_data(client,
 					MAX1668_REG_LIML_WR(index),
-					data->temp_max[index]))
+					data->temp_min[index]))
 		count = -EIO;
 	mutex_unlock(&data->update_lock);
 
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index 8c23203..8a17f01 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -145,7 +145,7 @@
 static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
 {
 	struct iio_channel *channel = pdata->chan;
-	unsigned int result;
+	s64 result;
 	int val, ret;
 
 	ret = iio_read_channel_raw(channel, &val);
@@ -155,10 +155,10 @@
 	}
 
 	/* unit: mV */
-	result = pdata->pullup_uv * val;
+	result = pdata->pullup_uv * (s64) val;
 	result >>= 12;
 
-	return result;
+	return (int)result;
 }
 
 static const struct of_device_id ntc_match[] = {
diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index 3cbf66e..291d11f 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -90,7 +90,8 @@
 
 	u32 flags;		/* from platform data */
 
-	int exponent;		/* linear mode: exponent for output voltages */
+	int exponent[PMBUS_PAGES];
+				/* linear mode: exponent for output voltages */
 
 	const struct pmbus_driver_info *info;
 
@@ -410,7 +411,7 @@
 	long val;
 
 	if (sensor->class == PSC_VOLTAGE_OUT) {	/* LINEAR16 */
-		exponent = data->exponent;
+		exponent = data->exponent[sensor->page];
 		mantissa = (u16) sensor->data;
 	} else {				/* LINEAR11 */
 		exponent = ((s16)sensor->data) >> 11;
@@ -516,7 +517,7 @@
 #define MIN_MANTISSA	(511 * 1000)
 
 static u16 pmbus_data2reg_linear(struct pmbus_data *data,
-				 enum pmbus_sensor_classes class, long val)
+				 struct pmbus_sensor *sensor, long val)
 {
 	s16 exponent = 0, mantissa;
 	bool negative = false;
@@ -525,7 +526,7 @@
 	if (val == 0)
 		return 0;
 
-	if (class == PSC_VOLTAGE_OUT) {
+	if (sensor->class == PSC_VOLTAGE_OUT) {
 		/* LINEAR16 does not support negative voltages */
 		if (val < 0)
 			return 0;
@@ -534,10 +535,10 @@
 		 * For a static exponents, we don't have a choice
 		 * but to adjust the value to it.
 		 */
-		if (data->exponent < 0)
-			val <<= -data->exponent;
+		if (data->exponent[sensor->page] < 0)
+			val <<= -data->exponent[sensor->page];
 		else
-			val >>= data->exponent;
+			val >>= data->exponent[sensor->page];
 		val = DIV_ROUND_CLOSEST(val, 1000);
 		return val & 0xffff;
 	}
@@ -548,14 +549,14 @@
 	}
 
 	/* Power is in uW. Convert to mW before converting. */
-	if (class == PSC_POWER)
+	if (sensor->class == PSC_POWER)
 		val = DIV_ROUND_CLOSEST(val, 1000L);
 
 	/*
 	 * For simplicity, convert fan data to milli-units
 	 * before calculating the exponent.
 	 */
-	if (class == PSC_FAN)
+	if (sensor->class == PSC_FAN)
 		val = val * 1000;
 
 	/* Reduce large mantissa until it fits into 10 bit */
@@ -585,22 +586,22 @@
 }
 
 static u16 pmbus_data2reg_direct(struct pmbus_data *data,
-				 enum pmbus_sensor_classes class, long val)
+				 struct pmbus_sensor *sensor, long val)
 {
 	long m, b, R;
 
-	m = data->info->m[class];
-	b = data->info->b[class];
-	R = data->info->R[class];
+	m = data->info->m[sensor->class];
+	b = data->info->b[sensor->class];
+	R = data->info->R[sensor->class];
 
 	/* Power is in uW. Adjust R and b. */
-	if (class == PSC_POWER) {
+	if (sensor->class == PSC_POWER) {
 		R -= 3;
 		b *= 1000;
 	}
 
 	/* Calculate Y = (m * X + b) * 10^R */
-	if (class != PSC_FAN) {
+	if (sensor->class != PSC_FAN) {
 		R -= 3;		/* Adjust R and b for data in milli-units */
 		b *= 1000;
 	}
@@ -619,7 +620,7 @@
 }
 
 static u16 pmbus_data2reg_vid(struct pmbus_data *data,
-			      enum pmbus_sensor_classes class, long val)
+			      struct pmbus_sensor *sensor, long val)
 {
 	val = clamp_val(val, 500, 1600);
 
@@ -627,20 +628,20 @@
 }
 
 static u16 pmbus_data2reg(struct pmbus_data *data,
-			  enum pmbus_sensor_classes class, long val)
+			  struct pmbus_sensor *sensor, long val)
 {
 	u16 regval;
 
-	switch (data->info->format[class]) {
+	switch (data->info->format[sensor->class]) {
 	case direct:
-		regval = pmbus_data2reg_direct(data, class, val);
+		regval = pmbus_data2reg_direct(data, sensor, val);
 		break;
 	case vid:
-		regval = pmbus_data2reg_vid(data, class, val);
+		regval = pmbus_data2reg_vid(data, sensor, val);
 		break;
 	case linear:
 	default:
-		regval = pmbus_data2reg_linear(data, class, val);
+		regval = pmbus_data2reg_linear(data, sensor, val);
 		break;
 	}
 	return regval;
@@ -746,7 +747,7 @@
 		return -EINVAL;
 
 	mutex_lock(&data->update_lock);
-	regval = pmbus_data2reg(data, sensor->class, val);
+	regval = pmbus_data2reg(data, sensor, val);
 	ret = _pmbus_write_word_data(client, sensor->page, sensor->reg, regval);
 	if (ret < 0)
 		rv = ret;
@@ -1643,12 +1644,13 @@
  * This function is called for all chips.
  */
 static int pmbus_identify_common(struct i2c_client *client,
-				 struct pmbus_data *data)
+				 struct pmbus_data *data, int page)
 {
 	int vout_mode = -1;
 
-	if (pmbus_check_byte_register(client, 0, PMBUS_VOUT_MODE))
-		vout_mode = _pmbus_read_byte_data(client, 0, PMBUS_VOUT_MODE);
+	if (pmbus_check_byte_register(client, page, PMBUS_VOUT_MODE))
+		vout_mode = _pmbus_read_byte_data(client, page,
+						  PMBUS_VOUT_MODE);
 	if (vout_mode >= 0 && vout_mode != 0xff) {
 		/*
 		 * Not all chips support the VOUT_MODE command,
@@ -1659,7 +1661,7 @@
 			if (data->info->format[PSC_VOLTAGE_OUT] != linear)
 				return -ENODEV;
 
-			data->exponent = ((s8)(vout_mode << 3)) >> 3;
+			data->exponent[page] = ((s8)(vout_mode << 3)) >> 3;
 			break;
 		case 1: /* VID mode         */
 			if (data->info->format[PSC_VOLTAGE_OUT] != vid)
@@ -1674,7 +1676,7 @@
 		}
 	}
 
-	pmbus_clear_fault_page(client, 0);
+	pmbus_clear_fault_page(client, page);
 	return 0;
 }
 
@@ -1682,7 +1684,7 @@
 			     struct pmbus_driver_info *info)
 {
 	struct device *dev = &client->dev;
-	int ret;
+	int page, ret;
 
 	/*
 	 * Some PMBus chips don't support PMBUS_STATUS_BYTE, so try
@@ -1715,10 +1717,12 @@
 		return -ENODEV;
 	}
 
-	ret = pmbus_identify_common(client, data);
-	if (ret < 0) {
-		dev_err(dev, "Failed to identify chip capabilities\n");
-		return ret;
+	for (page = 0; page < info->pages; page++) {
+		ret = pmbus_identify_common(client, data, page);
+		if (ret < 0) {
+			dev_err(dev, "Failed to identify chip capabilities\n");
+			return ret;
+		}
 	}
 	return 0;
 }
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index f5ed031..de17c55 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -387,7 +387,7 @@
 
 config I2C_CPM
 	tristate "Freescale CPM1 or CPM2 (MPC8xx/826x)"
-	depends on (CPM1 || CPM2) && OF_I2C
+	depends on CPM1 || CPM2
 	help
 	  This supports the use of the I2C interface on Freescale
 	  processors with CPM1 or CPM2.
diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c
index be7f0a2..f3b89a4 100644
--- a/drivers/i2c/busses/i2c-cpm.c
+++ b/drivers/i2c/busses/i2c-cpm.c
@@ -39,7 +39,9 @@
 #include <linux/i2c.h>
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
+#include <linux/of_address.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <sysdev/fsl_soc.h>
 #include <asm/cpm.h>
diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c
index b8c5187..d52d849 100644
--- a/drivers/i2c/busses/i2c-mv64xxx.c
+++ b/drivers/i2c/busses/i2c-mv64xxx.c
@@ -97,7 +97,6 @@
 enum {
 	MV64XXX_I2C_ACTION_INVALID,
 	MV64XXX_I2C_ACTION_CONTINUE,
-	MV64XXX_I2C_ACTION_OFFLOAD_SEND_START,
 	MV64XXX_I2C_ACTION_SEND_START,
 	MV64XXX_I2C_ACTION_SEND_RESTART,
 	MV64XXX_I2C_ACTION_OFFLOAD_RESTART,
@@ -204,6 +203,9 @@
 	unsigned long ctrl_reg;
 	struct i2c_msg *msg = drv_data->msgs;
 
+	if (!drv_data->offload_enabled)
+		return -EOPNOTSUPP;
+
 	drv_data->msg = msg;
 	drv_data->byte_posn = 0;
 	drv_data->bytes_left = msg->len;
@@ -433,8 +435,7 @@
 
 		drv_data->msgs++;
 		drv_data->num_msgs--;
-		if (!(drv_data->offload_enabled &&
-				mv64xxx_i2c_offload_msg(drv_data))) {
+		if (mv64xxx_i2c_offload_msg(drv_data) < 0) {
 			drv_data->cntl_bits |= MV64XXX_I2C_REG_CONTROL_START;
 			writel(drv_data->cntl_bits,
 			drv_data->reg_base + drv_data->reg_offsets.control);
@@ -458,15 +459,14 @@
 			drv_data->reg_base + drv_data->reg_offsets.control);
 		break;
 
-	case MV64XXX_I2C_ACTION_OFFLOAD_SEND_START:
-		if (!mv64xxx_i2c_offload_msg(drv_data))
-			break;
-		else
-			drv_data->action = MV64XXX_I2C_ACTION_SEND_START;
-		/* FALLTHRU */
 	case MV64XXX_I2C_ACTION_SEND_START:
-		writel(drv_data->cntl_bits | MV64XXX_I2C_REG_CONTROL_START,
-			drv_data->reg_base + drv_data->reg_offsets.control);
+		/* Can we offload this msg ? */
+		if (mv64xxx_i2c_offload_msg(drv_data) < 0) {
+			/* No, switch to standard path */
+			mv64xxx_i2c_prepare_for_io(drv_data, drv_data->msgs);
+			writel(drv_data->cntl_bits | MV64XXX_I2C_REG_CONTROL_START,
+				drv_data->reg_base + drv_data->reg_offsets.control);
+		}
 		break;
 
 	case MV64XXX_I2C_ACTION_SEND_ADDR_1:
@@ -625,15 +625,10 @@
 	unsigned long	flags;
 
 	spin_lock_irqsave(&drv_data->lock, flags);
-	if (drv_data->offload_enabled) {
-		drv_data->action = MV64XXX_I2C_ACTION_OFFLOAD_SEND_START;
-		drv_data->state = MV64XXX_I2C_STATE_WAITING_FOR_START_COND;
-	} else {
-		mv64xxx_i2c_prepare_for_io(drv_data, msg);
 
-		drv_data->action = MV64XXX_I2C_ACTION_SEND_START;
-		drv_data->state = MV64XXX_I2C_STATE_WAITING_FOR_START_COND;
-	}
+	drv_data->action = MV64XXX_I2C_ACTION_SEND_START;
+	drv_data->state = MV64XXX_I2C_STATE_WAITING_FOR_START_COND;
+
 	drv_data->send_stop = is_last;
 	drv_data->block = 1;
 	mv64xxx_i2c_do_action(drv_data);
diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c
index 3bec922..bfec313 100644
--- a/drivers/iio/accel/bma180.c
+++ b/drivers/iio/accel/bma180.c
@@ -447,14 +447,14 @@
 	{ },
 };
 
-#define BMA180_CHANNEL(_index) {					\
+#define BMA180_CHANNEL(_axis) {					\
 	.type = IIO_ACCEL,						\
-	.indexed = 1,							\
-	.channel = (_index),						\
+	.modified = 1,							\
+	.channel2 = IIO_MOD_##_axis,					\
 	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |			\
 		BIT(IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY),	\
 	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),		\
-	.scan_index = (_index),						\
+	.scan_index = AXIS_##_axis,					\
 	.scan_type = {							\
 		.sign = 's',						\
 		.realbits = 14,						\
@@ -465,10 +465,10 @@
 }
 
 static const struct iio_chan_spec bma180_channels[] = {
-	BMA180_CHANNEL(AXIS_X),
-	BMA180_CHANNEL(AXIS_Y),
-	BMA180_CHANNEL(AXIS_Z),
-	IIO_CHAN_SOFT_TIMESTAMP(4),
+	BMA180_CHANNEL(X),
+	BMA180_CHANNEL(Y),
+	BMA180_CHANNEL(Z),
+	IIO_CHAN_SOFT_TIMESTAMP(3),
 };
 
 static irqreturn_t bma180_trigger_handler(int irq, void *p)
diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c
index e283f2f..3602592 100644
--- a/drivers/iio/adc/max1363.c
+++ b/drivers/iio/adc/max1363.c
@@ -1560,7 +1560,7 @@
 	st->client = client;
 
 	st->vref_uv = st->chip_info->int_vref_mv * 1000;
-	vref = devm_regulator_get(&client->dev, "vref");
+	vref = devm_regulator_get_optional(&client->dev, "vref");
 	if (!IS_ERR(vref)) {
 		int vref_uv;
 
diff --git a/drivers/iio/gyro/Kconfig b/drivers/iio/gyro/Kconfig
index 41c64a4..ac2d69e 100644
--- a/drivers/iio/gyro/Kconfig
+++ b/drivers/iio/gyro/Kconfig
@@ -70,7 +70,7 @@
 	select IIO_TRIGGERED_BUFFER if (IIO_BUFFER)
 	help
 	  Say yes here to build support for STMicroelectronics gyroscopes:
-	  L3G4200D, LSM330DL, L3GD20, L3GD20H, LSM330DLC, L3G4IS, LSM330.
+	  L3G4200D, LSM330DL, L3GD20, LSM330DLC, L3G4IS, LSM330.
 
 	  This driver can also be built as a module. If so, these modules
 	  will be created:
diff --git a/drivers/iio/gyro/st_gyro.h b/drivers/iio/gyro/st_gyro.h
index f8f2bf8..c197360 100644
--- a/drivers/iio/gyro/st_gyro.h
+++ b/drivers/iio/gyro/st_gyro.h
@@ -19,7 +19,6 @@
 #define LSM330DL_GYRO_DEV_NAME		"lsm330dl_gyro"
 #define LSM330DLC_GYRO_DEV_NAME		"lsm330dlc_gyro"
 #define L3GD20_GYRO_DEV_NAME		"l3gd20"
-#define L3GD20H_GYRO_DEV_NAME		"l3gd20h"
 #define L3G4IS_GYRO_DEV_NAME		"l3g4is_ui"
 #define LSM330_GYRO_DEV_NAME		"lsm330_gyro"
 
diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c
index d53d91a..a8e174a 100644
--- a/drivers/iio/gyro/st_gyro_core.c
+++ b/drivers/iio/gyro/st_gyro_core.c
@@ -167,11 +167,10 @@
 		.wai = ST_GYRO_2_WAI_EXP,
 		.sensors_supported = {
 			[0] = L3GD20_GYRO_DEV_NAME,
-			[1] = L3GD20H_GYRO_DEV_NAME,
-			[2] = LSM330D_GYRO_DEV_NAME,
-			[3] = LSM330DLC_GYRO_DEV_NAME,
-			[4] = L3G4IS_GYRO_DEV_NAME,
-			[5] = LSM330_GYRO_DEV_NAME,
+			[1] = LSM330D_GYRO_DEV_NAME,
+			[2] = LSM330DLC_GYRO_DEV_NAME,
+			[3] = L3G4IS_GYRO_DEV_NAME,
+			[4] = LSM330_GYRO_DEV_NAME,
 		},
 		.ch = (struct iio_chan_spec *)st_gyro_16bit_channels,
 		.odr = {
diff --git a/drivers/iio/gyro/st_gyro_i2c.c b/drivers/iio/gyro/st_gyro_i2c.c
index 16b8b8d..23c12f3 100644
--- a/drivers/iio/gyro/st_gyro_i2c.c
+++ b/drivers/iio/gyro/st_gyro_i2c.c
@@ -55,7 +55,6 @@
 	{ LSM330DL_GYRO_DEV_NAME },
 	{ LSM330DLC_GYRO_DEV_NAME },
 	{ L3GD20_GYRO_DEV_NAME },
-	{ L3GD20H_GYRO_DEV_NAME },
 	{ L3G4IS_GYRO_DEV_NAME },
 	{ LSM330_GYRO_DEV_NAME },
 	{},
diff --git a/drivers/iio/gyro/st_gyro_spi.c b/drivers/iio/gyro/st_gyro_spi.c
index 94763e2..b4ad3be 100644
--- a/drivers/iio/gyro/st_gyro_spi.c
+++ b/drivers/iio/gyro/st_gyro_spi.c
@@ -54,7 +54,6 @@
 	{ LSM330DL_GYRO_DEV_NAME },
 	{ LSM330DLC_GYRO_DEV_NAME },
 	{ L3GD20_GYRO_DEV_NAME },
-	{ L3GD20H_GYRO_DEV_NAME },
 	{ L3G4IS_GYRO_DEV_NAME },
 	{ LSM330_GYRO_DEV_NAME },
 	{},
diff --git a/drivers/iio/imu/adis16400.h b/drivers/iio/imu/adis16400.h
index 2f8f9d6..0916bf6 100644
--- a/drivers/iio/imu/adis16400.h
+++ b/drivers/iio/imu/adis16400.h
@@ -189,6 +189,7 @@
 	ADIS16300_SCAN_INCLI_X,
 	ADIS16300_SCAN_INCLI_Y,
 	ADIS16400_SCAN_ADC,
+	ADIS16400_SCAN_TIMESTAMP,
 };
 
 #ifdef CONFIG_IIO_BUFFER
diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c
index 368660d..7c582f7 100644
--- a/drivers/iio/imu/adis16400_core.c
+++ b/drivers/iio/imu/adis16400_core.c
@@ -632,7 +632,7 @@
 	ADIS16400_MAGN_CHAN(Z, ADIS16400_ZMAGN_OUT, 14),
 	ADIS16400_TEMP_CHAN(ADIS16400_TEMP_OUT, 12),
 	ADIS16400_AUX_ADC_CHAN(ADIS16400_AUX_ADC, 12),
-	IIO_CHAN_SOFT_TIMESTAMP(12)
+	IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
 };
 
 static const struct iio_chan_spec adis16448_channels[] = {
@@ -659,7 +659,7 @@
 		},
 	},
 	ADIS16400_TEMP_CHAN(ADIS16448_TEMP_OUT, 12),
-	IIO_CHAN_SOFT_TIMESTAMP(11)
+	IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
 };
 
 static const struct iio_chan_spec adis16350_channels[] = {
@@ -677,7 +677,7 @@
 	ADIS16400_MOD_TEMP_CHAN(X, ADIS16350_XTEMP_OUT, 12),
 	ADIS16400_MOD_TEMP_CHAN(Y, ADIS16350_YTEMP_OUT, 12),
 	ADIS16400_MOD_TEMP_CHAN(Z, ADIS16350_ZTEMP_OUT, 12),
-	IIO_CHAN_SOFT_TIMESTAMP(11)
+	IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
 };
 
 static const struct iio_chan_spec adis16300_channels[] = {
@@ -690,7 +690,7 @@
 	ADIS16400_AUX_ADC_CHAN(ADIS16300_AUX_ADC, 12),
 	ADIS16400_INCLI_CHAN(X, ADIS16300_PITCH_OUT, 13),
 	ADIS16400_INCLI_CHAN(Y, ADIS16300_ROLL_OUT, 13),
-	IIO_CHAN_SOFT_TIMESTAMP(14)
+	IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
 };
 
 static const struct iio_chan_spec adis16334_channels[] = {
@@ -701,7 +701,7 @@
 	ADIS16400_ACCEL_CHAN(Y, ADIS16400_YACCL_OUT, 14),
 	ADIS16400_ACCEL_CHAN(Z, ADIS16400_ZACCL_OUT, 14),
 	ADIS16400_TEMP_CHAN(ADIS16350_XTEMP_OUT, 12),
-	IIO_CHAN_SOFT_TIMESTAMP(8)
+	IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
 };
 
 static struct attribute *adis16400_attributes[] = {
diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c
index f17b4e6..47a6dba 100644
--- a/drivers/iio/light/cm32181.c
+++ b/drivers/iio/light/cm32181.c
@@ -103,13 +103,13 @@
 /**
  *  cm32181_read_als_it() - Get sensor integration time (ms)
  *  @cm32181:	pointer of struct cm32181
- *  @val:	pointer of int to load the als_it value.
+ *  @val2:	pointer of int to load the als_it value.
  *
  *  Report the current integartion time by millisecond.
  *
- *  Return: IIO_VAL_INT for success, otherwise -EINVAL.
+ *  Return: IIO_VAL_INT_PLUS_MICRO for success, otherwise -EINVAL.
  */
-static int cm32181_read_als_it(struct cm32181_chip *cm32181, int *val)
+static int cm32181_read_als_it(struct cm32181_chip *cm32181, int *val2)
 {
 	u16 als_it;
 	int i;
@@ -119,8 +119,8 @@
 	als_it >>= CM32181_CMD_ALS_IT_SHIFT;
 	for (i = 0; i < ARRAY_SIZE(als_it_bits); i++) {
 		if (als_it == als_it_bits[i]) {
-			*val = als_it_value[i];
-			return IIO_VAL_INT;
+			*val2 = als_it_value[i];
+			return IIO_VAL_INT_PLUS_MICRO;
 		}
 	}
 
@@ -221,7 +221,7 @@
 		*val = cm32181->calibscale;
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_INT_TIME:
-		ret = cm32181_read_als_it(cm32181, val);
+		ret = cm32181_read_als_it(cm32181, val2);
 		return ret;
 	}
 
@@ -240,7 +240,7 @@
 		cm32181->calibscale = val;
 		return val;
 	case IIO_CHAN_INFO_INT_TIME:
-		ret = cm32181_write_als_it(cm32181, val);
+		ret = cm32181_write_als_it(cm32181, val2);
 		return ret;
 	}
 
@@ -264,7 +264,7 @@
 
 	n = ARRAY_SIZE(als_it_value);
 	for (i = 0, len = 0; i < n; i++)
-		len += sprintf(buf + len, "%d ", als_it_value[i]);
+		len += sprintf(buf + len, "0.%06u ", als_it_value[i]);
 	return len + sprintf(buf + len, "\n");
 }
 
diff --git a/drivers/iio/light/cm36651.c b/drivers/iio/light/cm36651.c
index 0a142af..a45e074 100644
--- a/drivers/iio/light/cm36651.c
+++ b/drivers/iio/light/cm36651.c
@@ -50,10 +50,10 @@
 #define CM36651_CS_CONF2_DEFAULT_BIT	0x08
 
 /* CS_CONF3 channel integration time */
-#define CM36651_CS_IT1			0x00 /* Integration time 80000 usec */
-#define CM36651_CS_IT2			0x40 /* Integration time 160000 usec */
-#define CM36651_CS_IT3			0x80 /* Integration time 320000 usec */
-#define CM36651_CS_IT4			0xC0 /* Integration time 640000 usec */
+#define CM36651_CS_IT1			0x00 /* Integration time 80 msec */
+#define CM36651_CS_IT2			0x40 /* Integration time 160 msec */
+#define CM36651_CS_IT3			0x80 /* Integration time 320 msec */
+#define CM36651_CS_IT4			0xC0 /* Integration time 640 msec */
 
 /* PS_CONF1 command code */
 #define CM36651_PS_ENABLE		0x00
@@ -64,10 +64,10 @@
 #define CM36651_PS_PERS4		0x0C
 
 /* PS_CONF1 command code: integration time */
-#define CM36651_PS_IT1			0x00 /* Integration time 320 usec */
-#define CM36651_PS_IT2			0x10 /* Integration time 420 usec */
-#define CM36651_PS_IT3			0x20 /* Integration time 520 usec */
-#define CM36651_PS_IT4			0x30 /* Integration time 640 usec */
+#define CM36651_PS_IT1			0x00 /* Integration time 0.32 msec */
+#define CM36651_PS_IT2			0x10 /* Integration time 0.42 msec */
+#define CM36651_PS_IT3			0x20 /* Integration time 0.52 msec */
+#define CM36651_PS_IT4			0x30 /* Integration time 0.64 msec */
 
 /* PS_CONF1 command code: duty ratio */
 #define CM36651_PS_DR1			0x00 /* Duty ratio 1/80 */
@@ -93,8 +93,8 @@
 #define CM36651_CLOSE_PROXIMITY		0x32
 #define CM36651_FAR_PROXIMITY			0x33
 
-#define CM36651_CS_INT_TIME_AVAIL	"80000 160000 320000 640000"
-#define CM36651_PS_INT_TIME_AVAIL	"320 420 520 640"
+#define CM36651_CS_INT_TIME_AVAIL	"0.08 0.16 0.32 0.64"
+#define CM36651_PS_INT_TIME_AVAIL	"0.000320 0.000420 0.000520 0.000640"
 
 enum cm36651_operation_mode {
 	CM36651_LIGHT_EN,
@@ -356,30 +356,30 @@
 }
 
 static int cm36651_read_int_time(struct cm36651_data *cm36651,
-				struct iio_chan_spec const *chan, int *val)
+				struct iio_chan_spec const *chan, int *val2)
 {
 	switch (chan->type) {
 	case IIO_LIGHT:
 		if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT1)
-			*val = 80000;
+			*val2 = 80000;
 		else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT2)
-			*val = 160000;
+			*val2 = 160000;
 		else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT3)
-			*val = 320000;
+			*val2 = 320000;
 		else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT4)
-			*val = 640000;
+			*val2 = 640000;
 		else
 			return -EINVAL;
 		break;
 	case IIO_PROXIMITY:
 		if (cm36651->ps_int_time == CM36651_PS_IT1)
-			*val = 320;
+			*val2 = 320;
 		else if (cm36651->ps_int_time == CM36651_PS_IT2)
-			*val = 420;
+			*val2 = 420;
 		else if (cm36651->ps_int_time == CM36651_PS_IT3)
-			*val = 520;
+			*val2 = 520;
 		else if (cm36651->ps_int_time == CM36651_PS_IT4)
-			*val = 640;
+			*val2 = 640;
 		else
 			return -EINVAL;
 		break;
@@ -387,7 +387,7 @@
 		return -EINVAL;
 	}
 
-	return IIO_VAL_INT;
+	return IIO_VAL_INT_PLUS_MICRO;
 }
 
 static int cm36651_write_int_time(struct cm36651_data *cm36651,
@@ -459,7 +459,8 @@
 		ret = cm36651_read_channel(cm36651, chan, val);
 		break;
 	case IIO_CHAN_INFO_INT_TIME:
-		ret = cm36651_read_int_time(cm36651, chan, val);
+		*val = 0;
+		ret = cm36651_read_int_time(cm36651, chan, val2);
 		break;
 	default:
 		ret = -EINVAL;
@@ -479,7 +480,7 @@
 	int ret = -EINVAL;
 
 	if (mask == IIO_CHAN_INFO_INT_TIME) {
-		ret = cm36651_write_int_time(cm36651, chan, val);
+		ret = cm36651_write_int_time(cm36651, chan, val2);
 		if (ret < 0)
 			dev_err(&client->dev, "Integration time write failed\n");
 	}
diff --git a/drivers/iio/light/tsl2563.c b/drivers/iio/light/tsl2563.c
index 3d81101..94daa9f 100644
--- a/drivers/iio/light/tsl2563.c
+++ b/drivers/iio/light/tsl2563.c
@@ -460,10 +460,14 @@
 {
 	struct tsl2563_chip *chip = iio_priv(indio_dev);
 
-	if (chan->channel == IIO_MOD_LIGHT_BOTH)
+	if (mask != IIO_CHAN_INFO_CALIBSCALE)
+		return -EINVAL;
+	if (chan->channel2 == IIO_MOD_LIGHT_BOTH)
 		chip->calib0 = calib_from_sysfs(val);
-	else
+	else if (chan->channel2 == IIO_MOD_LIGHT_IR)
 		chip->calib1 = calib_from_sysfs(val);
+	else
+		return -EINVAL;
 
 	return 0;
 }
@@ -472,14 +476,14 @@
 			    struct iio_chan_spec const *chan,
 			    int *val,
 			    int *val2,
-			    long m)
+			    long mask)
 {
 	int ret = -EINVAL;
 	u32 calib0, calib1;
 	struct tsl2563_chip *chip = iio_priv(indio_dev);
 
 	mutex_lock(&chip->lock);
-	switch (m) {
+	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
 	case IIO_CHAN_INFO_PROCESSED:
 		switch (chan->type) {
@@ -498,7 +502,7 @@
 			ret = tsl2563_get_adc(chip);
 			if (ret)
 				goto error_ret;
-			if (chan->channel == 0)
+			if (chan->channel2 == IIO_MOD_LIGHT_BOTH)
 				*val = chip->data0;
 			else
 				*val = chip->data1;
@@ -510,7 +514,7 @@
 		break;
 
 	case IIO_CHAN_INFO_CALIBSCALE:
-		if (chan->channel == 0)
+		if (chan->channel2 == IIO_MOD_LIGHT_BOTH)
 			*val = calib_to_sysfs(chip->calib0);
 		else
 			*val = calib_to_sysfs(chip->calib1);
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index ff284e5..0542354 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -85,6 +85,7 @@
 #define AK8975_MAX_CONVERSION_TIMEOUT	500
 #define AK8975_CONVERSION_DONE_POLL_TIME 10
 #define AK8975_DATA_READY_TIMEOUT	((100*HZ)/1000)
+#define RAW_TO_GAUSS(asa) ((((asa) + 128) * 3000) / 256)
 
 /*
  * Per-instance context data for the device.
@@ -265,15 +266,15 @@
  *
  * Since 1uT = 0.01 gauss, our final scale factor becomes:
  *
- * Hadj = H * ((ASA + 128) / 256) * 3/10 * 100
- * Hadj = H * ((ASA + 128) * 30 / 256
+ * Hadj = H * ((ASA + 128) / 256) * 3/10 * 1/100
+ * Hadj = H * ((ASA + 128) * 0.003) / 256
  *
  * Since ASA doesn't change, we cache the resultant scale factor into the
  * device context in ak8975_setup().
  */
-	data->raw_to_gauss[0] = ((data->asa[0] + 128) * 30) >> 8;
-	data->raw_to_gauss[1] = ((data->asa[1] + 128) * 30) >> 8;
-	data->raw_to_gauss[2] = ((data->asa[2] + 128) * 30) >> 8;
+	data->raw_to_gauss[0] = RAW_TO_GAUSS(data->asa[0]);
+	data->raw_to_gauss[1] = RAW_TO_GAUSS(data->asa[1]);
+	data->raw_to_gauss[2] = RAW_TO_GAUSS(data->asa[2]);
 
 	return 0;
 }
@@ -428,8 +429,9 @@
 	case IIO_CHAN_INFO_RAW:
 		return ak8975_read_axis(indio_dev, chan->address, val);
 	case IIO_CHAN_INFO_SCALE:
-		*val = data->raw_to_gauss[chan->address];
-		return IIO_VAL_INT;
+		*val = 0;
+		*val2 = data->raw_to_gauss[chan->address];
+		return IIO_VAL_INT_PLUS_MICRO;
 	}
 	return -EINVAL;
 }
diff --git a/drivers/iio/magnetometer/mag3110.c b/drivers/iio/magnetometer/mag3110.c
index 4b65b6d..f66955f 100644
--- a/drivers/iio/magnetometer/mag3110.c
+++ b/drivers/iio/magnetometer/mag3110.c
@@ -106,7 +106,7 @@
 
 	while (n-- > 0)
 		len += scnprintf(buf + len, PAGE_SIZE - len,
-			"%d.%d ", vals[n][0], vals[n][1]);
+			"%d.%06d ", vals[n][0], vals[n][1]);
 
 	/* replace trailing space by newline */
 	buf[len - 1] = '\n';
@@ -154,6 +154,9 @@
 
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
+		if (iio_buffer_enabled(indio_dev))
+			return -EBUSY;
+
 		switch (chan->type) {
 		case IIO_MAGN: /* in 0.1 uT / LSB */
 			ret = mag3110_read(data, buffer);
@@ -199,6 +202,9 @@
 	struct mag3110_data *data = iio_priv(indio_dev);
 	int rate;
 
+	if (iio_buffer_enabled(indio_dev))
+		return -EBUSY;
+
 	switch (mask) {
 	case IIO_CHAN_INFO_SAMP_FREQ:
 		rate = mag3110_get_samp_freq_index(data, val, val2);
diff --git a/drivers/infiniband/hw/amso1100/c2.c b/drivers/infiniband/hw/amso1100/c2.c
index d53cf51..00400c3 100644
--- a/drivers/infiniband/hw/amso1100/c2.c
+++ b/drivers/infiniband/hw/amso1100/c2.c
@@ -1082,6 +1082,7 @@
 
 	/* Initialize network device */
 	if ((netdev = c2_devinit(c2dev, mmio_regs)) == NULL) {
+		ret = -ENOMEM;
 		iounmap(mmio_regs);
 		goto bail4;
 	}
@@ -1151,7 +1152,8 @@
 		goto bail10;
 	}
 
-	if (c2_register_device(c2dev))
+	ret = c2_register_device(c2dev);
+	if (ret)
 		goto bail10;
 
 	return 0;
diff --git a/drivers/infiniband/hw/amso1100/c2_rnic.c b/drivers/infiniband/hw/amso1100/c2_rnic.c
index b7c9869..d2a6d96 100644
--- a/drivers/infiniband/hw/amso1100/c2_rnic.c
+++ b/drivers/infiniband/hw/amso1100/c2_rnic.c
@@ -576,7 +576,8 @@
 		goto bail4;
 
 	/* Initialize cached the adapter limits */
-	if (c2_rnic_query(c2dev, &c2dev->props))
+	err = c2_rnic_query(c2dev, &c2dev->props);
+	if (err)
 		goto bail5;
 
 	/* Initialize the PD pool */
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 4512687..d286bde 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -3352,6 +3352,7 @@
 		goto free_dst;
 	}
 
+	neigh_release(neigh);
 	step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan;
 	rss_qid = dev->rdev.lldi.rxq_ids[pi->port_id * step];
 	window = (__force u16) htons((__force u16)tcph->window);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index c2702f5..f9c12e9 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -53,8 +53,8 @@
 #include "user.h"
 
 #define DRV_NAME	MLX4_IB_DRV_NAME
-#define DRV_VERSION	"1.0"
-#define DRV_RELDATE	"April 4, 2008"
+#define DRV_VERSION	"2.2-1"
+#define DRV_RELDATE	"Feb 2014"
 
 #define MLX4_IB_FLOW_MAX_PRIO 0xFFF
 #define MLX4_IB_FLOW_QPN_MASK 0xFFFFFF
@@ -347,7 +347,7 @@
 	props->active_width	=  (((u8 *)mailbox->buf)[5] == 0x40) ?
 						IB_WIDTH_4X : IB_WIDTH_1X;
 	props->active_speed	= IB_SPEED_QDR;
-	props->port_cap_flags	= IB_PORT_CM_SUP;
+	props->port_cap_flags	= IB_PORT_CM_SUP | IB_PORT_IP_BASED_GIDS;
 	props->gid_tbl_len	= mdev->dev->caps.gid_table_len[port];
 	props->max_msg_sz	= mdev->dev->caps.max_msg_sz;
 	props->pkey_tbl_len	= 1;
@@ -1357,6 +1357,21 @@
 	&dev_attr_board_id
 };
 
+static void mlx4_addrconf_ifid_eui48(u8 *eui, u16 vlan_id,
+				     struct net_device *dev)
+{
+	memcpy(eui, dev->dev_addr, 3);
+	memcpy(eui + 5, dev->dev_addr + 3, 3);
+	if (vlan_id < 0x1000) {
+		eui[3] = vlan_id >> 8;
+		eui[4] = vlan_id & 0xff;
+	} else {
+		eui[3] = 0xff;
+		eui[4] = 0xfe;
+	}
+	eui[0] ^= 2;
+}
+
 static void update_gids_task(struct work_struct *work)
 {
 	struct update_gid_work *gw = container_of(work, struct update_gid_work, work);
@@ -1393,7 +1408,6 @@
 	struct mlx4_cmd_mailbox *mailbox;
 	union ib_gid *gids;
 	int err;
-	int i;
 	struct mlx4_dev	*dev = gw->dev->dev;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -1405,18 +1419,16 @@
 	gids = mailbox->buf;
 	memcpy(gids, gw->gids, sizeof(gw->gids));
 
-	for (i = 1; i < gw->dev->num_ports + 1; i++) {
-		if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, i) ==
-					    IB_LINK_LAYER_ETHERNET) {
-			err = mlx4_cmd(dev, mailbox->dma,
-				       MLX4_SET_PORT_GID_TABLE << 8 | i,
-				       1, MLX4_CMD_SET_PORT,
-				       MLX4_CMD_TIME_CLASS_B,
-				       MLX4_CMD_WRAPPED);
-			if (err)
-				pr_warn(KERN_WARNING
-					"set port %d command failed\n", i);
-		}
+	if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, gw->port) ==
+				    IB_LINK_LAYER_ETHERNET) {
+		err = mlx4_cmd(dev, mailbox->dma,
+			       MLX4_SET_PORT_GID_TABLE << 8 | gw->port,
+			       1, MLX4_CMD_SET_PORT,
+			       MLX4_CMD_TIME_CLASS_B,
+			       MLX4_CMD_WRAPPED);
+		if (err)
+			pr_warn(KERN_WARNING
+				"set port %d command failed\n", gw->port);
 	}
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
@@ -1425,7 +1437,8 @@
 }
 
 static int update_gid_table(struct mlx4_ib_dev *dev, int port,
-			    union ib_gid *gid, int clear)
+			    union ib_gid *gid, int clear,
+			    int default_gid)
 {
 	struct update_gid_work *work;
 	int i;
@@ -1434,26 +1447,31 @@
 	int found = -1;
 	int max_gids;
 
-	max_gids = dev->dev->caps.gid_table_len[port];
-	for (i = 0; i < max_gids; ++i) {
-		if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid,
-			    sizeof(*gid)))
-			found = i;
-
-		if (clear) {
-			if (found >= 0) {
-				need_update = 1;
-				dev->iboe.gid_table[port - 1][found] = zgid;
-				break;
-			}
-		} else {
-			if (found >= 0)
-				break;
-
-			if (free < 0 &&
-			    !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid,
+	if (default_gid) {
+		free = 0;
+	} else {
+		max_gids = dev->dev->caps.gid_table_len[port];
+		for (i = 1; i < max_gids; ++i) {
+			if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid,
 				    sizeof(*gid)))
-				free = i;
+				found = i;
+
+			if (clear) {
+				if (found >= 0) {
+					need_update = 1;
+					dev->iboe.gid_table[port - 1][found] =
+						zgid;
+					break;
+				}
+			} else {
+				if (found >= 0)
+					break;
+
+				if (free < 0 &&
+				    !memcmp(&dev->iboe.gid_table[port - 1][i],
+					    &zgid, sizeof(*gid)))
+					free = i;
+			}
 		}
 	}
 
@@ -1478,18 +1496,26 @@
 	return 0;
 }
 
-static int reset_gid_table(struct mlx4_ib_dev *dev)
+static void mlx4_make_default_gid(struct  net_device *dev, union ib_gid *gid)
+{
+	gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+	mlx4_addrconf_ifid_eui48(&gid->raw[8], 0xffff, dev);
+}
+
+
+static int reset_gid_table(struct mlx4_ib_dev *dev, u8 port)
 {
 	struct update_gid_work *work;
 
-
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work)
 		return -ENOMEM;
-	memset(dev->iboe.gid_table, 0, sizeof(dev->iboe.gid_table));
+
+	memset(dev->iboe.gid_table[port - 1], 0, sizeof(work->gids));
 	memset(work->gids, 0, sizeof(work->gids));
 	INIT_WORK(&work->work, reset_gids_task);
 	work->dev = dev;
+	work->port = port;
 	queue_work(wq, &work->work);
 	return 0;
 }
@@ -1502,6 +1528,12 @@
 	struct net_device *real_dev = rdma_vlan_dev_real_dev(event_netdev) ?
 				rdma_vlan_dev_real_dev(event_netdev) :
 				event_netdev;
+	union ib_gid default_gid;
+
+	mlx4_make_default_gid(real_dev, &default_gid);
+
+	if (!memcmp(gid, &default_gid, sizeof(*gid)))
+		return 0;
 
 	if (event != NETDEV_DOWN && event != NETDEV_UP)
 		return 0;
@@ -1520,7 +1552,7 @@
 		     (!netif_is_bond_master(real_dev) &&
 		     (real_dev == iboe->netdevs[port - 1])))
 			update_gid_table(ibdev, port, gid,
-					 event == NETDEV_DOWN);
+					 event == NETDEV_DOWN, 0);
 
 	spin_unlock(&iboe->lock);
 	return 0;
@@ -1536,7 +1568,6 @@
 				rdma_vlan_dev_real_dev(dev) : dev;
 
 	iboe = &ibdev->iboe;
-	spin_lock(&iboe->lock);
 
 	for (port = 1; port <= MLX4_MAX_PORTS; ++port)
 		if ((netif_is_bond_master(real_dev) &&
@@ -1545,8 +1576,6 @@
 		     (real_dev == iboe->netdevs[port - 1])))
 			break;
 
-	spin_unlock(&iboe->lock);
-
 	if ((port == 0) || (port > MLX4_MAX_PORTS))
 		return 0;
 	else
@@ -1607,7 +1636,7 @@
 			/*ifa->ifa_address;*/
 			ipv6_addr_set_v4mapped(ifa->ifa_address,
 					       (struct in6_addr *)&gid);
-			update_gid_table(ibdev, port, &gid, 0);
+			update_gid_table(ibdev, port, &gid, 0, 0);
 		}
 		endfor_ifa(in_dev);
 		in_dev_put(in_dev);
@@ -1619,7 +1648,7 @@
 		read_lock_bh(&in6_dev->lock);
 		list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
 			pgid = (union ib_gid *)&ifp->addr;
-			update_gid_table(ibdev, port, pgid, 0);
+			update_gid_table(ibdev, port, pgid, 0, 0);
 		}
 		read_unlock_bh(&in6_dev->lock);
 		in6_dev_put(in6_dev);
@@ -1627,14 +1656,26 @@
 #endif
 }
 
+static void mlx4_ib_set_default_gid(struct mlx4_ib_dev *ibdev,
+				 struct  net_device *dev, u8 port)
+{
+	union ib_gid gid;
+	mlx4_make_default_gid(dev, &gid);
+	update_gid_table(ibdev, port, &gid, 0, 1);
+}
+
 static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev)
 {
 	struct	net_device *dev;
+	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
+	int i;
 
-	if (reset_gid_table(ibdev))
-		return -1;
+	for (i = 1; i <= ibdev->num_ports; ++i)
+		if (reset_gid_table(ibdev, i))
+			return -1;
 
 	read_lock(&dev_base_lock);
+	spin_lock(&iboe->lock);
 
 	for_each_netdev(&init_net, dev) {
 		u8 port = mlx4_ib_get_dev_port(dev, ibdev);
@@ -1642,6 +1683,7 @@
 			mlx4_ib_get_dev_addr(dev, ibdev, port);
 	}
 
+	spin_unlock(&iboe->lock);
 	read_unlock(&dev_base_lock);
 
 	return 0;
@@ -1656,25 +1698,57 @@
 
 	spin_lock(&iboe->lock);
 	mlx4_foreach_ib_transport_port(port, ibdev->dev) {
+		enum ib_port_state	port_state = IB_PORT_NOP;
 		struct net_device *old_master = iboe->masters[port - 1];
+		struct net_device *curr_netdev;
 		struct net_device *curr_master;
+
 		iboe->netdevs[port - 1] =
 			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
+		if (iboe->netdevs[port - 1])
+			mlx4_ib_set_default_gid(ibdev,
+						iboe->netdevs[port - 1], port);
+		curr_netdev = iboe->netdevs[port - 1];
 
 		if (iboe->netdevs[port - 1] &&
 		    netif_is_bond_slave(iboe->netdevs[port - 1])) {
-			rtnl_lock();
 			iboe->masters[port - 1] = netdev_master_upper_dev_get(
 				iboe->netdevs[port - 1]);
-			rtnl_unlock();
+		} else {
+			iboe->masters[port - 1] = NULL;
 		}
 		curr_master = iboe->masters[port - 1];
 
+		if (curr_netdev) {
+			port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ?
+						IB_PORT_ACTIVE : IB_PORT_DOWN;
+			mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
+		} else {
+			reset_gid_table(ibdev, port);
+		}
+		/* if using bonding/team and a slave port is down, we don't the bond IP
+		 * based gids in the table since flows that select port by gid may get
+		 * the down port.
+		 */
+		if (curr_master && (port_state == IB_PORT_DOWN)) {
+			reset_gid_table(ibdev, port);
+			mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
+		}
 		/* if bonding is used it is possible that we add it to masters
-		    only after IP address is assigned to the net bonding
-		    interface */
-		if (curr_master && (old_master != curr_master))
+		 * only after IP address is assigned to the net bonding
+		 * interface.
+		*/
+		if (curr_master && (old_master != curr_master)) {
+			reset_gid_table(ibdev, port);
+			mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
 			mlx4_ib_get_dev_addr(curr_master, ibdev, port);
+		}
+
+		if (!curr_master && (old_master != curr_master)) {
+			reset_gid_table(ibdev, port);
+			mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
+			mlx4_ib_get_dev_addr(curr_netdev, ibdev, port);
+		}
 	}
 
 	spin_unlock(&iboe->lock);
@@ -1810,6 +1884,7 @@
 	int i, j;
 	int err;
 	struct mlx4_ib_iboe *iboe;
+	int ib_num_ports = 0;
 
 	pr_info_once("%s", mlx4_ib_version);
 
@@ -1985,10 +2060,14 @@
 				ibdev->counters[i] = -1;
 	}
 
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+		ib_num_ports++;
+
 	spin_lock_init(&ibdev->sm_lock);
 	mutex_init(&ibdev->cap_mask_mutex);
 
-	if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) {
+	if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED &&
+	    ib_num_ports) {
 		ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS;
 		err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count,
 					    MLX4_IB_UC_STEER_QPN_ALIGN,
@@ -2051,7 +2130,11 @@
 			}
 		}
 #endif
+		for (i = 1 ; i <= ibdev->num_ports ; ++i)
+			reset_gid_table(ibdev, i);
+		rtnl_lock();
 		mlx4_ib_scan_netdevs(ibdev);
+		rtnl_unlock();
 		mlx4_ib_init_gid_table(ibdev);
 	}
 
diff --git a/drivers/infiniband/hw/mlx5/Kconfig b/drivers/infiniband/hw/mlx5/Kconfig
index 8e6aebf..10df386 100644
--- a/drivers/infiniband/hw/mlx5/Kconfig
+++ b/drivers/infiniband/hw/mlx5/Kconfig
@@ -1,6 +1,6 @@
 config MLX5_INFINIBAND
 	tristate "Mellanox Connect-IB HCA support"
-	depends on NETDEVICES && ETHERNET && PCI && X86
+	depends on NETDEVICES && ETHERNET && PCI
 	select NET_VENDOR_MELLANOX
 	select MLX5_CORE
 	---help---
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 9660d09..bf90057 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -46,8 +46,8 @@
 #include "mlx5_ib.h"
 
 #define DRIVER_NAME "mlx5_ib"
-#define DRIVER_VERSION "1.0"
-#define DRIVER_RELDATE	"June 2013"
+#define DRIVER_VERSION "2.2-1"
+#define DRIVER_RELDATE	"Feb 2014"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver");
@@ -261,8 +261,7 @@
 	props->device_cap_flags    = IB_DEVICE_CHANGE_PHY_PORT |
 		IB_DEVICE_PORT_ACTIVE_EVENT		|
 		IB_DEVICE_SYS_IMAGE_GUID		|
-		IB_DEVICE_RC_RNR_NAK_GEN		|
-		IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
+		IB_DEVICE_RC_RNR_NAK_GEN;
 	flags = dev->mdev.caps.flags;
 	if (flags & MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR)
 		props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR;
@@ -536,24 +535,38 @@
 						  struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
-	struct mlx5_ib_alloc_ucontext_req req;
+	struct mlx5_ib_alloc_ucontext_req_v2 req;
 	struct mlx5_ib_alloc_ucontext_resp resp;
 	struct mlx5_ib_ucontext *context;
 	struct mlx5_uuar_info *uuari;
 	struct mlx5_uar *uars;
 	int gross_uuars;
 	int num_uars;
+	int ver;
 	int uuarn;
 	int err;
 	int i;
+	int reqlen;
 
 	if (!dev->ib_active)
 		return ERR_PTR(-EAGAIN);
 
-	err = ib_copy_from_udata(&req, udata, sizeof(req));
+	memset(&req, 0, sizeof(req));
+	reqlen = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr);
+	if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req))
+		ver = 0;
+	else if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req_v2))
+		ver = 2;
+	else
+		return ERR_PTR(-EINVAL);
+
+	err = ib_copy_from_udata(&req, udata, reqlen);
 	if (err)
 		return ERR_PTR(err);
 
+	if (req.flags || req.reserved)
+		return ERR_PTR(-EINVAL);
+
 	if (req.total_num_uuars > MLX5_MAX_UUARS)
 		return ERR_PTR(-ENOMEM);
 
@@ -626,6 +639,7 @@
 	if (err)
 		goto out_uars;
 
+	uuari->ver = ver;
 	uuari->num_low_latency_uuars = req.num_low_latency_uuars;
 	uuari->uars = uars;
 	uuari->num_uars = num_uars;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index ae37fb9..7dfe8a1 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -216,7 +216,9 @@
 
 	case IB_QPT_UC:
 		size += sizeof(struct mlx5_wqe_ctrl_seg) +
-			sizeof(struct mlx5_wqe_raddr_seg);
+			sizeof(struct mlx5_wqe_raddr_seg) +
+			sizeof(struct mlx5_wqe_umr_ctrl_seg) +
+			sizeof(struct mlx5_mkey_seg);
 		break;
 
 	case IB_QPT_UD:
@@ -428,11 +430,17 @@
 		break;
 
 	case MLX5_IB_LATENCY_CLASS_MEDIUM:
-		uuarn = alloc_med_class_uuar(uuari);
+		if (uuari->ver < 2)
+			uuarn = -ENOMEM;
+		else
+			uuarn = alloc_med_class_uuar(uuari);
 		break;
 
 	case MLX5_IB_LATENCY_CLASS_HIGH:
-		uuarn = alloc_high_class_uuar(uuari);
+		if (uuari->ver < 2)
+			uuarn = -ENOMEM;
+		else
+			uuarn = alloc_high_class_uuar(uuari);
 		break;
 
 	case MLX5_IB_LATENCY_CLASS_FAST_PATH:
@@ -657,8 +665,8 @@
 	int err;
 
 	uuari = &dev->mdev.priv.uuari;
-	if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK)
-		qp->flags |= MLX5_IB_QP_BLOCK_MULTICAST_LOOPBACK;
+	if (init_attr->create_flags)
+		return -EINVAL;
 
 	if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR)
 		lc = MLX5_IB_LATENCY_CLASS_FAST_PATH;
diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h
index 32a2a5d..0f4f8e4 100644
--- a/drivers/infiniband/hw/mlx5/user.h
+++ b/drivers/infiniband/hw/mlx5/user.h
@@ -62,6 +62,13 @@
 	__u32	num_low_latency_uuars;
 };
 
+struct mlx5_ib_alloc_ucontext_req_v2 {
+	__u32	total_num_uuars;
+	__u32	num_low_latency_uuars;
+	__u32	flags;
+	__u32	reserved;
+};
+
 struct mlx5_ib_alloc_ucontext_resp {
 	__u32	qp_tab_size;
 	__u32	bf_reg_size;
diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c
index 4291410..353c7b0 100644
--- a/drivers/infiniband/hw/nes/nes.c
+++ b/drivers/infiniband/hw/nes/nes.c
@@ -675,8 +675,11 @@
 	INIT_DELAYED_WORK(&nesdev->work, nes_recheck_link_status);
 
 	/* Initialize network devices */
-	if ((netdev = nes_netdev_init(nesdev, mmio_regs)) == NULL)
+	netdev = nes_netdev_init(nesdev, mmio_regs);
+	if (netdev == NULL) {
+		ret = -ENOMEM;
 		goto bail7;
+	}
 
 	/* Register network device */
 	ret = register_netdev(netdev);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 2ca86ca..1a8a945 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -127,7 +127,7 @@
 
 	is_vlan = netdev->priv_flags & IFF_802_1Q_VLAN;
 	if (is_vlan)
-		netdev = vlan_dev_real_dev(netdev);
+		netdev = rdma_vlan_dev_real_dev(netdev);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(dev, &ocrdma_dev_list, entry) {
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index aa92f40..e0cc201 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -176,7 +176,7 @@
 	props->port_cap_flags =
 	    IB_PORT_CM_SUP |
 	    IB_PORT_REINIT_SUP |
-	    IB_PORT_DEVICE_MGMT_SUP | IB_PORT_VENDOR_CLASS_SUP;
+	    IB_PORT_DEVICE_MGMT_SUP | IB_PORT_VENDOR_CLASS_SUP | IB_PORT_IP_BASED_GIDS;
 	props->gid_tbl_len = OCRDMA_MAX_SGID;
 	props->pkey_tbl_len = 1;
 	props->bad_pkey_cntr = 0;
@@ -1416,7 +1416,7 @@
 					  OCRDMA_QP_PARAMS_HOP_LMT_MASK) >>
 						OCRDMA_QP_PARAMS_HOP_LMT_SHIFT;
 	qp_attr->ah_attr.grh.traffic_class = (params.tclass_sq_psn &
-					      OCRDMA_QP_PARAMS_SQ_PSN_MASK) >>
+					      OCRDMA_QP_PARAMS_TCLASS_MASK) >>
 						OCRDMA_QP_PARAMS_TCLASS_SHIFT;
 
 	qp_attr->ah_attr.ah_flags = IB_AH_GRH;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 5bfc02f..d1bd213 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -2395,6 +2395,11 @@
 	qib_write_kreg_port(ppd, krp_ibcctrl_a, ppd->cpspec->ibcctrl_a);
 	qib_write_kreg(dd, kr_scratch, 0ULL);
 
+	/* ensure previous Tx parameters are not still forced */
+	qib_write_kreg_port(ppd, krp_tx_deemph_override,
+		SYM_MASK(IBSD_TX_DEEMPHASIS_OVERRIDE_0,
+		reset_tx_deemphasis_override));
+
 	if (qib_compat_ddr_negotiate) {
 		ppd->cpspec->ibdeltainprog = 1;
 		ppd->cpspec->ibsymsnap = read_7322_creg32_port(ppd,
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c
index 7ecc606..f8dfd76 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c
@@ -629,6 +629,7 @@
 {
 	enum usnic_transport_type trans_type = qp_flow->trans_type;
 	int err;
+	uint16_t port_num = 0;
 
 	switch (trans_type) {
 	case USNIC_TRANSPORT_ROCE_CUSTOM:
@@ -637,9 +638,15 @@
 	case USNIC_TRANSPORT_IPV4_UDP:
 		err = usnic_transport_sock_get_addr(qp_flow->udp.sock,
 							NULL, NULL,
-							(uint16_t *) id);
+							&port_num);
 		if (err)
 			return err;
+		/*
+		 * Copy port_num to stack first and then to *id,
+		 * so that the short to int cast works for little
+		 * and big endian systems.
+		 */
+		*id = port_num;
 		break;
 	default:
 		usnic_err("Unsupported transport %u\n", trans_type);
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index 5388226..334f34b 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -610,11 +610,12 @@
 		ib_dma_unmap_single(device->ib_device, tx_desc->dma_addr,
 					ISER_HEADERS_LEN, DMA_TO_DEVICE);
 		kmem_cache_free(ig.desc_cache, tx_desc);
+		tx_desc = NULL;
 	}
 
 	atomic_dec(&ib_conn->post_send_buf_count);
 
-	if (tx_desc->type == ISCSI_TX_CONTROL) {
+	if (tx_desc && tx_desc->type == ISCSI_TX_CONTROL) {
 		/* this arithmetic is legal by libiscsi dd_data allocation */
 		task = (void *) ((long)(void *)tx_desc -
 				  sizeof(struct iscsi_task));
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index afe9567..ca37ede 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -652,9 +652,13 @@
 	/* getting here when the state is UP means that the conn is being *
 	 * terminated asynchronously from the iSCSI layer's perspective.  */
 	if (iser_conn_state_comp_exch(ib_conn, ISER_CONN_UP,
-				      ISER_CONN_TERMINATING))
-		iscsi_conn_failure(ib_conn->iser_conn->iscsi_conn,
-				   ISCSI_ERR_CONN_FAILED);
+					ISER_CONN_TERMINATING)){
+		if (ib_conn->iser_conn)
+			iscsi_conn_failure(ib_conn->iser_conn->iscsi_conn,
+					   ISCSI_ERR_CONN_FAILED);
+		else
+			iser_err("iscsi_iser connection isn't bound\n");
+	}
 
 	/* Complete the termination process if no posts are pending */
 	if (ib_conn->post_recv_buf_count == 0 &&
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 2b161be..8ee228e 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -453,6 +453,7 @@
 		if (ret) {
 			pr_err("Failed to create fastreg descriptor err=%d\n",
 			       ret);
+			kfree(fr_desc);
 			goto err;
 		}
 
@@ -491,12 +492,11 @@
 	isert_conn->state = ISER_CONN_INIT;
 	INIT_LIST_HEAD(&isert_conn->conn_accept_node);
 	init_completion(&isert_conn->conn_login_comp);
-	init_waitqueue_head(&isert_conn->conn_wait);
-	init_waitqueue_head(&isert_conn->conn_wait_comp_err);
+	init_completion(&isert_conn->conn_wait);
+	init_completion(&isert_conn->conn_wait_comp_err);
 	kref_init(&isert_conn->conn_kref);
 	kref_get(&isert_conn->conn_kref);
 	mutex_init(&isert_conn->conn_mutex);
-	mutex_init(&isert_conn->conn_comp_mutex);
 	spin_lock_init(&isert_conn->conn_lock);
 
 	cma_id->context = isert_conn;
@@ -687,11 +687,11 @@
 
 	pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
 	mutex_lock(&isert_conn->conn_mutex);
-	isert_conn->state = ISER_CONN_DOWN;
+	if (isert_conn->state == ISER_CONN_UP)
+		isert_conn->state = ISER_CONN_TERMINATING;
 
 	if (isert_conn->post_recv_buf_count == 0 &&
 	    atomic_read(&isert_conn->post_send_buf_count) == 0) {
-		pr_debug("Calling wake_up(&isert_conn->conn_wait);\n");
 		mutex_unlock(&isert_conn->conn_mutex);
 		goto wake_up;
 	}
@@ -711,7 +711,7 @@
 	mutex_unlock(&isert_conn->conn_mutex);
 
 wake_up:
-	wake_up(&isert_conn->conn_wait);
+	complete(&isert_conn->conn_wait);
 	isert_put_conn(isert_conn);
 }
 
@@ -887,16 +887,17 @@
 	 * Coalesce send completion interrupts by only setting IB_SEND_SIGNALED
 	 * bit for every ISERT_COMP_BATCH_COUNT number of ib_post_send() calls.
 	 */
-	mutex_lock(&isert_conn->conn_comp_mutex);
-	if (coalesce &&
+	mutex_lock(&isert_conn->conn_mutex);
+	if (coalesce && isert_conn->state == ISER_CONN_UP &&
 	    ++isert_conn->conn_comp_batch < ISERT_COMP_BATCH_COUNT) {
+		tx_desc->llnode_active = true;
 		llist_add(&tx_desc->comp_llnode, &isert_conn->conn_comp_llist);
-		mutex_unlock(&isert_conn->conn_comp_mutex);
+		mutex_unlock(&isert_conn->conn_mutex);
 		return;
 	}
 	isert_conn->conn_comp_batch = 0;
 	tx_desc->comp_llnode_batch = llist_del_all(&isert_conn->conn_comp_llist);
-	mutex_unlock(&isert_conn->conn_comp_mutex);
+	mutex_unlock(&isert_conn->conn_mutex);
 
 	send_wr->send_flags = IB_SEND_SIGNALED;
 }
@@ -1463,7 +1464,7 @@
 	case ISCSI_OP_SCSI_CMD:
 		spin_lock_bh(&conn->cmd_lock);
 		if (!list_empty(&cmd->i_conn_node))
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		if (cmd->data_direction == DMA_TO_DEVICE)
@@ -1475,7 +1476,7 @@
 	case ISCSI_OP_SCSI_TMFUNC:
 		spin_lock_bh(&conn->cmd_lock);
 		if (!list_empty(&cmd->i_conn_node))
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		transport_generic_free_cmd(&cmd->se_cmd, 0);
@@ -1485,7 +1486,7 @@
 	case ISCSI_OP_TEXT:
 		spin_lock_bh(&conn->cmd_lock);
 		if (!list_empty(&cmd->i_conn_node))
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		/*
@@ -1548,6 +1549,7 @@
 	iscsit_stop_dataout_timer(cmd);
 	device->unreg_rdma_mem(isert_cmd, isert_conn);
 	cmd->write_data_done = wr->cur_rdma_length;
+	wr->send_wr_num = 0;
 
 	pr_debug("Cmd: %p RDMA_READ comp calling execute_cmd\n", isert_cmd);
 	spin_lock_bh(&cmd->istate_lock);
@@ -1588,7 +1590,7 @@
 		pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n");
 		/*
 		 * Call atomic_dec(&isert_conn->post_send_buf_count)
-		 * from isert_free_conn()
+		 * from isert_wait_conn()
 		 */
 		isert_conn->logout_posted = true;
 		iscsit_logout_post_handler(cmd, cmd->conn);
@@ -1612,6 +1614,7 @@
 			  struct ib_device *ib_dev)
 {
 	struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
+	struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
 
 	if (cmd->i_state == ISTATE_SEND_TASKMGTRSP ||
 	    cmd->i_state == ISTATE_SEND_LOGOUTRSP ||
@@ -1623,7 +1626,7 @@
 		queue_work(isert_comp_wq, &isert_cmd->comp_work);
 		return;
 	}
-	atomic_dec(&isert_conn->post_send_buf_count);
+	atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 
 	cmd->i_state = ISTATE_SENT_STATUS;
 	isert_completion_put(tx_desc, isert_cmd, ib_dev);
@@ -1661,7 +1664,7 @@
 	case ISER_IB_RDMA_READ:
 		pr_debug("isert_send_completion: Got ISER_IB_RDMA_READ:\n");
 
-		atomic_dec(&isert_conn->post_send_buf_count);
+		atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
 		isert_completion_rdma_read(tx_desc, isert_cmd);
 		break;
 	default:
@@ -1690,31 +1693,76 @@
 }
 
 static void
-isert_cq_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
+isert_cq_drain_comp_llist(struct isert_conn *isert_conn, struct ib_device *ib_dev)
+{
+	struct llist_node *llnode;
+	struct isert_rdma_wr *wr;
+	struct iser_tx_desc *t;
+
+	mutex_lock(&isert_conn->conn_mutex);
+	llnode = llist_del_all(&isert_conn->conn_comp_llist);
+	isert_conn->conn_comp_batch = 0;
+	mutex_unlock(&isert_conn->conn_mutex);
+
+	while (llnode) {
+		t = llist_entry(llnode, struct iser_tx_desc, comp_llnode);
+		llnode = llist_next(llnode);
+		wr = &t->isert_cmd->rdma_wr;
+
+		atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
+		isert_completion_put(t, t->isert_cmd, ib_dev);
+	}
+}
+
+static void
+isert_cq_tx_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
 {
 	struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+	struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
+	struct llist_node *llnode = tx_desc->comp_llnode_batch;
+	struct isert_rdma_wr *wr;
+	struct iser_tx_desc *t;
 
-	if (tx_desc) {
-		struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
+	while (llnode) {
+		t = llist_entry(llnode, struct iser_tx_desc, comp_llnode);
+		llnode = llist_next(llnode);
+		wr = &t->isert_cmd->rdma_wr;
 
-		if (!isert_cmd)
-			isert_unmap_tx_desc(tx_desc, ib_dev);
-		else
-			isert_completion_put(tx_desc, isert_cmd, ib_dev);
+		atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
+		isert_completion_put(t, t->isert_cmd, ib_dev);
+	}
+	tx_desc->comp_llnode_batch = NULL;
+
+	if (!isert_cmd)
+		isert_unmap_tx_desc(tx_desc, ib_dev);
+	else
+		isert_completion_put(tx_desc, isert_cmd, ib_dev);
+}
+
+static void
+isert_cq_rx_comp_err(struct isert_conn *isert_conn)
+{
+	struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+	struct iscsi_conn *conn = isert_conn->conn;
+
+	if (isert_conn->post_recv_buf_count)
+		return;
+
+	isert_cq_drain_comp_llist(isert_conn, ib_dev);
+
+	if (conn->sess) {
+		target_sess_cmd_list_set_waiting(conn->sess->se_sess);
+		target_wait_for_sess_cmds(conn->sess->se_sess);
 	}
 
-	if (isert_conn->post_recv_buf_count == 0 &&
-	    atomic_read(&isert_conn->post_send_buf_count) == 0) {
-		pr_debug("isert_cq_comp_err >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
-		pr_debug("Calling wake_up from isert_cq_comp_err\n");
+	while (atomic_read(&isert_conn->post_send_buf_count))
+		msleep(3000);
 
-		mutex_lock(&isert_conn->conn_mutex);
-		if (isert_conn->state != ISER_CONN_DOWN)
-			isert_conn->state = ISER_CONN_TERMINATING;
-		mutex_unlock(&isert_conn->conn_mutex);
+	mutex_lock(&isert_conn->conn_mutex);
+	isert_conn->state = ISER_CONN_DOWN;
+	mutex_unlock(&isert_conn->conn_mutex);
 
-		wake_up(&isert_conn->conn_wait_comp_err);
-	}
+	complete(&isert_conn->conn_wait_comp_err);
 }
 
 static void
@@ -1739,8 +1787,14 @@
 			pr_debug("TX wc.status != IB_WC_SUCCESS >>>>>>>>>>>>>>\n");
 			pr_debug("TX wc.status: 0x%08x\n", wc.status);
 			pr_debug("TX wc.vendor_err: 0x%08x\n", wc.vendor_err);
-			atomic_dec(&isert_conn->post_send_buf_count);
-			isert_cq_comp_err(tx_desc, isert_conn);
+
+			if (wc.wr_id != ISER_FASTREG_LI_WRID) {
+				if (tx_desc->llnode_active)
+					continue;
+
+				atomic_dec(&isert_conn->post_send_buf_count);
+				isert_cq_tx_comp_err(tx_desc, isert_conn);
+			}
 		}
 	}
 
@@ -1783,7 +1837,7 @@
 					 wc.vendor_err);
 			}
 			isert_conn->post_recv_buf_count--;
-			isert_cq_comp_err(NULL, isert_conn);
+			isert_cq_rx_comp_err(isert_conn);
 		}
 	}
 
@@ -2201,6 +2255,7 @@
 
 	if (!fr_desc->valid) {
 		memset(&inv_wr, 0, sizeof(inv_wr));
+		inv_wr.wr_id = ISER_FASTREG_LI_WRID;
 		inv_wr.opcode = IB_WR_LOCAL_INV;
 		inv_wr.ex.invalidate_rkey = fr_desc->data_mr->rkey;
 		wr = &inv_wr;
@@ -2211,6 +2266,7 @@
 
 	/* Prepare FASTREG WR */
 	memset(&fr_wr, 0, sizeof(fr_wr));
+	fr_wr.wr_id = ISER_FASTREG_LI_WRID;
 	fr_wr.opcode = IB_WR_FAST_REG_MR;
 	fr_wr.wr.fast_reg.iova_start =
 		fr_desc->data_frpl->page_list[0] + page_off;
@@ -2376,12 +2432,12 @@
 	isert_init_send_wr(isert_conn, isert_cmd,
 			   &isert_cmd->tx_desc.send_wr, true);
 
-	atomic_inc(&isert_conn->post_send_buf_count);
+	atomic_add(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 
 	rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed);
 	if (rc) {
 		pr_warn("ib_post_send() failed for IB_WR_RDMA_WRITE\n");
-		atomic_dec(&isert_conn->post_send_buf_count);
+		atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 	}
 	pr_debug("Cmd: %p posted RDMA_WRITE + Response for iSER Data READ\n",
 		 isert_cmd);
@@ -2409,12 +2465,12 @@
 		return rc;
 	}
 
-	atomic_inc(&isert_conn->post_send_buf_count);
+	atomic_add(wr->send_wr_num, &isert_conn->post_send_buf_count);
 
 	rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed);
 	if (rc) {
 		pr_warn("ib_post_send() failed for IB_WR_RDMA_READ\n");
-		atomic_dec(&isert_conn->post_send_buf_count);
+		atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
 	}
 	pr_debug("Cmd: %p posted RDMA_READ memory for ISER Data WRITE\n",
 		 isert_cmd);
@@ -2701,22 +2757,11 @@
 	kfree(isert_np);
 }
 
-static int isert_check_state(struct isert_conn *isert_conn, int state)
-{
-	int ret;
-
-	mutex_lock(&isert_conn->conn_mutex);
-	ret = (isert_conn->state == state);
-	mutex_unlock(&isert_conn->conn_mutex);
-
-	return ret;
-}
-
-static void isert_free_conn(struct iscsi_conn *conn)
+static void isert_wait_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
 
-	pr_debug("isert_free_conn: Starting \n");
+	pr_debug("isert_wait_conn: Starting \n");
 	/*
 	 * Decrement post_send_buf_count for special case when called
 	 * from isert_do_control_comp() -> iscsit_logout_post_handler()
@@ -2726,38 +2771,29 @@
 		atomic_dec(&isert_conn->post_send_buf_count);
 
 	if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) {
-		pr_debug("Calling rdma_disconnect from isert_free_conn\n");
+		pr_debug("Calling rdma_disconnect from isert_wait_conn\n");
 		rdma_disconnect(isert_conn->conn_cm_id);
 	}
 	/*
 	 * Only wait for conn_wait_comp_err if the isert_conn made it
 	 * into full feature phase..
 	 */
-	if (isert_conn->state == ISER_CONN_UP) {
-		pr_debug("isert_free_conn: Before wait_event comp_err %d\n",
-			 isert_conn->state);
-		mutex_unlock(&isert_conn->conn_mutex);
-
-		wait_event(isert_conn->conn_wait_comp_err,
-			  (isert_check_state(isert_conn, ISER_CONN_TERMINATING)));
-
-		wait_event(isert_conn->conn_wait,
-			  (isert_check_state(isert_conn, ISER_CONN_DOWN)));
-
-		isert_put_conn(isert_conn);
-		return;
-	}
 	if (isert_conn->state == ISER_CONN_INIT) {
 		mutex_unlock(&isert_conn->conn_mutex);
-		isert_put_conn(isert_conn);
 		return;
 	}
-	pr_debug("isert_free_conn: wait_event conn_wait %d\n",
-		 isert_conn->state);
+	if (isert_conn->state == ISER_CONN_UP)
+		isert_conn->state = ISER_CONN_TERMINATING;
 	mutex_unlock(&isert_conn->conn_mutex);
 
-	wait_event(isert_conn->conn_wait,
-		  (isert_check_state(isert_conn, ISER_CONN_DOWN)));
+	wait_for_completion(&isert_conn->conn_wait_comp_err);
+
+	wait_for_completion(&isert_conn->conn_wait);
+}
+
+static void isert_free_conn(struct iscsi_conn *conn)
+{
+	struct isert_conn *isert_conn = conn->context;
 
 	isert_put_conn(isert_conn);
 }
@@ -2770,6 +2806,7 @@
 	.iscsit_setup_np	= isert_setup_np,
 	.iscsit_accept_np	= isert_accept_np,
 	.iscsit_free_np		= isert_free_np,
+	.iscsit_wait_conn	= isert_wait_conn,
 	.iscsit_free_conn	= isert_free_conn,
 	.iscsit_get_login_rx	= isert_get_login_rx,
 	.iscsit_put_login_tx	= isert_put_login_tx,
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 708a069..f6ae7f5 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -6,6 +6,7 @@
 
 #define ISERT_RDMA_LISTEN_BACKLOG	10
 #define ISCSI_ISER_SG_TABLESIZE		256
+#define ISER_FASTREG_LI_WRID		0xffffffffffffffffULL
 
 enum isert_desc_type {
 	ISCSI_TX_CONTROL,
@@ -45,6 +46,7 @@
 	struct isert_cmd *isert_cmd;
 	struct llist_node *comp_llnode_batch;
 	struct llist_node comp_llnode;
+	bool		llnode_active;
 	struct ib_send_wr send_wr;
 } __packed;
 
@@ -116,8 +118,8 @@
 	struct isert_device	*conn_device;
 	struct work_struct	conn_logout_work;
 	struct mutex		conn_mutex;
-	wait_queue_head_t	conn_wait;
-	wait_queue_head_t	conn_wait_comp_err;
+	struct completion	conn_wait;
+	struct completion	conn_wait_comp_err;
 	struct kref		conn_kref;
 	struct list_head	conn_fr_pool;
 	int			conn_fr_pool_size;
@@ -126,7 +128,6 @@
 #define ISERT_COMP_BATCH_COUNT	8
 	int			conn_comp_batch;
 	struct llist_head	conn_comp_llist;
-	struct mutex		conn_comp_mutex;
 };
 
 #define ISERT_MAX_CQ 64
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 520a7e5..0e537d8 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -3666,9 +3666,9 @@
 	unsigned long val;
 	int ret;
 
-	ret = strict_strtoul(page, 0, &val);
+	ret = kstrtoul(page, 0, &val);
 	if (ret < 0) {
-		pr_err("strict_strtoul() failed with ret: %d\n", ret);
+		pr_err("kstrtoul() failed with ret: %d\n", ret);
 		return -EINVAL;
 	}
 	if (val > MAX_SRPT_RDMA_SIZE) {
@@ -3706,9 +3706,9 @@
 	unsigned long val;
 	int ret;
 
-	ret = strict_strtoul(page, 0, &val);
+	ret = kstrtoul(page, 0, &val);
 	if (ret < 0) {
-		pr_err("strict_strtoul() failed with ret: %d\n", ret);
+		pr_err("kstrtoul() failed with ret: %d\n", ret);
 		return -EINVAL;
 	}
 	if (val > MAX_SRPT_RSP_SIZE) {
@@ -3746,9 +3746,9 @@
 	unsigned long val;
 	int ret;
 
-	ret = strict_strtoul(page, 0, &val);
+	ret = kstrtoul(page, 0, &val);
 	if (ret < 0) {
-		pr_err("strict_strtoul() failed with ret: %d\n", ret);
+		pr_err("kstrtoul() failed with ret: %d\n", ret);
 		return -EINVAL;
 	}
 	if (val > MAX_SRPT_SRQ_SIZE) {
@@ -3793,7 +3793,7 @@
 	unsigned long tmp;
         int ret;
 
-	ret = strict_strtoul(page, 0, &tmp);
+	ret = kstrtoul(page, 0, &tmp);
 	if (ret < 0) {
 		printk(KERN_ERR "Unable to extract srpt_tpg_store_enable\n");
 		return -EINVAL;
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index a06e125..ce953d8 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -954,11 +954,13 @@
 			return -EFAULT;
 
 		error = input_ff_upload(dev, &effect, file);
+		if (error)
+			return error;
 
 		if (put_user(effect.id, &(((struct ff_effect __user *)p)->id)))
 			return -EFAULT;
 
-		return error;
+		return 0;
 	}
 
 	/* Multi-number variable-length handlers */
diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c
index bb3b57b..5ef7fcf 100644
--- a/drivers/input/keyboard/adp5588-keys.c
+++ b/drivers/input/keyboard/adp5588-keys.c
@@ -76,8 +76,18 @@
 	struct adp5588_kpad *kpad = container_of(chip, struct adp5588_kpad, gc);
 	unsigned int bank = ADP5588_BANK(kpad->gpiomap[off]);
 	unsigned int bit = ADP5588_BIT(kpad->gpiomap[off]);
+	int val;
 
-	return !!(adp5588_read(kpad->client, GPIO_DAT_STAT1 + bank) & bit);
+	mutex_lock(&kpad->gpio_lock);
+
+	if (kpad->dir[bank] & bit)
+		val = kpad->dat_out[bank];
+	else
+		val = adp5588_read(kpad->client, GPIO_DAT_STAT1 + bank);
+
+	mutex_unlock(&kpad->gpio_lock);
+
+	return !!(val & bit);
 }
 
 static void adp5588_gpio_set_value(struct gpio_chip *chip,
diff --git a/drivers/input/misc/arizona-haptics.c b/drivers/input/misc/arizona-haptics.c
index 7a04f54..ef2e281 100644
--- a/drivers/input/misc/arizona-haptics.c
+++ b/drivers/input/misc/arizona-haptics.c
@@ -37,7 +37,6 @@
 						       struct arizona_haptics,
 						       work);
 	struct arizona *arizona = haptics->arizona;
-	struct mutex *dapm_mutex = &arizona->dapm->card->dapm_mutex;
 	int ret;
 
 	if (!haptics->arizona->dapm) {
@@ -67,13 +66,10 @@
 			return;
 		}
 
-		mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
 		ret = snd_soc_dapm_enable_pin(arizona->dapm, "HAPTICS");
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to start HAPTICS: %d\n",
 				ret);
-			mutex_unlock(dapm_mutex);
 			return;
 		}
 
@@ -81,21 +77,14 @@
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
 				ret);
-			mutex_unlock(dapm_mutex);
 			return;
 		}
-
-		mutex_unlock(dapm_mutex);
-
 	} else {
 		/* This disable sequence will be a noop if already enabled */
-		mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
 		ret = snd_soc_dapm_disable_pin(arizona->dapm, "HAPTICS");
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to disable HAPTICS: %d\n",
 				ret);
-			mutex_unlock(dapm_mutex);
 			return;
 		}
 
@@ -103,12 +92,9 @@
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
 				ret);
-			mutex_unlock(dapm_mutex);
 			return;
 		}
 
-		mutex_unlock(dapm_mutex);
-
 		ret = regmap_update_bits(arizona->regmap,
 					 ARIZONA_HAPTICS_CONTROL_1,
 					 ARIZONA_HAP_CTRL_MASK,
@@ -155,16 +141,11 @@
 static void arizona_haptics_close(struct input_dev *input)
 {
 	struct arizona_haptics *haptics = input_get_drvdata(input);
-	struct mutex *dapm_mutex = &haptics->arizona->dapm->card->dapm_mutex;
 
 	cancel_work_sync(&haptics->work);
 
-	mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
 	if (haptics->arizona->dapm)
 		snd_soc_dapm_disable_pin(haptics->arizona->dapm, "HAPTICS");
-
-	mutex_unlock(dapm_mutex);
 }
 
 static int arizona_haptics_probe(struct platform_device *pdev)
diff --git a/drivers/input/misc/da9052_onkey.c b/drivers/input/misc/da9052_onkey.c
index 1f695f2..184c8f2 100644
--- a/drivers/input/misc/da9052_onkey.c
+++ b/drivers/input/misc/da9052_onkey.c
@@ -27,29 +27,32 @@
 
 static void da9052_onkey_query(struct da9052_onkey *onkey)
 {
-	int key_stat;
+	int ret;
 
-	key_stat = da9052_reg_read(onkey->da9052, DA9052_EVENT_B_REG);
-	if (key_stat < 0) {
+	ret = da9052_reg_read(onkey->da9052, DA9052_STATUS_A_REG);
+	if (ret < 0) {
 		dev_err(onkey->da9052->dev,
-			"Failed to read onkey event %d\n", key_stat);
+			"Failed to read onkey event err=%d\n", ret);
 	} else {
 		/*
 		 * Since interrupt for deassertion of ONKEY pin is not
 		 * generated, onkey event state determines the onkey
 		 * button state.
 		 */
-		key_stat &= DA9052_EVENTB_ENONKEY;
-		input_report_key(onkey->input, KEY_POWER, key_stat);
-		input_sync(onkey->input);
-	}
+		bool pressed = !(ret & DA9052_STATUSA_NONKEY);
 
-	/*
-	 * Interrupt is generated only when the ONKEY pin is asserted.
-	 * Hence the deassertion of the pin is simulated through work queue.
-	 */
-	if (key_stat)
-		schedule_delayed_work(&onkey->work, msecs_to_jiffies(50));
+		input_report_key(onkey->input, KEY_POWER, pressed);
+		input_sync(onkey->input);
+
+		/*
+		 * Interrupt is generated only when the ONKEY pin
+		 * is asserted.  Hence the deassertion of the pin
+		 * is simulated through work queue.
+		 */
+		if (pressed)
+			schedule_delayed_work(&onkey->work,
+						msecs_to_jiffies(50));
+	}
 }
 
 static void da9052_onkey_work(struct work_struct *work)
diff --git a/drivers/input/mouse/cypress_ps2.c b/drivers/input/mouse/cypress_ps2.c
index 87095e2..8af34ff 100644
--- a/drivers/input/mouse/cypress_ps2.c
+++ b/drivers/input/mouse/cypress_ps2.c
@@ -409,7 +409,6 @@
 	__clear_bit(REL_X, input->relbit);
 	__clear_bit(REL_Y, input->relbit);
 
-	__set_bit(INPUT_PROP_BUTTONPAD, input->propbit);
 	__set_bit(EV_KEY, input->evbit);
 	__set_bit(BTN_LEFT, input->keybit);
 	__set_bit(BTN_RIGHT, input->keybit);
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 26386f9..d8d49d1 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -265,11 +265,22 @@
  * Read touchpad resolution and maximum reported coordinates
  * Resolution is left zero if touchpad does not support the query
  */
+
+static const int *quirk_min_max;
+
 static int synaptics_resolution(struct psmouse *psmouse)
 {
 	struct synaptics_data *priv = psmouse->private;
 	unsigned char resp[3];
 
+	if (quirk_min_max) {
+		priv->x_min = quirk_min_max[0];
+		priv->x_max = quirk_min_max[1];
+		priv->y_min = quirk_min_max[2];
+		priv->y_max = quirk_min_max[3];
+		return 0;
+	}
+
 	if (SYN_ID_MAJOR(priv->identity) < 4)
 		return 0;
 
@@ -1485,10 +1496,54 @@
 	{ }
 };
 
+static const struct dmi_system_id min_max_dmi_table[] __initconst = {
+#if defined(CONFIG_DMI)
+	{
+		/* Lenovo ThinkPad Helix */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"),
+		},
+		.driver_data = (int []){1024, 5052, 2258, 4832},
+	},
+	{
+		/* Lenovo ThinkPad X240 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X240"),
+		},
+		.driver_data = (int []){1232, 5710, 1156, 4696},
+	},
+	{
+		/* Lenovo ThinkPad T440s */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T440"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
+		/* Lenovo ThinkPad T540p */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T540"),
+		},
+		.driver_data = (int []){1024, 5056, 2058, 4832},
+	},
+#endif
+	{ }
+};
+
 void __init synaptics_module_init(void)
 {
+	const struct dmi_system_id *min_max_dmi;
+
 	impaired_toshiba_kbc = dmi_check_system(toshiba_dmi_table);
 	broken_olpc_ec = dmi_check_system(olpc_dmi_table);
+
+	min_max_dmi = dmi_first_match(min_max_dmi_table);
+	if (min_max_dmi)
+		quirk_min_max = min_max_dmi->driver_data;
 }
 
 static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode)
diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c
index 4c842c3..b604564 100644
--- a/drivers/input/mousedev.c
+++ b/drivers/input/mousedev.c
@@ -67,7 +67,6 @@
 	struct device dev;
 	struct cdev cdev;
 	bool exist;
-	bool is_mixdev;
 
 	struct list_head mixdev_node;
 	bool opened_by_mixdev;
@@ -77,6 +76,9 @@
 	int old_x[4], old_y[4];
 	int frac_dx, frac_dy;
 	unsigned long touch;
+
+	int (*open_device)(struct mousedev *mousedev);
+	void (*close_device)(struct mousedev *mousedev);
 };
 
 enum mousedev_emul {
@@ -116,9 +118,6 @@
 static struct mousedev *mousedev_mix;
 static LIST_HEAD(mousedev_mix_list);
 
-static void mixdev_open_devices(void);
-static void mixdev_close_devices(void);
-
 #define fx(i)  (mousedev->old_x[(mousedev->pkt_count - (i)) & 03])
 #define fy(i)  (mousedev->old_y[(mousedev->pkt_count - (i)) & 03])
 
@@ -428,9 +427,7 @@
 	if (retval)
 		return retval;
 
-	if (mousedev->is_mixdev)
-		mixdev_open_devices();
-	else if (!mousedev->exist)
+	if (!mousedev->exist)
 		retval = -ENODEV;
 	else if (!mousedev->open++) {
 		retval = input_open_device(&mousedev->handle);
@@ -446,9 +443,7 @@
 {
 	mutex_lock(&mousedev->mutex);
 
-	if (mousedev->is_mixdev)
-		mixdev_close_devices();
-	else if (mousedev->exist && !--mousedev->open)
+	if (mousedev->exist && !--mousedev->open)
 		input_close_device(&mousedev->handle);
 
 	mutex_unlock(&mousedev->mutex);
@@ -459,21 +454,29 @@
  * stream. Note that this function is called with mousedev_mix->mutex
  * held.
  */
-static void mixdev_open_devices(void)
+static int mixdev_open_devices(struct mousedev *mixdev)
 {
-	struct mousedev *mousedev;
+	int error;
 
-	if (mousedev_mix->open++)
-		return;
+	error = mutex_lock_interruptible(&mixdev->mutex);
+	if (error)
+		return error;
 
-	list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
-		if (!mousedev->opened_by_mixdev) {
-			if (mousedev_open_device(mousedev))
-				continue;
+	if (!mixdev->open++) {
+		struct mousedev *mousedev;
 
-			mousedev->opened_by_mixdev = true;
+		list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
+			if (!mousedev->opened_by_mixdev) {
+				if (mousedev_open_device(mousedev))
+					continue;
+
+				mousedev->opened_by_mixdev = true;
+			}
 		}
 	}
+
+	mutex_unlock(&mixdev->mutex);
+	return 0;
 }
 
 /*
@@ -481,19 +484,22 @@
  * device. Note that this function is called with mousedev_mix->mutex
  * held.
  */
-static void mixdev_close_devices(void)
+static void mixdev_close_devices(struct mousedev *mixdev)
 {
-	struct mousedev *mousedev;
+	mutex_lock(&mixdev->mutex);
 
-	if (--mousedev_mix->open)
-		return;
+	if (!--mixdev->open) {
+		struct mousedev *mousedev;
 
-	list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
-		if (mousedev->opened_by_mixdev) {
-			mousedev->opened_by_mixdev = false;
-			mousedev_close_device(mousedev);
+		list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
+			if (mousedev->opened_by_mixdev) {
+				mousedev->opened_by_mixdev = false;
+				mousedev_close_device(mousedev);
+			}
 		}
 	}
+
+	mutex_unlock(&mixdev->mutex);
 }
 
 
@@ -522,7 +528,7 @@
 	mousedev_detach_client(mousedev, client);
 	kfree(client);
 
-	mousedev_close_device(mousedev);
+	mousedev->close_device(mousedev);
 
 	return 0;
 }
@@ -550,7 +556,7 @@
 	client->mousedev = mousedev;
 	mousedev_attach_client(mousedev, client);
 
-	error = mousedev_open_device(mousedev);
+	error = mousedev->open_device(mousedev);
 	if (error)
 		goto err_free_client;
 
@@ -861,16 +867,21 @@
 
 	if (mixdev) {
 		dev_set_name(&mousedev->dev, "mice");
+
+		mousedev->open_device = mixdev_open_devices;
+		mousedev->close_device = mixdev_close_devices;
 	} else {
 		int dev_no = minor;
 		/* Normalize device number if it falls into legacy range */
 		if (dev_no < MOUSEDEV_MINOR_BASE + MOUSEDEV_MINORS)
 			dev_no -= MOUSEDEV_MINOR_BASE;
 		dev_set_name(&mousedev->dev, "mouse%d", dev_no);
+
+		mousedev->open_device = mousedev_open_device;
+		mousedev->close_device = mousedev_close_device;
 	}
 
 	mousedev->exist = true;
-	mousedev->is_mixdev = mixdev;
 	mousedev->handle.dev = input_get_device(dev);
 	mousedev->handle.name = dev_name(&mousedev->dev);
 	mousedev->handle.handler = handler;
@@ -919,7 +930,7 @@
 	device_del(&mousedev->dev);
 	mousedev_cleanup(mousedev);
 	input_free_minor(MINOR(mousedev->dev.devt));
-	if (!mousedev->is_mixdev)
+	if (mousedev != mousedev_mix)
 		input_unregister_handle(&mousedev->handle);
 	put_device(&mousedev->dev);
 }
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 8911850..1d9ab39 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -79,7 +79,6 @@
 
 #define ARM_SMMU_PTE_CONT_SIZE		(PAGE_SIZE * ARM_SMMU_PTE_CONT_ENTRIES)
 #define ARM_SMMU_PTE_CONT_MASK		(~(ARM_SMMU_PTE_CONT_SIZE - 1))
-#define ARM_SMMU_PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(pte_t))
 
 /* Stage-1 PTE */
 #define ARM_SMMU_PTE_AP_UNPRIV		(((pteval_t)1) << 6)
@@ -191,6 +190,9 @@
 #define ARM_SMMU_GR1_CBAR(n)		(0x0 + ((n) << 2))
 #define CBAR_VMID_SHIFT			0
 #define CBAR_VMID_MASK			0xff
+#define CBAR_S1_BPSHCFG_SHIFT		8
+#define CBAR_S1_BPSHCFG_MASK		3
+#define CBAR_S1_BPSHCFG_NSH		3
 #define CBAR_S1_MEMATTR_SHIFT		12
 #define CBAR_S1_MEMATTR_MASK		0xf
 #define CBAR_S1_MEMATTR_WB		0xf
@@ -393,7 +395,7 @@
 	struct arm_smmu_cfg		root_cfg;
 	phys_addr_t			output_mask;
 
-	struct mutex			lock;
+	spinlock_t			lock;
 };
 
 static DEFINE_SPINLOCK(arm_smmu_devices_lock);
@@ -632,6 +634,28 @@
 	return IRQ_HANDLED;
 }
 
+static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr,
+				   size_t size)
+{
+	unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
+
+
+	/* Ensure new page tables are visible to the hardware walker */
+	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) {
+		dsb();
+	} else {
+		/*
+		 * If the SMMU can't walk tables in the CPU caches, treat them
+		 * like non-coherent DMA since we need to flush the new entries
+		 * all the way out to memory. There's no possibility of
+		 * recursion here as the SMMU table walker will not be wired
+		 * through another SMMU.
+		 */
+		dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
+				DMA_TO_DEVICE);
+	}
+}
+
 static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 {
 	u32 reg;
@@ -650,11 +674,16 @@
 	if (smmu->version == 1)
 	      reg |= root_cfg->irptndx << CBAR_IRPTNDX_SHIFT;
 
-	/* Use the weakest memory type, so it is overridden by the pte */
-	if (stage1)
-		reg |= (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
-	else
+	/*
+	 * Use the weakest shareability/memory types, so they are
+	 * overridden by the ttbcr/pte.
+	 */
+	if (stage1) {
+		reg |= (CBAR_S1_BPSHCFG_NSH << CBAR_S1_BPSHCFG_SHIFT) |
+			(CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
+	} else {
 		reg |= ARM_SMMU_CB_VMID(root_cfg) << CBAR_VMID_SHIFT;
+	}
 	writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(root_cfg->cbndx));
 
 	if (smmu->version > 1) {
@@ -715,6 +744,8 @@
 	}
 
 	/* TTBR0 */
+	arm_smmu_flush_pgtable(smmu, root_cfg->pgd,
+			       PTRS_PER_PGD * sizeof(pgd_t));
 	reg = __pa(root_cfg->pgd);
 	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
 	reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
@@ -901,7 +932,7 @@
 		goto out_free_domain;
 	smmu_domain->root_cfg.pgd = pgd;
 
-	mutex_init(&smmu_domain->lock);
+	spin_lock_init(&smmu_domain->lock);
 	domain->priv = smmu_domain;
 	return 0;
 
@@ -1128,6 +1159,7 @@
 	struct arm_smmu_domain *smmu_domain = domain->priv;
 	struct arm_smmu_device *device_smmu = dev->archdata.iommu;
 	struct arm_smmu_master *master;
+	unsigned long flags;
 
 	if (!device_smmu) {
 		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
@@ -1138,7 +1170,7 @@
 	 * Sanity check the domain. We don't currently support domains
 	 * that cross between different SMMU chains.
 	 */
-	mutex_lock(&smmu_domain->lock);
+	spin_lock_irqsave(&smmu_domain->lock, flags);
 	if (!smmu_domain->leaf_smmu) {
 		/* Now that we have a master, we can finalise the domain */
 		ret = arm_smmu_init_domain_context(domain, dev);
@@ -1153,7 +1185,7 @@
 			dev_name(device_smmu->dev));
 		goto err_unlock;
 	}
-	mutex_unlock(&smmu_domain->lock);
+	spin_unlock_irqrestore(&smmu_domain->lock, flags);
 
 	/* Looks ok, so add the device to the domain */
 	master = find_smmu_master(smmu_domain->leaf_smmu, dev->of_node);
@@ -1163,7 +1195,7 @@
 	return arm_smmu_domain_add_master(smmu_domain, master);
 
 err_unlock:
-	mutex_unlock(&smmu_domain->lock);
+	spin_unlock_irqrestore(&smmu_domain->lock, flags);
 	return ret;
 }
 
@@ -1177,23 +1209,6 @@
 		arm_smmu_domain_remove_master(smmu_domain, master);
 }
 
-static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr,
-				   size_t size)
-{
-	unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
-
-	/*
-	 * If the SMMU can't walk tables in the CPU caches, treat them
-	 * like non-coherent DMA since we need to flush the new entries
-	 * all the way out to memory. There's no possibility of recursion
-	 * here as the SMMU table walker will not be wired through another
-	 * SMMU.
-	 */
-	if (!(smmu->features & ARM_SMMU_FEAT_COHERENT_WALK))
-		dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
-			     DMA_TO_DEVICE);
-}
-
 static bool arm_smmu_pte_is_contiguous_range(unsigned long addr,
 					     unsigned long end)
 {
@@ -1210,12 +1225,11 @@
 
 	if (pmd_none(*pmd)) {
 		/* Allocate a new set of tables */
-		pgtable_t table = alloc_page(PGALLOC_GFP);
+		pgtable_t table = alloc_page(GFP_ATOMIC|__GFP_ZERO);
 		if (!table)
 			return -ENOMEM;
 
-		arm_smmu_flush_pgtable(smmu, page_address(table),
-				       ARM_SMMU_PTE_HWTABLE_SIZE);
+		arm_smmu_flush_pgtable(smmu, page_address(table), PAGE_SIZE);
 		if (!pgtable_page_ctor(table)) {
 			__free_page(table);
 			return -ENOMEM;
@@ -1317,9 +1331,15 @@
 
 #ifndef __PAGETABLE_PMD_FOLDED
 	if (pud_none(*pud)) {
-		pmd = pmd_alloc_one(NULL, addr);
+		pmd = (pmd_t *)get_zeroed_page(GFP_ATOMIC);
 		if (!pmd)
 			return -ENOMEM;
+
+		arm_smmu_flush_pgtable(smmu, pmd, PAGE_SIZE);
+		pud_populate(NULL, pud, pmd);
+		arm_smmu_flush_pgtable(smmu, pud, sizeof(*pud));
+
+		pmd += pmd_index(addr);
 	} else
 #endif
 		pmd = pmd_offset(pud, addr);
@@ -1328,8 +1348,6 @@
 		next = pmd_addr_end(addr, end);
 		ret = arm_smmu_alloc_init_pte(smmu, pmd, addr, end, pfn,
 					      flags, stage);
-		pud_populate(NULL, pud, pmd);
-		arm_smmu_flush_pgtable(smmu, pud, sizeof(*pud));
 		phys += next - addr;
 	} while (pmd++, addr = next, addr < end);
 
@@ -1346,9 +1364,15 @@
 
 #ifndef __PAGETABLE_PUD_FOLDED
 	if (pgd_none(*pgd)) {
-		pud = pud_alloc_one(NULL, addr);
+		pud = (pud_t *)get_zeroed_page(GFP_ATOMIC);
 		if (!pud)
 			return -ENOMEM;
+
+		arm_smmu_flush_pgtable(smmu, pud, PAGE_SIZE);
+		pgd_populate(NULL, pgd, pud);
+		arm_smmu_flush_pgtable(smmu, pgd, sizeof(*pgd));
+
+		pud += pud_index(addr);
 	} else
 #endif
 		pud = pud_offset(pgd, addr);
@@ -1357,8 +1381,6 @@
 		next = pud_addr_end(addr, end);
 		ret = arm_smmu_alloc_init_pmd(smmu, pud, addr, next, phys,
 					      flags, stage);
-		pgd_populate(NULL, pud, pgd);
-		arm_smmu_flush_pgtable(smmu, pgd, sizeof(*pgd));
 		phys += next - addr;
 	} while (pud++, addr = next, addr < end);
 
@@ -1375,6 +1397,7 @@
 	struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
 	pgd_t *pgd = root_cfg->pgd;
 	struct arm_smmu_device *smmu = root_cfg->smmu;
+	unsigned long irqflags;
 
 	if (root_cfg->cbar == CBAR_TYPE_S2_TRANS) {
 		stage = 2;
@@ -1397,7 +1420,7 @@
 	if (paddr & ~output_mask)
 		return -ERANGE;
 
-	mutex_lock(&smmu_domain->lock);
+	spin_lock_irqsave(&smmu_domain->lock, irqflags);
 	pgd += pgd_index(iova);
 	end = iova + size;
 	do {
@@ -1413,11 +1436,7 @@
 	} while (pgd++, iova != end);
 
 out_unlock:
-	mutex_unlock(&smmu_domain->lock);
-
-	/* Ensure new page tables are visible to the hardware walker */
-	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
-		dsb();
+	spin_unlock_irqrestore(&smmu_domain->lock, irqflags);
 
 	return ret;
 }
@@ -1987,8 +2006,10 @@
 	if (!iommu_present(&platform_bus_type))
 		bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
 
+#ifdef CONFIG_ARM_AMBA
 	if (!iommu_present(&amba_bustype))
 		bus_set_iommu(&amba_bustype, &arm_smmu_ops);
+#endif
 
 	return 0;
 }
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
index d97fbe4..80fffba 100644
--- a/drivers/iommu/omap-iommu-debug.c
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -354,8 +354,8 @@
 			return -ENOMEM;					\
 	}
 
-#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 600)
-#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 400)
+#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 0600)
+#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 0400)
 
 static int iommu_debug_register(struct device *dev, void *data)
 {
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 86b484c..5194afb 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -21,6 +21,7 @@
 obj-$(CONFIG_RENESAS_INTC_IRQPIN)	+= irq-renesas-intc-irqpin.o
 obj-$(CONFIG_RENESAS_IRQC)		+= irq-renesas-irqc.o
 obj-$(CONFIG_VERSATILE_FPGA_IRQ)	+= irq-versatile-fpga.o
+obj-$(CONFIG_ARCH_NSPIRE)		+= irq-zevio.o
 obj-$(CONFIG_ARCH_VT8500)		+= irq-vt8500.o
 obj-$(CONFIG_TB10X_IRQC)		+= irq-tb10x.o
 obj-$(CONFIG_XTENSA)			+= irq-xtensa-pic.o
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 433cc85..5409564 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -59,8 +59,6 @@
 #define PCI_MSI_DOORBELL_END                    (32)
 #define PCI_MSI_DOORBELL_MASK                   0xFFFF0000
 
-static DEFINE_RAW_SPINLOCK(irq_controller_lock);
-
 static void __iomem *per_cpu_int_base;
 static void __iomem *main_int_base;
 static struct irq_domain *armada_370_xp_mpic_domain;
@@ -239,6 +237,8 @@
 #endif
 
 #ifdef CONFIG_SMP
+static DEFINE_RAW_SPINLOCK(irq_controller_lock);
+
 static int armada_xp_set_affinity(struct irq_data *d,
 				  const struct cpumask *mask_val, bool force)
 {
@@ -381,7 +381,7 @@
 						ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS)
 				& PCI_MSI_DOORBELL_MASK;
 
-			writel(~PCI_MSI_DOORBELL_MASK, per_cpu_int_base +
+			writel(~msimask, per_cpu_int_base +
 			       ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
 
 			for (msinr = PCI_MSI_DOORBELL_START;
@@ -407,7 +407,7 @@
 						ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS)
 				& IPI_DOORBELL_MASK;
 
-			writel(~IPI_DOORBELL_MASK, per_cpu_int_base +
+			writel(~ipimask, per_cpu_int_base +
 				ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
 
 			/* Handle all pending doorbells */
diff --git a/drivers/irqchip/irq-metag-ext.c b/drivers/irqchip/irq-metag-ext.c
index 92c41ab..2cb474a 100644
--- a/drivers/irqchip/irq-metag-ext.c
+++ b/drivers/irqchip/irq-metag-ext.c
@@ -515,7 +515,7 @@
 	 * one cpu (the interrupt code doesn't support it), so we just
 	 * pick the first cpu we find in 'cpumask'.
 	 */
-	cpu = cpumask_any(cpumask);
+	cpu = cpumask_any_and(cpumask, cpu_online_mask);
 	thread = cpu_2_hwthread_id[cpu];
 
 	metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR2(thread)), vec_addr);
diff --git a/drivers/irqchip/irq-metag.c b/drivers/irqchip/irq-metag.c
index 8e94d7a..c16c186 100644
--- a/drivers/irqchip/irq-metag.c
+++ b/drivers/irqchip/irq-metag.c
@@ -201,7 +201,7 @@
 	 * one cpu (the interrupt code doesn't support it), so we just
 	 * pick the first cpu we find in 'cpumask'.
 	 */
-	cpu = cpumask_any(cpumask);
+	cpu = cpumask_any_and(cpumask, cpu_online_mask);
 	thread = cpu_2_hwthread_id[cpu];
 
 	metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR1(thread)),
diff --git a/drivers/irqchip/irq-orion.c b/drivers/irqchip/irq-orion.c
index e51d400..8e41be6 100644
--- a/drivers/irqchip/irq-orion.c
+++ b/drivers/irqchip/irq-orion.c
@@ -111,7 +111,8 @@
 static void orion_bridge_irq_handler(unsigned int irq, struct irq_desc *desc)
 {
 	struct irq_domain *d = irq_get_handler_data(irq);
-	struct irq_chip_generic *gc = irq_get_domain_generic_chip(d, irq);
+
+	struct irq_chip_generic *gc = irq_get_domain_generic_chip(d, 0);
 	u32 stat = readl_relaxed(gc->reg_base + ORION_BRIDGE_IRQ_CAUSE) &
 		   gc->mask_cache;
 
@@ -123,6 +124,19 @@
 	}
 }
 
+/*
+ * Bridge IRQ_CAUSE is asserted regardless of IRQ_MASK register.
+ * To avoid interrupt events on stale irqs, we clear them before unmask.
+ */
+static unsigned int orion_bridge_irq_startup(struct irq_data *d)
+{
+	struct irq_chip_type *ct = irq_data_get_chip_type(d);
+
+	ct->chip.irq_ack(d);
+	ct->chip.irq_unmask(d);
+	return 0;
+}
+
 static int __init orion_bridge_irq_init(struct device_node *np,
 					struct device_node *parent)
 {
@@ -143,7 +157,7 @@
 	}
 
 	ret = irq_alloc_domain_generic_chips(domain, nrirqs, 1, np->name,
-			     handle_level_irq, clr, 0, IRQ_GC_INIT_MASK_CACHE);
+			     handle_edge_irq, clr, 0, IRQ_GC_INIT_MASK_CACHE);
 	if (ret) {
 		pr_err("%s: unable to alloc irq domain gc\n", np->name);
 		return ret;
@@ -176,12 +190,14 @@
 
 	gc->chip_types[0].regs.ack = ORION_BRIDGE_IRQ_CAUSE;
 	gc->chip_types[0].regs.mask = ORION_BRIDGE_IRQ_MASK;
+	gc->chip_types[0].chip.irq_startup = orion_bridge_irq_startup;
 	gc->chip_types[0].chip.irq_ack = irq_gc_ack_clr_bit;
 	gc->chip_types[0].chip.irq_mask = irq_gc_mask_clr_bit;
 	gc->chip_types[0].chip.irq_unmask = irq_gc_mask_set_bit;
 
-	/* mask all interrupts */
+	/* mask and clear all interrupts */
 	writel(0, gc->reg_base + ORION_BRIDGE_IRQ_MASK);
+	writel(0, gc->reg_base + ORION_BRIDGE_IRQ_CAUSE);
 
 	irq_set_handler_data(irq, domain);
 	irq_set_chained_handler(irq, orion_bridge_irq_handler);
diff --git a/drivers/irqchip/irq-zevio.c b/drivers/irqchip/irq-zevio.c
new file mode 100644
index 0000000..8ed04c4
--- /dev/null
+++ b/drivers/irqchip/irq-zevio.c
@@ -0,0 +1,127 @@
+/*
+ *  linux/drivers/irqchip/irq-zevio.c
+ *
+ *  Copyright (C) 2013 Daniel Tang <tangrs@tangrs.id.au>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2, as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#include <asm/mach/irq.h>
+#include <asm/exception.h>
+
+#include "irqchip.h"
+
+#define IO_STATUS	0x000
+#define IO_RAW_STATUS	0x004
+#define IO_ENABLE	0x008
+#define IO_DISABLE	0x00C
+#define IO_CURRENT	0x020
+#define IO_RESET	0x028
+#define IO_MAX_PRIOTY	0x02C
+
+#define IO_IRQ_BASE	0x000
+#define IO_FIQ_BASE	0x100
+
+#define IO_INVERT_SEL	0x200
+#define IO_STICKY_SEL	0x204
+#define IO_PRIORITY_SEL	0x300
+
+#define MAX_INTRS	32
+#define FIQ_START	MAX_INTRS
+
+static struct irq_domain *zevio_irq_domain;
+static void __iomem *zevio_irq_io;
+
+static void zevio_irq_ack(struct irq_data *irqd)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(irqd);
+	struct irq_chip_regs *regs =
+		&container_of(irqd->chip, struct irq_chip_type, chip)->regs;
+
+	readl(gc->reg_base + regs->ack);
+}
+
+static asmlinkage void __exception_irq_entry zevio_handle_irq(struct pt_regs *regs)
+{
+	int irqnr;
+
+	while (readl(zevio_irq_io + IO_STATUS)) {
+		irqnr = readl(zevio_irq_io + IO_CURRENT);
+		irqnr = irq_find_mapping(zevio_irq_domain, irqnr);
+		handle_IRQ(irqnr, regs);
+	};
+}
+
+static void __init zevio_init_irq_base(void __iomem *base)
+{
+	/* Disable all interrupts */
+	writel(~0, base + IO_DISABLE);
+
+	/* Accept interrupts of all priorities */
+	writel(0xF, base + IO_MAX_PRIOTY);
+
+	/* Reset existing interrupts */
+	readl(base + IO_RESET);
+}
+
+static int __init zevio_of_init(struct device_node *node,
+				struct device_node *parent)
+{
+	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
+	struct irq_chip_generic *gc;
+	int ret;
+
+	if (WARN_ON(zevio_irq_io || zevio_irq_domain))
+		return -EBUSY;
+
+	zevio_irq_io = of_iomap(node, 0);
+	BUG_ON(!zevio_irq_io);
+
+	/* Do not invert interrupt status bits */
+	writel(~0, zevio_irq_io + IO_INVERT_SEL);
+
+	/* Disable sticky interrupts */
+	writel(0, zevio_irq_io + IO_STICKY_SEL);
+
+	/* We don't use IRQ priorities. Set each IRQ to highest priority. */
+	memset_io(zevio_irq_io + IO_PRIORITY_SEL, 0, MAX_INTRS * sizeof(u32));
+
+	/* Init IRQ and FIQ */
+	zevio_init_irq_base(zevio_irq_io + IO_IRQ_BASE);
+	zevio_init_irq_base(zevio_irq_io + IO_FIQ_BASE);
+
+	zevio_irq_domain = irq_domain_add_linear(node, MAX_INTRS,
+						 &irq_generic_chip_ops, NULL);
+	BUG_ON(!zevio_irq_domain);
+
+	ret = irq_alloc_domain_generic_chips(zevio_irq_domain, MAX_INTRS, 1,
+					     "zevio_intc", handle_level_irq,
+					     clr, 0, IRQ_GC_INIT_MASK_CACHE);
+	BUG_ON(ret);
+
+	gc = irq_get_domain_generic_chip(zevio_irq_domain, 0);
+	gc->reg_base				= zevio_irq_io;
+	gc->chip_types[0].chip.irq_ack		= zevio_irq_ack;
+	gc->chip_types[0].chip.irq_mask		= irq_gc_mask_disable_reg;
+	gc->chip_types[0].chip.irq_unmask	= irq_gc_unmask_enable_reg;
+	gc->chip_types[0].regs.mask		= IO_IRQ_BASE + IO_ENABLE;
+	gc->chip_types[0].regs.enable		= IO_IRQ_BASE + IO_ENABLE;
+	gc->chip_types[0].regs.disable		= IO_IRQ_BASE + IO_DISABLE;
+	gc->chip_types[0].regs.ack		= IO_IRQ_BASE + IO_RESET;
+
+	set_handle_irq(zevio_handle_irq);
+
+	pr_info("TI-NSPIRE classic IRQ controller\n");
+	return 0;
+}
+
+IRQCHIP_DECLARE(zevio_irq, "lsi,zevio-intc", zevio_of_init);
diff --git a/drivers/isdn/capi/Kconfig b/drivers/isdn/capi/Kconfig
index f046865..9816c51 100644
--- a/drivers/isdn/capi/Kconfig
+++ b/drivers/isdn/capi/Kconfig
@@ -16,16 +16,6 @@
 	  This will increase the size of the kernelcapi module by 20 KB.
 	  If unsure, say Y.
 
-config ISDN_CAPI_MIDDLEWARE
-	bool "CAPI2.0 Middleware support"
-	depends on TTY
-	help
-	  This option will enhance the capabilities of the /dev/capi20
-	  interface.  It will provide a means of moving a data connection,
-	  established via the usual /dev/capi20 interface to a special tty
-	  device.  If you want to use pppd with pppdcapiplugin to dial up to
-	  your ISP, say Y here.
-
 config ISDN_CAPI_CAPI20
 	tristate "CAPI2.0 /dev/capi support"
 	help
@@ -34,6 +24,16 @@
 	  standardized libcapi20 to access this functionality.  You should say
 	  Y/M here.
 
+config ISDN_CAPI_MIDDLEWARE
+	bool "CAPI2.0 Middleware support"
+	depends on ISDN_CAPI_CAPI20 && TTY
+	help
+	  This option will enhance the capabilities of the /dev/capi20
+	  interface.  It will provide a means of moving a data connection,
+	  established via the usual /dev/capi20 interface to a special tty
+	  device.  If you want to use pppd with pppdcapiplugin to dial up to
+	  your ISP, say Y here.
+
 config ISDN_CAPI_CAPIDRV
 	tristate "CAPI2.0 capidrv interface support"
 	depends on ISDN_I4L
diff --git a/drivers/isdn/hisax/q931.c b/drivers/isdn/hisax/q931.c
index af1b020..b420f8b 100644
--- a/drivers/isdn/hisax/q931.c
+++ b/drivers/isdn/hisax/q931.c
@@ -810,7 +810,7 @@
 	dp += sprintf(dp, "    octet 3  ");
 	dp += prbits(dp, *p, 8, 8);
 	*dp++ = '\n';
-	if (!(*p++ & 80)) {
+	if (!(*p++ & 0x80)) {
 		dp += sprintf(dp, "    octet 4  ");
 		dp += prbits(dp, *p++, 8, 8);
 		*dp++ = '\n';
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 9a06fe8..95ad936 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -254,16 +254,6 @@
        ---help---
          Provides thin provisioning and snapshots that share a data store.
 
-config DM_DEBUG_BLOCK_STACK_TRACING
-	boolean "Keep stack trace of persistent data block lock holders"
-	depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA
-	select STACKTRACE
-	---help---
-	  Enable this for messages that may help debug problems with the
-	  block manager locking used by thin provisioning and caching.
-
-	  If unsure, say N.
-
 config DM_CACHE
        tristate "Cache target (EXPERIMENTAL)"
        depends on BLK_DEV_DM
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 0c707e4..a4c7306 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -210,7 +210,9 @@
 #define GC_MARK_RECLAIMABLE	0
 #define GC_MARK_DIRTY		1
 #define GC_MARK_METADATA	2
-BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 13);
+#define GC_SECTORS_USED_SIZE	13
+#define MAX_GC_SECTORS_USED	(~(~0ULL << GC_SECTORS_USED_SIZE))
+BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, GC_SECTORS_USED_SIZE);
 BITMASK(GC_MOVE, struct bucket, gc_mark, 15, 1);
 
 #include "journal.h"
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 4f6b594..3f74b4b 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -23,7 +23,7 @@
 	for (k = i->start; k < bset_bkey_last(i); k = next) {
 		next = bkey_next(k);
 
-		printk(KERN_ERR "block %u key %zi/%u: ", set,
+		printk(KERN_ERR "block %u key %li/%u: ", set,
 		       (uint64_t *) k - i->d, i->keys);
 
 		if (b->ops->key_dump)
@@ -1185,9 +1185,12 @@
 	struct bset *out = (void *) __get_free_pages(__GFP_NOWARN|GFP_NOIO,
 						     order);
 	if (!out) {
+		struct page *outp;
+
 		BUG_ON(order > state->page_order);
 
-		out = page_address(mempool_alloc(state->pool, GFP_NOIO));
+		outp = mempool_alloc(state->pool, GFP_NOIO);
+		out = page_address(outp);
 		used_mempool = true;
 		order = state->page_order;
 	}
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 98cc0a8..5f9c2a6 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1167,7 +1167,7 @@
 		/* guard against overflow */
 		SET_GC_SECTORS_USED(g, min_t(unsigned,
 					     GC_SECTORS_USED(g) + KEY_SIZE(k),
-					     (1 << 14) - 1));
+					     MAX_GC_SECTORS_USED));
 
 		BUG_ON(!GC_SECTORS_USED(g));
 	}
@@ -1805,7 +1805,7 @@
 
 static size_t insert_u64s_remaining(struct btree *b)
 {
-	ssize_t ret = bch_btree_keys_u64s_remaining(&b->keys);
+	long ret = bch_btree_keys_u64s_remaining(&b->keys);
 
 	/*
 	 * Might land in the middle of an existing extent and have to split it
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index c3ead58..416d1a3 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -194,7 +194,7 @@
 	mutex_unlock(&b->c->bucket_lock);
 	bch_extent_to_text(buf, sizeof(buf), k);
 	btree_bug(b,
-"inconsistent btree pointer %s: bucket %li pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i",
+"inconsistent btree pointer %s: bucket %zi pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i",
 		  buf, PTR_BUCKET_NR(b->c, k, i), atomic_read(&g->pin),
 		  g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen);
 	return true;
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 72cd213..5d5d031 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -353,14 +353,14 @@
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 	struct bio *bio = op->bio, *n;
 
-	if (op->bypass)
-		return bch_data_invalidate(cl);
-
 	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) {
 		set_gc_sectors(op->c);
 		wake_up_gc(op->c);
 	}
 
+	if (op->bypass)
+		return bch_data_invalidate(cl);
+
 	/*
 	 * Journal writes are marked REQ_FLUSH; if the original write was a
 	 * flush, it'll wait on the journal write.
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index c6ab693..d8458d4 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -416,7 +416,7 @@
 	return MAP_CONTINUE;
 }
 
-int bch_bset_print_stats(struct cache_set *c, char *buf)
+static int bch_bset_print_stats(struct cache_set *c, char *buf)
 {
 	struct bset_stats_op op;
 	int ret;
diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c
index 1e018e9..0e385e4 100644
--- a/drivers/md/dm-cache-policy-mq.c
+++ b/drivers/md/dm-cache-policy-mq.c
@@ -872,7 +872,7 @@
 {
 	struct mq_policy *mq = to_mq_policy(p);
 
-	kfree(mq->table);
+	vfree(mq->table);
 	epool_exit(&mq->cache_pool);
 	epool_exit(&mq->pre_cache_pool);
 	kfree(mq);
@@ -1245,7 +1245,7 @@
 
 	mq->nr_buckets = next_power(from_cblock(cache_size) / 2, 16);
 	mq->hash_bits = ffs(mq->nr_buckets) - 1;
-	mq->table = kzalloc(sizeof(*mq->table) * mq->nr_buckets, GFP_KERNEL);
+	mq->table = vzalloc(sizeof(*mq->table) * mq->nr_buckets);
 	if (!mq->table)
 		goto bad_alloc_table;
 
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index ffd472e..074b9c8 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -289,6 +289,7 @@
 	bool tick:1;
 	unsigned req_nr:2;
 	struct dm_deferred_entry *all_io_entry;
+	struct dm_hook_info hook_info;
 
 	/*
 	 * writethrough fields.  These MUST remain at the end of this
@@ -297,7 +298,6 @@
 	 */
 	struct cache *cache;
 	dm_cblock_t cblock;
-	struct dm_hook_info hook_info;
 	struct dm_bio_details bio_details;
 };
 
@@ -671,15 +671,16 @@
 			   dm_cblock_t cblock)
 {
 	sector_t bi_sector = bio->bi_iter.bi_sector;
+	sector_t block = from_cblock(cblock);
 
 	bio->bi_bdev = cache->cache_dev->bdev;
 	if (!block_size_is_power_of_two(cache))
 		bio->bi_iter.bi_sector =
-			(from_cblock(cblock) * cache->sectors_per_block) +
+			(block * cache->sectors_per_block) +
 			sector_div(bi_sector, cache->sectors_per_block);
 	else
 		bio->bi_iter.bi_sector =
-			(from_cblock(cblock) << cache->sectors_per_block_shift) |
+			(block << cache->sectors_per_block_shift) |
 			(bi_sector & (cache->sectors_per_block - 1));
 }
 
@@ -978,12 +979,13 @@
 	int r;
 	struct dm_io_region o_region, c_region;
 	struct cache *cache = mg->cache;
+	sector_t cblock = from_cblock(mg->cblock);
 
 	o_region.bdev = cache->origin_dev->bdev;
 	o_region.count = cache->sectors_per_block;
 
 	c_region.bdev = cache->cache_dev->bdev;
-	c_region.sector = from_cblock(mg->cblock) * cache->sectors_per_block;
+	c_region.sector = cblock * cache->sectors_per_block;
 	c_region.count = cache->sectors_per_block;
 
 	if (mg->writeback || mg->demote) {
@@ -1010,13 +1012,15 @@
 	struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);
 	unsigned long flags;
 
+	dm_unhook_bio(&pb->hook_info, bio);
+
 	if (err)
 		mg->err = true;
 
+	mg->requeue_holder = false;
+
 	spin_lock_irqsave(&cache->lock, flags);
 	list_add_tail(&mg->list, &cache->completed_migrations);
-	dm_unhook_bio(&pb->hook_info, bio);
-	mg->requeue_holder = false;
 	spin_unlock_irqrestore(&cache->lock, flags);
 
 	wake_worker(cache);
@@ -2461,20 +2465,18 @@
 	bool discarded_block;
 	struct dm_bio_prison_cell *cell;
 	struct policy_result lookup_result;
-	struct per_bio_data *pb;
+	struct per_bio_data *pb = init_per_bio_data(bio, pb_data_size);
 
-	if (from_oblock(block) > from_oblock(cache->origin_blocks)) {
+	if (unlikely(from_oblock(block) >= from_oblock(cache->origin_blocks))) {
 		/*
 		 * This can only occur if the io goes to a partial block at
 		 * the end of the origin device.  We don't cache these.
 		 * Just remap to the origin and carry on.
 		 */
-		remap_to_origin_clear_discard(cache, bio, block);
+		remap_to_origin(cache, bio);
 		return DM_MAPIO_REMAPPED;
 	}
 
-	pb = init_per_bio_data(bio, pb_data_size);
-
 	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD)) {
 		defer_bio(cache, bio);
 		return DM_MAPIO_SUBMITTED;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index b2b8a10..3842ac7 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -201,29 +201,28 @@
 /*
  * Functions for getting the pages from a bvec.
  */
-static void bio_get_page(struct dpages *dp,
-		  struct page **p, unsigned long *len, unsigned *offset)
+static void bio_get_page(struct dpages *dp, struct page **p,
+			 unsigned long *len, unsigned *offset)
 {
-	struct bio *bio = dp->context_ptr;
-	struct bio_vec bvec = bio_iovec(bio);
-	*p = bvec.bv_page;
-	*len = bvec.bv_len;
-	*offset = bvec.bv_offset;
+	struct bio_vec *bvec = dp->context_ptr;
+	*p = bvec->bv_page;
+	*len = bvec->bv_len - dp->context_u;
+	*offset = bvec->bv_offset + dp->context_u;
 }
 
 static void bio_next_page(struct dpages *dp)
 {
-	struct bio *bio = dp->context_ptr;
-	struct bio_vec bvec = bio_iovec(bio);
-
-	bio_advance(bio, bvec.bv_len);
+	struct bio_vec *bvec = dp->context_ptr;
+	dp->context_ptr = bvec + 1;
+	dp->context_u = 0;
 }
 
 static void bio_dp_init(struct dpages *dp, struct bio *bio)
 {
 	dp->get_page = bio_get_page;
 	dp->next_page = bio_next_page;
-	dp->context_ptr = bio;
+	dp->context_ptr = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
+	dp->context_u = bio->bi_iter.bi_bvec_done;
 }
 
 /*
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 6eb9dc9..422a9fd 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1626,8 +1626,11 @@
 	/*
 	 * Only pass ioctls through if the device sizes match exactly.
 	 */
-	if (!r && ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT)
-		r = scsi_verify_blk_ioctl(NULL, cmd);
+	if (!bdev || ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) {
+		int err = scsi_verify_blk_ioctl(NULL, cmd);
+		if (err)
+			r = err;
+	}
 
 	if (r == -ENOTCONN && !fatal_signal_pending(current))
 		queue_work(kmultipathd, &m->process_queued_ios);
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index f284e0b..7dfdb5c 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1244,6 +1244,9 @@
 
 			dm_bio_restore(bd, bio);
 			bio_record->details.bi_bdev = NULL;
+
+			atomic_inc(&bio->bi_remaining);
+
 			queue_bio(ms, bio, rw);
 			return DM_ENDIO_INCOMPLETE;
 		}
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index afc3d01..d6e8817 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -546,6 +546,9 @@
 		r = insert_exceptions(ps, area, callback, callback_context,
 				      &full);
 
+		if (!full)
+			memcpy(ps->area, area, ps->store->chunk_size << SECTOR_SHIFT);
+
 		dm_bufio_release(bp);
 
 		dm_bufio_forget(client, chunk);
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 7da3476..fb9efc8 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -76,7 +76,7 @@
 
 #define THIN_SUPERBLOCK_MAGIC 27022010
 #define THIN_SUPERBLOCK_LOCATION 0
-#define THIN_VERSION 1
+#define THIN_VERSION 2
 #define THIN_METADATA_CACHE_SIZE 64
 #define SECTOR_TO_BLOCK_SHIFT 3
 
@@ -483,7 +483,7 @@
 
 	disk_super->data_mapping_root = cpu_to_le64(pmd->root);
 	disk_super->device_details_root = cpu_to_le64(pmd->details_root);
-	disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
+	disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE);
 	disk_super->metadata_nr_blocks = cpu_to_le64(bdev_size >> SECTOR_TO_BLOCK_SHIFT);
 	disk_super->data_block_size = cpu_to_le32(pmd->data_block_size);
 
@@ -651,7 +651,7 @@
 {
 	int r;
 
-	pmd->bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE,
+	pmd->bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
 					  THIN_METADATA_CACHE_SIZE,
 					  THIN_MAX_CONCURRENT_LOCKS);
 	if (IS_ERR(pmd->bm)) {
@@ -1489,6 +1489,23 @@
 	return r;
 }
 
+bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd)
+{
+	bool r = false;
+	struct dm_thin_device *td, *tmp;
+
+	down_read(&pmd->root_lock);
+	list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) {
+		if (td->changed) {
+			r = td->changed;
+			break;
+		}
+	}
+	up_read(&pmd->root_lock);
+
+	return r;
+}
+
 bool dm_thin_aborted_changes(struct dm_thin_device *td)
 {
 	bool r;
@@ -1738,3 +1755,38 @@
 
 	return r;
 }
+
+int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd)
+{
+	int r;
+	struct dm_block *sblock;
+	struct thin_disk_superblock *disk_super;
+
+	down_write(&pmd->root_lock);
+	pmd->flags |= THIN_METADATA_NEEDS_CHECK_FLAG;
+
+	r = superblock_lock(pmd, &sblock);
+	if (r) {
+		DMERR("couldn't read superblock");
+		goto out;
+	}
+
+	disk_super = dm_block_data(sblock);
+	disk_super->flags = cpu_to_le32(pmd->flags);
+
+	dm_bm_unlock(sblock);
+out:
+	up_write(&pmd->root_lock);
+	return r;
+}
+
+bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd)
+{
+	bool needs_check;
+
+	down_read(&pmd->root_lock);
+	needs_check = pmd->flags & THIN_METADATA_NEEDS_CHECK_FLAG;
+	up_read(&pmd->root_lock);
+
+	return needs_check;
+}
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 9a36856..e3c857d 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -9,16 +9,14 @@
 
 #include "persistent-data/dm-block-manager.h"
 #include "persistent-data/dm-space-map.h"
+#include "persistent-data/dm-space-map-metadata.h"
 
-#define THIN_METADATA_BLOCK_SIZE 4096
+#define THIN_METADATA_BLOCK_SIZE DM_SM_METADATA_BLOCK_SIZE
 
 /*
  * The metadata device is currently limited in size.
- *
- * We have one block of index, which can hold 255 index entries.  Each
- * index entry contains allocation info about 16k metadata blocks.
  */
-#define THIN_METADATA_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT)))
+#define THIN_METADATA_MAX_SECTORS DM_SM_METADATA_MAX_SECTORS
 
 /*
  * A metadata device larger than 16GB triggers a warning.
@@ -27,6 +25,11 @@
 
 /*----------------------------------------------------------------*/
 
+/*
+ * Thin metadata superblock flags.
+ */
+#define THIN_METADATA_NEEDS_CHECK_FLAG (1 << 0)
+
 struct dm_pool_metadata;
 struct dm_thin_device;
 
@@ -161,6 +164,8 @@
  */
 bool dm_thin_changed_this_transaction(struct dm_thin_device *td);
 
+bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd);
+
 bool dm_thin_aborted_changes(struct dm_thin_device *td);
 
 int dm_thin_get_highest_mapped_block(struct dm_thin_device *td,
@@ -202,6 +207,12 @@
 					dm_sm_threshold_fn fn,
 					void *context);
 
+/*
+ * Updates the superblock immediately.
+ */
+int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd);
+bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd);
+
 /*----------------------------------------------------------------*/
 
 #endif
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index faaf944..be70d38 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -130,10 +130,11 @@
 struct dm_thin_new_mapping;
 
 /*
- * The pool runs in 3 modes.  Ordered in degraded order for comparisons.
+ * The pool runs in 4 modes.  Ordered in degraded order for comparisons.
  */
 enum pool_mode {
 	PM_WRITE,		/* metadata may be changed */
+	PM_OUT_OF_DATA_SPACE,	/* metadata may be changed, though data may not be allocated */
 	PM_READ_ONLY,		/* metadata may not be changed */
 	PM_FAIL,		/* all I/O fails */
 };
@@ -198,7 +199,6 @@
 };
 
 static enum pool_mode get_pool_mode(struct pool *pool);
-static void out_of_data_space(struct pool *pool);
 static void metadata_operation_failed(struct pool *pool, const char *op, int r);
 
 /*
@@ -226,6 +226,7 @@
 
 	struct pool *pool;
 	struct dm_thin_device *td;
+	bool requeue_mode:1;
 };
 
 /*----------------------------------------------------------------*/
@@ -369,14 +370,18 @@
 	struct dm_thin_new_mapping *overwrite_mapping;
 };
 
-static void __requeue_bio_list(struct thin_c *tc, struct bio_list *master)
+static void requeue_bio_list(struct thin_c *tc, struct bio_list *master)
 {
 	struct bio *bio;
 	struct bio_list bios;
+	unsigned long flags;
 
 	bio_list_init(&bios);
+
+	spin_lock_irqsave(&tc->pool->lock, flags);
 	bio_list_merge(&bios, master);
 	bio_list_init(master);
+	spin_unlock_irqrestore(&tc->pool->lock, flags);
 
 	while ((bio = bio_list_pop(&bios))) {
 		struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
@@ -391,12 +396,26 @@
 static void requeue_io(struct thin_c *tc)
 {
 	struct pool *pool = tc->pool;
+
+	requeue_bio_list(tc, &pool->deferred_bios);
+	requeue_bio_list(tc, &pool->retry_on_resume_list);
+}
+
+static void error_retry_list(struct pool *pool)
+{
+	struct bio *bio;
 	unsigned long flags;
+	struct bio_list bios;
+
+	bio_list_init(&bios);
 
 	spin_lock_irqsave(&pool->lock, flags);
-	__requeue_bio_list(tc, &pool->deferred_bios);
-	__requeue_bio_list(tc, &pool->retry_on_resume_list);
+	bio_list_merge(&bios, &pool->retry_on_resume_list);
+	bio_list_init(&pool->retry_on_resume_list);
 	spin_unlock_irqrestore(&pool->lock, flags);
+
+	while ((bio = bio_list_pop(&bios)))
+		bio_io_error(bio);
 }
 
 /*
@@ -925,13 +944,15 @@
 	}
 }
 
+static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
+
 static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
 {
 	int r;
 	dm_block_t free_blocks;
 	struct pool *pool = tc->pool;
 
-	if (get_pool_mode(pool) != PM_WRITE)
+	if (WARN_ON(get_pool_mode(pool) != PM_WRITE))
 		return -EINVAL;
 
 	r = dm_pool_get_free_block_count(pool->pmd, &free_blocks);
@@ -958,7 +979,7 @@
 		}
 
 		if (!free_blocks) {
-			out_of_data_space(pool);
+			set_pool_mode(pool, PM_OUT_OF_DATA_SPACE);
 			return -ENOSPC;
 		}
 	}
@@ -988,15 +1009,32 @@
 	spin_unlock_irqrestore(&pool->lock, flags);
 }
 
+static bool should_error_unserviceable_bio(struct pool *pool)
+{
+	enum pool_mode m = get_pool_mode(pool);
+
+	switch (m) {
+	case PM_WRITE:
+		/* Shouldn't get here */
+		DMERR_LIMIT("bio unserviceable, yet pool is in PM_WRITE mode");
+		return true;
+
+	case PM_OUT_OF_DATA_SPACE:
+		return pool->pf.error_if_no_space;
+
+	case PM_READ_ONLY:
+	case PM_FAIL:
+		return true;
+	default:
+		/* Shouldn't get here */
+		DMERR_LIMIT("bio unserviceable, yet pool has an unknown mode");
+		return true;
+	}
+}
+
 static void handle_unserviceable_bio(struct pool *pool, struct bio *bio)
 {
-	/*
-	 * When pool is read-only, no cell locking is needed because
-	 * nothing is changing.
-	 */
-	WARN_ON_ONCE(get_pool_mode(pool) != PM_READ_ONLY);
-
-	if (pool->pf.error_if_no_space)
+	if (should_error_unserviceable_bio(pool))
 		bio_io_error(bio);
 	else
 		retry_on_resume(bio);
@@ -1007,11 +1045,20 @@
 	struct bio *bio;
 	struct bio_list bios;
 
+	if (should_error_unserviceable_bio(pool)) {
+		cell_error(pool, cell);
+		return;
+	}
+
 	bio_list_init(&bios);
 	cell_release(pool, cell, &bios);
 
-	while ((bio = bio_list_pop(&bios)))
-		handle_unserviceable_bio(pool, bio);
+	if (should_error_unserviceable_bio(pool))
+		while ((bio = bio_list_pop(&bios)))
+			bio_io_error(bio);
+	else
+		while ((bio = bio_list_pop(&bios)))
+			retry_on_resume(bio);
 }
 
 static void process_discard(struct thin_c *tc, struct bio *bio)
@@ -1296,6 +1343,11 @@
 	}
 }
 
+static void process_bio_success(struct thin_c *tc, struct bio *bio)
+{
+	bio_endio(bio, 0);
+}
+
 static void process_bio_fail(struct thin_c *tc, struct bio *bio)
 {
 	bio_io_error(bio);
@@ -1328,6 +1380,11 @@
 		struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
 		struct thin_c *tc = h->tc;
 
+		if (tc->requeue_mode) {
+			bio_endio(bio, DM_ENDIO_REQUEUE);
+			continue;
+		}
+
 		/*
 		 * If we've got no free new_mapping structs, and processing
 		 * this bio might require one, we pause until there are some
@@ -1357,7 +1414,8 @@
 	bio_list_init(&pool->deferred_flush_bios);
 	spin_unlock_irqrestore(&pool->lock, flags);
 
-	if (bio_list_empty(&bios) && !need_commit_due_to_time(pool))
+	if (bio_list_empty(&bios) &&
+	    !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool)))
 		return;
 
 	if (commit(pool)) {
@@ -1393,51 +1451,134 @@
 
 /*----------------------------------------------------------------*/
 
+struct noflush_work {
+	struct work_struct worker;
+	struct thin_c *tc;
+
+	atomic_t complete;
+	wait_queue_head_t wait;
+};
+
+static void complete_noflush_work(struct noflush_work *w)
+{
+	atomic_set(&w->complete, 1);
+	wake_up(&w->wait);
+}
+
+static void do_noflush_start(struct work_struct *ws)
+{
+	struct noflush_work *w = container_of(ws, struct noflush_work, worker);
+	w->tc->requeue_mode = true;
+	requeue_io(w->tc);
+	complete_noflush_work(w);
+}
+
+static void do_noflush_stop(struct work_struct *ws)
+{
+	struct noflush_work *w = container_of(ws, struct noflush_work, worker);
+	w->tc->requeue_mode = false;
+	complete_noflush_work(w);
+}
+
+static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *))
+{
+	struct noflush_work w;
+
+	INIT_WORK(&w.worker, fn);
+	w.tc = tc;
+	atomic_set(&w.complete, 0);
+	init_waitqueue_head(&w.wait);
+
+	queue_work(tc->pool->wq, &w.worker);
+
+	wait_event(w.wait, atomic_read(&w.complete));
+}
+
+/*----------------------------------------------------------------*/
+
 static enum pool_mode get_pool_mode(struct pool *pool)
 {
 	return pool->pf.mode;
 }
 
+static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode)
+{
+	dm_table_event(pool->ti->table);
+	DMINFO("%s: switching pool to %s mode",
+	       dm_device_name(pool->pool_md), new_mode);
+}
+
 static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 {
-	int r;
-	enum pool_mode old_mode = pool->pf.mode;
+	struct pool_c *pt = pool->ti->private;
+	bool needs_check = dm_pool_metadata_needs_check(pool->pmd);
+	enum pool_mode old_mode = get_pool_mode(pool);
+
+	/*
+	 * Never allow the pool to transition to PM_WRITE mode if user
+	 * intervention is required to verify metadata and data consistency.
+	 */
+	if (new_mode == PM_WRITE && needs_check) {
+		DMERR("%s: unable to switch pool to write mode until repaired.",
+		      dm_device_name(pool->pool_md));
+		if (old_mode != new_mode)
+			new_mode = old_mode;
+		else
+			new_mode = PM_READ_ONLY;
+	}
+	/*
+	 * If we were in PM_FAIL mode, rollback of metadata failed.  We're
+	 * not going to recover without a thin_repair.	So we never let the
+	 * pool move out of the old mode.
+	 */
+	if (old_mode == PM_FAIL)
+		new_mode = old_mode;
 
 	switch (new_mode) {
 	case PM_FAIL:
 		if (old_mode != new_mode)
-			DMERR("%s: switching pool to failure mode",
-			      dm_device_name(pool->pool_md));
+			notify_of_pool_mode_change(pool, "failure");
 		dm_pool_metadata_read_only(pool->pmd);
 		pool->process_bio = process_bio_fail;
 		pool->process_discard = process_bio_fail;
 		pool->process_prepared_mapping = process_prepared_mapping_fail;
 		pool->process_prepared_discard = process_prepared_discard_fail;
+
+		error_retry_list(pool);
 		break;
 
 	case PM_READ_ONLY:
 		if (old_mode != new_mode)
-			DMERR("%s: switching pool to read-only mode",
-			      dm_device_name(pool->pool_md));
-		r = dm_pool_abort_metadata(pool->pmd);
-		if (r) {
-			DMERR("%s: aborting transaction failed",
-			      dm_device_name(pool->pool_md));
-			new_mode = PM_FAIL;
-			set_pool_mode(pool, new_mode);
-		} else {
-			dm_pool_metadata_read_only(pool->pmd);
-			pool->process_bio = process_bio_read_only;
-			pool->process_discard = process_discard;
-			pool->process_prepared_mapping = process_prepared_mapping_fail;
-			pool->process_prepared_discard = process_prepared_discard_passdown;
-		}
+			notify_of_pool_mode_change(pool, "read-only");
+		dm_pool_metadata_read_only(pool->pmd);
+		pool->process_bio = process_bio_read_only;
+		pool->process_discard = process_bio_success;
+		pool->process_prepared_mapping = process_prepared_mapping_fail;
+		pool->process_prepared_discard = process_prepared_discard_passdown;
+
+		error_retry_list(pool);
+		break;
+
+	case PM_OUT_OF_DATA_SPACE:
+		/*
+		 * Ideally we'd never hit this state; the low water mark
+		 * would trigger userland to extend the pool before we
+		 * completely run out of data space.  However, many small
+		 * IOs to unprovisioned space can consume data space at an
+		 * alarming rate.  Adjust your low water mark if you're
+		 * frequently seeing this mode.
+		 */
+		if (old_mode != new_mode)
+			notify_of_pool_mode_change(pool, "out-of-data-space");
+		pool->process_bio = process_bio_read_only;
+		pool->process_discard = process_discard;
+		pool->process_prepared_mapping = process_prepared_mapping;
+		pool->process_prepared_discard = process_prepared_discard_passdown;
 		break;
 
 	case PM_WRITE:
 		if (old_mode != new_mode)
-			DMINFO("%s: switching pool to write mode",
-			       dm_device_name(pool->pool_md));
+			notify_of_pool_mode_change(pool, "write");
 		dm_pool_metadata_read_write(pool->pmd);
 		pool->process_bio = process_bio;
 		pool->process_discard = process_discard;
@@ -1447,32 +1588,35 @@
 	}
 
 	pool->pf.mode = new_mode;
+	/*
+	 * The pool mode may have changed, sync it so bind_control_target()
+	 * doesn't cause an unexpected mode transition on resume.
+	 */
+	pt->adjusted_pf.mode = new_mode;
 }
 
-/*
- * Rather than calling set_pool_mode directly, use these which describe the
- * reason for mode degradation.
- */
-static void out_of_data_space(struct pool *pool)
+static void abort_transaction(struct pool *pool)
 {
-	DMERR_LIMIT("%s: no free data space available.",
-		    dm_device_name(pool->pool_md));
-	set_pool_mode(pool, PM_READ_ONLY);
+	const char *dev_name = dm_device_name(pool->pool_md);
+
+	DMERR_LIMIT("%s: aborting current metadata transaction", dev_name);
+	if (dm_pool_abort_metadata(pool->pmd)) {
+		DMERR("%s: failed to abort metadata transaction", dev_name);
+		set_pool_mode(pool, PM_FAIL);
+	}
+
+	if (dm_pool_metadata_set_needs_check(pool->pmd)) {
+		DMERR("%s: failed to set 'needs_check' flag in metadata", dev_name);
+		set_pool_mode(pool, PM_FAIL);
+	}
 }
 
 static void metadata_operation_failed(struct pool *pool, const char *op, int r)
 {
-	dm_block_t free_blocks;
-
 	DMERR_LIMIT("%s: metadata operation '%s' failed: error = %d",
 		    dm_device_name(pool->pool_md), op, r);
 
-	if (r == -ENOSPC &&
-	    !dm_pool_get_free_metadata_block_count(pool->pmd, &free_blocks) &&
-	    !free_blocks)
-		DMERR_LIMIT("%s: no free metadata space available.",
-			    dm_device_name(pool->pool_md));
-
+	abort_transaction(pool);
 	set_pool_mode(pool, PM_READ_ONLY);
 }
 
@@ -1523,6 +1667,11 @@
 
 	thin_hook_bio(tc, bio);
 
+	if (tc->requeue_mode) {
+		bio_endio(bio, DM_ENDIO_REQUEUE);
+		return DM_MAPIO_SUBMITTED;
+	}
+
 	if (get_pool_mode(tc->pool) == PM_FAIL) {
 		bio_io_error(bio);
 		return DM_MAPIO_SUBMITTED;
@@ -1686,7 +1835,7 @@
 	/*
 	 * We want to make sure that a pool in PM_FAIL mode is never upgraded.
 	 */
-	enum pool_mode old_mode = pool->pf.mode;
+	enum pool_mode old_mode = get_pool_mode(pool);
 	enum pool_mode new_mode = pt->adjusted_pf.mode;
 
 	/*
@@ -1700,16 +1849,6 @@
 	pool->pf = pt->adjusted_pf;
 	pool->low_water_blocks = pt->low_water_blocks;
 
-	/*
-	 * If we were in PM_FAIL mode, rollback of metadata failed.  We're
-	 * not going to recover without a thin_repair.  So we never let the
-	 * pool move out of the old mode.  On the other hand a PM_READ_ONLY
-	 * may have been due to a lack of metadata or data space, and may
-	 * now work (ie. if the underlying devices have been resized).
-	 */
-	if (old_mode == PM_FAIL)
-		new_mode = old_mode;
-
 	set_pool_mode(pool, new_mode);
 
 	return 0;
@@ -1999,16 +2138,27 @@
 	dm_table_event(pool->ti->table);
 }
 
-static sector_t get_metadata_dev_size(struct block_device *bdev)
+static sector_t get_dev_size(struct block_device *bdev)
 {
-	sector_t metadata_dev_size = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+	return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+}
+
+static void warn_if_metadata_device_too_big(struct block_device *bdev)
+{
+	sector_t metadata_dev_size = get_dev_size(bdev);
 	char buffer[BDEVNAME_SIZE];
 
-	if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING) {
+	if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING)
 		DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.",
 		       bdevname(bdev, buffer), THIN_METADATA_MAX_SECTORS);
-		metadata_dev_size = THIN_METADATA_MAX_SECTORS_WARNING;
-	}
+}
+
+static sector_t get_metadata_dev_size(struct block_device *bdev)
+{
+	sector_t metadata_dev_size = get_dev_size(bdev);
+
+	if (metadata_dev_size > THIN_METADATA_MAX_SECTORS)
+		metadata_dev_size = THIN_METADATA_MAX_SECTORS;
 
 	return metadata_dev_size;
 }
@@ -2017,7 +2167,7 @@
 {
 	sector_t metadata_dev_size = get_metadata_dev_size(bdev);
 
-	sector_div(metadata_dev_size, THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
+	sector_div(metadata_dev_size, THIN_METADATA_BLOCK_SIZE);
 
 	return metadata_dev_size;
 }
@@ -2095,12 +2245,7 @@
 		ti->error = "Error opening metadata block device";
 		goto out_unlock;
 	}
-
-	/*
-	 * Run for the side-effect of possibly issuing a warning if the
-	 * device is too big.
-	 */
-	(void) get_metadata_dev_size(metadata_dev->bdev);
+	warn_if_metadata_device_too_big(metadata_dev->bdev);
 
 	r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev);
 	if (r) {
@@ -2246,6 +2391,12 @@
 		return -EINVAL;
 
 	} else if (data_size > sb_data_size) {
+		if (dm_pool_metadata_needs_check(pool->pmd)) {
+			DMERR("%s: unable to grow the data device until repaired.",
+			      dm_device_name(pool->pool_md));
+			return 0;
+		}
+
 		if (sb_data_size)
 			DMINFO("%s: growing the data device from %llu to %llu blocks",
 			       dm_device_name(pool->pool_md),
@@ -2287,6 +2438,13 @@
 		return -EINVAL;
 
 	} else if (metadata_dev_size > sb_metadata_dev_size) {
+		if (dm_pool_metadata_needs_check(pool->pmd)) {
+			DMERR("%s: unable to grow the metadata device until repaired.",
+			      dm_device_name(pool->pool_md));
+			return 0;
+		}
+
+		warn_if_metadata_device_too_big(pool->md_dev);
 		DMINFO("%s: growing the metadata device from %llu to %llu blocks",
 		       dm_device_name(pool->pool_md),
 		       sb_metadata_dev_size, metadata_dev_size);
@@ -2673,7 +2831,9 @@
 		else
 			DMEMIT("- ");
 
-		if (pool->pf.mode == PM_READ_ONLY)
+		if (pool->pf.mode == PM_OUT_OF_DATA_SPACE)
+			DMEMIT("out_of_data_space ");
+		else if (pool->pf.mode == PM_READ_ONLY)
 			DMEMIT("ro ");
 		else
 			DMEMIT("rw ");
@@ -2787,7 +2947,7 @@
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 10, 0},
+	.version = {1, 11, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -2894,6 +3054,7 @@
 
 	if (get_pool_mode(tc->pool) == PM_FAIL) {
 		ti->error = "Couldn't open thin device, Pool is in fail mode";
+		r = -EINVAL;
 		goto bad_thin_open;
 	}
 
@@ -2905,7 +3066,7 @@
 
 	r = dm_set_target_max_io_len(ti, tc->pool->sectors_per_block);
 	if (r)
-		goto bad_thin_open;
+		goto bad_target_max_io_len;
 
 	ti->num_flush_bios = 1;
 	ti->flush_supported = true;
@@ -2926,6 +3087,8 @@
 
 	return 0;
 
+bad_target_max_io_len:
+	dm_pool_close_thin_device(tc->td);
 bad_thin_open:
 	__pool_dec(tc->pool);
 bad_pool_lookup:
@@ -2986,10 +3149,23 @@
 	return 0;
 }
 
+static void thin_presuspend(struct dm_target *ti)
+{
+	struct thin_c *tc = ti->private;
+
+	if (dm_noflush_suspending(ti))
+		noflush_work(tc, do_noflush_start);
+}
+
 static void thin_postsuspend(struct dm_target *ti)
 {
-	if (dm_noflush_suspending(ti))
-		requeue_io((struct thin_c *)ti->private);
+	struct thin_c *tc = ti->private;
+
+	/*
+	 * The dm_noflush_suspending flag has been cleared by now, so
+	 * unfortunately we must always run this.
+	 */
+	noflush_work(tc, do_noflush_stop);
 }
 
 /*
@@ -3074,12 +3250,13 @@
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 10, 0},
+	.version = {1, 11, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
 	.map = thin_map,
 	.end_io = thin_endio,
+	.presuspend = thin_presuspend,
 	.postsuspend = thin_postsuspend,
 	.status = thin_status,
 	.iterate_devices = thin_iterate_devices,
diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig
index 19b2687..0c2dec7 100644
--- a/drivers/md/persistent-data/Kconfig
+++ b/drivers/md/persistent-data/Kconfig
@@ -6,3 +6,13 @@
        ---help---
 	 Library providing immutable on-disk data structure support for
 	 device-mapper targets such as the thin provisioning target.
+
+config DM_DEBUG_BLOCK_STACK_TRACING
+       boolean "Keep stack trace of persistent data block lock holders"
+       depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA
+       select STACKTRACE
+       ---help---
+	 Enable this for messages that may help debug problems with the
+	 block manager locking used by thin provisioning and caching.
+
+	 If unsure, say N.
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 536782e..786b689 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -91,6 +91,69 @@
 	dm_block_t block;
 };
 
+struct bop_ring_buffer {
+	unsigned begin;
+	unsigned end;
+	struct block_op bops[MAX_RECURSIVE_ALLOCATIONS + 1];
+};
+
+static void brb_init(struct bop_ring_buffer *brb)
+{
+	brb->begin = 0;
+	brb->end = 0;
+}
+
+static bool brb_empty(struct bop_ring_buffer *brb)
+{
+	return brb->begin == brb->end;
+}
+
+static unsigned brb_next(struct bop_ring_buffer *brb, unsigned old)
+{
+	unsigned r = old + 1;
+	return (r >= (sizeof(brb->bops) / sizeof(*brb->bops))) ? 0 : r;
+}
+
+static int brb_push(struct bop_ring_buffer *brb,
+		    enum block_op_type type, dm_block_t b)
+{
+	struct block_op *bop;
+	unsigned next = brb_next(brb, brb->end);
+
+	/*
+	 * We don't allow the last bop to be filled, this way we can
+	 * differentiate between full and empty.
+	 */
+	if (next == brb->begin)
+		return -ENOMEM;
+
+	bop = brb->bops + brb->end;
+	bop->type = type;
+	bop->block = b;
+
+	brb->end = next;
+
+	return 0;
+}
+
+static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result)
+{
+	struct block_op *bop;
+
+	if (brb_empty(brb))
+		return -ENODATA;
+
+	bop = brb->bops + brb->begin;
+	result->type = bop->type;
+	result->block = bop->block;
+
+	brb->begin = brb_next(brb, brb->begin);
+
+	return 0;
+}
+
+/*----------------------------------------------------------------*/
+
 struct sm_metadata {
 	struct dm_space_map sm;
 
@@ -101,25 +164,20 @@
 
 	unsigned recursion_count;
 	unsigned allocated_this_transaction;
-	unsigned nr_uncommitted;
-	struct block_op uncommitted[MAX_RECURSIVE_ALLOCATIONS];
+	struct bop_ring_buffer uncommitted;
 
 	struct threshold threshold;
 };
 
 static int add_bop(struct sm_metadata *smm, enum block_op_type type, dm_block_t b)
 {
-	struct block_op *op;
+	int r = brb_push(&smm->uncommitted, type, b);
 
-	if (smm->nr_uncommitted == MAX_RECURSIVE_ALLOCATIONS) {
+	if (r) {
 		DMERR("too many recursive allocations");
 		return -ENOMEM;
 	}
 
-	op = smm->uncommitted + smm->nr_uncommitted++;
-	op->type = type;
-	op->block = b;
-
 	return 0;
 }
 
@@ -158,11 +216,17 @@
 		return -ENOMEM;
 	}
 
-	if (smm->recursion_count == 1 && smm->nr_uncommitted) {
-		while (smm->nr_uncommitted && !r) {
-			smm->nr_uncommitted--;
-			r = commit_bop(smm, smm->uncommitted +
-				       smm->nr_uncommitted);
+	if (smm->recursion_count == 1) {
+		while (!brb_empty(&smm->uncommitted)) {
+			struct block_op bop;
+
+			r = brb_pop(&smm->uncommitted, &bop);
+			if (r) {
+				DMERR("bug in bop ring buffer");
+				break;
+			}
+
+			r = commit_bop(smm, &bop);
 			if (r)
 				break;
 		}
@@ -217,7 +281,8 @@
 static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b,
 				 uint32_t *result)
 {
-	int r, i;
+	int r;
+	unsigned i;
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 	unsigned adjustment = 0;
 
@@ -225,8 +290,10 @@
 	 * We may have some uncommitted adjustments to add.  This list
 	 * should always be really short.
 	 */
-	for (i = 0; i < smm->nr_uncommitted; i++) {
-		struct block_op *op = smm->uncommitted + i;
+	for (i = smm->uncommitted.begin;
+	     i != smm->uncommitted.end;
+	     i = brb_next(&smm->uncommitted, i)) {
+		struct block_op *op = smm->uncommitted.bops + i;
 
 		if (op->block != b)
 			continue;
@@ -254,7 +321,8 @@
 static int sm_metadata_count_is_more_than_one(struct dm_space_map *sm,
 					      dm_block_t b, int *result)
 {
-	int r, i, adjustment = 0;
+	int r, adjustment = 0;
+	unsigned i;
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 	uint32_t rc;
 
@@ -262,8 +330,11 @@
 	 * We may have some uncommitted adjustments to add.  This list
 	 * should always be really short.
 	 */
-	for (i = 0; i < smm->nr_uncommitted; i++) {
-		struct block_op *op = smm->uncommitted + i;
+	for (i = smm->uncommitted.begin;
+	     i != smm->uncommitted.end;
+	     i = brb_next(&smm->uncommitted, i)) {
+
+		struct block_op *op = smm->uncommitted.bops + i;
 
 		if (op->block != b)
 			continue;
@@ -671,7 +742,7 @@
 	smm->begin = superblock + 1;
 	smm->recursion_count = 0;
 	smm->allocated_this_transaction = 0;
-	smm->nr_uncommitted = 0;
+	brb_init(&smm->uncommitted);
 	threshold_init(&smm->threshold);
 
 	memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm));
@@ -680,6 +751,8 @@
 	if (r)
 		return r;
 
+	if (nr_blocks > DM_SM_METADATA_MAX_BLOCKS)
+		nr_blocks = DM_SM_METADATA_MAX_BLOCKS;
 	r = sm_ll_extend(&smm->ll, nr_blocks);
 	if (r)
 		return r;
@@ -713,7 +786,7 @@
 	smm->begin = 0;
 	smm->recursion_count = 0;
 	smm->allocated_this_transaction = 0;
-	smm->nr_uncommitted = 0;
+	brb_init(&smm->uncommitted);
 	threshold_init(&smm->threshold);
 
 	memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll));
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.h b/drivers/md/persistent-data/dm-space-map-metadata.h
index 39bba08..64df923 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.h
+++ b/drivers/md/persistent-data/dm-space-map-metadata.h
@@ -9,6 +9,17 @@
 
 #include "dm-transaction-manager.h"
 
+#define DM_SM_METADATA_BLOCK_SIZE (4096 >> SECTOR_SHIFT)
+
+/*
+ * The metadata device is currently limited in size.
+ *
+ * We have one block of index, which can hold 255 index entries.  Each
+ * index entry contains allocation info about ~16k metadata blocks.
+ */
+#define DM_SM_METADATA_MAX_BLOCKS (255 * ((1 << 14) - 64))
+#define DM_SM_METADATA_MAX_SECTORS (DM_SM_METADATA_MAX_BLOCKS * DM_SM_METADATA_BLOCK_SIZE)
+
 /*
  * Unfortunately we have to use two-phase construction due to the cycle
  * between the tm and sm.
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index fd3a2a1..4a6ca1c 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1953,11 +1953,15 @@
 	for (i = 0; i < conf->raid_disks * 2; i++) {
 		int j;
 		int size;
+		int uptodate;
 		struct bio *b = r1_bio->bios[i];
 		if (b->bi_end_io != end_sync_read)
 			continue;
-		/* fixup the bio for reuse */
+		/* fixup the bio for reuse, but preserve BIO_UPTODATE */
+		uptodate = test_bit(BIO_UPTODATE, &b->bi_flags);
 		bio_reset(b);
+		if (!uptodate)
+			clear_bit(BIO_UPTODATE, &b->bi_flags);
 		b->bi_vcnt = vcnt;
 		b->bi_iter.bi_size = r1_bio->sectors << 9;
 		b->bi_iter.bi_sector = r1_bio->sector +
@@ -1990,11 +1994,14 @@
 		int j;
 		struct bio *pbio = r1_bio->bios[primary];
 		struct bio *sbio = r1_bio->bios[i];
+		int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags);
 
 		if (sbio->bi_end_io != end_sync_read)
 			continue;
+		/* Now we can 'fixup' the BIO_UPTODATE flag */
+		set_bit(BIO_UPTODATE, &sbio->bi_flags);
 
-		if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
+		if (uptodate) {
 			for (j = vcnt; j-- ; ) {
 				struct page *p, *s;
 				p = pbio->bi_io_vec[j].bv_page;
@@ -2009,7 +2016,7 @@
 		if (j >= 0)
 			atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
 		if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
-			      && test_bit(BIO_UPTODATE, &sbio->bi_flags))) {
+			      && uptodate)) {
 			/* No need to write to this device. */
 			sbio->bi_end_io = NULL;
 			rdev_dec_pending(conf->mirrors[i].rdev, mddev);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f1feade..16f5c21 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5514,23 +5514,43 @@
 	return sectors * (raid_disks - conf->max_degraded);
 }
 
+static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+	safe_put_page(percpu->spare_page);
+	kfree(percpu->scribble);
+	percpu->spare_page = NULL;
+	percpu->scribble = NULL;
+}
+
+static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+	if (conf->level == 6 && !percpu->spare_page)
+		percpu->spare_page = alloc_page(GFP_KERNEL);
+	if (!percpu->scribble)
+		percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
+
+	if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
+		free_scratch_buffer(conf, percpu);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static void raid5_free_percpu(struct r5conf *conf)
 {
-	struct raid5_percpu *percpu;
 	unsigned long cpu;
 
 	if (!conf->percpu)
 		return;
 
-	get_online_cpus();
-	for_each_possible_cpu(cpu) {
-		percpu = per_cpu_ptr(conf->percpu, cpu);
-		safe_put_page(percpu->spare_page);
-		kfree(percpu->scribble);
-	}
 #ifdef CONFIG_HOTPLUG_CPU
 	unregister_cpu_notifier(&conf->cpu_notify);
 #endif
+
+	get_online_cpus();
+	for_each_possible_cpu(cpu)
+		free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
 	put_online_cpus();
 
 	free_percpu(conf->percpu);
@@ -5557,15 +5577,7 @@
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		if (conf->level == 6 && !percpu->spare_page)
-			percpu->spare_page = alloc_page(GFP_KERNEL);
-		if (!percpu->scribble)
-			percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
-
-		if (!percpu->scribble ||
-		    (conf->level == 6 && !percpu->spare_page)) {
-			safe_put_page(percpu->spare_page);
-			kfree(percpu->scribble);
+		if (alloc_scratch_buffer(conf, percpu)) {
 			pr_err("%s: failed memory allocation for cpu%ld\n",
 			       __func__, cpu);
 			return notifier_from_errno(-ENOMEM);
@@ -5573,10 +5585,7 @@
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		safe_put_page(percpu->spare_page);
-		kfree(percpu->scribble);
-		percpu->spare_page = NULL;
-		percpu->scribble = NULL;
+		free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
 		break;
 	default:
 		break;
@@ -5588,40 +5597,29 @@
 static int raid5_alloc_percpu(struct r5conf *conf)
 {
 	unsigned long cpu;
-	struct page *spare_page;
-	struct raid5_percpu __percpu *allcpus;
-	void *scribble;
-	int err;
+	int err = 0;
 
-	allcpus = alloc_percpu(struct raid5_percpu);
-	if (!allcpus)
+	conf->percpu = alloc_percpu(struct raid5_percpu);
+	if (!conf->percpu)
 		return -ENOMEM;
-	conf->percpu = allcpus;
 
-	get_online_cpus();
-	err = 0;
-	for_each_present_cpu(cpu) {
-		if (conf->level == 6) {
-			spare_page = alloc_page(GFP_KERNEL);
-			if (!spare_page) {
-				err = -ENOMEM;
-				break;
-			}
-			per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page;
-		}
-		scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
-		if (!scribble) {
-			err = -ENOMEM;
-			break;
-		}
-		per_cpu_ptr(conf->percpu, cpu)->scribble = scribble;
-	}
 #ifdef CONFIG_HOTPLUG_CPU
 	conf->cpu_notify.notifier_call = raid456_cpu_notify;
 	conf->cpu_notify.priority = 0;
-	if (err == 0)
-		err = register_cpu_notifier(&conf->cpu_notify);
+	err = register_cpu_notifier(&conf->cpu_notify);
+	if (err)
+		return err;
 #endif
+
+	get_online_cpus();
+	for_each_present_cpu(cpu) {
+		err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
+		if (err) {
+			pr_err("%s: failed memory allocation for cpu%ld\n",
+			       __func__, cpu);
+			break;
+		}
+	}
 	put_online_cpus();
 
 	return err;
diff --git a/drivers/media/dvb-frontends/cx24117.c b/drivers/media/dvb-frontends/cx24117.c
index 68f768a..a6c3c9e 100644
--- a/drivers/media/dvb-frontends/cx24117.c
+++ b/drivers/media/dvb-frontends/cx24117.c
@@ -1176,7 +1176,7 @@
 
 	switch (demod) {
 	case 0:
-		dev_err(&state->priv->i2c->dev,
+		dev_err(&i2c->dev,
 			"%s: Error attaching frontend %d\n",
 			KBUILD_MODNAME, demod);
 		goto error1;
@@ -1200,12 +1200,6 @@
 	state->demod = demod - 1;
 	state->priv = priv;
 
-	/* test i2c bus for ack */
-	if (demod == 0) {
-		if (cx24117_readreg(state, 0x00) < 0)
-			goto error3;
-	}
-
 	dev_info(&state->priv->i2c->dev,
 		"%s: Attaching frontend %d\n",
 		KBUILD_MODNAME, state->demod);
@@ -1216,8 +1210,6 @@
 	state->frontend.demodulator_priv = state;
 	return &state->frontend;
 
-error3:
-	kfree(state);
 error2:
 	cx24117_release_priv(priv);
 error1:
diff --git a/drivers/media/dvb-frontends/nxt200x.c b/drivers/media/dvb-frontends/nxt200x.c
index 4bf0575..8a8e1ec 100644
--- a/drivers/media/dvb-frontends/nxt200x.c
+++ b/drivers/media/dvb-frontends/nxt200x.c
@@ -2,7 +2,7 @@
  *    Support for NXT2002 and NXT2004 - VSB/QAM
  *
  *    Copyright (C) 2005 Kirk Lapray <kirk.lapray@gmail.com>
- *    Copyright (C) 2006 Michael Krufky <mkrufky@m1k.net>
+ *    Copyright (C) 2006-2014 Michael Krufky <mkrufky@linuxtv.org>
  *    based on nxt2002 by Taylor Jacob <rtjacob@earthlink.net>
  *    and nxt2004 by Jean-Francois Thibert <jeanfrancois@sagetv.com>
  *
diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c
index 1effc21..9bbd665 100644
--- a/drivers/media/i2c/adv7842.c
+++ b/drivers/media/i2c/adv7842.c
@@ -2554,7 +2554,7 @@
 	sdp_write_and_or(sd, 0xdd, 0xf0, pdata->sdp_free_run_force |
 					 (pdata->sdp_free_run_cbar_en << 1) |
 					 (pdata->sdp_free_run_man_col_en << 2) |
-					 (pdata->sdp_free_run_force << 3));
+					 (pdata->sdp_free_run_auto << 3));
 
 	/* TODO from platform data */
 	cp_write(sd, 0x69, 0x14);   /* Enable CP CSC */
diff --git a/drivers/media/i2c/s5k5baf.c b/drivers/media/i2c/s5k5baf.c
index 4b83811..77e10e0 100644
--- a/drivers/media/i2c/s5k5baf.c
+++ b/drivers/media/i2c/s5k5baf.c
@@ -478,25 +478,33 @@
 				  u16 count, const u16 *seq)
 {
 	struct i2c_client *c = v4l2_get_subdevdata(&state->sd);
-	__be16 buf[count + 1];
-	int ret, n;
+	__be16 buf[65];
 
 	s5k5baf_i2c_write(state, REG_CMDWR_ADDR, addr);
 	if (state->error)
 		return;
 
-	buf[0] = __constant_cpu_to_be16(REG_CMD_BUF);
-	for (n = 1; n <= count; ++n)
-		buf[n] = cpu_to_be16(*seq++);
-
-	n *= 2;
-	ret = i2c_master_send(c, (char *)buf, n);
 	v4l2_dbg(3, debug, c, "i2c_write_seq(count=%d): %*ph\n", count,
-		 min(2 * count, 64), seq - count);
+		 min(2 * count, 64), seq);
 
-	if (ret != n) {
-		v4l2_err(c, "i2c_write_seq: error during transfer (%d)\n", ret);
-		state->error = ret;
+	buf[0] = __constant_cpu_to_be16(REG_CMD_BUF);
+
+	while (count > 0) {
+		int n = min_t(int, count, ARRAY_SIZE(buf) - 1);
+		int ret, i;
+
+		for (i = 1; i <= n; ++i)
+			buf[i] = cpu_to_be16(*seq++);
+
+		i *= 2;
+		ret = i2c_master_send(c, (char *)buf, i);
+		if (ret != i) {
+			v4l2_err(c, "i2c_write_seq: error during transfer (%d)\n", ret);
+			state->error = ret;
+			break;
+		}
+
+		count -= n;
 	}
 }
 
diff --git a/drivers/media/pci/bt8xx/bttv-cards.c b/drivers/media/pci/bt8xx/bttv-cards.c
index d85cb0a..6662b49 100644
--- a/drivers/media/pci/bt8xx/bttv-cards.c
+++ b/drivers/media/pci/bt8xx/bttv-cards.c
@@ -2426,7 +2426,7 @@
 	},
 		/* ---- card 0x87---------------------------------- */
 	[BTTV_BOARD_DVICO_FUSIONHDTV_5_LITE] = {
-		/* Michael Krufky <mkrufky@m1k.net> */
+		/* Michael Krufky <mkrufky@linuxtv.org> */
 		.name           = "DViCO FusionHDTV 5 Lite",
 		.tuner_type     = TUNER_LG_TDVS_H06XF, /* TDVS-H064F */
 		.tuner_addr	= ADDR_UNSET,
diff --git a/drivers/media/pci/bt8xx/bttv-gpio.c b/drivers/media/pci/bt8xx/bttv-gpio.c
index 922e823..3f364b7 100644
--- a/drivers/media/pci/bt8xx/bttv-gpio.c
+++ b/drivers/media/pci/bt8xx/bttv-gpio.c
@@ -98,7 +98,7 @@
 
 	err = device_register(&sub->dev);
 	if (0 != err) {
-		kfree(sub);
+		put_device(&sub->dev);
 		return err;
 	}
 	pr_info("%d: add subdevice \"%s\"\n", core->nr, dev_name(&sub->dev));
diff --git a/drivers/media/pci/saa7134/saa7134-cards.c b/drivers/media/pci/saa7134/saa7134-cards.c
index d45e7f6..c9b2350 100644
--- a/drivers/media/pci/saa7134/saa7134-cards.c
+++ b/drivers/media/pci/saa7134/saa7134-cards.c
@@ -2590,7 +2590,7 @@
 		}},
 	},
 	[SAA7134_BOARD_AVERMEDIA_AVERTVHD_A180] = {
-		/* Michael Krufky <mkrufky@m1k.net>
+		/* Michael Krufky <mkrufky@linuxtv.org>
 		 * Uses Alps Electric TDHU2, containing NXT2004 ATSC Decoder
 		 * AFAIK, there is no analog demod, thus,
 		 * no support for analog television.
diff --git a/drivers/media/platform/exynos4-is/fimc-core.c b/drivers/media/platform/exynos4-is/fimc-core.c
index a7dfd07..da2fc86 100644
--- a/drivers/media/platform/exynos4-is/fimc-core.c
+++ b/drivers/media/platform/exynos4-is/fimc-core.c
@@ -1027,7 +1027,8 @@
 	return 0;
 
 err_gclk:
-	clk_disable(fimc->clock[CLK_GATE]);
+	if (!pm_runtime_enabled(dev))
+		clk_disable(fimc->clock[CLK_GATE]);
 err_sd:
 	fimc_unregister_capture_subdev(fimc);
 err_sclk:
@@ -1036,6 +1037,7 @@
 	return ret;
 }
 
+#ifdef CONFIG_PM_RUNTIME
 static int fimc_runtime_resume(struct device *dev)
 {
 	struct fimc_dev *fimc =	dev_get_drvdata(dev);
@@ -1068,6 +1070,7 @@
 	dbg("fimc%d: state: 0x%lx", fimc->id, fimc->state);
 	return ret;
 }
+#endif
 
 #ifdef CONFIG_PM_SLEEP
 static int fimc_resume(struct device *dev)
diff --git a/drivers/media/platform/exynos4-is/fimc-lite.c b/drivers/media/platform/exynos4-is/fimc-lite.c
index 1234734..779ec3c 100644
--- a/drivers/media/platform/exynos4-is/fimc-lite.c
+++ b/drivers/media/platform/exynos4-is/fimc-lite.c
@@ -1563,7 +1563,7 @@
 	if (!pm_runtime_enabled(dev)) {
 		ret = clk_enable(fimc->clock);
 		if (ret < 0)
-			goto err_clk_put;
+			goto err_sd;
 	}
 
 	fimc->alloc_ctx = vb2_dma_contig_init_ctx(dev);
@@ -1579,7 +1579,8 @@
 	return 0;
 
 err_clk_dis:
-	clk_disable(fimc->clock);
+	if (!pm_runtime_enabled(dev))
+		clk_disable(fimc->clock);
 err_sd:
 	fimc_lite_unregister_capture_subdev(fimc);
 err_clk_put:
@@ -1587,6 +1588,7 @@
 	return ret;
 }
 
+#ifdef CONFIG_PM_RUNTIME
 static int fimc_lite_runtime_resume(struct device *dev)
 {
 	struct fimc_lite *fimc = dev_get_drvdata(dev);
@@ -1602,6 +1604,7 @@
 	clk_disable(fimc->clock);
 	return 0;
 }
+#endif
 
 #ifdef CONFIG_PM_SLEEP
 static int fimc_lite_resume(struct device *dev)
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c
index a1c78c8..7d68d0b 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-core.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c
@@ -175,7 +175,7 @@
 	{
 		.name		= "YUV 4:2:0 planar, Y/CbCr",
 		.fourcc		= V4L2_PIX_FMT_NV12,
-		.depth		= 16,
+		.depth		= 12,
 		.colplanes	= 2,
 		.h_align	= 1,
 		.v_align	= 1,
@@ -188,10 +188,10 @@
 	{
 		.name		= "YUV 4:2:0 planar, Y/CbCr",
 		.fourcc		= V4L2_PIX_FMT_NV12,
-		.depth		= 16,
-		.colplanes	= 4,
+		.depth		= 12,
+		.colplanes	= 2,
 		.h_align	= 4,
-		.v_align	= 1,
+		.v_align	= 4,
 		.flags		= SJPEG_FMT_FLAG_ENC_OUTPUT |
 				  SJPEG_FMT_FLAG_DEC_CAPTURE |
 				  SJPEG_FMT_FLAG_S5P |
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index 8f9b2cea..8ede8ea 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -1539,6 +1539,8 @@
 		&af9035_props, "TerraTec Cinergy T Stick Dual RC (rev. 2)", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_LEADTEK, 0x6a05,
 		&af9035_props, "Leadtek WinFast DTV Dongle Dual", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_HAUPPAUGE, 0xf900,
+		&af9035_props, "Hauppauge WinTV-MiniStick 2", NULL) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, af9035_id_table);
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
index d83df4b..0a98d04 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-demod.c - driver for the MaxLinear MXL111SF DVB-T demodulator
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -601,7 +601,7 @@
 EXPORT_SYMBOL_GPL(mxl111sf_demod_attach);
 
 MODULE_DESCRIPTION("MaxLinear MxL111SF DVB-T demodulator driver");
-MODULE_AUTHOR("Michael Krufky <mkrufky@kernellabs.com>");
+MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("0.1");
 
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h
index 3f3f8bf..2d4530f 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-demod.h - driver for the MaxLinear MXL111SF DVB-T demodulator
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.c
index e4121cb..a619410 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.c
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-gpio.c - driver for the MaxLinear MXL111SF
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.h
index 0220f54..b85a577 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.h
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-gpio.h - driver for the MaxLinear MXL111SF
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.c
index 3443455..a101d06 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.c
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-i2c.c - driver for the MaxLinear MXL111SF
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.h
index a57a45f..4657621 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.h
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-i2c.h - driver for the MaxLinear MXL111SF
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.c
index b741b3a..f6b3480 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.c
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-phy.c - driver for the MaxLinear MXL111SF
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.h
index f075607..0643738 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.h
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-phy.h - driver for the MaxLinear MXL111SF
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-reg.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-reg.h
index 17831b0..89bf115 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-reg.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-reg.h
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-reg.h - driver for the MaxLinear MXL111SF
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
index 879c529..a8d2c70 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-tuner.c - driver for the MaxLinear MXL111SF CMOS tuner
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -512,7 +512,7 @@
 EXPORT_SYMBOL_GPL(mxl111sf_tuner_attach);
 
 MODULE_DESCRIPTION("MaxLinear MxL111SF CMOS tuner driver");
-MODULE_AUTHOR("Michael Krufky <mkrufky@kernellabs.com>");
+MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("0.1");
 
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
index 90f583e..2046db2 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
@@ -1,7 +1,7 @@
 /*
  *  mxl111sf-tuner.h - driver for the MaxLinear MXL111SF CMOS tuner
  *
- *  Copyright (C) 2010 Michael Krufky <mkrufky@kernellabs.com>
+ *  Copyright (C) 2010-2014 Michael Krufky <mkrufky@linuxtv.org>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -68,7 +68,7 @@
 #else
 static inline
 struct dvb_frontend *mxl111sf_tuner_attach(struct dvb_frontend *fe,
-					   struct mxl111sf_state *mxl_state
+					   struct mxl111sf_state *mxl_state,
 					   struct mxl111sf_tuner_config *cfg)
 {
 	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf.c b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
index 08240e4..c7304fa 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2010 Michael Krufky (mkrufky@kernellabs.com)
+ * Copyright (C) 2010-2014 Michael Krufky (mkrufky@linuxtv.org)
  *
  *   This program is free software; you can redistribute it and/or modify it
  *   under the terms of the GNU General Public License as published by the Free
@@ -105,7 +105,7 @@
 		ret = -EINVAL;
 	}
 
-	pr_debug("R: (0x%02x, 0x%02x)\n", addr, *data);
+	pr_debug("R: (0x%02x, 0x%02x)\n", addr, buf[1]);
 fail:
 	return ret;
 }
@@ -1421,7 +1421,7 @@
 
 module_usb_driver(mxl111sf_usb_driver);
 
-MODULE_AUTHOR("Michael Krufky <mkrufky@kernellabs.com>");
+MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_DESCRIPTION("Driver for MaxLinear MxL111SF");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf.h b/drivers/media/usb/dvb-usb-v2/mxl111sf.h
index 9816de8..8516c01 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2010 Michael Krufky (mkrufky@kernellabs.com)
+ * Copyright (C) 2010-2014 Michael Krufky (mkrufky@linuxtv.org)
  *
  *   This program is free software; you can redistribute it and/or modify it
  *   under the terms of the GNU General Public License as published by the Free
diff --git a/drivers/media/usb/hdpvr/hdpvr-core.c b/drivers/media/usb/hdpvr/hdpvr-core.c
index 2f0c89c..c563896 100644
--- a/drivers/media/usb/hdpvr/hdpvr-core.c
+++ b/drivers/media/usb/hdpvr/hdpvr-core.c
@@ -198,7 +198,6 @@
 	hex_dump_to_buffer(response, 8, 16, 1, print_buf, 5*buf_size+1, 0);
 	v4l2_dbg(MSG_INFO, hdpvr_debug, &dev->v4l2_dev, " response: %s\n",
 		 print_buf);
-	kfree(print_buf);
 #endif
 
 	msleep(100);
@@ -214,6 +213,9 @@
 	retval = ret != 8;
 unlock:
 	mutex_unlock(&dev->usbc_mutex);
+#ifdef HDPVR_DEBUG
+	kfree(print_buf);
+#endif
 	return retval;
 }
 
diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c
index ee52b9f4..f7902fe 100644
--- a/drivers/media/v4l2-core/v4l2-dv-timings.c
+++ b/drivers/media/v4l2-core/v4l2-dv-timings.c
@@ -515,6 +515,7 @@
 		aspect.denominator = 9;
 	}
 	image_width = ((image_height * aspect.numerator) / aspect.denominator);
+	image_width = (image_width + GTF_CELL_GRAN/2) & ~(GTF_CELL_GRAN - 1);
 
 	/* Horizontal */
 	if (default_gtf)
diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c
index 65411ad..7e6b209 100644
--- a/drivers/media/v4l2-core/videobuf-dma-contig.c
+++ b/drivers/media/v4l2-core/videobuf-dma-contig.c
@@ -66,14 +66,11 @@
 static void videobuf_vm_open(struct vm_area_struct *vma)
 {
 	struct videobuf_mapping *map = vma->vm_private_data;
-	struct videobuf_queue *q = map->q;
 
-	dev_dbg(q->dev, "vm_open %p [count=%u,vma=%08lx-%08lx]\n",
+	dev_dbg(map->q->dev, "vm_open %p [count=%u,vma=%08lx-%08lx]\n",
 		map, map->count, vma->vm_start, vma->vm_end);
 
-	videobuf_queue_lock(q);
 	map->count++;
-	videobuf_queue_unlock(q);
 }
 
 static void videobuf_vm_close(struct vm_area_struct *vma)
@@ -85,11 +82,12 @@
 	dev_dbg(q->dev, "vm_close %p [count=%u,vma=%08lx-%08lx]\n",
 		map, map->count, vma->vm_start, vma->vm_end);
 
-	videobuf_queue_lock(q);
-	if (!--map->count) {
+	map->count--;
+	if (0 == map->count) {
 		struct videobuf_dma_contig_memory *mem;
 
 		dev_dbg(q->dev, "munmap %p q=%p\n", map, q);
+		videobuf_queue_lock(q);
 
 		/* We need first to cancel streams, before unmapping */
 		if (q->streaming)
@@ -128,8 +126,8 @@
 
 		kfree(map);
 
+		videobuf_queue_unlock(q);
 	}
-	videobuf_queue_unlock(q);
 }
 
 static const struct vm_operations_struct videobuf_vm_ops = {
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 9db674c..828e7c1 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -338,14 +338,11 @@
 static void videobuf_vm_open(struct vm_area_struct *vma)
 {
 	struct videobuf_mapping *map = vma->vm_private_data;
-	struct videobuf_queue *q = map->q;
 
 	dprintk(2, "vm_open %p [count=%d,vma=%08lx-%08lx]\n", map,
 		map->count, vma->vm_start, vma->vm_end);
 
-	videobuf_queue_lock(q);
 	map->count++;
-	videobuf_queue_unlock(q);
 }
 
 static void videobuf_vm_close(struct vm_area_struct *vma)
@@ -358,9 +355,10 @@
 	dprintk(2, "vm_close %p [count=%d,vma=%08lx-%08lx]\n", map,
 		map->count, vma->vm_start, vma->vm_end);
 
-	videobuf_queue_lock(q);
-	if (!--map->count) {
+	map->count--;
+	if (0 == map->count) {
 		dprintk(1, "munmap %p q=%p\n", map, q);
+		videobuf_queue_lock(q);
 		for (i = 0; i < VIDEO_MAX_FRAME; i++) {
 			if (NULL == q->bufs[i])
 				continue;
@@ -376,9 +374,9 @@
 			q->bufs[i]->baddr = 0;
 			q->ops->buf_release(q, q->bufs[i]);
 		}
+		videobuf_queue_unlock(q);
 		kfree(map);
 	}
-	videobuf_queue_unlock(q);
 	return;
 }
 
diff --git a/drivers/media/v4l2-core/videobuf-vmalloc.c b/drivers/media/v4l2-core/videobuf-vmalloc.c
index 1365c65..2ff7fcc 100644
--- a/drivers/media/v4l2-core/videobuf-vmalloc.c
+++ b/drivers/media/v4l2-core/videobuf-vmalloc.c
@@ -54,14 +54,11 @@
 static void videobuf_vm_open(struct vm_area_struct *vma)
 {
 	struct videobuf_mapping *map = vma->vm_private_data;
-	struct videobuf_queue *q = map->q;
 
 	dprintk(2, "vm_open %p [count=%u,vma=%08lx-%08lx]\n", map,
 		map->count, vma->vm_start, vma->vm_end);
 
-	videobuf_queue_lock(q);
 	map->count++;
-	videobuf_queue_unlock(q);
 }
 
 static void videobuf_vm_close(struct vm_area_struct *vma)
@@ -73,11 +70,12 @@
 	dprintk(2, "vm_close %p [count=%u,vma=%08lx-%08lx]\n", map,
 		map->count, vma->vm_start, vma->vm_end);
 
-	videobuf_queue_lock(q);
-	if (!--map->count) {
+	map->count--;
+	if (0 == map->count) {
 		struct videobuf_vmalloc_memory *mem;
 
 		dprintk(1, "munmap %p q=%p\n", map, q);
+		videobuf_queue_lock(q);
 
 		/* We need first to cancel streams, before unmapping */
 		if (q->streaming)
@@ -116,8 +114,8 @@
 
 		kfree(map);
 
+		videobuf_queue_unlock(q);
 	}
-	videobuf_queue_unlock(q);
 
 	return;
 }
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 5a5fb7f..a127925 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -1776,6 +1776,11 @@
 		return 0;
 	}
 
+	if (!q->num_buffers) {
+		dprintk(1, "streamon: no buffers have been allocated\n");
+		return -EINVAL;
+	}
+
 	/*
 	 * If any buffers were queued before streamon,
 	 * we can now pass them to driver for processing.
diff --git a/drivers/message/i2o/i2o_config.c b/drivers/message/i2o/i2o_config.c
index a60c188..04bd3b6 100644
--- a/drivers/message/i2o/i2o_config.c
+++ b/drivers/message/i2o/i2o_config.c
@@ -754,19 +754,19 @@
 				 unsigned long arg)
 {
 	int ret;
-	mutex_lock(&i2o_cfg_mutex);
 	switch (cmd) {
 	case I2OGETIOPS:
 		ret = i2o_cfg_ioctl(file, cmd, arg);
 		break;
 	case I2OPASSTHRU32:
+		mutex_lock(&i2o_cfg_mutex);
 		ret = i2o_cfg_passthru32(file, cmd, arg);
+		mutex_unlock(&i2o_cfg_mutex);
 		break;
 	default:
 		ret = -ENOIOCTLCMD;
 		break;
 	}
-	mutex_unlock(&i2o_cfg_mutex);
 	return ret;
 }
 
diff --git a/drivers/mfd/da9055-i2c.c b/drivers/mfd/da9055-i2c.c
index 13af7e5..8103e43 100644
--- a/drivers/mfd/da9055-i2c.c
+++ b/drivers/mfd/da9055-i2c.c
@@ -53,17 +53,25 @@
 	return 0;
 }
 
+/*
+ * DO NOT change the device Ids. The naming is intentionally specific as both
+ * the PMIC and CODEC parts of this chip are instantiated separately as I2C
+ * devices (both have configurable I2C addresses, and are to all intents and
+ * purposes separate). As a result there are specific DA9055 ids for PMIC
+ * and CODEC, which must be different to operate together.
+ */
 static struct i2c_device_id da9055_i2c_id[] = {
-	{"da9055", 0},
+	{"da9055-pmic", 0},
 	{ }
 };
+MODULE_DEVICE_TABLE(i2c, da9055_i2c_id);
 
 static struct i2c_driver da9055_i2c_driver = {
 	.probe = da9055_i2c_probe,
 	.remove = da9055_i2c_remove,
 	.id_table = da9055_i2c_id,
 	.driver = {
-		.name = "da9055",
+		.name = "da9055-pmic",
 		.owner = THIS_MODULE,
 	},
 };
diff --git a/drivers/mfd/max14577.c b/drivers/mfd/max14577.c
index ac514fb..71aa14a 100644
--- a/drivers/mfd/max14577.c
+++ b/drivers/mfd/max14577.c
@@ -173,6 +173,7 @@
 };
 MODULE_DEVICE_TABLE(i2c, max14577_i2c_id);
 
+#ifdef CONFIG_PM_SLEEP
 static int max14577_suspend(struct device *dev)
 {
 	struct i2c_client *i2c = container_of(dev, struct i2c_client, dev);
@@ -208,6 +209,7 @@
 
 	return 0;
 }
+#endif /* CONFIG_PM_SLEEP */
 
 static struct of_device_id max14577_dt_match[] = {
 	{ .compatible = "maxim,max14577", },
diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c
index be88a3b..5adede0 100644
--- a/drivers/mfd/max8997.c
+++ b/drivers/mfd/max8997.c
@@ -164,15 +164,15 @@
 	return pd;
 }
 
-static inline int max8997_i2c_get_driver_data(struct i2c_client *i2c,
+static inline unsigned long max8997_i2c_get_driver_data(struct i2c_client *i2c,
 						const struct i2c_device_id *id)
 {
 	if (IS_ENABLED(CONFIG_OF) && i2c->dev.of_node) {
 		const struct of_device_id *match;
 		match = of_match_node(max8997_pmic_dt_match, i2c->dev.of_node);
-		return (int)match->data;
+		return (unsigned long)match->data;
 	}
-	return (int)id->driver_data;
+	return id->driver_data;
 }
 
 static int max8997_i2c_probe(struct i2c_client *i2c,
diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c
index 612ca40..5d5e186 100644
--- a/drivers/mfd/max8998.c
+++ b/drivers/mfd/max8998.c
@@ -169,16 +169,16 @@
 	return pd;
 }
 
-static inline int max8998_i2c_get_driver_data(struct i2c_client *i2c,
+static inline unsigned long max8998_i2c_get_driver_data(struct i2c_client *i2c,
 						const struct i2c_device_id *id)
 {
 	if (IS_ENABLED(CONFIG_OF) && i2c->dev.of_node) {
 		const struct of_device_id *match;
 		match = of_match_node(max8998_dt_match, i2c->dev.of_node);
-		return (int)(long)match->data;
+		return (unsigned long)match->data;
 	}
 
-	return (int)id->driver_data;
+	return id->driver_data;
 }
 
 static int max8998_i2c_probe(struct i2c_client *i2c,
diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index a139798..714e213 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -315,6 +315,7 @@
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int sec_pmic_suspend(struct device *dev)
 {
 	struct i2c_client *i2c = container_of(dev, struct i2c_client, dev);
@@ -349,6 +350,7 @@
 
 	return 0;
 }
+#endif /* CONFIG_PM_SLEEP */
 
 static SIMPLE_DEV_PM_OPS(sec_pmic_pm_ops, sec_pmic_suspend, sec_pmic_resume);
 
diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c
index 966cf65..3cc4c70 100644
--- a/drivers/mfd/tps65217.c
+++ b/drivers/mfd/tps65217.c
@@ -158,7 +158,7 @@
 {
 	struct tps65217 *tps;
 	unsigned int version;
-	unsigned int chip_id = ids->driver_data;
+	unsigned long chip_id = ids->driver_data;
 	const struct of_device_id *match;
 	bool status_off = false;
 	int ret;
@@ -170,7 +170,7 @@
 				"Failed to find matching dt id\n");
 			return -EINVAL;
 		}
-		chip_id = (unsigned int)(unsigned long)match->data;
+		chip_id = (unsigned long)match->data;
 		status_off = of_property_read_bool(client->dev.of_node,
 					"ti,pmic-shutdown-controller");
 	}
diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index ba04f1b..e6fab94 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -636,7 +636,7 @@
 	if (i2c->dev.of_node) {
 		of_id = of_match_device(wm8994_of_match, &i2c->dev);
 		if (of_id)
-			wm8994->type = (int)of_id->data;
+			wm8994->type = (enum wm8994_type)of_id->data;
 	} else {
 		wm8994->type = id->driver_data;
 	}
diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c
index 8f8a6b3..2c2c9cc 100644
--- a/drivers/misc/genwqe/card_dev.c
+++ b/drivers/misc/genwqe/card_dev.c
@@ -787,6 +787,7 @@
 	if (rc != 0) {
 		dev_err(&pci_dev->dev,
 			"[%s] genwqe_user_vmap rc=%d\n", __func__, rc);
+		kfree(dma_map);
 		return rc;
 	}
 
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 1ee2b94..89a5579 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -666,7 +666,6 @@
 		goto err;
 
 	cb->fop_type = MEI_FOP_READ;
-	cl->read_cb = cb;
 	if (dev->hbuf_is_ready) {
 		dev->hbuf_is_ready = false;
 		if (mei_hbm_cl_flow_control_req(dev, cl)) {
@@ -678,6 +677,9 @@
 	} else {
 		list_add_tail(&cb->list, &dev->ctrl_wr_list.list);
 	}
+
+	cl->read_cb = cb;
+
 	return rets;
 err:
 	mei_io_cb_free(cb);
@@ -908,7 +910,6 @@
 	list_for_each_entry_safe(cl, next, &dev->file_list, link) {
 		cl->state = MEI_FILE_DISCONNECTED;
 		cl->mei_flow_ctrl_creds = 0;
-		cl->read_cb = NULL;
 		cl->timer_count = 0;
 	}
 }
@@ -942,8 +943,16 @@
 void mei_cl_all_write_clear(struct mei_device *dev)
 {
 	struct mei_cl_cb *cb, *next;
+	struct list_head *list;
 
-	list_for_each_entry_safe(cb, next, &dev->write_list.list, list) {
+	list = &dev->write_list.list;
+	list_for_each_entry_safe(cb, next, list, list) {
+		list_del(&cb->list);
+		mei_io_cb_free(cb);
+	}
+
+	list = &dev->write_waiting_list.list;
+	list_for_each_entry_safe(cb, next, list, list) {
 		list_del(&cb->list);
 		mei_io_cb_free(cb);
 	}
diff --git a/drivers/misc/mic/host/mic_virtio.c b/drivers/misc/mic/host/mic_virtio.c
index 752ff87..7e1ef0e 100644
--- a/drivers/misc/mic/host/mic_virtio.c
+++ b/drivers/misc/mic/host/mic_virtio.c
@@ -156,7 +156,8 @@
 static int _mic_virtio_copy(struct mic_vdev *mvdev,
 	struct mic_copy_desc *copy)
 {
-	int ret = 0, iovcnt = copy->iovcnt;
+	int ret = 0;
+	u32 iovcnt = copy->iovcnt;
 	struct iovec iov;
 	struct iovec __user *u_iov = copy->iov;
 	void __user *ubuf = NULL;
diff --git a/drivers/misc/sgi-gru/grukdump.c b/drivers/misc/sgi-gru/grukdump.c
index 9b2062d..2bef3f7 100644
--- a/drivers/misc/sgi-gru/grukdump.c
+++ b/drivers/misc/sgi-gru/grukdump.c
@@ -139,8 +139,11 @@
 
 	ubuf += sizeof(hdr);
 	ubufcch = ubuf;
-	if (gru_user_copy_handle(&ubuf, cch))
-		goto fail;
+	if (gru_user_copy_handle(&ubuf, cch)) {
+		if (cch_locked)
+			unlock_cch_handle(cch);
+		return -EFAULT;
+	}
 	if (cch_locked)
 		ubufcch->delresp = 0;
 	bytes = sizeof(hdr) + GRU_CACHE_LINE_BYTES;
@@ -179,10 +182,6 @@
 		ret = -EFAULT;
 
 	return ret ? ret : bytes;
-
-fail:
-	unlock_cch_handle(cch);
-	return -EFAULT;
 }
 
 int gru_dump_chiplet_request(unsigned long arg)
diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
index b9e2000..95c8944 100644
--- a/drivers/misc/sgi-xp/xpc_uv.c
+++ b/drivers/misc/sgi-xp/xpc_uv.c
@@ -240,7 +240,7 @@
 
 	nid = cpu_to_node(cpu);
 	page = alloc_pages_exact_node(nid,
-				      GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				      GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				      pg_order);
 	if (page == NULL) {
 		dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to alloc %d "
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 357bbc5..3e049c1 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -197,7 +197,7 @@
 	struct mmc_queue_req *mqrq_prev = &mq->mqrq[1];
 
 	if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask)
-		limit = dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT;
+		limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT;
 
 	mq->card = card;
 	mq->queue = blk_init_queue(mmc_request_fn, lock);
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 55cd110..c204b7d 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -2607,7 +2607,7 @@
 
 	tasklet_init(&host->tasklet, dw_mci_tasklet_func, (unsigned long)host);
 	host->card_workqueue = alloc_workqueue("dw-mci-card",
-			WQ_MEM_RECLAIM | WQ_NON_REENTRANT, 1);
+			WQ_MEM_RECLAIM, 1);
 	if (!host->card_workqueue) {
 		ret = -ENOMEM;
 		goto err_dmaunmap;
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 59eba5d..9715a7b 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -1584,7 +1584,7 @@
 			}
 
 			if (mtd->ecc_stats.failed - ecc_failures) {
-				if (retry_mode + 1 <= chip->read_retries) {
+				if (retry_mode + 1 < chip->read_retries) {
 					retry_mode++;
 					ret = nand_setup_read_retry(mtd,
 							retry_mode);
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index ef4190a..bf642ce 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1633,6 +1633,7 @@
 	int				i;
 	dma_cap_mask_t			mask;
 	unsigned			sig;
+	unsigned			oob_index;
 	struct resource			*res;
 	struct mtd_part_parser_data	ppdata = {};
 
@@ -1826,11 +1827,14 @@
 							(mtd->writesize /
 							nand_chip->ecc.size);
 		if (nand_chip->options & NAND_BUSWIDTH_16)
-			ecclayout->eccpos[0]	= BADBLOCK_MARKER_LENGTH;
+			oob_index		= BADBLOCK_MARKER_LENGTH;
 		else
-			ecclayout->eccpos[0]	= 1;
-		ecclayout->oobfree->offset	= ecclayout->eccpos[0] +
-							ecclayout->eccbytes;
+			oob_index		= 1;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
+			ecclayout->eccpos[i]	= oob_index;
+		/* no reserved-marker in ecclayout for this ecc-scheme */
+		ecclayout->oobfree->offset	=
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
@@ -1847,9 +1851,15 @@
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
 							nand_chip->ecc.size);
-		ecclayout->eccpos[0]		= BADBLOCK_MARKER_LENGTH;
-		ecclayout->oobfree->offset	= ecclayout->eccpos[0] +
-							ecclayout->eccbytes;
+		oob_index			= BADBLOCK_MARKER_LENGTH;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) {
+			ecclayout->eccpos[i] = oob_index;
+			if (((i + 1) % nand_chip->ecc.bytes) == 0)
+				oob_index++;
+		}
+		/* include reserved-marker in ecclayout->oobfree calculation */
+		ecclayout->oobfree->offset	= 1 +
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		/* software bch library is used for locating errors */
 		nand_chip->ecc.priv		= nand_bch_init(mtd,
 							nand_chip->ecc.size,
@@ -1883,9 +1893,12 @@
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
 							nand_chip->ecc.size);
-		ecclayout->eccpos[0]		= BADBLOCK_MARKER_LENGTH;
-		ecclayout->oobfree->offset	= ecclayout->eccpos[0] +
-							ecclayout->eccbytes;
+		oob_index			= BADBLOCK_MARKER_LENGTH;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
+			ecclayout->eccpos[i]	= oob_index;
+		/* reserved marker already included in ecclayout->eccbytes */
+		ecclayout->oobfree->offset	=
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		/* This ECC scheme requires ELM H/W block */
 		if (is_elm_present(info, pdata->elm_of_node, BCH4_ECC) < 0) {
 			pr_err("nand: error: could not initialize ELM\n");
@@ -1913,9 +1926,15 @@
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
 							nand_chip->ecc.size);
-		ecclayout->eccpos[0]		= BADBLOCK_MARKER_LENGTH;
-		ecclayout->oobfree->offset	= ecclayout->eccpos[0] +
-							ecclayout->eccbytes;
+		oob_index			= BADBLOCK_MARKER_LENGTH;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) {
+			ecclayout->eccpos[i] = oob_index;
+			if (((i + 1) % nand_chip->ecc.bytes) == 0)
+				oob_index++;
+		}
+		/* include reserved-marker in ecclayout->oobfree calculation */
+		ecclayout->oobfree->offset	= 1 +
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		/* software bch library is used for locating errors */
 		nand_chip->ecc.priv		= nand_bch_init(mtd,
 							nand_chip->ecc.size,
@@ -1956,9 +1975,12 @@
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
 							nand_chip->ecc.size);
-		ecclayout->eccpos[0]		= BADBLOCK_MARKER_LENGTH;
-		ecclayout->oobfree->offset	= ecclayout->eccpos[0] +
-							ecclayout->eccbytes;
+		oob_index			= BADBLOCK_MARKER_LENGTH;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
+			ecclayout->eccpos[i]	= oob_index;
+		/* reserved marker already included in ecclayout->eccbytes */
+		ecclayout->oobfree->offset	=
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		break;
 #else
 		pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
@@ -1972,11 +1994,8 @@
 		goto return_error;
 	}
 
-	/* populate remaining ECC layout data */
-	ecclayout->oobfree->length = mtd->oobsize - (BADBLOCK_MARKER_LENGTH +
-							ecclayout->eccbytes);
-	for (i = 1; i < ecclayout->eccbytes; i++)
-		ecclayout->eccpos[i] = ecclayout->eccpos[0] + i;
+	/* all OOB bytes from oobfree->offset till end off OOB are free */
+	ecclayout->oobfree->length = mtd->oobsize - ecclayout->oobfree->offset;
 	/* check if NAND device's OOB is enough to store ECC signatures */
 	if (mtd->oobsize < (ecclayout->eccbytes + BADBLOCK_MARKER_LENGTH)) {
 		pr_err("not enough OOB bytes required = %d, available=%d\n",
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index ead8613..c5dad65 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -463,8 +463,8 @@
 				}
 			}
 			if (found_orphan) {
-				kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 				list_del(&tmp_aeb->u.list);
+				kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 			}
 
 			new_aeb = kmem_cache_alloc(ai->aeb_slab_cache,
@@ -846,16 +846,16 @@
 	ret = UBI_BAD_FASTMAP;
 fail:
 	list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &used, u.list) {
-		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 		list_del(&tmp_aeb->u.list);
+		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 	}
 	list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &eba_orphans, u.list) {
-		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 		list_del(&tmp_aeb->u.list);
+		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 	}
 	list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &free, u.list) {
-		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 		list_del(&tmp_aeb->u.list);
+		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 	}
 
 	return ret;
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index f342278..494b888 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -139,7 +139,7 @@
 	  This adds a specialized tap character device driver that is based
 	  on the MAC-VLAN network interface, called macvtap. A macvtap device
 	  can be added in the same way as a macvlan device, using 'type
-	  macvlan', and then be accessed through the tap user space interface.
+	  macvtap', and then be accessed through the tap user space interface.
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called macvtap.
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index cce1f1b..dcde5605 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -181,7 +181,7 @@
  */
 static inline void __disable_port(struct port *port)
 {
-	bond_set_slave_inactive_flags(port->slave);
+	bond_set_slave_inactive_flags(port->slave, BOND_SLAVE_NOTIFY_LATER);
 }
 
 /**
@@ -193,7 +193,7 @@
 	struct slave *slave = port->slave;
 
 	if ((slave->link == BOND_LINK_UP) && IS_UP(slave->dev))
-		bond_set_slave_active_flags(slave);
+		bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_LATER);
 }
 
 /**
@@ -1796,8 +1796,6 @@
 	BOND_AD_INFO(bond).agg_select_timer = timeout;
 }
 
-static u16 aggregator_identifier;
-
 /**
  * bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures
  * @bond: bonding struct to work on
@@ -1811,7 +1809,7 @@
 	if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr),
 				bond->dev->dev_addr)) {
 
-		aggregator_identifier = 0;
+		BOND_AD_INFO(bond).aggregator_identifier = 0;
 
 		BOND_AD_INFO(bond).system.sys_priority = 0xFFFF;
 		BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr);
@@ -1880,7 +1878,7 @@
 		ad_initialize_agg(aggregator);
 
 		aggregator->aggregator_mac_address = *((struct mac_addr *)bond->dev->dev_addr);
-		aggregator->aggregator_identifier = (++aggregator_identifier);
+		aggregator->aggregator_identifier = ++BOND_AD_INFO(bond).aggregator_identifier;
 		aggregator->slave = slave;
 		aggregator->is_active = 0;
 		aggregator->num_of_ports = 0;
@@ -2064,6 +2062,7 @@
 	struct list_head *iter;
 	struct slave *slave;
 	struct port *port;
+	bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER;
 
 	read_lock(&bond->lock);
 	rcu_read_lock();
@@ -2121,8 +2120,19 @@
 	}
 
 re_arm:
+	bond_for_each_slave_rcu(bond, slave, iter) {
+		if (slave->should_notify) {
+			should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW;
+			break;
+		}
+	}
 	rcu_read_unlock();
 	read_unlock(&bond->lock);
+
+	if (should_notify_rtnl && rtnl_trylock()) {
+		bond_slave_state_notify(bond);
+		rtnl_unlock();
+	}
 	queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks);
 }
 
diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h
index 13dc9d3..f4dd959 100644
--- a/drivers/net/bonding/bond_3ad.h
+++ b/drivers/net/bonding/bond_3ad.h
@@ -253,6 +253,7 @@
 struct ad_bond_info {
 	struct ad_system system;	    /* 802.3ad system structure */
 	u32 agg_select_timer;	    // Timer to select aggregator after all adapter's hand shakes
+	u16 aggregator_identifier;
 };
 
 struct ad_slave_info {
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index a2c4747..e8f133e 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -730,7 +730,7 @@
 			client_info->ntt = 0;
 		}
 
-		if (!vlan_get_tag(skb, &client_info->vlan_id))
+		if (vlan_get_tag(skb, &client_info->vlan_id))
 			client_info->vlan_id = 0;
 
 		if (!client_info->assigned) {
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 4c08018..e5628fc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -829,21 +829,25 @@
 	if (bond_is_lb(bond)) {
 		bond_alb_handle_active_change(bond, new_active);
 		if (old_active)
-			bond_set_slave_inactive_flags(old_active);
+			bond_set_slave_inactive_flags(old_active,
+						      BOND_SLAVE_NOTIFY_NOW);
 		if (new_active)
-			bond_set_slave_active_flags(new_active);
+			bond_set_slave_active_flags(new_active,
+						    BOND_SLAVE_NOTIFY_NOW);
 	} else {
 		rcu_assign_pointer(bond->curr_active_slave, new_active);
 	}
 
 	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
 		if (old_active)
-			bond_set_slave_inactive_flags(old_active);
+			bond_set_slave_inactive_flags(old_active,
+						      BOND_SLAVE_NOTIFY_NOW);
 
 		if (new_active) {
 			bool should_notify_peers = false;
 
-			bond_set_slave_active_flags(new_active);
+			bond_set_slave_active_flags(new_active,
+						    BOND_SLAVE_NOTIFY_NOW);
 
 			if (bond->params.fail_over_mac)
 				bond_do_fail_over_mac(bond, new_active,
@@ -1193,6 +1197,11 @@
 		return -EBUSY;
 	}
 
+	if (bond_dev == slave_dev) {
+		pr_err("%s: cannot enslave bond to itself.\n", bond_dev->name);
+		return -EPERM;
+	}
+
 	/* vlan challenged mutual exclusion */
 	/* no need to lock since we're protected by rtnl_lock */
 	if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) {
@@ -1270,9 +1279,13 @@
 
 	if (slave_ops->ndo_set_mac_address == NULL) {
 		if (!bond_has_slaves(bond)) {
-			pr_warning("%s: Warning: The first slave device specified does not support setting the MAC address. Setting fail_over_mac to active.",
-				   bond_dev->name);
-			bond->params.fail_over_mac = BOND_FOM_ACTIVE;
+			pr_warn("%s: Warning: The first slave device specified does not support setting the MAC address.\n",
+				bond_dev->name);
+			if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
+				bond->params.fail_over_mac = BOND_FOM_ACTIVE;
+				pr_warn("%s: Setting fail_over_mac to active for active-backup mode.\n",
+					bond_dev->name);
+			}
 		} else if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
 			pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active.\n",
 			       bond_dev->name);
@@ -1315,7 +1328,8 @@
 	 */
 	memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN);
 
-	if (!bond->params.fail_over_mac) {
+	if (!bond->params.fail_over_mac ||
+	    bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
 		/*
 		 * Set slave to master's mac address.  The application already
 		 * set the master's mac address to that of the first slave
@@ -1458,14 +1472,15 @@
 
 	switch (bond->params.mode) {
 	case BOND_MODE_ACTIVEBACKUP:
-		bond_set_slave_inactive_flags(new_slave);
+		bond_set_slave_inactive_flags(new_slave,
+					      BOND_SLAVE_NOTIFY_NOW);
 		break;
 	case BOND_MODE_8023AD:
 		/* in 802.3ad mode, the internal mechanism
 		 * will activate the slaves in the selected
 		 * aggregator
 		 */
-		bond_set_slave_inactive_flags(new_slave);
+		bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW);
 		/* if this is the first slave */
 		if (!prev_slave) {
 			SLAVE_AD_INFO(new_slave).id = 1;
@@ -1483,7 +1498,7 @@
 	case BOND_MODE_TLB:
 	case BOND_MODE_ALB:
 		bond_set_active_slave(new_slave);
-		bond_set_slave_inactive_flags(new_slave);
+		bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW);
 		break;
 	default:
 		pr_debug("This slave is always active in trunk mode\n");
@@ -1505,7 +1520,6 @@
 	slave_dev->npinfo = bond->dev->npinfo;
 	if (slave_dev->npinfo) {
 		if (slave_enable_netpoll(new_slave)) {
-			read_unlock(&bond->lock);
 			pr_info("Error, %s: master_dev is using netpoll, "
 				 "but new slave device does not support netpoll.\n",
 				 bond_dev->name);
@@ -1539,9 +1553,11 @@
 	bond_set_carrier(bond);
 
 	if (USES_PRIMARY(bond->params.mode)) {
+		block_netpoll_tx();
 		write_lock_bh(&bond->curr_slave_lock);
 		bond_select_active_slave(bond);
 		write_unlock_bh(&bond->curr_slave_lock);
+		unblock_netpoll_tx();
 	}
 
 	pr_info("%s: enslaving %s as a%s interface with a%s link.\n",
@@ -1567,10 +1583,12 @@
 	if (bond->primary_slave == new_slave)
 		bond->primary_slave = NULL;
 	if (bond->curr_active_slave == new_slave) {
+		block_netpoll_tx();
 		write_lock_bh(&bond->curr_slave_lock);
 		bond_change_active_slave(bond, NULL);
 		bond_select_active_slave(bond);
 		write_unlock_bh(&bond->curr_slave_lock);
+		unblock_netpoll_tx();
 	}
 	slave_disable_netpoll(new_slave);
 
@@ -1579,7 +1597,8 @@
 	dev_close(slave_dev);
 
 err_restore_mac:
-	if (!bond->params.fail_over_mac) {
+	if (!bond->params.fail_over_mac ||
+	    bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
 		/* XXX TODO - fom follow mode needs to change master's
 		 * MAC if this slave's MAC is in use by the bond, or at
 		 * least print a warning.
@@ -1645,9 +1664,6 @@
 		return -EINVAL;
 	}
 
-	/* release the slave from its bond */
-	bond->slave_cnt--;
-
 	bond_sysfs_slave_del(slave);
 
 	bond_upper_dev_unlink(bond_dev, slave_dev);
@@ -1672,7 +1688,8 @@
 
 	bond->current_arp_slave = NULL;
 
-	if (!all && !bond->params.fail_over_mac) {
+	if (!all && (!bond->params.fail_over_mac ||
+		     bond->params.mode != BOND_MODE_ACTIVEBACKUP)) {
 		if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
 		    bond_has_slaves(bond))
 			pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n",
@@ -1728,6 +1745,7 @@
 
 	unblock_netpoll_tx();
 	synchronize_rcu();
+	bond->slave_cnt--;
 
 	if (!bond_has_slaves(bond)) {
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev);
@@ -1769,7 +1787,8 @@
 	/* close slave before restoring its mac address */
 	dev_close(slave_dev);
 
-	if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
+	if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
+	    bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
 		/* restore original ("permanent") mac address */
 		memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
 		addr.sa_family = slave_dev->type;
@@ -2004,7 +2023,8 @@
 
 			if (bond->params.mode == BOND_MODE_ACTIVEBACKUP ||
 			    bond->params.mode == BOND_MODE_8023AD)
-				bond_set_slave_inactive_flags(slave);
+				bond_set_slave_inactive_flags(slave,
+							      BOND_SLAVE_NOTIFY_NOW);
 
 			pr_info("%s: link status definitely down for interface %s, disabling it\n",
 				bond->dev->name, slave->dev->name);
@@ -2551,7 +2571,8 @@
 				slave->link = BOND_LINK_UP;
 				if (bond->current_arp_slave) {
 					bond_set_slave_inactive_flags(
-						bond->current_arp_slave);
+						bond->current_arp_slave,
+						BOND_SLAVE_NOTIFY_NOW);
 					bond->current_arp_slave = NULL;
 				}
 
@@ -2571,7 +2592,8 @@
 				slave->link_failure_count++;
 
 			slave->link = BOND_LINK_DOWN;
-			bond_set_slave_inactive_flags(slave);
+			bond_set_slave_inactive_flags(slave,
+						      BOND_SLAVE_NOTIFY_NOW);
 
 			pr_info("%s: link status definitely down for interface %s, disabling it\n",
 				bond->dev->name, slave->dev->name);
@@ -2604,17 +2626,17 @@
 
 /*
  * Send ARP probes for active-backup mode ARP monitor.
+ *
+ * Called with rcu_read_lock hold.
  */
 static bool bond_ab_arp_probe(struct bonding *bond)
 {
 	struct slave *slave, *before = NULL, *new_slave = NULL,
-		     *curr_arp_slave, *curr_active_slave;
+		     *curr_arp_slave = rcu_dereference(bond->current_arp_slave),
+		     *curr_active_slave = rcu_dereference(bond->curr_active_slave);
 	struct list_head *iter;
 	bool found = false;
-
-	rcu_read_lock();
-	curr_arp_slave = rcu_dereference(bond->current_arp_slave);
-	curr_active_slave = rcu_dereference(bond->curr_active_slave);
+	bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER;
 
 	if (curr_arp_slave && curr_active_slave)
 		pr_info("PROBE: c_arp %s && cas %s BAD\n",
@@ -2623,32 +2645,23 @@
 
 	if (curr_active_slave) {
 		bond_arp_send_all(bond, curr_active_slave);
-		rcu_read_unlock();
-		return true;
+		return should_notify_rtnl;
 	}
-	rcu_read_unlock();
 
 	/* if we don't have a curr_active_slave, search for the next available
 	 * backup slave from the current_arp_slave and make it the candidate
 	 * for becoming the curr_active_slave
 	 */
 
-	if (!rtnl_trylock())
-		return false;
-	/* curr_arp_slave might have gone away */
-	curr_arp_slave = ACCESS_ONCE(bond->current_arp_slave);
-
 	if (!curr_arp_slave) {
-		curr_arp_slave = bond_first_slave(bond);
-		if (!curr_arp_slave) {
-			rtnl_unlock();
-			return true;
-		}
+		curr_arp_slave = bond_first_slave_rcu(bond);
+		if (!curr_arp_slave)
+			return should_notify_rtnl;
 	}
 
-	bond_set_slave_inactive_flags(curr_arp_slave);
+	bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER);
 
-	bond_for_each_slave(bond, slave, iter) {
+	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (!found && !before && IS_UP(slave->dev))
 			before = slave;
 
@@ -2666,7 +2679,8 @@
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
-			bond_set_slave_inactive_flags(slave);
+			bond_set_slave_inactive_flags(slave,
+						      BOND_SLAVE_NOTIFY_LATER);
 
 			pr_info("%s: backup interface %s is now down.\n",
 				bond->dev->name, slave->dev->name);
@@ -2678,26 +2692,31 @@
 	if (!new_slave && before)
 		new_slave = before;
 
-	if (!new_slave) {
-		rtnl_unlock();
-		return true;
-	}
+	if (!new_slave)
+		goto check_state;
 
 	new_slave->link = BOND_LINK_BACK;
-	bond_set_slave_active_flags(new_slave);
+	bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER);
 	bond_arp_send_all(bond, new_slave);
 	new_slave->jiffies = jiffies;
 	rcu_assign_pointer(bond->current_arp_slave, new_slave);
-	rtnl_unlock();
 
-	return true;
+check_state:
+	bond_for_each_slave_rcu(bond, slave, iter) {
+		if (slave->should_notify) {
+			should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW;
+			break;
+		}
+	}
+	return should_notify_rtnl;
 }
 
 static void bond_activebackup_arp_mon(struct work_struct *work)
 {
 	struct bonding *bond = container_of(work, struct bonding,
 					    arp_work.work);
-	bool should_notify_peers = false, should_commit = false;
+	bool should_notify_peers = false;
+	bool should_notify_rtnl = false;
 	int delta_in_ticks;
 
 	delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
@@ -2706,11 +2725,12 @@
 		goto re_arm;
 
 	rcu_read_lock();
-	should_notify_peers = bond_should_notify_peers(bond);
-	should_commit = bond_ab_arp_inspect(bond);
-	rcu_read_unlock();
 
-	if (should_commit) {
+	should_notify_peers = bond_should_notify_peers(bond);
+
+	if (bond_ab_arp_inspect(bond)) {
+		rcu_read_unlock();
+
 		/* Race avoidance with bond_close flush of workqueue */
 		if (!rtnl_trylock()) {
 			delta_in_ticks = 1;
@@ -2719,23 +2739,28 @@
 		}
 
 		bond_ab_arp_commit(bond);
+
 		rtnl_unlock();
+		rcu_read_lock();
 	}
 
-	if (!bond_ab_arp_probe(bond)) {
-		/* rtnl locking failed, re-arm */
-		delta_in_ticks = 1;
-		should_notify_peers = false;
-	}
+	should_notify_rtnl = bond_ab_arp_probe(bond);
+	rcu_read_unlock();
 
 re_arm:
 	if (bond->params.arp_interval)
 		queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
 
-	if (should_notify_peers) {
+	if (should_notify_peers || should_notify_rtnl) {
 		if (!rtnl_trylock())
 			return;
-		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
+
+		if (should_notify_peers)
+			call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
+						 bond->dev);
+		if (should_notify_rtnl)
+			bond_slave_state_notify(bond);
+
 		rtnl_unlock();
 	}
 }
@@ -2857,9 +2882,12 @@
 		pr_info("%s: Primary slave changed to %s, reselecting active slave.\n",
 			bond->dev->name, bond->primary_slave ? slave_dev->name :
 							       "none");
+
+		block_netpoll_tx();
 		write_lock_bh(&bond->curr_slave_lock);
 		bond_select_active_slave(bond);
 		write_unlock_bh(&bond->curr_slave_lock);
+		unblock_netpoll_tx();
 		break;
 	case NETDEV_FEAT_CHANGE:
 		bond_compute_features(bond);
@@ -3032,9 +3060,11 @@
 		bond_for_each_slave(bond, slave, iter) {
 			if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP)
 				&& (slave != bond->curr_active_slave)) {
-				bond_set_slave_inactive_flags(slave);
+				bond_set_slave_inactive_flags(slave,
+							      BOND_SLAVE_NOTIFY_NOW);
 			} else {
-				bond_set_slave_active_flags(slave);
+				bond_set_slave_active_flags(slave,
+							    BOND_SLAVE_NOTIFY_NOW);
 			}
 		}
 		read_unlock(&bond->curr_slave_lock);
@@ -3431,7 +3461,8 @@
 	/* If fail_over_mac is enabled, do nothing and return success.
 	 * Returning an error causes ifenslave to fail.
 	 */
-	if (bond->params.fail_over_mac)
+	if (bond->params.fail_over_mac &&
+	    bond->params.mode == BOND_MODE_ACTIVEBACKUP)
 		return 0;
 
 	if (!is_valid_ether_addr(sa->sa_data))
@@ -3692,7 +3723,7 @@
 
 
 static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv)
+			     void *accel_priv, select_queue_fallback_t fallback)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 11cb943..298c265 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -14,7 +14,7 @@
 #include <linux/errno.h>
 #include <linux/if.h>
 #include <linux/netdevice.h>
-#include <linux/rwlock.h>
+#include <linux/spinlock.h>
 #include <linux/rcupdate.h>
 #include <linux/ctype.h>
 #include <linux/inet.h>
@@ -121,6 +121,7 @@
 static struct bond_opt_value bond_lp_interval_tbl[] = {
 	{ "minval",  1,       BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT},
 	{ "maxval",  INT_MAX, BOND_VALFLAG_MAX},
+	{ NULL,      -1,      0},
 };
 
 static struct bond_option bond_opts[] = {
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 86ccfb9..2b0fdec 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -195,7 +195,8 @@
 	s8     new_link;
 	u8     backup:1,   /* indicates backup slave. Value corresponds with
 			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
-	       inactive:1; /* indicates inactive slave */
+	       inactive:1, /* indicates inactive slave */
+	       should_notify:1; /* indicateds whether the state changed */
 	u8     duplex;
 	u32    original_mtu;
 	u32    link_failure_count;
@@ -303,6 +304,24 @@
 	}
 }
 
+static inline void bond_set_slave_state(struct slave *slave,
+					int slave_state, bool notify)
+{
+	if (slave->backup == slave_state)
+		return;
+
+	slave->backup = slave_state;
+	if (notify) {
+		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL);
+		slave->should_notify = 0;
+	} else {
+		if (slave->should_notify)
+			slave->should_notify = 0;
+		else
+			slave->should_notify = 1;
+	}
+}
+
 static inline void bond_slave_state_change(struct bonding *bond)
 {
 	struct list_head *iter;
@@ -316,6 +335,19 @@
 	}
 }
 
+static inline void bond_slave_state_notify(struct bonding *bond)
+{
+	struct list_head *iter;
+	struct slave *tmp;
+
+	bond_for_each_slave(bond, tmp, iter) {
+		if (tmp->should_notify) {
+			rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_KERNEL);
+			tmp->should_notify = 0;
+		}
+	}
+}
+
 static inline int bond_slave_state(struct slave *slave)
 {
 	return slave->backup;
@@ -343,6 +375,9 @@
 #define BOND_ARP_VALIDATE_ALL		(BOND_ARP_VALIDATE_ACTIVE | \
 					 BOND_ARP_VALIDATE_BACKUP)
 
+#define BOND_SLAVE_NOTIFY_NOW		true
+#define BOND_SLAVE_NOTIFY_LATER		false
+
 static inline int slave_do_arp_validate(struct bonding *bond,
 					struct slave *slave)
 {
@@ -394,17 +429,19 @@
 }
 #endif
 
-static inline void bond_set_slave_inactive_flags(struct slave *slave)
+static inline void bond_set_slave_inactive_flags(struct slave *slave,
+						 bool notify)
 {
 	if (!bond_is_lb(slave->bond))
-		bond_set_backup_slave(slave);
+		bond_set_slave_state(slave, BOND_STATE_BACKUP, notify);
 	if (!slave->bond->params.all_slaves_active)
 		slave->inactive = 1;
 }
 
-static inline void bond_set_slave_active_flags(struct slave *slave)
+static inline void bond_set_slave_active_flags(struct slave *slave,
+					       bool notify)
 {
-	bond_set_active_slave(slave);
+	bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify);
 	slave->inactive = 0;
 }
 
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index d447b88..9e7d95d 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -104,7 +104,7 @@
 
 config CAN_FLEXCAN
 	tristate "Support for Freescale FLEXCAN based chips"
-	depends on (ARM && CPU_LITTLE_ENDIAN) || PPC
+	depends on ARM || PPC
 	---help---
 	  Say Y here if you want to support for Freescale FlexCAN.
 
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 13a9098..fc59bc6 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -323,19 +323,10 @@
 	}
 
 	if (!priv->echo_skb[idx]) {
-		struct sock *srcsk = skb->sk;
 
-		if (atomic_read(&skb->users) != 1) {
-			struct sk_buff *old_skb = skb;
-
-			skb = skb_clone(old_skb, GFP_ATOMIC);
-			kfree_skb(old_skb);
-			if (!skb)
-				return;
-		} else
-			skb_orphan(skb);
-
-		skb->sk = srcsk;
+		skb = can_create_echo_skb(skb);
+		if (!skb)
+			return;
 
 		/* make settings for echo to reduce code in irq context */
 		skb->protocol = htons(ETH_P_CAN);
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index aaed97b..61376ab 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -144,6 +144,8 @@
 
 #define FLEXCAN_MB_CODE_MASK		(0xf0ffffff)
 
+#define FLEXCAN_TIMEOUT_US             (50)
+
 /*
  * FLEXCAN hardware feature flags
  *
@@ -235,9 +237,12 @@
 };
 
 /*
- * Abstract off the read/write for arm versus ppc.
+ * Abstract off the read/write for arm versus ppc. This
+ * assumes that PPC uses big-endian registers and everything
+ * else uses little-endian registers, independent of CPU
+ * endianess.
  */
-#if defined(__BIG_ENDIAN)
+#if defined(CONFIG_PPC)
 static inline u32 flexcan_read(void __iomem *addr)
 {
 	return in_be32(addr);
@@ -259,6 +264,22 @@
 }
 #endif
 
+static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv)
+{
+	if (!priv->reg_xceiver)
+		return 0;
+
+	return regulator_enable(priv->reg_xceiver);
+}
+
+static inline int flexcan_transceiver_disable(const struct flexcan_priv *priv)
+{
+	if (!priv->reg_xceiver)
+		return 0;
+
+	return regulator_disable(priv->reg_xceiver);
+}
+
 static inline int flexcan_has_and_handle_berr(const struct flexcan_priv *priv,
 					      u32 reg_esr)
 {
@@ -266,26 +287,95 @@
 		(reg_esr & FLEXCAN_ESR_ERR_BUS);
 }
 
-static inline void flexcan_chip_enable(struct flexcan_priv *priv)
+static int flexcan_chip_enable(struct flexcan_priv *priv)
 {
 	struct flexcan_regs __iomem *regs = priv->base;
+	unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
 	u32 reg;
 
 	reg = flexcan_read(&regs->mcr);
 	reg &= ~FLEXCAN_MCR_MDIS;
 	flexcan_write(reg, &regs->mcr);
 
-	udelay(10);
+	while (timeout-- && (flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK))
+		usleep_range(10, 20);
+
+	if (flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK)
+		return -ETIMEDOUT;
+
+	return 0;
 }
 
-static inline void flexcan_chip_disable(struct flexcan_priv *priv)
+static int flexcan_chip_disable(struct flexcan_priv *priv)
 {
 	struct flexcan_regs __iomem *regs = priv->base;
+	unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
 	u32 reg;
 
 	reg = flexcan_read(&regs->mcr);
 	reg |= FLEXCAN_MCR_MDIS;
 	flexcan_write(reg, &regs->mcr);
+
+	while (timeout-- && !(flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK))
+		usleep_range(10, 20);
+
+	if (!(flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int flexcan_chip_freeze(struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->base;
+	unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate;
+	u32 reg;
+
+	reg = flexcan_read(&regs->mcr);
+	reg |= FLEXCAN_MCR_HALT;
+	flexcan_write(reg, &regs->mcr);
+
+	while (timeout-- && !(flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK))
+		usleep_range(100, 200);
+
+	if (!(flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int flexcan_chip_unfreeze(struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->base;
+	unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
+	u32 reg;
+
+	reg = flexcan_read(&regs->mcr);
+	reg &= ~FLEXCAN_MCR_HALT;
+	flexcan_write(reg, &regs->mcr);
+
+	while (timeout-- && (flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK))
+		usleep_range(10, 20);
+
+	if (flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int flexcan_chip_softreset(struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->base;
+	unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
+
+	flexcan_write(FLEXCAN_MCR_SOFTRST, &regs->mcr);
+	while (timeout-- && (flexcan_read(&regs->mcr) & FLEXCAN_MCR_SOFTRST))
+		usleep_range(10, 20);
+
+	if (flexcan_read(&regs->mcr) & FLEXCAN_MCR_SOFTRST)
+		return -ETIMEDOUT;
+
+	return 0;
 }
 
 static int flexcan_get_berr_counter(const struct net_device *dev,
@@ -706,19 +796,14 @@
 	u32 reg_mcr, reg_ctrl;
 
 	/* enable module */
-	flexcan_chip_enable(priv);
+	err = flexcan_chip_enable(priv);
+	if (err)
+		return err;
 
 	/* soft reset */
-	flexcan_write(FLEXCAN_MCR_SOFTRST, &regs->mcr);
-	udelay(10);
-
-	reg_mcr = flexcan_read(&regs->mcr);
-	if (reg_mcr & FLEXCAN_MCR_SOFTRST) {
-		netdev_err(dev, "Failed to softreset can module (mcr=0x%08x)\n",
-			   reg_mcr);
-		err = -ENODEV;
-		goto out;
-	}
+	err = flexcan_chip_softreset(priv);
+	if (err)
+		goto out_chip_disable;
 
 	flexcan_set_bittiming(dev);
 
@@ -785,16 +870,14 @@
 	if (priv->devtype_data->features & FLEXCAN_HAS_V10_FEATURES)
 		flexcan_write(0x0, &regs->rxfgmask);
 
-	if (priv->reg_xceiver)	{
-		err = regulator_enable(priv->reg_xceiver);
-		if (err)
-			goto out;
-	}
+	err = flexcan_transceiver_enable(priv);
+	if (err)
+		goto out_chip_disable;
 
 	/* synchronize with the can bus */
-	reg_mcr = flexcan_read(&regs->mcr);
-	reg_mcr &= ~FLEXCAN_MCR_HALT;
-	flexcan_write(reg_mcr, &regs->mcr);
+	err = flexcan_chip_unfreeze(priv);
+	if (err)
+		goto out_transceiver_disable;
 
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 
@@ -807,7 +890,9 @@
 
 	return 0;
 
- out:
+ out_transceiver_disable:
+	flexcan_transceiver_disable(priv);
+ out_chip_disable:
 	flexcan_chip_disable(priv);
 	return err;
 }
@@ -822,18 +907,17 @@
 {
 	struct flexcan_priv *priv = netdev_priv(dev);
 	struct flexcan_regs __iomem *regs = priv->base;
-	u32 reg;
+
+	/* freeze + disable module */
+	flexcan_chip_freeze(priv);
+	flexcan_chip_disable(priv);
 
 	/* Disable all interrupts */
 	flexcan_write(0, &regs->imask1);
+	flexcan_write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL,
+		      &regs->ctrl);
 
-	/* Disable + halt module */
-	reg = flexcan_read(&regs->mcr);
-	reg |= FLEXCAN_MCR_MDIS | FLEXCAN_MCR_HALT;
-	flexcan_write(reg, &regs->mcr);
-
-	if (priv->reg_xceiver)
-		regulator_disable(priv->reg_xceiver);
+	flexcan_transceiver_disable(priv);
 	priv->can.state = CAN_STATE_STOPPED;
 
 	return;
@@ -863,7 +947,7 @@
 	/* start chip and queuing */
 	err = flexcan_chip_start(dev);
 	if (err)
-		goto out_close;
+		goto out_free_irq;
 
 	can_led_event(dev, CAN_LED_EVENT_OPEN);
 
@@ -872,6 +956,8 @@
 
 	return 0;
 
+ out_free_irq:
+	free_irq(dev->irq, dev);
  out_close:
 	close_candev(dev);
  out_disable_per:
@@ -942,12 +1028,16 @@
 		goto out_disable_ipg;
 
 	/* select "bus clock", chip must be disabled */
-	flexcan_chip_disable(priv);
+	err = flexcan_chip_disable(priv);
+	if (err)
+		goto out_disable_per;
 	reg = flexcan_read(&regs->ctrl);
 	reg |= FLEXCAN_CTRL_CLK_SRC;
 	flexcan_write(reg, &regs->ctrl);
 
-	flexcan_chip_enable(priv);
+	err = flexcan_chip_enable(priv);
+	if (err)
+		goto out_chip_disable;
 
 	/* set freeze, halt and activate FIFO, restrict register access */
 	reg = flexcan_read(&regs->mcr);
@@ -964,14 +1054,15 @@
 	if (!(reg & FLEXCAN_MCR_FEN)) {
 		netdev_err(dev, "Could not enable RX FIFO, unsupported core\n");
 		err = -ENODEV;
-		goto out_disable_per;
+		goto out_chip_disable;
 	}
 
 	err = register_candev(dev);
 
- out_disable_per:
 	/* disable core and turn off clocks */
+ out_chip_disable:
 	flexcan_chip_disable(priv);
+ out_disable_per:
 	clk_disable_unprepare(priv->clk_per);
  out_disable_ipg:
 	clk_disable_unprepare(priv->clk_ipg);
@@ -1101,9 +1192,10 @@
 static int flexcan_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
+	struct flexcan_priv *priv = netdev_priv(dev);
 
 	unregister_flexcandev(dev);
-
+	netif_napi_del(&priv->napi);
 	free_candev(dev);
 
 	return 0;
@@ -1114,8 +1206,11 @@
 {
 	struct net_device *dev = dev_get_drvdata(device);
 	struct flexcan_priv *priv = netdev_priv(dev);
+	int err;
 
-	flexcan_chip_disable(priv);
+	err = flexcan_chip_disable(priv);
+	if (err)
+		return err;
 
 	if (netif_running(dev)) {
 		netif_stop_queue(dev);
@@ -1136,9 +1231,7 @@
 		netif_device_attach(dev);
 		netif_start_queue(dev);
 	}
-	flexcan_chip_enable(priv);
-
-	return 0;
+	return flexcan_chip_enable(priv);
 }
 #endif /* CONFIG_PM_SLEEP */
 
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index e24e669..71594e5 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -18,6 +18,7 @@
 #include <linux/netdevice.h>
 #include <linux/can.h>
 #include <linux/can/dev.h>
+#include <linux/can/skb.h>
 #include <linux/can/error.h>
 
 #include <linux/mfd/janz.h>
@@ -1133,20 +1134,9 @@
  */
 static void ican3_put_echo_skb(struct ican3_dev *mod, struct sk_buff *skb)
 {
-	struct sock *srcsk = skb->sk;
-
-	if (atomic_read(&skb->users) != 1) {
-		struct sk_buff *old_skb = skb;
-
-		skb = skb_clone(old_skb, GFP_ATOMIC);
-		kfree_skb(old_skb);
-		if (!skb)
-			return;
-	} else {
-		skb_orphan(skb);
-	}
-
-	skb->sk = srcsk;
+	skb = can_create_echo_skb(skb);
+	if (!skb)
+		return;
 
 	/* save this skb for tx interrupt echo handling */
 	skb_queue_tail(&mod->echoq, skb);
@@ -1322,7 +1312,7 @@
 
 	/* process all communication messages */
 	while (true) {
-		struct ican3_msg msg;
+		struct ican3_msg uninitialized_var(msg);
 		ret = ican3_recv_msg(mod, &msg);
 		if (ret)
 			break;
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 6c859bb..e77d110 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -473,6 +473,8 @@
 		return err;
 
 	dev->nchannels = msg.u.cardinfo.nchannels;
+	if (dev->nchannels > MAX_NET_DEVICES)
+		return -EINVAL;
 
 	return 0;
 }
diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c
index 0a2a5ee..4e94057 100644
--- a/drivers/net/can/vcan.c
+++ b/drivers/net/can/vcan.c
@@ -46,6 +46,7 @@
 #include <linux/if_ether.h>
 #include <linux/can.h>
 #include <linux/can/dev.h>
+#include <linux/can/skb.h>
 #include <linux/slab.h>
 #include <net/rtnetlink.h>
 
@@ -109,25 +110,23 @@
 			stats->rx_packets++;
 			stats->rx_bytes += cfd->len;
 		}
-		kfree_skb(skb);
+		consume_skb(skb);
 		return NETDEV_TX_OK;
 	}
 
 	/* perform standard echo handling for CAN network interfaces */
 
 	if (loop) {
-		struct sock *srcsk = skb->sk;
 
-		skb = skb_share_check(skb, GFP_ATOMIC);
+		skb = can_create_echo_skb(skb);
 		if (!skb)
 			return NETDEV_TX_OK;
 
 		/* receive with packet counting */
-		skb->sk = srcsk;
 		vcan_rx(skb, dev);
 	} else {
 		/* no looped packets => no counting */
-		kfree_skb(skb);
+		consume_skb(skb);
 	}
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 0f4241c..238ccea 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -3294,7 +3294,6 @@
 
 static void __exit vortex_eisa_cleanup(void)
 {
-	struct vortex_private *vp;
 	void __iomem *ioaddr;
 
 #ifdef CONFIG_EISA
@@ -3303,7 +3302,6 @@
 #endif
 
 	if (compaq_net_device) {
-		vp = netdev_priv(compaq_net_device);
 		ioaddr = ioport_map(compaq_net_device->base_addr,
 		                    VORTEX_TOTAL_SIZE);
 
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 0cc2143..511f6ee 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -929,6 +929,9 @@
 }
 
 static const struct of_device_id emac_of_match[] = {
+	{.compatible = "allwinner,sun4i-a10-emac",},
+
+	/* Deprecated */
 	{.compatible = "allwinner,sun4i-emac",},
 	{},
 };
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index e92ffd6..380d249 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1248,19 +1248,13 @@
 	 * shared register for the high 32 bits, so only a single, aligned,
 	 * 4 GB physical address range can be used for descriptors.
 	 */
-	if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) &&
-	    !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) {
+	if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
 		dev_dbg(&pdev->dev, "DMA to 64-BIT addresses\n");
 	} else {
-		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
-			err = dma_set_coherent_mask(&pdev->dev,
-						    DMA_BIT_MASK(32));
-			if (err) {
-				dev_err(&pdev->dev,
-					"No usable DMA config, aborting\n");
-				goto out_pci_disable;
-			}
+			dev_err(&pdev->dev, "No usable DMA config, aborting\n");
+			goto out_pci_disable;
 		}
 	}
 
@@ -1292,6 +1286,7 @@
 	alx = netdev_priv(netdev);
 	spin_lock_init(&alx->hw.mdio_lock);
 	spin_lock_init(&alx->irq_lock);
+	spin_lock_init(&alx->stats_lock);
 	alx->dev = netdev;
 	alx->hw.pdev = pdev;
 	alx->msg_enable = NETIF_MSG_LINK | NETIF_MSG_HW | NETIF_MSG_IFUP |
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index d5c2d3e..422aab2 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -2436,7 +2436,7 @@
 err_register:
 err_sw_init:
 err_eeprom:
-	iounmap(adapter->hw.hw_addr);
+	pci_iounmap(pdev, adapter->hw.hw_addr);
 err_init_netdev:
 err_ioremap:
 	free_netdev(netdev);
@@ -2474,7 +2474,7 @@
 	unregister_netdev(netdev);
 	atl1e_free_ring_resources(adapter);
 	atl1e_force_ps(&adapter->hw);
-	iounmap(adapter->hw.hw_addr);
+	pci_iounmap(pdev, adapter->hw.hw_addr);
 	pci_release_regions(pdev);
 	free_netdev(netdev);
 	pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 1f7b5aa..8a7bf7d 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -1484,6 +1484,10 @@
 	add_timer(&bp->timer);
 
 	b44_enable_ints(bp);
+
+	if (bp->flags & B44_FLAG_EXTERNAL_PHY)
+		phy_start(bp->phydev);
+
 	netif_start_queue(dev);
 out:
 	return err;
@@ -1646,6 +1650,9 @@
 
 	netif_stop_queue(dev);
 
+	if (bp->flags & B44_FLAG_EXTERNAL_PHY)
+		phy_stop(bp->phydev);
+
 	napi_disable(&bp->napi);
 
 	del_timer_sync(&bp->timer);
@@ -2222,7 +2229,12 @@
 	}
 
 	if (status_changed) {
-		b44_check_phy(bp);
+		u32 val = br32(bp, B44_TX_CTRL);
+		if (bp->flags & B44_FLAG_FULL_DUPLEX)
+			val |= TX_CTRL_DUPLEX;
+		else
+			val &= ~TX_CTRL_DUPLEX;
+		bw32(bp, B44_TX_CTRL, val);
 		phy_print_status(phydev);
 	}
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 9d2deda..6c9e1c9 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -85,7 +85,7 @@
 
 static int disable_msi = 0;
 
-module_param(disable_msi, int, 0);
+module_param(disable_msi, int, S_IRUGO);
 MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)");
 
 typedef enum {
@@ -2507,6 +2507,7 @@
 
 	bp->fw_wr_seq++;
 	msg_data |= bp->fw_wr_seq;
+	bp->fw_last_msg = msg_data;
 
 	bnx2_shmem_wr(bp, BNX2_DRV_MB, msg_data);
 
@@ -4000,8 +4001,23 @@
 			wol_msg = BNX2_DRV_MSG_CODE_SUSPEND_NO_WOL;
 	}
 
-	if (!(bp->flags & BNX2_FLAG_NO_WOL))
-		bnx2_fw_sync(bp, BNX2_DRV_MSG_DATA_WAIT3 | wol_msg, 1, 0);
+	if (!(bp->flags & BNX2_FLAG_NO_WOL)) {
+		u32 val;
+
+		wol_msg |= BNX2_DRV_MSG_DATA_WAIT3;
+		if (bp->fw_last_msg || BNX2_CHIP(bp) != BNX2_CHIP_5709) {
+			bnx2_fw_sync(bp, wol_msg, 1, 0);
+			return;
+		}
+		/* Tell firmware not to power down the PHY yet, otherwise
+		 * the chip will take a long time to respond to MMIO reads.
+		 */
+		val = bnx2_shmem_rd(bp, BNX2_PORT_FEATURE);
+		bnx2_shmem_wr(bp, BNX2_PORT_FEATURE,
+			      val | BNX2_PORT_FEATURE_ASF_ENABLED);
+		bnx2_fw_sync(bp, wol_msg, 1, 0);
+		bnx2_shmem_wr(bp, BNX2_PORT_FEATURE, val);
+	}
 
 }
 
@@ -4033,9 +4049,22 @@
 
 			if (bp->wol)
 				pci_set_power_state(bp->pdev, PCI_D3hot);
-		} else {
-			pci_set_power_state(bp->pdev, PCI_D3hot);
+			break;
+
 		}
+		if (!bp->fw_last_msg && BNX2_CHIP(bp) == BNX2_CHIP_5709) {
+			u32 val;
+
+			/* Tell firmware not to power down the PHY yet,
+			 * otherwise the other port may not respond to
+			 * MMIO reads.
+			 */
+			val = bnx2_shmem_rd(bp, BNX2_BC_STATE_CONDITION);
+			val &= ~BNX2_CONDITION_PM_STATE_MASK;
+			val |= BNX2_CONDITION_PM_STATE_UNPREP;
+			bnx2_shmem_wr(bp, BNX2_BC_STATE_CONDITION, val);
+		}
+		pci_set_power_state(bp->pdev, PCI_D3hot);
 
 		/* No more memory access after this point until
 		 * device is brought back to D0.
diff --git a/drivers/net/ethernet/broadcom/bnx2.h b/drivers/net/ethernet/broadcom/bnx2.h
index f1cf2c4..e341bc3 100644
--- a/drivers/net/ethernet/broadcom/bnx2.h
+++ b/drivers/net/ethernet/broadcom/bnx2.h
@@ -6900,6 +6900,7 @@
 
 	u16			fw_wr_seq;
 	u16			fw_drv_pulse_wr_seq;
+	u32			fw_last_msg;
 
 	int			rx_max_ring;
 	int			rx_ring_size;
@@ -7406,6 +7407,10 @@
 #define BNX2_CONDITION_MFW_RUN_NCSI		 0x00006000
 #define BNX2_CONDITION_MFW_RUN_NONE		 0x0000e000
 #define BNX2_CONDITION_MFW_RUN_MASK		 0x0000e000
+#define BNX2_CONDITION_PM_STATE_MASK		 0x00030000
+#define BNX2_CONDITION_PM_STATE_FULL		 0x00030000
+#define BNX2_CONDITION_PM_STATE_PREP		 0x00020000
+#define BNX2_CONDITION_PM_STATE_UNPREP		 0x00010000
 
 #define BNX2_BC_STATE_DEBUG_CMD			0x1dc
 #define BNX2_BC_STATE_BC_DBG_CMD_SIGNATURE	 0x42440000
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 9d7419e..dbcff50 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1873,7 +1873,7 @@
 }
 
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv)
+		       void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
@@ -1895,7 +1895,7 @@
 	}
 
 	/* select a non-FCoE queue */
-	return __netdev_pick_tx(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp);
+	return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp);
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)
@@ -3875,7 +3875,9 @@
 						     xmit_type);
 		}
 
-		/* Add the macs to the parsing BD this is a vf */
+		/* Add the macs to the parsing BD if this is a vf or if
+		 * Tx Switching is enabled.
+		 */
 		if (IS_VF(bp)) {
 			/* override GRE parameters in BD */
 			bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.src_hi,
@@ -3887,6 +3889,11 @@
 					      &pbd_e2->data.mac_addr.dst_mid,
 					      &pbd_e2->data.mac_addr.dst_lo,
 					      eth->h_dest);
+		} else if (bp->flags & TX_SWITCHING) {
+			bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.dst_hi,
+					      &pbd_e2->data.mac_addr.dst_mid,
+					      &pbd_e2->data.mac_addr.dst_lo,
+					      eth->h_dest);
 		}
 
 		SET_FLAG(pbd_e2_parsing_data,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 17d1689..a89a40f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -496,7 +496,7 @@
 
 /* select_queue callback */
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv);
+		       void *accel_priv, select_queue_fallback_t fallback);
 
 static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 					struct bnx2x_fastpath *fp,
@@ -936,7 +936,7 @@
 	else /* CHIP_IS_E1X */
 		start_params->network_cos_mode = FW_WRR;
 
-	start_params->gre_tunnel_mode = IPGRE_TUNNEL;
+	start_params->gre_tunnel_mode = L2GRE_TUNNEL;
 	start_params->gre_tunnel_rss = GRE_INNER_HEADERS_RSS;
 
 	return bnx2x_func_state_change(bp, &func_params);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c9c445e..7d43822 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -95,29 +95,29 @@
 MODULE_FIRMWARE(FW_FILE_NAME_E2);
 
 int bnx2x_num_queues;
-module_param_named(num_queues, bnx2x_num_queues, int, 0);
+module_param_named(num_queues, bnx2x_num_queues, int, S_IRUGO);
 MODULE_PARM_DESC(num_queues,
 		 " Set number of queues (default is as a number of CPUs)");
 
 static int disable_tpa;
-module_param(disable_tpa, int, 0);
+module_param(disable_tpa, int, S_IRUGO);
 MODULE_PARM_DESC(disable_tpa, " Disable the TPA (LRO) feature");
 
 static int int_mode;
-module_param(int_mode, int, 0);
+module_param(int_mode, int, S_IRUGO);
 MODULE_PARM_DESC(int_mode, " Force interrupt mode other than MSI-X "
 				"(1 INT#x; 2 MSI)");
 
 static int dropless_fc;
-module_param(dropless_fc, int, 0);
+module_param(dropless_fc, int, S_IRUGO);
 MODULE_PARM_DESC(dropless_fc, " Pause on exhausted host ring");
 
 static int mrrs = -1;
-module_param(mrrs, int, 0);
+module_param(mrrs, int, S_IRUGO);
 MODULE_PARM_DESC(mrrs, " Force Max Read Req Size (0..3) (for debug)");
 
 static int debug;
-module_param(debug, int, 0);
+module_param(debug, int, S_IRUGO);
 MODULE_PARM_DESC(debug, " Default debug msglevel");
 
 struct workqueue_struct *bnx2x_wq;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index aec5ef2..e42f48d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1446,12 +1446,12 @@
 	if (vf->cfg_flags & VF_CFG_INT_SIMD)
 		val |= IGU_VF_CONF_SINGLE_ISR_EN;
 	val &= ~IGU_VF_CONF_PARENT_MASK;
-	val |= BP_FUNC(bp) << IGU_VF_CONF_PARENT_SHIFT;	/* parent PF */
+	val |= (BP_ABS_FUNC(bp) >> 1) << IGU_VF_CONF_PARENT_SHIFT;
 	REG_WR(bp, IGU_REG_VF_CONFIGURATION, val);
 
 	DP(BNX2X_MSG_IOV,
-	   "value in IGU_REG_VF_CONFIGURATION of vf %d after write %x\n",
-	   vf->abs_vfid, REG_RD(bp, IGU_REG_VF_CONFIGURATION));
+	   "value in IGU_REG_VF_CONFIGURATION of vf %d after write is 0x%08x\n",
+	   vf->abs_vfid, val);
 
 	bnx2x_pretend_func(bp, BP_ABS_FUNC(bp));
 
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index fcf9105a5..09f3fef 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -1,6 +1,6 @@
 /* cnic.c: Broadcom CNIC core network driver.
  *
- * Copyright (c) 2006-2013 Broadcom Corporation
+ * Copyright (c) 2006-2014 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -342,7 +342,7 @@
 	while (retry < 3) {
 		rc = 0;
 		rcu_read_lock();
-		ulp_ops = rcu_dereference(cnic_ulp_tbl[CNIC_ULP_ISCSI]);
+		ulp_ops = rcu_dereference(cp->ulp_ops[CNIC_ULP_ISCSI]);
 		if (ulp_ops)
 			rc = ulp_ops->iscsi_nl_send_msg(
 				cp->ulp_handle[CNIC_ULP_ISCSI],
@@ -726,7 +726,7 @@
 
 	for (i = 0; i < dma->num_pages; i++) {
 		if (dma->pg_arr[i]) {
-			dma_free_coherent(&dev->pcidev->dev, BNX2_PAGE_SIZE,
+			dma_free_coherent(&dev->pcidev->dev, CNIC_PAGE_SIZE,
 					  dma->pg_arr[i], dma->pg_map_arr[i]);
 			dma->pg_arr[i] = NULL;
 		}
@@ -785,7 +785,7 @@
 
 	for (i = 0; i < pages; i++) {
 		dma->pg_arr[i] = dma_alloc_coherent(&dev->pcidev->dev,
-						    BNX2_PAGE_SIZE,
+						    CNIC_PAGE_SIZE,
 						    &dma->pg_map_arr[i],
 						    GFP_ATOMIC);
 		if (dma->pg_arr[i] == NULL)
@@ -794,8 +794,8 @@
 	if (!use_pg_tbl)
 		return 0;
 
-	dma->pgtbl_size = ((pages * 8) + BNX2_PAGE_SIZE - 1) &
-			  ~(BNX2_PAGE_SIZE - 1);
+	dma->pgtbl_size = ((pages * 8) + CNIC_PAGE_SIZE - 1) &
+			  ~(CNIC_PAGE_SIZE - 1);
 	dma->pgtbl = dma_alloc_coherent(&dev->pcidev->dev, dma->pgtbl_size,
 					&dma->pgtbl_map, GFP_ATOMIC);
 	if (dma->pgtbl == NULL)
@@ -900,8 +900,8 @@
 	if (BNX2_CHIP(cp) == BNX2_CHIP_5709) {
 		int i, k, arr_size;
 
-		cp->ctx_blk_size = BNX2_PAGE_SIZE;
-		cp->cids_per_blk = BNX2_PAGE_SIZE / 128;
+		cp->ctx_blk_size = CNIC_PAGE_SIZE;
+		cp->cids_per_blk = CNIC_PAGE_SIZE / 128;
 		arr_size = BNX2_MAX_CID / cp->cids_per_blk *
 			   sizeof(struct cnic_ctx);
 		cp->ctx_arr = kzalloc(arr_size, GFP_KERNEL);
@@ -933,7 +933,7 @@
 		for (i = 0; i < cp->ctx_blks; i++) {
 			cp->ctx_arr[i].ctx =
 				dma_alloc_coherent(&dev->pcidev->dev,
-						   BNX2_PAGE_SIZE,
+						   CNIC_PAGE_SIZE,
 						   &cp->ctx_arr[i].mapping,
 						   GFP_KERNEL);
 			if (cp->ctx_arr[i].ctx == NULL)
@@ -1013,7 +1013,7 @@
 	if (udev->l2_ring)
 		return 0;
 
-	udev->l2_ring_size = pages * BNX2_PAGE_SIZE;
+	udev->l2_ring_size = pages * CNIC_PAGE_SIZE;
 	udev->l2_ring = dma_alloc_coherent(&udev->pdev->dev, udev->l2_ring_size,
 					   &udev->l2_ring_map,
 					   GFP_KERNEL | __GFP_COMP);
@@ -1021,7 +1021,7 @@
 		return -ENOMEM;
 
 	udev->l2_buf_size = (cp->l2_rx_ring_size + 1) * cp->l2_single_buf_size;
-	udev->l2_buf_size = PAGE_ALIGN(udev->l2_buf_size);
+	udev->l2_buf_size = CNIC_PAGE_ALIGN(udev->l2_buf_size);
 	udev->l2_buf = dma_alloc_coherent(&udev->pdev->dev, udev->l2_buf_size,
 					  &udev->l2_buf_map,
 					  GFP_KERNEL | __GFP_COMP);
@@ -1102,7 +1102,7 @@
 		uinfo->mem[0].size = MB_GET_CID_ADDR(TX_TSS_CID +
 						     TX_MAX_TSS_RINGS + 1);
 		uinfo->mem[1].addr = (unsigned long) cp->status_blk.gen &
-					PAGE_MASK;
+					CNIC_PAGE_MASK;
 		if (cp->ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX)
 			uinfo->mem[1].size = BNX2_SBLK_MSIX_ALIGN_SIZE * 9;
 		else
@@ -1113,7 +1113,7 @@
 		uinfo->mem[0].size = pci_resource_len(dev->pcidev, 0);
 
 		uinfo->mem[1].addr = (unsigned long) cp->bnx2x_def_status_blk &
-			PAGE_MASK;
+			CNIC_PAGE_MASK;
 		uinfo->mem[1].size = sizeof(*cp->bnx2x_def_status_blk);
 
 		uinfo->name = "bnx2x_cnic";
@@ -1267,14 +1267,14 @@
 	for (i = MAX_ISCSI_TBL_SZ; i < cp->max_cid_space; i++)
 		cp->ctx_tbl[i].ulp_proto_id = CNIC_ULP_FCOE;
 
-	pages = PAGE_ALIGN(cp->max_cid_space * CNIC_KWQ16_DATA_SIZE) /
-		PAGE_SIZE;
+	pages = CNIC_PAGE_ALIGN(cp->max_cid_space * CNIC_KWQ16_DATA_SIZE) /
+		CNIC_PAGE_SIZE;
 
 	ret = cnic_alloc_dma(dev, kwq_16_dma, pages, 0);
 	if (ret)
 		return -ENOMEM;
 
-	n = PAGE_SIZE / CNIC_KWQ16_DATA_SIZE;
+	n = CNIC_PAGE_SIZE / CNIC_KWQ16_DATA_SIZE;
 	for (i = 0, j = 0; i < cp->max_cid_space; i++) {
 		long off = CNIC_KWQ16_DATA_SIZE * (i % n);
 
@@ -1296,7 +1296,7 @@
 			goto error;
 	}
 
-	pages = PAGE_ALIGN(BNX2X_ISCSI_GLB_BUF_SIZE) / PAGE_SIZE;
+	pages = CNIC_PAGE_ALIGN(BNX2X_ISCSI_GLB_BUF_SIZE) / CNIC_PAGE_SIZE;
 	ret = cnic_alloc_dma(dev, &cp->gbl_buf_info, pages, 0);
 	if (ret)
 		goto error;
@@ -1466,8 +1466,8 @@
 	cp->r2tq_size = cp->num_iscsi_tasks * BNX2X_ISCSI_MAX_PENDING_R2TS *
 			BNX2X_ISCSI_R2TQE_SIZE;
 	cp->hq_size = cp->num_ccells * BNX2X_ISCSI_HQ_BD_SIZE;
-	pages = PAGE_ALIGN(cp->hq_size) / PAGE_SIZE;
-	hq_bds = pages * (PAGE_SIZE / BNX2X_ISCSI_HQ_BD_SIZE);
+	pages = CNIC_PAGE_ALIGN(cp->hq_size) / CNIC_PAGE_SIZE;
+	hq_bds = pages * (CNIC_PAGE_SIZE / BNX2X_ISCSI_HQ_BD_SIZE);
 	cp->num_cqs = req1->num_cqs;
 
 	if (!dev->max_iscsi_conn)
@@ -1477,9 +1477,9 @@
 	CNIC_WR16(dev, BAR_TSTRORM_INTMEM + TSTORM_ISCSI_RQ_SIZE_OFFSET(pfid),
 		  req1->rq_num_wqes);
 	CNIC_WR16(dev, BAR_TSTRORM_INTMEM + TSTORM_ISCSI_PAGE_SIZE_OFFSET(pfid),
-		  PAGE_SIZE);
+		  CNIC_PAGE_SIZE);
 	CNIC_WR8(dev, BAR_TSTRORM_INTMEM +
-		 TSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT);
+		 TSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS);
 	CNIC_WR16(dev, BAR_TSTRORM_INTMEM +
 		  TSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid),
 		  req1->num_tasks_per_conn);
@@ -1489,9 +1489,9 @@
 		  USTORM_ISCSI_RQ_BUFFER_SIZE_OFFSET(pfid),
 		  req1->rq_buffer_size);
 	CNIC_WR16(dev, BAR_USTRORM_INTMEM + USTORM_ISCSI_PAGE_SIZE_OFFSET(pfid),
-		  PAGE_SIZE);
+		  CNIC_PAGE_SIZE);
 	CNIC_WR8(dev, BAR_USTRORM_INTMEM +
-		 USTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT);
+		 USTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS);
 	CNIC_WR16(dev, BAR_USTRORM_INTMEM +
 		  USTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid),
 		  req1->num_tasks_per_conn);
@@ -1504,9 +1504,9 @@
 
 	/* init Xstorm RAM */
 	CNIC_WR16(dev, BAR_XSTRORM_INTMEM + XSTORM_ISCSI_PAGE_SIZE_OFFSET(pfid),
-		  PAGE_SIZE);
+		  CNIC_PAGE_SIZE);
 	CNIC_WR8(dev, BAR_XSTRORM_INTMEM +
-		 XSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT);
+		 XSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS);
 	CNIC_WR16(dev, BAR_XSTRORM_INTMEM +
 		  XSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid),
 		  req1->num_tasks_per_conn);
@@ -1519,9 +1519,9 @@
 
 	/* init Cstorm RAM */
 	CNIC_WR16(dev, BAR_CSTRORM_INTMEM + CSTORM_ISCSI_PAGE_SIZE_OFFSET(pfid),
-		  PAGE_SIZE);
+		  CNIC_PAGE_SIZE);
 	CNIC_WR8(dev, BAR_CSTRORM_INTMEM +
-		 CSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT);
+		 CSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS);
 	CNIC_WR16(dev, BAR_CSTRORM_INTMEM +
 		  CSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid),
 		  req1->num_tasks_per_conn);
@@ -1623,18 +1623,18 @@
 	}
 
 	ctx->cid = cid;
-	pages = PAGE_ALIGN(cp->task_array_size) / PAGE_SIZE;
+	pages = CNIC_PAGE_ALIGN(cp->task_array_size) / CNIC_PAGE_SIZE;
 
 	ret = cnic_alloc_dma(dev, &iscsi->task_array_info, pages, 1);
 	if (ret)
 		goto error;
 
-	pages = PAGE_ALIGN(cp->r2tq_size) / PAGE_SIZE;
+	pages = CNIC_PAGE_ALIGN(cp->r2tq_size) / CNIC_PAGE_SIZE;
 	ret = cnic_alloc_dma(dev, &iscsi->r2tq_info, pages, 1);
 	if (ret)
 		goto error;
 
-	pages = PAGE_ALIGN(cp->hq_size) / PAGE_SIZE;
+	pages = CNIC_PAGE_ALIGN(cp->hq_size) / CNIC_PAGE_SIZE;
 	ret = cnic_alloc_dma(dev, &iscsi->hq_info, pages, 1);
 	if (ret)
 		goto error;
@@ -1760,7 +1760,7 @@
 	ictx->tstorm_st_context.iscsi.hdr_bytes_2_fetch = ISCSI_HEADER_SIZE;
 	/* TSTORM requires the base address of RQ DB & not PTE */
 	ictx->tstorm_st_context.iscsi.rq_db_phy_addr.lo =
-		req2->rq_page_table_addr_lo & PAGE_MASK;
+		req2->rq_page_table_addr_lo & CNIC_PAGE_MASK;
 	ictx->tstorm_st_context.iscsi.rq_db_phy_addr.hi =
 		req2->rq_page_table_addr_hi;
 	ictx->tstorm_st_context.iscsi.iscsi_conn_id = req1->iscsi_conn_id;
@@ -1842,7 +1842,7 @@
 	/* CSTORM and USTORM initialization is different, CSTORM requires
 	 * CQ DB base & not PTE addr */
 	ictx->cstorm_st_context.cq_db_base.lo =
-		req1->cq_page_table_addr_lo & PAGE_MASK;
+		req1->cq_page_table_addr_lo & CNIC_PAGE_MASK;
 	ictx->cstorm_st_context.cq_db_base.hi = req1->cq_page_table_addr_hi;
 	ictx->cstorm_st_context.iscsi_conn_id = req1->iscsi_conn_id;
 	ictx->cstorm_st_context.cq_proc_en_bit_map = (1 << cp->num_cqs) - 1;
@@ -2911,7 +2911,7 @@
 	u16 hw_cons, sw_cons;
 	struct cnic_uio_dev *udev = cp->udev;
 	union eth_rx_cqe *cqe, *cqe_ring = (union eth_rx_cqe *)
-					(udev->l2_ring + (2 * BNX2_PAGE_SIZE));
+					(udev->l2_ring + (2 * CNIC_PAGE_SIZE));
 	u32 cmd;
 	int comp = 0;
 
@@ -3244,7 +3244,8 @@
 	int rc;
 
 	mutex_lock(&cnic_lock);
-	ulp_ops = cnic_ulp_tbl_prot(ulp_type);
+	ulp_ops = rcu_dereference_protected(cp->ulp_ops[ulp_type],
+					    lockdep_is_held(&cnic_lock));
 	if (ulp_ops && ulp_ops->cnic_get_stats)
 		rc = ulp_ops->cnic_get_stats(cp->ulp_handle[ulp_type]);
 	else
@@ -4384,7 +4385,7 @@
 		u32 idx = cp->ctx_arr[i].cid / cp->cids_per_blk;
 		u32 val;
 
-		memset(cp->ctx_arr[i].ctx, 0, BNX2_PAGE_SIZE);
+		memset(cp->ctx_arr[i].ctx, 0, CNIC_PAGE_SIZE);
 
 		CNIC_WR(dev, BNX2_CTX_HOST_PAGE_TBL_DATA0,
 			(cp->ctx_arr[i].mapping & 0xffffffff) | valid_bit);
@@ -4628,7 +4629,7 @@
 		val = BNX2_L2CTX_L2_STATUSB_NUM(sb_id);
 	cnic_ctx_wr(dev, cid_addr, BNX2_L2CTX_HOST_BDIDX, val);
 
-	rxbd = udev->l2_ring + BNX2_PAGE_SIZE;
+	rxbd = udev->l2_ring + CNIC_PAGE_SIZE;
 	for (i = 0; i < BNX2_MAX_RX_DESC_CNT; i++, rxbd++) {
 		dma_addr_t buf_map;
 		int n = (i % cp->l2_rx_ring_size) + 1;
@@ -4639,11 +4640,11 @@
 		rxbd->rx_bd_haddr_hi = (u64) buf_map >> 32;
 		rxbd->rx_bd_haddr_lo = (u64) buf_map & 0xffffffff;
 	}
-	val = (u64) (ring_map + BNX2_PAGE_SIZE) >> 32;
+	val = (u64) (ring_map + CNIC_PAGE_SIZE) >> 32;
 	cnic_ctx_wr(dev, cid_addr, BNX2_L2CTX_NX_BDHADDR_HI, val);
 	rxbd->rx_bd_haddr_hi = val;
 
-	val = (u64) (ring_map + BNX2_PAGE_SIZE) & 0xffffffff;
+	val = (u64) (ring_map + CNIC_PAGE_SIZE) & 0xffffffff;
 	cnic_ctx_wr(dev, cid_addr, BNX2_L2CTX_NX_BDHADDR_LO, val);
 	rxbd->rx_bd_haddr_lo = val;
 
@@ -4709,10 +4710,10 @@
 
 	val = CNIC_RD(dev, BNX2_MQ_CONFIG);
 	val &= ~BNX2_MQ_CONFIG_KNL_BYP_BLK_SIZE;
-	if (BNX2_PAGE_BITS > 12)
+	if (CNIC_PAGE_BITS > 12)
 		val |= (12 - 8)  << 4;
 	else
-		val |= (BNX2_PAGE_BITS - 8)  << 4;
+		val |= (CNIC_PAGE_BITS - 8)  << 4;
 
 	CNIC_WR(dev, BNX2_MQ_CONFIG, val);
 
@@ -4742,13 +4743,13 @@
 
 	/* Initialize the kernel work queue context. */
 	val = KRNLQ_TYPE_TYPE_KRNLQ | KRNLQ_SIZE_TYPE_SIZE |
-	      (BNX2_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ;
+	      (CNIC_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ;
 	cnic_ctx_wr(dev, kwq_cid_addr, L5_KRNLQ_TYPE, val);
 
-	val = (BNX2_PAGE_SIZE / sizeof(struct kwqe) - 1) << 16;
+	val = (CNIC_PAGE_SIZE / sizeof(struct kwqe) - 1) << 16;
 	cnic_ctx_wr(dev, kwq_cid_addr, L5_KRNLQ_QE_SELF_SEQ_MAX, val);
 
-	val = ((BNX2_PAGE_SIZE / sizeof(struct kwqe)) << 16) | KWQ_PAGE_CNT;
+	val = ((CNIC_PAGE_SIZE / sizeof(struct kwqe)) << 16) | KWQ_PAGE_CNT;
 	cnic_ctx_wr(dev, kwq_cid_addr, L5_KRNLQ_PGTBL_NPAGES, val);
 
 	val = (u32) ((u64) cp->kwq_info.pgtbl_map >> 32);
@@ -4768,13 +4769,13 @@
 
 	/* Initialize the kernel complete queue context. */
 	val = KRNLQ_TYPE_TYPE_KRNLQ | KRNLQ_SIZE_TYPE_SIZE |
-	      (BNX2_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ;
+	      (CNIC_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ;
 	cnic_ctx_wr(dev, kcq_cid_addr, L5_KRNLQ_TYPE, val);
 
-	val = (BNX2_PAGE_SIZE / sizeof(struct kcqe) - 1) << 16;
+	val = (CNIC_PAGE_SIZE / sizeof(struct kcqe) - 1) << 16;
 	cnic_ctx_wr(dev, kcq_cid_addr, L5_KRNLQ_QE_SELF_SEQ_MAX, val);
 
-	val = ((BNX2_PAGE_SIZE / sizeof(struct kcqe)) << 16) | KCQ_PAGE_CNT;
+	val = ((CNIC_PAGE_SIZE / sizeof(struct kcqe)) << 16) | KCQ_PAGE_CNT;
 	cnic_ctx_wr(dev, kcq_cid_addr, L5_KRNLQ_PGTBL_NPAGES, val);
 
 	val = (u32) ((u64) cp->kcq1.dma.pgtbl_map >> 32);
@@ -4918,7 +4919,7 @@
 	u32 cli = cp->ethdev->iscsi_l2_client_id;
 	u32 val;
 
-	memset(txbd, 0, BNX2_PAGE_SIZE);
+	memset(txbd, 0, CNIC_PAGE_SIZE);
 
 	buf_map = udev->l2_buf_map;
 	for (i = 0; i < BNX2_MAX_TX_DESC_CNT; i += 3, txbd += 3) {
@@ -4978,9 +4979,9 @@
 	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct cnic_uio_dev *udev = cp->udev;
 	struct eth_rx_bd *rxbd = (struct eth_rx_bd *) (udev->l2_ring +
-				BNX2_PAGE_SIZE);
+				CNIC_PAGE_SIZE);
 	struct eth_rx_cqe_next_page *rxcqe = (struct eth_rx_cqe_next_page *)
-				(udev->l2_ring + (2 * BNX2_PAGE_SIZE));
+				(udev->l2_ring + (2 * CNIC_PAGE_SIZE));
 	struct host_sp_status_block *sb = cp->bnx2x_def_status_blk;
 	int i;
 	u32 cli = cp->ethdev->iscsi_l2_client_id;
@@ -5004,20 +5005,20 @@
 		rxbd->addr_lo = cpu_to_le32(buf_map & 0xffffffff);
 	}
 
-	val = (u64) (ring_map + BNX2_PAGE_SIZE) >> 32;
+	val = (u64) (ring_map + CNIC_PAGE_SIZE) >> 32;
 	rxbd->addr_hi = cpu_to_le32(val);
 	data->rx.bd_page_base.hi = cpu_to_le32(val);
 
-	val = (u64) (ring_map + BNX2_PAGE_SIZE) & 0xffffffff;
+	val = (u64) (ring_map + CNIC_PAGE_SIZE) & 0xffffffff;
 	rxbd->addr_lo = cpu_to_le32(val);
 	data->rx.bd_page_base.lo = cpu_to_le32(val);
 
 	rxcqe += BNX2X_MAX_RCQ_DESC_CNT;
-	val = (u64) (ring_map + (2 * BNX2_PAGE_SIZE)) >> 32;
+	val = (u64) (ring_map + (2 * CNIC_PAGE_SIZE)) >> 32;
 	rxcqe->addr_hi = cpu_to_le32(val);
 	data->rx.cqe_page_base.hi = cpu_to_le32(val);
 
-	val = (u64) (ring_map + (2 * BNX2_PAGE_SIZE)) & 0xffffffff;
+	val = (u64) (ring_map + (2 * CNIC_PAGE_SIZE)) & 0xffffffff;
 	rxcqe->addr_lo = cpu_to_le32(val);
 	data->rx.cqe_page_base.lo = cpu_to_le32(val);
 
@@ -5265,8 +5266,8 @@
 		msleep(10);
 	}
 	clear_bit(CNIC_LCL_FL_RINGS_INITED, &cp->cnic_local_flags);
-	rx_ring = udev->l2_ring + BNX2_PAGE_SIZE;
-	memset(rx_ring, 0, BNX2_PAGE_SIZE);
+	rx_ring = udev->l2_ring + CNIC_PAGE_SIZE;
+	memset(rx_ring, 0, CNIC_PAGE_SIZE);
 }
 
 static int cnic_register_netdev(struct cnic_dev *dev)
diff --git a/drivers/net/ethernet/broadcom/cnic.h b/drivers/net/ethernet/broadcom/cnic.h
index 0d6b13f..d535ae4 100644
--- a/drivers/net/ethernet/broadcom/cnic.h
+++ b/drivers/net/ethernet/broadcom/cnic.h
@@ -1,6 +1,6 @@
 /* cnic.h: Broadcom CNIC core network driver.
  *
- * Copyright (c) 2006-2013 Broadcom Corporation
+ * Copyright (c) 2006-2014 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/ethernet/broadcom/cnic_defs.h b/drivers/net/ethernet/broadcom/cnic_defs.h
index 95a8e4b..dcbca69 100644
--- a/drivers/net/ethernet/broadcom/cnic_defs.h
+++ b/drivers/net/ethernet/broadcom/cnic_defs.h
@@ -1,7 +1,7 @@
 
 /* cnic.c: Broadcom CNIC core network driver.
  *
- * Copyright (c) 2006-2013 Broadcom Corporation
+ * Copyright (c) 2006-2014 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/ethernet/broadcom/cnic_if.h b/drivers/net/ethernet/broadcom/cnic_if.h
index 8cf6b192..5f4d557 100644
--- a/drivers/net/ethernet/broadcom/cnic_if.h
+++ b/drivers/net/ethernet/broadcom/cnic_if.h
@@ -1,6 +1,6 @@
 /* cnic_if.h: Broadcom CNIC core network driver.
  *
- * Copyright (c) 2006-2013 Broadcom Corporation
+ * Copyright (c) 2006-2014 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -14,8 +14,8 @@
 
 #include "bnx2x/bnx2x_mfw_req.h"
 
-#define CNIC_MODULE_VERSION	"2.5.19"
-#define CNIC_MODULE_RELDATE	"December 19, 2013"
+#define CNIC_MODULE_VERSION	"2.5.20"
+#define CNIC_MODULE_RELDATE	"March 14, 2014"
 
 #define CNIC_ULP_RDMA		0
 #define CNIC_ULP_ISCSI		1
@@ -24,6 +24,16 @@
 #define MAX_CNIC_ULP_TYPE_EXT	3
 #define MAX_CNIC_ULP_TYPE	4
 
+/* Use CPU native page size up to 16K for cnic ring sizes.  */
+#if (PAGE_SHIFT > 14)
+#define CNIC_PAGE_BITS	14
+#else
+#define CNIC_PAGE_BITS	PAGE_SHIFT
+#endif
+#define CNIC_PAGE_SIZE	(1 << (CNIC_PAGE_BITS))
+#define CNIC_PAGE_ALIGN(addr) ALIGN(addr, CNIC_PAGE_SIZE)
+#define CNIC_PAGE_MASK	(~((CNIC_PAGE_SIZE) - 1))
+
 struct kwqe {
 	u32 kwqe_op_flag;
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index e2ca03e..70a225c8 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -2609,13 +2609,14 @@
 
 	tg3_writephy(tp, MII_CTRL1000, phy9_orig);
 
-	if (!tg3_readphy(tp, MII_TG3_EXT_CTRL, &reg32)) {
-		reg32 &= ~0x3000;
-		tg3_writephy(tp, MII_TG3_EXT_CTRL, reg32);
-	} else if (!err)
-		err = -EBUSY;
+	err = tg3_readphy(tp, MII_TG3_EXT_CTRL, &reg32);
+	if (err)
+		return err;
 
-	return err;
+	reg32 &= ~0x3000;
+	tg3_writephy(tp, MII_TG3_EXT_CTRL, reg32);
+
+	return 0;
 }
 
 static void tg3_carrier_off(struct tg3 *tp)
@@ -6842,8 +6843,7 @@
 
 		work_mask |= opaque_key;
 
-		if ((desc->err_vlan & RXD_ERR_MASK) != 0 &&
-		    (desc->err_vlan != RXD_ERR_ODD_NIBBLE_RCVD_MII)) {
+		if (desc->err_vlan & RXD_ERR_MASK) {
 		drop_it:
 			tg3_recycle_rx(tnapi, tpr, opaque_key,
 				       desc_idx, *post_ptr);
@@ -14113,12 +14113,12 @@
 
 	tg3_netif_stop(tp);
 
+	tg3_set_mtu(dev, tp, new_mtu);
+
 	tg3_full_lock(tp, 1);
 
 	tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
 
-	tg3_set_mtu(dev, tp, new_mtu);
-
 	/* Reset PHY, otherwise the read DMA engine will be in a mode that
 	 * breaks all requests to 256 bytes.
 	 */
@@ -17649,8 +17649,6 @@
 
 	tg3_init_bufmgr_config(tp);
 
-	features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
-
 	/* 5700 B0 chips do not support checksumming correctly due
 	 * to hardware bugs.
 	 */
@@ -17682,7 +17680,8 @@
 			features |= NETIF_F_TSO_ECN;
 	}
 
-	dev->features |= features;
+	dev->features |= features | NETIF_F_HW_VLAN_CTAG_TX |
+			 NETIF_F_HW_VLAN_CTAG_RX;
 	dev->vlan_features |= features;
 
 	/*
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index ef47238..04321e5 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -2608,7 +2608,11 @@
 #define RXD_ERR_TOO_SMALL		0x00400000
 #define RXD_ERR_NO_RESOURCES		0x00800000
 #define RXD_ERR_HUGE_FRAME		0x01000000
-#define RXD_ERR_MASK			0xffff0000
+
+#define RXD_ERR_MASK	(RXD_ERR_BAD_CRC | RXD_ERR_COLLISION |		\
+			 RXD_ERR_LINK_LOST | RXD_ERR_PHY_DECODE |	\
+			 RXD_ERR_MAC_ABRT | RXD_ERR_TOO_SMALL |		\
+			 RXD_ERR_NO_RESOURCES | RXD_ERR_HUGE_FRAME)
 
 	u32				reserved;
 	u32				opaque;
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 1803c39..354ae97 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -1704,7 +1704,7 @@
 	while (!bfa_raw_sem_get(bar)) {
 		if (--n <= 0)
 			return BFA_STATUS_BADFLASH;
-		udelay(10000);
+		mdelay(10);
 	}
 	return BFA_STATUS_OK;
 }
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index cf64f3d..4ad1187 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -707,7 +707,8 @@
 		else
 			skb_checksum_none_assert(skb);
 
-		if (flags & BNA_CQ_EF_VLAN)
+		if ((flags & BNA_CQ_EF_VLAN) &&
+		    (bnad->netdev->features & NETIF_F_HW_VLAN_CTAG_RX))
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(cmpl->vlan_tag));
 
 		if (BNAD_RXBUF_IS_SK_BUFF(unmap_q->type))
@@ -2094,7 +2095,9 @@
 		rx_config->q1_buf_size = BFI_SMALL_RXBUF_SIZE;
 	}
 
-	rx_config->vlan_strip_status = BNA_STATUS_T_ENABLED;
+	rx_config->vlan_strip_status =
+		(bnad->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) ?
+		BNA_STATUS_T_ENABLED : BNA_STATUS_T_DISABLED;
 }
 
 static void
@@ -3245,11 +3248,6 @@
 			BNA_RXMODE_ALLMULTI;
 	bna_rx_mode_set(bnad->rx_info[0].rx, new_mode, mode_mask, NULL);
 
-	if (bnad->cfg_flags & BNAD_CF_PROMISC)
-		bna_rx_vlan_strip_disable(bnad->rx_info[0].rx);
-	else
-		bna_rx_vlan_strip_enable(bnad->rx_info[0].rx);
-
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 }
 
@@ -3374,6 +3372,27 @@
 	return 0;
 }
 
+static int bnad_set_features(struct net_device *dev, netdev_features_t features)
+{
+	struct bnad *bnad = netdev_priv(dev);
+	netdev_features_t changed = features ^ dev->features;
+
+	if ((changed & NETIF_F_HW_VLAN_CTAG_RX) && netif_running(dev)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&bnad->bna_lock, flags);
+
+		if (features & NETIF_F_HW_VLAN_CTAG_RX)
+			bna_rx_vlan_strip_enable(bnad->rx_info[0].rx);
+		else
+			bna_rx_vlan_strip_disable(bnad->rx_info[0].rx);
+
+		spin_unlock_irqrestore(&bnad->bna_lock, flags);
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void
 bnad_netpoll(struct net_device *netdev)
@@ -3421,6 +3440,7 @@
 	.ndo_change_mtu		= bnad_change_mtu,
 	.ndo_vlan_rx_add_vid    = bnad_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = bnad_vlan_rx_kill_vid,
+	.ndo_set_features	= bnad_set_features,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller    = bnad_netpoll
 #endif
@@ -3433,14 +3453,14 @@
 
 	netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-		NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_TX;
+		NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_TX |
+		NETIF_F_HW_VLAN_CTAG_RX;
 
 	netdev->vlan_features = NETIF_F_SG | NETIF_F_HIGHDMA |
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 		NETIF_F_TSO | NETIF_F_TSO6;
 
-	netdev->features |= netdev->hw_features |
-		NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER;
+	netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	if (using_dac)
 		netdev->features |= NETIF_F_HIGHDMA;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 3190d38..d0c38e0 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -632,11 +632,16 @@
 					   "Unable to allocate sk_buff\n");
 				break;
 			}
-			bp->rx_skbuff[entry] = skb;
 
 			/* now fill corresponding descriptor entry */
 			paddr = dma_map_single(&bp->pdev->dev, skb->data,
 					       bp->rx_buffer_size, DMA_FROM_DEVICE);
+			if (dma_mapping_error(&bp->pdev->dev, paddr)) {
+				dev_kfree_skb(skb);
+				break;
+			}
+
+			bp->rx_skbuff[entry] = skb;
 
 			if (entry == RX_RING_SIZE - 1)
 				paddr |= MACB_BIT(RX_WRAP);
@@ -725,7 +730,7 @@
 		skb_put(skb, len);
 		addr = MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, addr));
 		dma_unmap_single(&bp->pdev->dev, addr,
-				 len, DMA_FROM_DEVICE);
+				 bp->rx_buffer_size, DMA_FROM_DEVICE);
 
 		skb->protocol = eth_type_trans(skb, bp->dev);
 		skb_checksum_none_assert(skb);
@@ -1036,11 +1041,15 @@
 	}
 
 	entry = macb_tx_ring_wrap(bp->tx_head);
-	bp->tx_head++;
 	netdev_vdbg(bp->dev, "Allocated ring entry %u\n", entry);
 	mapping = dma_map_single(&bp->pdev->dev, skb->data,
 				 len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&bp->pdev->dev, mapping)) {
+		kfree_skb(skb);
+		goto unlock;
+	}
 
+	bp->tx_head++;
 	tx_skb = &bp->tx_skb[entry];
 	tx_skb->skb = skb;
 	tx_skb->mapping = mapping;
@@ -1066,6 +1075,7 @@
 	if (CIRC_SPACE(bp->tx_head, bp->tx_tail, TX_RING_SIZE) < 1)
 		netif_stop_queue(dev);
 
+unlock:
 	spin_unlock_irqrestore(&bp->lock, flags);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 43ab35f..34e2488 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -6179,6 +6179,7 @@
 	.id_table = cxgb4_pci_tbl,
 	.probe    = init_one,
 	.remove   = remove_one,
+	.shutdown = remove_one,
 	.err_handler = &cxgb4_eeh,
 };
 
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index add05f1..1642de7 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -1939,6 +1939,7 @@
 	pci_iounmap(pdev, tp->base_addr);
 	free_netdev (dev);
 	pci_release_regions (pdev);
+	pci_disable_device(pdev);
 
 	/* pci_power_off (pdev, -1); */
 }
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 8d09615..05529e2 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -350,11 +350,13 @@
 	u32 roce_drops_crc;
 };
 
+/* A vlan-id of 0xFFFF must be used to clear transparent vlan-tagging */
+#define BE_RESET_VLAN_TAG_ID	0xFFFF
+
 struct be_vf_cfg {
 	unsigned char mac_addr[ETH_ALEN];
 	int if_handle;
 	int pmac_id;
-	u16 def_vid;
 	u16 vlan_tag;
 	u32 tx_rate;
 };
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 04ac9c6..36c8061 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -913,24 +913,14 @@
 	return BE3_chip(adapter) && be_ipv6_exthdr_check(skb);
 }
 
-static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter,
-					   struct sk_buff *skb,
-					   bool *skip_hw_vlan)
+static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter,
+						  struct sk_buff *skb,
+						  bool *skip_hw_vlan)
 {
 	struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 	unsigned int eth_hdr_len;
 	struct iphdr *ip;
 
-	/* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or less
-	 * may cause a transmit stall on that port. So the work-around is to
-	 * pad short packets (<= 32 bytes) to a 36-byte length.
-	 */
-	if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) {
-		if (skb_padto(skb, 36))
-			goto tx_drop;
-		skb->len = 36;
-	}
-
 	/* For padded packets, BE HW modifies tot_len field in IP header
 	 * incorrecly when VLAN tag is inserted by HW.
 	 * For padded packets, Lancer computes incorrect checksum.
@@ -959,7 +949,7 @@
 	    vlan_tx_tag_present(skb)) {
 		skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan);
 		if (unlikely(!skb))
-			goto tx_drop;
+			goto err;
 	}
 
 	/* HW may lockup when VLAN HW tagging is requested on
@@ -981,15 +971,39 @@
 	    be_vlan_tag_tx_chk(adapter, skb)) {
 		skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan);
 		if (unlikely(!skb))
-			goto tx_drop;
+			goto err;
 	}
 
 	return skb;
 tx_drop:
 	dev_kfree_skb_any(skb);
+err:
 	return NULL;
 }
 
+static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter,
+					   struct sk_buff *skb,
+					   bool *skip_hw_vlan)
+{
+	/* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or
+	 * less may cause a transmit stall on that port. So the work-around is
+	 * to pad short packets (<= 32 bytes) to a 36-byte length.
+	 */
+	if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) {
+		if (skb_padto(skb, 36))
+			return NULL;
+		skb->len = 36;
+	}
+
+	if (BEx_chip(adapter) || lancer_chip(adapter)) {
+		skb = be_lancer_xmit_workarounds(adapter, skb, skip_hw_vlan);
+		if (!skb)
+			return NULL;
+	}
+
+	return skb;
+}
+
 static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
@@ -1157,6 +1171,14 @@
 	return status;
 }
 
+static void be_clear_promisc(struct be_adapter *adapter)
+{
+	adapter->promiscuous = false;
+	adapter->flags &= ~BE_FLAGS_VLAN_PROMISC;
+
+	be_cmd_rx_filter(adapter, IFF_PROMISC, OFF);
+}
+
 static void be_set_rx_mode(struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
@@ -1170,9 +1192,7 @@
 
 	/* BE was previously in promiscuous mode; disable it */
 	if (adapter->promiscuous) {
-		adapter->promiscuous = false;
-		be_cmd_rx_filter(adapter, IFF_PROMISC, OFF);
-
+		be_clear_promisc(adapter);
 		if (adapter->vlans_added)
 			be_vid_config(adapter);
 	}
@@ -1287,24 +1307,20 @@
 
 	if (vlan || qos) {
 		vlan |= qos << VLAN_PRIO_SHIFT;
-		if (vf_cfg->vlan_tag != vlan) {
-			/* If this is new value, program it. Else skip. */
-			vf_cfg->vlan_tag = vlan;
+		if (vf_cfg->vlan_tag != vlan)
 			status = be_cmd_set_hsw_config(adapter, vlan, vf + 1,
 						       vf_cfg->if_handle, 0);
-		}
 	} else {
 		/* Reset Transparent Vlan Tagging. */
-		vf_cfg->vlan_tag = 0;
-		vlan = vf_cfg->def_vid;
-		status = be_cmd_set_hsw_config(adapter, vlan, vf + 1,
-					       vf_cfg->if_handle, 0);
+		status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID,
+					       vf + 1, vf_cfg->if_handle, 0);
 	}
 
-
-	if (status)
+	if (!status)
+		vf_cfg->vlan_tag = vlan;
+	else
 		dev_info(&adapter->pdev->dev,
-				"VLAN %d config on VF %d failed\n", vlan, vf);
+			 "VLAN %d config on VF %d failed\n", vlan, vf);
 	return status;
 }
 
@@ -3013,11 +3029,11 @@
 
 static int be_vf_setup(struct be_adapter *adapter)
 {
-	struct be_vf_cfg *vf_cfg;
-	u16 def_vlan, lnk_speed;
-	int status, old_vfs, vf;
 	struct device *dev = &adapter->pdev->dev;
+	struct be_vf_cfg *vf_cfg;
+	int status, old_vfs, vf;
 	u32 privileges;
+	u16 lnk_speed;
 
 	old_vfs = pci_num_vf(adapter->pdev);
 	if (old_vfs) {
@@ -3084,12 +3100,6 @@
 		if (!status)
 			vf_cfg->tx_rate = lnk_speed;
 
-		status = be_cmd_get_hsw_config(adapter, &def_vlan,
-					       vf + 1, vf_cfg->if_handle, NULL);
-		if (status)
-			goto err;
-		vf_cfg->def_vid = def_vlan;
-
 		if (!old_vfs)
 			be_cmd_enable_vf(adapter, vf + 1);
 	}
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 4de8cfd..55e0fa0 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -13,6 +13,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/etherdevice.h>
+#include <linux/clk.h>
 #include <linux/crc32.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -51,6 +52,7 @@
 #define	ETH_HASH0	0x48
 #define	ETH_HASH1	0x4c
 #define	ETH_TXCTRL	0x50
+#define	ETH_END		0x54
 
 /* mode register */
 #define	MODER_RXEN	(1 <<  0) /* receive enable */
@@ -179,6 +181,7 @@
  * @membase:	pointer to buffer memory region
  * @dma_alloc:	dma allocated buffer size
  * @io_region_size:	I/O memory region size
+ * @num_bd:	number of buffer descriptors
  * @num_tx:	number of send buffers
  * @cur_tx:	last send buffer written
  * @dty_tx:	last buffer actually sent
@@ -199,6 +202,7 @@
 	int dma_alloc;
 	resource_size_t io_region_size;
 
+	unsigned int num_bd;
 	unsigned int num_tx;
 	unsigned int cur_tx;
 	unsigned int dty_tx;
@@ -216,6 +220,7 @@
 
 	struct phy_device *phy;
 	struct mii_bus *mdio;
+	struct clk *clk;
 	s8 phy_id;
 };
 
@@ -688,6 +693,11 @@
 	}
 
 	priv->phy = phy;
+	phy->advertising &= ~(ADVERTISED_1000baseT_Full |
+			      ADVERTISED_1000baseT_Half);
+	phy->supported &= ~(SUPPORTED_1000baseT_Full |
+			    SUPPORTED_1000baseT_Half);
+
 	return 0;
 }
 
@@ -890,6 +900,102 @@
 	return NETDEV_TX_OK;
 }
 
+static int ethoc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+	struct ethoc *priv = netdev_priv(dev);
+	struct phy_device *phydev = priv->phy;
+
+	if (!phydev)
+		return -EOPNOTSUPP;
+
+	return phy_ethtool_gset(phydev, cmd);
+}
+
+static int ethoc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+	struct ethoc *priv = netdev_priv(dev);
+	struct phy_device *phydev = priv->phy;
+
+	if (!phydev)
+		return -EOPNOTSUPP;
+
+	return phy_ethtool_sset(phydev, cmd);
+}
+
+static int ethoc_get_regs_len(struct net_device *netdev)
+{
+	return ETH_END;
+}
+
+static void ethoc_get_regs(struct net_device *dev, struct ethtool_regs *regs,
+			   void *p)
+{
+	struct ethoc *priv = netdev_priv(dev);
+	u32 *regs_buff = p;
+	unsigned i;
+
+	regs->version = 0;
+	for (i = 0; i < ETH_END / sizeof(u32); ++i)
+		regs_buff[i] = ethoc_read(priv, i * sizeof(u32));
+}
+
+static void ethoc_get_ringparam(struct net_device *dev,
+				struct ethtool_ringparam *ring)
+{
+	struct ethoc *priv = netdev_priv(dev);
+
+	ring->rx_max_pending = priv->num_bd - 1;
+	ring->rx_mini_max_pending = 0;
+	ring->rx_jumbo_max_pending = 0;
+	ring->tx_max_pending = priv->num_bd - 1;
+
+	ring->rx_pending = priv->num_rx;
+	ring->rx_mini_pending = 0;
+	ring->rx_jumbo_pending = 0;
+	ring->tx_pending = priv->num_tx;
+}
+
+static int ethoc_set_ringparam(struct net_device *dev,
+			       struct ethtool_ringparam *ring)
+{
+	struct ethoc *priv = netdev_priv(dev);
+
+	if (ring->tx_pending < 1 || ring->rx_pending < 1 ||
+	    ring->tx_pending + ring->rx_pending > priv->num_bd)
+		return -EINVAL;
+	if (ring->rx_mini_pending || ring->rx_jumbo_pending)
+		return -EINVAL;
+
+	if (netif_running(dev)) {
+		netif_tx_disable(dev);
+		ethoc_disable_rx_and_tx(priv);
+		ethoc_disable_irq(priv, INT_MASK_TX | INT_MASK_RX);
+		synchronize_irq(dev->irq);
+	}
+
+	priv->num_tx = rounddown_pow_of_two(ring->tx_pending);
+	priv->num_rx = ring->rx_pending;
+	ethoc_init_ring(priv, dev->mem_start);
+
+	if (netif_running(dev)) {
+		ethoc_enable_irq(priv, INT_MASK_TX | INT_MASK_RX);
+		ethoc_enable_rx_and_tx(priv);
+		netif_wake_queue(dev);
+	}
+	return 0;
+}
+
+const struct ethtool_ops ethoc_ethtool_ops = {
+	.get_settings = ethoc_get_settings,
+	.set_settings = ethoc_set_settings,
+	.get_regs_len = ethoc_get_regs_len,
+	.get_regs = ethoc_get_regs,
+	.get_link = ethtool_op_get_link,
+	.get_ringparam = ethoc_get_ringparam,
+	.set_ringparam = ethoc_set_ringparam,
+	.get_ts_info = ethtool_op_get_ts_info,
+};
+
 static const struct net_device_ops ethoc_netdev_ops = {
 	.ndo_open = ethoc_open,
 	.ndo_stop = ethoc_stop,
@@ -917,6 +1023,8 @@
 	int num_bd;
 	int ret = 0;
 	bool random_mac = false;
+	struct ethoc_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	u32 eth_clkfreq = pdata ? pdata->eth_clkfreq : 0;
 
 	/* allocate networking device */
 	netdev = alloc_etherdev(sizeof(struct ethoc));
@@ -1016,6 +1124,7 @@
 		ret = -ENODEV;
 		goto error;
 	}
+	priv->num_bd = num_bd;
 	/* num_tx must be a power of two */
 	priv->num_tx = rounddown_pow_of_two(num_bd >> 1);
 	priv->num_rx = num_bd - priv->num_tx;
@@ -1030,8 +1139,7 @@
 	}
 
 	/* Allow the platform setup code to pass in a MAC address. */
-	if (dev_get_platdata(&pdev->dev)) {
-		struct ethoc_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	if (pdata) {
 		memcpy(netdev->dev_addr, pdata->hwaddr, IFHWADDRLEN);
 		priv->phy_id = pdata->phy_id;
 	} else {
@@ -1069,6 +1177,27 @@
 	if (random_mac)
 		netdev->addr_assign_type = NET_ADDR_RANDOM;
 
+	/* Allow the platform setup code to adjust MII management bus clock. */
+	if (!eth_clkfreq) {
+		struct clk *clk = devm_clk_get(&pdev->dev, NULL);
+
+		if (!IS_ERR(clk)) {
+			priv->clk = clk;
+			clk_prepare_enable(clk);
+			eth_clkfreq = clk_get_rate(clk);
+		}
+	}
+	if (eth_clkfreq) {
+		u32 clkdiv = MIIMODER_CLKDIV(eth_clkfreq / 2500000 + 1);
+
+		if (!clkdiv)
+			clkdiv = 2;
+		dev_dbg(&pdev->dev, "setting MII clkdiv to %u\n", clkdiv);
+		ethoc_write(priv, MIIMODER,
+			    (ethoc_read(priv, MIIMODER) & MIIMODER_NOPRE) |
+			    clkdiv);
+	}
+
 	/* register MII bus */
 	priv->mdio = mdiobus_alloc();
 	if (!priv->mdio) {
@@ -1111,6 +1240,7 @@
 	netdev->netdev_ops = &ethoc_netdev_ops;
 	netdev->watchdog_timeo = ETHOC_TIMEOUT;
 	netdev->features |= 0;
+	netdev->ethtool_ops = &ethoc_ethtool_ops;
 
 	/* setup NAPI */
 	netif_napi_add(netdev, &priv->napi, ethoc_poll, 64);
@@ -1133,6 +1263,8 @@
 	kfree(priv->mdio->irq);
 	mdiobus_free(priv->mdio);
 free:
+	if (priv->clk)
+		clk_disable_unprepare(priv->clk);
 	free_netdev(netdev);
 out:
 	return ret;
@@ -1157,6 +1289,8 @@
 			kfree(priv->mdio->irq);
 			mdiobus_free(priv->mdio);
 		}
+		if (priv->clk)
+			clk_disable_unprepare(priv->clk);
 		unregister_netdev(netdev);
 		free_netdev(netdev);
 	}
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d4782b4..03a3513 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -389,12 +389,6 @@
 			netdev_err(ndev, "Tx DMA memory map failed\n");
 		return NETDEV_TX_OK;
 	}
-	/* Send it on its way.  Tell FEC it's ready, interrupt when done,
-	 * it's the last BD of the frame, and to put the CRC on the end.
-	 */
-	status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR
-			| BD_ENET_TX_LAST | BD_ENET_TX_TC);
-	bdp->cbd_sc = status;
 
 	if (fep->bufdesc_ex) {
 
@@ -416,6 +410,13 @@
 		}
 	}
 
+	/* Send it on its way.  Tell FEC it's ready, interrupt when done,
+	 * it's the last BD of the frame, and to put the CRC on the end.
+	 */
+	status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR
+			| BD_ENET_TX_LAST | BD_ENET_TX_TC);
+	bdp->cbd_sc = status;
+
 	bdp_pre = fec_enet_get_prevdesc(bdp, fep);
 	if ((id_entry->driver_data & FEC_QUIRK_ERR006358) &&
 	    !(bdp_pre->cbd_sc & BD_ENET_TX_READY)) {
@@ -527,13 +528,6 @@
 	/* Clear any outstanding interrupt. */
 	writel(0xffc00000, fep->hwp + FEC_IEVENT);
 
-	/* Setup multicast filter. */
-	set_multicast_list(ndev);
-#ifndef CONFIG_M5272
-	writel(0, fep->hwp + FEC_HASH_TABLE_HIGH);
-	writel(0, fep->hwp + FEC_HASH_TABLE_LOW);
-#endif
-
 	/* Set maximum receive buffer size. */
 	writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE);
 
@@ -654,6 +648,13 @@
 
 	writel(rcntl, fep->hwp + FEC_R_CNTRL);
 
+	/* Setup multicast filter. */
+	set_multicast_list(ndev);
+#ifndef CONFIG_M5272
+	writel(0, fep->hwp + FEC_HASH_TABLE_HIGH);
+	writel(0, fep->hwp + FEC_HASH_TABLE_LOW);
+#endif
+
 	if (id_entry->driver_data & FEC_QUIRK_ENET_MAC) {
 		/* enable ENET endian swap */
 		ecntl |= (1 << 8);
@@ -1778,8 +1779,6 @@
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int ret;
 
-	napi_enable(&fep->napi);
-
 	/* I should reset the ring buffers here, but I don't yet know
 	 * a simple way to do that.
 	 */
@@ -1794,6 +1793,8 @@
 		fec_enet_free_buffers(ndev);
 		return ret;
 	}
+
+	napi_enable(&fep->napi);
 	phy_start(fep->phy_dev);
 	netif_start_queue(ndev);
 	fep->opened = 1;
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 4be9715..1fc8334 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -522,10 +522,21 @@
 	return rc;
 }
 
+static u64 ibmveth_encode_mac_addr(u8 *mac)
+{
+	int i;
+	u64 encoded = 0;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		encoded = (encoded << 8) | mac[i];
+
+	return encoded;
+}
+
 static int ibmveth_open(struct net_device *netdev)
 {
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
-	u64 mac_address = 0;
+	u64 mac_address;
 	int rxq_entries = 1;
 	unsigned long lpar_rc;
 	int rc;
@@ -579,8 +590,7 @@
 	adapter->rx_queue.num_slots = rxq_entries;
 	adapter->rx_queue.toggle = 1;
 
-	memcpy(&mac_address, netdev->dev_addr, netdev->addr_len);
-	mac_address = mac_address >> 16;
+	mac_address = ibmveth_encode_mac_addr(netdev->dev_addr);
 
 	rxq_desc.fields.flags_len = IBMVETH_BUF_VALID |
 					adapter->rx_queue.queue_len;
@@ -1183,8 +1193,8 @@
 		/* add the addresses to the filter table */
 		netdev_for_each_mc_addr(ha, netdev) {
 			/* add the multicast address to the filter table */
-			unsigned long mcast_addr = 0;
-			memcpy(((char *)&mcast_addr)+2, ha->addr, ETH_ALEN);
+			u64 mcast_addr;
+			mcast_addr = ibmveth_encode_mac_addr(ha->addr);
 			lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
 						   IbmVethMcastAddFilter,
 						   mcast_addr);
@@ -1372,9 +1382,6 @@
 
 	netif_napi_add(netdev, &adapter->napi, ibmveth_poll, 16);
 
-	adapter->mac_addr = 0;
-	memcpy(&adapter->mac_addr, mac_addr_p, ETH_ALEN);
-
 	netdev->irq = dev->irq;
 	netdev->netdev_ops = &ibmveth_netdev_ops;
 	netdev->ethtool_ops = &netdev_ethtool_ops;
@@ -1383,7 +1390,7 @@
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	netdev->features |= netdev->hw_features;
 
-	memcpy(netdev->dev_addr, &adapter->mac_addr, netdev->addr_len);
+	memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN);
 
 	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
 		struct kobject *kobj = &adapter->rx_buff_pool[i].kobj;
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 451ba79..1f37499 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -138,7 +138,6 @@
     struct napi_struct napi;
     struct net_device_stats stats;
     unsigned int mcastFilterSize;
-    unsigned long mac_addr;
     void * buffer_list_addr;
     void * filter_list_addr;
     dma_addr_t buffer_list_dma;
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index cbaba44..bf7a01e 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -3034,7 +3034,7 @@
 		*enable_wake = false;
 	}
 
-	pci_disable_device(pdev);
+	pci_clear_master(pdev);
 }
 
 static int __e100_power_off(struct pci_dev *pdev, bool wake)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 6d4ada7..18076c4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6881,7 +6881,7 @@
 }
 
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
-			      void *accel_priv)
+			      void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
 #ifdef IXGBE_FCOE
@@ -6907,7 +6907,7 @@
 		if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
 			break;
 	default:
-		return __netdev_pick_tx(dev, skb);
+		return fallback(dev, skb);
 	}
 
 	f = &adapter->ring_feature[RING_F_FCOE];
@@ -6920,7 +6920,7 @@
 
 	return txq + f->offset;
 #else
-	return __netdev_pick_tx(dev, skb);
+	return fallback(dev, skb);
 #endif
 }
 
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 8f9266c..fd4b6ae 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -619,7 +619,7 @@
 
 static u16
 ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
-		      void *accel_priv)
+		      void *accel_priv, select_queue_fallback_t fallback)
 {
 	/* we are currently only using the first queue */
 	return 0;
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 6300fd2..68e6a66 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -43,12 +43,12 @@
 	  This driver is used by the MV643XX_ETH and MVNETA drivers.
 
 config MVNETA
-	tristate "Marvell Armada 370/XP network interface support"
-	depends on MACH_ARMADA_370_XP
+	tristate "Marvell Armada 370/38x/XP network interface support"
+	depends on PLAT_ORION
 	select MVMDIO
 	---help---
 	  This driver supports the network interface units in the
-	  Marvell ARMADA XP and ARMADA 370 SoC family.
+	  Marvell ARMADA XP, ARMADA 370 and ARMADA 38x SoC family.
 
 	  Note that this driver is distinct from the mv643xx_eth
 	  driver, which should be used for the older Marvell SoCs
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index f418f4f..8d76fca 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
+#include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
@@ -88,8 +89,9 @@
 #define      MVNETA_TX_IN_PRGRS                  BIT(1)
 #define      MVNETA_TX_FIFO_EMPTY                BIT(8)
 #define MVNETA_RX_MIN_FRAME_SIZE                 0x247c
-#define MVNETA_SGMII_SERDES_CFG			 0x24A0
+#define MVNETA_SERDES_CFG			 0x24A0
 #define      MVNETA_SGMII_SERDES_PROTO		 0x0cc7
+#define      MVNETA_RGMII_SERDES_PROTO		 0x0667
 #define MVNETA_TYPE_PRIO                         0x24bc
 #define      MVNETA_FORCE_UNI                    BIT(21)
 #define MVNETA_TXQ_CMD_1                         0x24e4
@@ -161,7 +163,7 @@
 #define      MVNETA_GMAC_MAX_RX_SIZE_MASK        0x7ffc
 #define      MVNETA_GMAC0_PORT_ENABLE            BIT(0)
 #define MVNETA_GMAC_CTRL_2                       0x2c08
-#define      MVNETA_GMAC2_PSC_ENABLE             BIT(3)
+#define      MVNETA_GMAC2_PCS_ENABLE             BIT(3)
 #define      MVNETA_GMAC2_PORT_RGMII             BIT(4)
 #define      MVNETA_GMAC2_PORT_RESET             BIT(6)
 #define MVNETA_GMAC_STATUS                       0x2c10
@@ -710,35 +712,6 @@
 	mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
 }
 
-
-
-/* Sets the RGMII Enable bit (RGMIIEn) in port MAC control register */
-static void mvneta_gmac_rgmii_set(struct mvneta_port *pp, int enable)
-{
-	u32  val;
-
-	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
-
-	if (enable)
-		val |= MVNETA_GMAC2_PORT_RGMII;
-	else
-		val &= ~MVNETA_GMAC2_PORT_RGMII;
-
-	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
-}
-
-/* Config SGMII port */
-static void mvneta_port_sgmii_config(struct mvneta_port *pp)
-{
-	u32 val;
-
-	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
-	val |= MVNETA_GMAC2_PSC_ENABLE;
-	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
-
-	mvreg_write(pp, MVNETA_SGMII_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
-}
-
 /* Start the Ethernet port RX and TX activity */
 static void mvneta_port_up(struct mvneta_port *pp)
 {
@@ -2756,12 +2729,15 @@
 	mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0);
 
 	if (phy_mode == PHY_INTERFACE_MODE_SGMII)
-		mvneta_port_sgmii_config(pp);
+		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
+	else
+		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_RGMII_SERDES_PROTO);
 
-	mvneta_gmac_rgmii_set(pp, 1);
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+
+	val |= MVNETA_GMAC2_PCS_ENABLE | MVNETA_GMAC2_PORT_RGMII;
 
 	/* Cancel Port Reset */
-	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
 	val &= ~MVNETA_GMAC2_PORT_RESET;
 	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
 
@@ -2774,6 +2750,7 @@
 static int mvneta_probe(struct platform_device *pdev)
 {
 	const struct mbus_dram_target_info *dram_target_info;
+	struct resource *res;
 	struct device_node *dn = pdev->dev.of_node;
 	struct device_node *phy_node;
 	u32 phy_addr;
@@ -2838,9 +2815,15 @@
 
 	clk_prepare_enable(pp->clk);
 
-	pp->base = of_iomap(dn, 0);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		err = -ENODEV;
+		goto err_clk;
+	}
+
+	pp->base = devm_ioremap_resource(&pdev->dev, res);
 	if (pp->base == NULL) {
-		err = -ENOMEM;
+		err = PTR_ERR(pp->base);
 		goto err_clk;
 	}
 
@@ -2848,7 +2831,7 @@
 	pp->stats = alloc_percpu(struct mvneta_pcpu_stats);
 	if (!pp->stats) {
 		err = -ENOMEM;
-		goto err_unmap;
+		goto err_clk;
 	}
 
 	for_each_possible_cpu(cpu) {
@@ -2913,8 +2896,6 @@
 	mvneta_deinit(pp);
 err_free_stats:
 	free_percpu(pp->stats);
-err_unmap:
-	iounmap(pp->base);
 err_clk:
 	clk_disable_unprepare(pp->clk);
 err_free_irq:
@@ -2934,7 +2915,6 @@
 	mvneta_deinit(pp);
 	clk_disable_unprepare(pp->clk);
 	free_percpu(pp->stats);
-	iounmap(pp->base);
 	irq_dispose_mapping(dev->irq);
 	free_netdev(dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index fad4531..84a96f7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -742,6 +742,14 @@
 				err = mlx4_en_uc_steer_add(priv, new_mac,
 							   &qpn,
 							   &entry->reg_id);
+				if (err)
+					return err;
+				if (priv->tunnel_reg_id) {
+					mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
+					priv->tunnel_reg_id = 0;
+				}
+				err = mlx4_en_tunnel_steer_add(priv, new_mac, qpn,
+							       &priv->tunnel_reg_id);
 				return err;
 			}
 		}
@@ -1792,6 +1800,8 @@
 		mc_list[5] = priv->port;
 		mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
 				      mc_list, MLX4_PROT_ETH, mclist->reg_id);
+		if (mclist->tunnel_reg_id)
+			mlx4_flow_detach(mdev->dev, mclist->tunnel_reg_id);
 	}
 	mlx4_en_clear_list(dev);
 	list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 8e8a7eb..1345703 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -629,7 +629,7 @@
 }
 
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 void *accel_priv)
+			 void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u16 rings_p_up = priv->num_tx_rings_p_up;
@@ -641,7 +641,7 @@
 	if (vlan_tx_tag_present(skb))
 		up = vlan_tx_tag_get(skb) >> VLAN_PRIO_SHIFT;
 
-	return __netdev_pick_tx(dev, skb) % rings_p_up + up * rings_p_up;
+	return fallback(dev, skb) % rings_p_up + up * rings_p_up;
 }
 
 static void mlx4_bf_copy(void __iomem *dst, unsigned long *src, unsigned bytecnt)
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 91b69ff..7e2995e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -129,13 +129,14 @@
 		[0] = "RSS support",
 		[1] = "RSS Toeplitz Hash Function support",
 		[2] = "RSS XOR Hash Function support",
-		[3] = "Device manage flow steering support",
+		[3] = "Device managed flow steering support",
 		[4] = "Automatic MAC reassignment support",
 		[5] = "Time stamping support",
 		[6] = "VST (control vlan insertion/stripping) support",
 		[7] = "FSM (MAC anti-spoofing) support",
 		[8] = "Dynamic QP updates support",
-		[9] = "TCP/IP offloads/flow-steering for VXLAN support"
+		[9] = "Device managed flow steering IPoIB support",
+		[10] = "TCP/IP offloads/flow-steering for VXLAN support"
 	};
 	int i;
 
@@ -859,7 +860,7 @@
 	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET);
 
 	/* For guests, disable vxlan tunneling */
-	MLX4_GET(field, outbox, QUERY_DEV_CAP_VXLAN);
+	MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_VXLAN);
 	field &= 0xf7;
 	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_VXLAN);
 
@@ -869,7 +870,7 @@
 	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_BF_OFFSET);
 
 	/* For guests, disable mw type 2 */
-	MLX4_GET(bmme_flags, outbox, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
+	MLX4_GET(bmme_flags, outbox->buf, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
 	bmme_flags &= ~MLX4_BMME_FLAG_TYPE_2_WIN;
 	MLX4_PUT(outbox->buf, bmme_flags, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
 
@@ -883,7 +884,7 @@
 	}
 
 	/* turn off ipoib managed steering for guests */
-	MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
+	MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
 	field &= ~0x80;
 	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index d711158..d413e60 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -150,6 +150,8 @@
 	struct pci_dev *pdev;
 };
 
+static atomic_t pf_loading = ATOMIC_INIT(0);
+
 int mlx4_check_port_params(struct mlx4_dev *dev,
 			   enum mlx4_port_type *port_type)
 {
@@ -749,7 +751,7 @@
 			has_eth_port = true;
 	}
 
-	if (has_ib_port)
+	if (has_ib_port || (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
 		request_module_nowait(IB_DRV_NAME);
 	if (has_eth_port)
 		request_module_nowait(EN_DRV_NAME);
@@ -1407,6 +1409,11 @@
 	u32 slave_read;
 	u32 cmd_channel_ver;
 
+	if (atomic_read(&pf_loading)) {
+		mlx4_warn(dev, "PF is not ready. Deferring probe\n");
+		return -EPROBE_DEFER;
+	}
+
 	mutex_lock(&priv->cmd.slave_cmd_mutex);
 	priv->cmd.max_cmds = 1;
 	mlx4_warn(dev, "Sending reset\n");
@@ -2319,7 +2326,11 @@
 
 		if (num_vfs) {
 			mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", num_vfs);
+
+			atomic_inc(&pf_loading);
 			err = pci_enable_sriov(pdev, num_vfs);
+			atomic_dec(&pf_loading);
+
 			if (err) {
 				mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n",
 					 err);
@@ -2670,7 +2681,11 @@
 
 static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
 {
-	int ret = __mlx4_init_one(pdev, 0);
+	const struct pci_device_id *id;
+	int ret;
+
+	id = pci_match_id(mlx4_pci_table, pdev);
+	ret = __mlx4_init_one(pdev, id->driver_data);
 
 	return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
@@ -2684,6 +2699,7 @@
 	.name		= DRV_NAME,
 	.id_table	= mlx4_pci_table,
 	.probe		= mlx4_init_one,
+	.shutdown	= mlx4_remove_one,
 	.remove		= mlx4_remove_one,
 	.err_handler    = &mlx4_err_handler,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 6b65f77..7aec6c8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -51,8 +51,8 @@
 
 #define DRV_NAME	"mlx4_core"
 #define PFX		DRV_NAME ": "
-#define DRV_VERSION	"1.1"
-#define DRV_RELDATE	"Dec, 2011"
+#define DRV_VERSION	"2.2-1"
+#define DRV_RELDATE	"Feb, 2014"
 
 #define MLX4_FS_UDP_UC_EN		(1 << 1)
 #define MLX4_FS_TCP_UC_EN		(1 << 2)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 3af04c3..b57e8c8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -57,8 +57,8 @@
 #include "en_port.h"
 
 #define DRV_NAME	"mlx4_en"
-#define DRV_VERSION	"2.0"
-#define DRV_RELDATE	"Dec 2011"
+#define DRV_VERSION	"2.2-1"
+#define DRV_RELDATE	"Feb 2014"
 
 #define MLX4_EN_MSG_LEVEL	(NETIF_MSG_LINK | NETIF_MSG_IFDOWN)
 
@@ -723,7 +723,7 @@
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq);
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 void *accel_priv);
+			 void *accel_priv, select_queue_fallback_t fallback);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 157fe8d..8ff57e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -4,5 +4,5 @@
 
 config MLX5_CORE
 	tristate
-	depends on PCI && X86
+	depends on PCI
 	default n
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a064f06..23b7e2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -46,8 +46,8 @@
 #include "mlx5_core.h"
 
 #define DRIVER_NAME "mlx5_core"
-#define DRIVER_VERSION "1.0"
-#define DRIVER_RELDATE	"June 2013"
+#define DRIVER_VERSION "2.2-1"
+#define DRIVER_RELDATE	"Feb 2014"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox ConnectX-IB HCA core library");
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 727b546a..e0c92e0 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -23,6 +23,7 @@
 #include <linux/crc32.h>
 #include <linux/mii.h>
 #include <linux/eeprom_93cx6.h>
+#include <linux/regulator/consumer.h>
 
 #include <linux/spi/spi.h>
 
@@ -83,6 +84,7 @@
  * @rc_rxqcr: Cached copy of KS_RXQCR.
  * @eeprom_size: Companion eeprom size in Bytes, 0 if no eeprom
  * @eeprom: 93CX6 EEPROM state for accessing on-board EEPROM.
+ * @vdd_reg:	Optional regulator supplying the chip
  *
  * The @lock ensures that the chip is protected when certain operations are
  * in progress. When the read or write packet transfer is in progress, most
@@ -130,6 +132,7 @@
 	struct spi_transfer	spi_xfer2[2];
 
 	struct eeprom_93cx6	eeprom;
+	struct regulator	*vdd_reg;
 };
 
 static int msg_enable;
@@ -1414,6 +1417,21 @@
 	ks->spidev = spi;
 	ks->tx_space = 6144;
 
+	ks->vdd_reg = regulator_get_optional(&spi->dev, "vdd");
+	if (IS_ERR(ks->vdd_reg)) {
+		ret = PTR_ERR(ks->vdd_reg);
+		if (ret == -EPROBE_DEFER)
+			goto err_reg;
+	} else {
+		ret = regulator_enable(ks->vdd_reg);
+		if (ret) {
+			dev_err(&spi->dev, "regulator enable fail: %d\n",
+				ret);
+			goto err_reg_en;
+		}
+	}
+
+
 	mutex_init(&ks->lock);
 	spin_lock_init(&ks->statelock);
 
@@ -1508,8 +1526,14 @@
 err_netdev:
 	free_irq(ndev->irq, ks);
 
-err_id:
 err_irq:
+err_id:
+	if (!IS_ERR(ks->vdd_reg))
+		regulator_disable(ks->vdd_reg);
+err_reg_en:
+	if (!IS_ERR(ks->vdd_reg))
+		regulator_put(ks->vdd_reg);
+err_reg:
 	free_netdev(ndev);
 	return ret;
 }
@@ -1523,6 +1547,10 @@
 
 	unregister_netdev(priv->netdev);
 	free_irq(spi->irq, priv);
+	if (!IS_ERR(priv->vdd_reg)) {
+		regulator_disable(priv->vdd_reg);
+		regulator_put(priv->vdd_reg);
+	}
 	free_netdev(priv->netdev);
 
 	return 0;
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 1ded50ca..e46e869 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -726,9 +726,6 @@
 	int vpath_idx = 0;
 	enum vxge_hw_status status = VXGE_HW_OK;
 	struct vxge_vpath *vpath = NULL;
-	struct __vxge_hw_device *hldev;
-
-	hldev = pci_get_drvdata(vdev->pdev);
 
 	mac_address = (u8 *)&mac_addr;
 	memcpy(mac_address, mac_header, ETH_ALEN);
@@ -2443,9 +2440,6 @@
 
 static void vxge_rem_isr(struct vxgedev *vdev)
 {
-	struct __vxge_hw_device *hldev;
-	hldev = pci_get_drvdata(vdev->pdev);
-
 #ifdef CONFIG_PCI_MSI
 	if (vdev->config.intr_type == MSI_X) {
 		vxge_rem_msix_isr(vdev);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 4146664..27c4f13 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -340,6 +340,7 @@
 			if (qlcnic_sriov_vf_check(adapter))
 				return -EINVAL;
 			num_msix = 1;
+			adapter->drv_sds_rings = QLCNIC_SINGLE_RING;
 			adapter->drv_tx_rings = QLCNIC_SINGLE_RING;
 		}
 	}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
index 77f1bce..7d4f549 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
@@ -807,7 +807,7 @@
 	    !type->tc_param_valid)
 		return;
 
-	if (tc < 0 || (tc > QLC_DCB_MAX_TC))
+	if (tc < 0 || (tc >= QLC_DCB_MAX_TC))
 		return;
 
 	tc_cfg = &type->tc_cfg[tc];
@@ -843,7 +843,7 @@
 	    !type->tc_param_valid)
 		return;
 
-	if (pgid < 0 || pgid > QLC_DCB_MAX_PG)
+	if (pgid < 0 || pgid >= QLC_DCB_MAX_PG)
 		return;
 
 	pgcfg = &type->pg_cfg[pgid];
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index ba78c74..1222865 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -816,9 +816,10 @@
 
 		if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) {
 			qlcnic_disable_multi_tx(adapter);
+			adapter->drv_sds_rings = QLCNIC_SINGLE_RING;
 
 			err = qlcnic_enable_msi_legacy(adapter);
-			if (!err)
+			if (err)
 				return err;
 		}
 	}
@@ -3863,7 +3864,7 @@
 		strcpy(buf, "Tx");
 	}
 
-	if (!qlcnic_use_msi_x && !qlcnic_use_msi) {
+	if (!QLCNIC_IS_MSI_FAMILY(adapter)) {
 		netdev_err(netdev, "No RSS/TSS support in INT-x mode\n");
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index 09acf15..e5277a6 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -13,8 +13,6 @@
 #define QLC_VF_MIN_TX_RATE	100
 #define QLC_VF_MAX_TX_RATE	9999
 #define QLC_MAC_OPCODE_MASK	0x7
-#define QLC_MAC_STAR_ADD	6
-#define QLC_MAC_STAR_DEL	7
 #define QLC_VF_FLOOD_BIT	BIT_16
 #define QLC_FLOOD_MODE		0x5
 
@@ -1206,13 +1204,6 @@
 	struct qlcnic_vport *vp = vf->vp;
 	u8 op, new_op;
 
-	if (((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_ADD) ||
-	    ((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_DEL)) {
-		netdev_err(adapter->netdev, "MAC + any VLAN filter not allowed from VF %d\n",
-			   vf->pci_func);
-		return -EINVAL;
-	}
-
 	if (!(cmd->req.arg[1] & BIT_8))
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index ce2cfdd..656c65d 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -4765,7 +4765,9 @@
 	ndev->features = ndev->hw_features;
 	ndev->vlan_features = ndev->hw_features;
 	/* vlan gets same features (except vlan filter) */
-	ndev->vlan_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+	ndev->vlan_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER |
+				 NETIF_F_HW_VLAN_CTAG_TX |
+				 NETIF_F_HW_VLAN_CTAG_RX);
 
 	if (test_bit(QL_DMA64, &qdev->flags))
 		ndev->features |= NETIF_F_HIGHDMA;
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 91a67ae..3ff7bc3 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -209,7 +209,7 @@
 	[RTL_GIGA_MAC_VER_16] =
 		_R("RTL8101e",		RTL_TD_0, NULL, JUMBO_1K, true),
 	[RTL_GIGA_MAC_VER_17] =
-		_R("RTL8168b/8111b",	RTL_TD_1, NULL, JUMBO_4K, false),
+		_R("RTL8168b/8111b",	RTL_TD_0, NULL, JUMBO_4K, false),
 	[RTL_GIGA_MAC_VER_18] =
 		_R("RTL8168cp/8111cp",	RTL_TD_1, NULL, JUMBO_6K, false),
 	[RTL_GIGA_MAC_VER_19] =
@@ -7118,6 +7118,8 @@
 	}
 
 	mutex_init(&tp->wk.mutex);
+	u64_stats_init(&tp->rx_stats.syncp);
+	u64_stats_init(&tp->tx_stats.syncp);
 
 	/* Get MAC address */
 	for (i = 0; i < ETH_ALEN; i++)
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index eb75fbd..d7a3682 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1668,6 +1668,13 @@
 	struct efx_ptp_data *ptp = efx->ptp_data;
 	int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE);
 
+	if (!ptp) {
+		if (net_ratelimit())
+			netif_warn(efx, drv, efx->net_dev,
+				   "Received PTP event but PTP not set up\n");
+		return;
+	}
+
 	if (!ptp->enabled)
 		return;
 
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index c49d1fb..75d11fa 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -429,7 +429,9 @@
 	}
 
 	/* Transfer ownership of the skb to the final buffer */
+#ifdef EFX_USE_PIO
 finish_packet:
+#endif
 	buffer->skb = skb;
 	buffer->flags = EFX_TX_BUF_SKB | dma_flags;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index e2f202e..f2d7c70 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -37,6 +37,17 @@
 	  stmmac device driver. This driver is used for A20/A31
 	  GMAC 	  ethernet controller.
 
+config DWMAC_STI
+	bool "STi GMAC support"
+	depends on STMMAC_PLATFORM && ARCH_STI
+	default y
+	---help---
+	  Support for ethernet controller on STi SOCs.
+
+	  This selects STi SoC glue layer support for the stmmac
+	  device driver. This driver is used on for the STi series
+	  SOCs GMAC ethernet controller.
+
 config STMMAC_PCI
 	bool "STMMAC PCI bus support"
 	depends on STMMAC_ETH && PCI
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index ecadece..dcef287 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -2,6 +2,7 @@
 stmmac-$(CONFIG_STMMAC_PLATFORM) += stmmac_platform.o
 stmmac-$(CONFIG_STMMAC_PCI) += stmmac_pci.o
 stmmac-$(CONFIG_DWMAC_SUNXI) += dwmac-sunxi.o
+stmmac-$(CONFIG_DWMAC_STI) += dwmac-sti.o
 stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o	\
 	      chain_mode.o dwmac_lib.o dwmac1000_core.o  dwmac1000_dma.o \
 	      dwmac100_core.o dwmac100_dma.o enh_desc.o  norm_desc.o \
diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
index 72d282b..c553f6b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
@@ -151,7 +151,7 @@
 					  sizeof(struct dma_desc)));
 }
 
-const struct stmmac_chain_mode_ops chain_mode_ops = {
+const struct stmmac_mode_ops chain_mode_ops = {
 	.init = stmmac_init_dma_chain,
 	.is_jumbo_frm = stmmac_is_jumbo_frm,
 	.jumbo_frm = stmmac_jumbo_frm,
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 7834a39..74610f3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -419,20 +419,13 @@
 	unsigned int data;	/* MII Data */
 };
 
-struct stmmac_ring_mode_ops {
-	unsigned int (*is_jumbo_frm) (int len, int ehn_desc);
-	unsigned int (*jumbo_frm) (void *priv, struct sk_buff *skb, int csum);
-	void (*refill_desc3) (void *priv, struct dma_desc *p);
-	void (*init_desc3) (struct dma_desc *p);
-	void (*clean_desc3) (void *priv, struct dma_desc *p);
-	int (*set_16kib_bfsize) (int mtu);
-};
-
-struct stmmac_chain_mode_ops {
+struct stmmac_mode_ops {
 	void (*init) (void *des, dma_addr_t phy_addr, unsigned int size,
 		      unsigned int extend_desc);
 	unsigned int (*is_jumbo_frm) (int len, int ehn_desc);
 	unsigned int (*jumbo_frm) (void *priv, struct sk_buff *skb, int csum);
+	int (*set_16kib_bfsize)(int mtu);
+	void (*init_desc3)(struct dma_desc *p);
 	void (*refill_desc3) (void *priv, struct dma_desc *p);
 	void (*clean_desc3) (void *priv, struct dma_desc *p);
 };
@@ -441,8 +434,7 @@
 	const struct stmmac_ops *mac;
 	const struct stmmac_desc_ops *desc;
 	const struct stmmac_dma_ops *dma;
-	const struct stmmac_ring_mode_ops *ring;
-	const struct stmmac_chain_mode_ops *chain;
+	const struct stmmac_mode_ops *mode;
 	const struct stmmac_hwtimestamp *ptp;
 	struct mii_regs mii;	/* MII register Addresses */
 	struct mac_link link;
@@ -460,7 +452,7 @@
 void stmmac_set_mac(void __iomem *ioaddr, bool enable);
 
 void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr);
-extern const struct stmmac_ring_mode_ops ring_mode_ops;
-extern const struct stmmac_chain_mode_ops chain_mode_ops;
+extern const struct stmmac_mode_ops ring_mode_ops;
+extern const struct stmmac_mode_ops chain_mode_ops;
 
 #endif /* __COMMON_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
new file mode 100644
index 0000000..552bbc1
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -0,0 +1,330 @@
+/**
+ * dwmac-sti.c - STMicroelectronics DWMAC Specific Glue layer
+ *
+ * Copyright (C) 2003-2014 STMicroelectronics (R&D) Limited
+ * Author: Srinivas Kandagatla <srinivas.kandagatla@st.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/stmmac.h>
+#include <linux/phy.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+
+/**
+ *			STi GMAC glue logic.
+ *			--------------------
+ *
+ *		 _
+ *		|  \
+ *	--------|0  \ ETH_SEL_INTERNAL_NOTEXT_PHYCLK
+ * phyclk	|    |___________________________________________
+ *		|    |	|			(phyclk-in)
+ *	--------|1  /	|
+ * int-clk	|_ /	|
+ *			|	 _
+ *			|	|  \
+ *			|_______|1  \ ETH_SEL_TX_RETIME_CLK
+ *				|    |___________________________
+ *				|    |		(tx-retime-clk)
+ *			 _______|0  /
+ *			|	|_ /
+ *		 _	|
+ *		|  \	|
+ *	--------|0  \	|
+ * clk_125	|    |__|
+ *		|    |	ETH_SEL_TXCLK_NOT_CLK125
+ *	--------|1  /
+ * txclk	|_ /
+ *
+ *
+ * ETH_SEL_INTERNAL_NOTEXT_PHYCLK is valid only for RMII where PHY can
+ * generate 50MHz clock or MAC can generate it.
+ * This bit is configured by "st,ext-phyclk" property.
+ *
+ * ETH_SEL_TXCLK_NOT_CLK125 is only valid for gigabit modes, where the 125Mhz
+ * clock either comes from clk-125 pin or txclk pin. This configuration is
+ * totally driven by the board wiring. This bit is configured by
+ * "st,tx-retime-src" property.
+ *
+ * TXCLK configuration is different for different phy interface modes
+ * and changes according to link speed in modes like RGMII.
+ *
+ * Below table summarizes the clock requirement and clock sources for
+ * supported phy interface modes with link speeds.
+ * ________________________________________________
+ *|  PHY_MODE	| 1000 Mbit Link | 100 Mbit Link   |
+ * ------------------------------------------------
+ *|	MII	|	n/a	 |	25Mhz	   |
+ *|		|		 |	txclk	   |
+ * ------------------------------------------------
+ *|	GMII	|     125Mhz	 |	25Mhz	   |
+ *|		|  clk-125/txclk |	txclk	   |
+ * ------------------------------------------------
+ *|	RGMII	|     125Mhz	 |	25Mhz	   |
+ *|		|  clk-125/txclk |	clkgen     |
+ * ------------------------------------------------
+ *|	RMII	|	n/a	 |	25Mhz	   |
+ *|		|		 |clkgen/phyclk-in |
+ * ------------------------------------------------
+ *
+ * TX lines are always retimed with a clk, which can vary depending
+ * on the board configuration. Below is the table of these bits
+ * in eth configuration register depending on source of retime clk.
+ *
+ *---------------------------------------------------------------
+ * src	 | tx_rt_clk	| int_not_ext_phyclk	| txclk_n_clk125|
+ *---------------------------------------------------------------
+ * txclk |	0	|	n/a		|	1	|
+ *---------------------------------------------------------------
+ * ck_125|	0	|	n/a		|	0	|
+ *---------------------------------------------------------------
+ * phyclk|	1	|	0		|	n/a	|
+ *---------------------------------------------------------------
+ * clkgen|	1	|	1		|	n/a	|
+ *---------------------------------------------------------------
+ */
+
+ /* Register definition */
+
+ /* 3 bits [8:6]
+  *  [6:6]      ETH_SEL_TXCLK_NOT_CLK125
+  *  [7:7]      ETH_SEL_INTERNAL_NOTEXT_PHYCLK
+  *  [8:8]      ETH_SEL_TX_RETIME_CLK
+  *
+  */
+
+#define TX_RETIME_SRC_MASK		GENMASK(8, 6)
+#define ETH_SEL_TX_RETIME_CLK		BIT(8)
+#define ETH_SEL_INTERNAL_NOTEXT_PHYCLK	BIT(7)
+#define ETH_SEL_TXCLK_NOT_CLK125	BIT(6)
+
+#define ENMII_MASK			GENMASK(5, 5)
+#define ENMII				BIT(5)
+
+/**
+ * 3 bits [4:2]
+ *	000-GMII/MII
+ *	001-RGMII
+ *	010-SGMII
+ *	100-RMII
+*/
+#define MII_PHY_SEL_MASK		GENMASK(4, 2)
+#define ETH_PHY_SEL_RMII		BIT(4)
+#define ETH_PHY_SEL_SGMII		BIT(3)
+#define ETH_PHY_SEL_RGMII		BIT(2)
+#define ETH_PHY_SEL_GMII		0x0
+#define ETH_PHY_SEL_MII			0x0
+
+#define IS_PHY_IF_MODE_RGMII(iface)	(iface == PHY_INTERFACE_MODE_RGMII || \
+			iface == PHY_INTERFACE_MODE_RGMII_ID || \
+			iface == PHY_INTERFACE_MODE_RGMII_RXID || \
+			iface == PHY_INTERFACE_MODE_RGMII_TXID)
+
+#define IS_PHY_IF_MODE_GBIT(iface)	(IS_PHY_IF_MODE_RGMII(iface) || \
+			iface == PHY_INTERFACE_MODE_GMII)
+
+struct sti_dwmac {
+	int interface;
+	bool ext_phyclk;
+	bool is_tx_retime_src_clk_125;
+	struct clk *clk;
+	int reg;
+	struct device *dev;
+	struct regmap *regmap;
+};
+
+static u32 phy_intf_sels[] = {
+	[PHY_INTERFACE_MODE_MII] = ETH_PHY_SEL_MII,
+	[PHY_INTERFACE_MODE_GMII] = ETH_PHY_SEL_GMII,
+	[PHY_INTERFACE_MODE_RGMII] = ETH_PHY_SEL_RGMII,
+	[PHY_INTERFACE_MODE_RGMII_ID] = ETH_PHY_SEL_RGMII,
+	[PHY_INTERFACE_MODE_SGMII] = ETH_PHY_SEL_SGMII,
+	[PHY_INTERFACE_MODE_RMII] = ETH_PHY_SEL_RMII,
+};
+
+enum {
+	TX_RETIME_SRC_NA = 0,
+	TX_RETIME_SRC_TXCLK = 1,
+	TX_RETIME_SRC_CLK_125,
+	TX_RETIME_SRC_PHYCLK,
+	TX_RETIME_SRC_CLKGEN,
+};
+
+static const char *const tx_retime_srcs[] = {
+	[TX_RETIME_SRC_NA] = "",
+	[TX_RETIME_SRC_TXCLK] = "txclk",
+	[TX_RETIME_SRC_CLK_125] = "clk_125",
+	[TX_RETIME_SRC_PHYCLK] = "phyclk",
+	[TX_RETIME_SRC_CLKGEN] = "clkgen",
+};
+
+static u32 tx_retime_val[] = {
+	[TX_RETIME_SRC_TXCLK] = ETH_SEL_TXCLK_NOT_CLK125,
+	[TX_RETIME_SRC_CLK_125] = 0x0,
+	[TX_RETIME_SRC_PHYCLK] = ETH_SEL_TX_RETIME_CLK,
+	[TX_RETIME_SRC_CLKGEN] = ETH_SEL_TX_RETIME_CLK |
+	    ETH_SEL_INTERNAL_NOTEXT_PHYCLK,
+};
+
+static void setup_retime_src(struct sti_dwmac *dwmac, u32 spd)
+{
+	u32 src = 0, freq = 0;
+
+	if (spd == SPEED_100) {
+		if (dwmac->interface == PHY_INTERFACE_MODE_MII ||
+		    dwmac->interface == PHY_INTERFACE_MODE_GMII) {
+			src = TX_RETIME_SRC_TXCLK;
+		} else if (dwmac->interface == PHY_INTERFACE_MODE_RMII) {
+			if (dwmac->ext_phyclk) {
+				src = TX_RETIME_SRC_PHYCLK;
+			} else {
+				src = TX_RETIME_SRC_CLKGEN;
+				freq = 50000000;
+			}
+
+		} else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) {
+			src = TX_RETIME_SRC_CLKGEN;
+			freq = 25000000;
+		}
+
+		if (src == TX_RETIME_SRC_CLKGEN && dwmac->clk)
+			clk_set_rate(dwmac->clk, freq);
+
+	} else if (spd == SPEED_1000) {
+		if (dwmac->is_tx_retime_src_clk_125)
+			src = TX_RETIME_SRC_CLK_125;
+		else
+			src = TX_RETIME_SRC_TXCLK;
+	}
+
+	regmap_update_bits(dwmac->regmap, dwmac->reg,
+			   TX_RETIME_SRC_MASK, tx_retime_val[src]);
+}
+
+static void sti_dwmac_exit(struct platform_device *pdev, void *priv)
+{
+	struct sti_dwmac *dwmac = priv;
+
+	if (dwmac->clk)
+		clk_disable_unprepare(dwmac->clk);
+}
+
+static void sti_fix_mac_speed(void *priv, unsigned int spd)
+{
+	struct sti_dwmac *dwmac = priv;
+
+	setup_retime_src(dwmac, spd);
+
+	return;
+}
+
+static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
+				struct platform_device *pdev)
+{
+	struct resource *res;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct regmap *regmap;
+	int err;
+
+	if (!np)
+		return -EINVAL;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sti-ethconf");
+	if (!res)
+		return -ENODATA;
+
+	regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon");
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	dwmac->dev = dev;
+	dwmac->interface = of_get_phy_mode(np);
+	dwmac->regmap = regmap;
+	dwmac->reg = res->start;
+	dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk");
+	dwmac->is_tx_retime_src_clk_125 = false;
+
+	if (IS_PHY_IF_MODE_GBIT(dwmac->interface)) {
+		const char *rs;
+
+		err = of_property_read_string(np, "st,tx-retime-src", &rs);
+		if (err < 0) {
+			dev_err(dev, "st,tx-retime-src not specified\n");
+			return err;
+		}
+
+		if (!strcasecmp(rs, "clk_125"))
+			dwmac->is_tx_retime_src_clk_125 = true;
+	}
+
+	dwmac->clk = devm_clk_get(dev, "sti-ethclk");
+
+	if (IS_ERR(dwmac->clk))
+		dwmac->clk = NULL;
+
+	return 0;
+}
+
+static int sti_dwmac_init(struct platform_device *pdev, void *priv)
+{
+	struct sti_dwmac *dwmac = priv;
+	struct regmap *regmap = dwmac->regmap;
+	int iface = dwmac->interface;
+	u32 reg = dwmac->reg;
+	u32 val, spd;
+
+	if (dwmac->clk)
+		clk_prepare_enable(dwmac->clk);
+
+	regmap_update_bits(regmap, reg, MII_PHY_SEL_MASK, phy_intf_sels[iface]);
+
+	val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII;
+	regmap_update_bits(regmap, reg, ENMII_MASK, val);
+
+	if (IS_PHY_IF_MODE_GBIT(iface))
+		spd = SPEED_1000;
+	else
+		spd = SPEED_100;
+
+	setup_retime_src(dwmac, spd);
+
+	return 0;
+}
+
+static void *sti_dwmac_setup(struct platform_device *pdev)
+{
+	struct sti_dwmac *dwmac;
+	int ret;
+
+	dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL);
+	if (!dwmac)
+		return ERR_PTR(-ENOMEM);
+
+	ret = sti_dwmac_parse_data(dwmac, pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Unable to parse OF data\n");
+		return ERR_PTR(ret);
+	}
+
+	return dwmac;
+}
+
+const struct stmmac_of_data sti_gmac_data = {
+	.fix_mac_speed = sti_fix_mac_speed,
+	.setup = sti_dwmac_setup,
+	.init = sti_dwmac_init,
+	.exit = sti_dwmac_exit,
+};
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index a96c7c2..650a4be 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -100,10 +100,9 @@
 {
 	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
 
-	if (unlikely(priv->plat->has_gmac))
-		/* Fill DES3 in case of RING mode */
-		if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
-			p->des3 = p->des2 + BUF_SIZE_8KiB;
+	/* Fill DES3 in case of RING mode */
+	if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
+		p->des3 = p->des2 + BUF_SIZE_8KiB;
 }
 
 /* In ring mode we need to fill the desc3 because it is used as buffer */
@@ -126,7 +125,7 @@
 	return ret;
 }
 
-const struct stmmac_ring_mode_ops ring_mode_ops = {
+const struct stmmac_mode_ops ring_mode_ops = {
 	.is_jumbo_frm = stmmac_is_jumbo_frm,
 	.jumbo_frm = stmmac_jumbo_frm,
 	.refill_desc3 = stmmac_refill_desc3,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index d9af26e..f9e60d7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -133,6 +133,9 @@
 #ifdef CONFIG_DWMAC_SUNXI
 extern const struct stmmac_of_data sun7i_gmac_data;
 #endif
+#ifdef CONFIG_DWMAC_STI
+extern const struct stmmac_of_data sti_gmac_data;
+#endif
 extern struct platform_driver stmmac_pltfr_driver;
 static inline int stmmac_register_platform(void)
 {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a2e7d2c..8543e1c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -92,8 +92,8 @@
 module_param(tc, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(tc, "DMA threshold control value");
 
-#define DMA_BUFFER_SIZE	BUF_SIZE_4KiB
-static int buf_sz = DMA_BUFFER_SIZE;
+#define	DEFAULT_BUFSIZE	1536
+static int buf_sz = DEFAULT_BUFSIZE;
 module_param(buf_sz, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(buf_sz, "DMA buffer size");
 
@@ -136,8 +136,8 @@
 		dma_rxsize = DMA_RX_SIZE;
 	if (unlikely(dma_txsize < 0))
 		dma_txsize = DMA_TX_SIZE;
-	if (unlikely((buf_sz < DMA_BUFFER_SIZE) || (buf_sz > BUF_SIZE_16KiB)))
-		buf_sz = DMA_BUFFER_SIZE;
+	if (unlikely((buf_sz < DEFAULT_BUFSIZE) || (buf_sz > BUF_SIZE_16KiB)))
+		buf_sz = DEFAULT_BUFSIZE;
 	if (unlikely(flow_ctrl > 1))
 		flow_ctrl = FLOW_AUTO;
 	else if (likely(flow_ctrl < 0))
@@ -286,10 +286,25 @@
 
 	/* MAC core supports the EEE feature. */
 	if (priv->dma_cap.eee) {
-		/* Check if the PHY supports EEE */
-		if (phy_init_eee(priv->phydev, 1))
-			goto out;
+		int tx_lpi_timer = priv->tx_lpi_timer;
 
+		/* Check if the PHY supports EEE */
+		if (phy_init_eee(priv->phydev, 1)) {
+			/* To manage at run-time if the EEE cannot be supported
+			 * anymore (for example because the lp caps have been
+			 * changed).
+			 * In that case the driver disable own timers.
+			 */
+			if (priv->eee_active) {
+				pr_debug("stmmac: disable EEE\n");
+				del_timer_sync(&priv->eee_ctrl_timer);
+				priv->hw->mac->set_eee_timer(priv->ioaddr, 0,
+							     tx_lpi_timer);
+			}
+			priv->eee_active = 0;
+			goto out;
+		}
+		/* Activate the EEE and start timers */
 		if (!priv->eee_active) {
 			priv->eee_active = 1;
 			init_timer(&priv->eee_ctrl_timer);
@@ -300,13 +315,13 @@
 
 			priv->hw->mac->set_eee_timer(priv->ioaddr,
 						     STMMAC_DEFAULT_LIT_LS,
-						     priv->tx_lpi_timer);
+						     tx_lpi_timer);
 		} else
 			/* Set HW EEE according to the speed */
 			priv->hw->mac->set_eee_pls(priv->ioaddr,
 						   priv->phydev->link);
 
-		pr_info("stmmac: Energy-Efficient Ethernet initialized\n");
+		pr_debug("stmmac: Energy-Efficient Ethernet initialized\n");
 
 		ret = true;
 	}
@@ -886,10 +901,10 @@
 		ret = BUF_SIZE_8KiB;
 	else if (mtu >= BUF_SIZE_2KiB)
 		ret = BUF_SIZE_4KiB;
-	else if (mtu >= DMA_BUFFER_SIZE)
+	else if (mtu > DEFAULT_BUFSIZE)
 		ret = BUF_SIZE_2KiB;
 	else
-		ret = DMA_BUFFER_SIZE;
+		ret = DEFAULT_BUFSIZE;
 
 	return ret;
 }
@@ -951,9 +966,9 @@
 
 	p->des2 = priv->rx_skbuff_dma[i];
 
-	if ((priv->mode == STMMAC_RING_MODE) &&
+	if ((priv->hw->mode->init_desc3) &&
 	    (priv->dma_buf_sz == BUF_SIZE_16KiB))
-		priv->hw->ring->init_desc3(p);
+		priv->hw->mode->init_desc3(p);
 
 	return 0;
 }
@@ -984,11 +999,8 @@
 	unsigned int bfsize = 0;
 	int ret = -ENOMEM;
 
-	/* Set the max buffer size according to the DESC mode
-	 * and the MTU. Note that RING mode allows 16KiB bsize.
-	 */
-	if (priv->mode == STMMAC_RING_MODE)
-		bfsize = priv->hw->ring->set_16kib_bfsize(dev->mtu);
+	if (priv->hw->mode->set_16kib_bfsize)
+		bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu);
 
 	if (bfsize < BUF_SIZE_16KiB)
 		bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz);
@@ -1029,15 +1041,15 @@
 	/* Setup the chained descriptor addresses */
 	if (priv->mode == STMMAC_CHAIN_MODE) {
 		if (priv->extend_desc) {
-			priv->hw->chain->init(priv->dma_erx, priv->dma_rx_phy,
-					      rxsize, 1);
-			priv->hw->chain->init(priv->dma_etx, priv->dma_tx_phy,
-					      txsize, 1);
+			priv->hw->mode->init(priv->dma_erx, priv->dma_rx_phy,
+					     rxsize, 1);
+			priv->hw->mode->init(priv->dma_etx, priv->dma_tx_phy,
+					     txsize, 1);
 		} else {
-			priv->hw->chain->init(priv->dma_rx, priv->dma_rx_phy,
-					      rxsize, 0);
-			priv->hw->chain->init(priv->dma_tx, priv->dma_tx_phy,
-					      txsize, 0);
+			priv->hw->mode->init(priv->dma_rx, priv->dma_rx_phy,
+					     rxsize, 0);
+			priv->hw->mode->init(priv->dma_tx, priv->dma_tx_phy,
+					     txsize, 0);
 		}
 	}
 
@@ -1288,7 +1300,7 @@
 					 DMA_TO_DEVICE);
 			priv->tx_skbuff_dma[entry] = 0;
 		}
-		priv->hw->ring->clean_desc3(priv, p);
+		priv->hw->mode->clean_desc3(priv, p);
 
 		if (likely(skb != NULL)) {
 			dev_kfree_skb(skb);
@@ -1705,7 +1717,7 @@
 	priv->dma_rx_size = STMMAC_ALIGN(dma_rxsize);
 	priv->dma_buf_sz = STMMAC_ALIGN(buf_sz);
 
-	alloc_dma_desc_resources(priv);
+	ret = alloc_dma_desc_resources(priv);
 	if (ret < 0) {
 		pr_err("%s: DMA descriptors allocation failed\n", __func__);
 		goto dma_desc_error;
@@ -1844,6 +1856,7 @@
 	int nfrags = skb_shinfo(skb)->nr_frags;
 	struct dma_desc *desc, *first;
 	unsigned int nopaged_len = skb_headlen(skb);
+	unsigned int enh_desc = priv->plat->enh_desc;
 
 	if (unlikely(stmmac_tx_avail(priv) < nfrags + 1)) {
 		if (!netif_queue_stopped(dev)) {
@@ -1871,27 +1884,19 @@
 	first = desc;
 
 	/* To program the descriptors according to the size of the frame */
-	if (priv->mode == STMMAC_RING_MODE) {
-		is_jumbo = priv->hw->ring->is_jumbo_frm(skb->len,
-							priv->plat->enh_desc);
-		if (unlikely(is_jumbo))
-			entry = priv->hw->ring->jumbo_frm(priv, skb,
-							  csum_insertion);
-	} else {
-		is_jumbo = priv->hw->chain->is_jumbo_frm(skb->len,
-							 priv->plat->enh_desc);
-		if (unlikely(is_jumbo))
-			entry = priv->hw->chain->jumbo_frm(priv, skb,
-							   csum_insertion);
-	}
+	if (enh_desc)
+		is_jumbo = priv->hw->mode->is_jumbo_frm(skb->len, enh_desc);
+
 	if (likely(!is_jumbo)) {
 		desc->des2 = dma_map_single(priv->device, skb->data,
 					    nopaged_len, DMA_TO_DEVICE);
 		priv->tx_skbuff_dma[entry] = desc->des2;
 		priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len,
 						csum_insertion, priv->mode);
-	} else
+	} else {
 		desc = first;
+		entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion);
+	}
 
 	for (i = 0; i < nfrags; i++) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
@@ -2029,7 +2034,7 @@
 
 			p->des2 = priv->rx_skbuff_dma[entry];
 
-			priv->hw->ring->refill_desc3(priv, p);
+			priv->hw->mode->refill_desc3(priv, p);
 
 			if (netif_msg_rx_status(priv))
 				pr_debug("\trefill entry #%d\n", entry);
@@ -2633,11 +2638,11 @@
 
 	/* To use the chained or ring mode */
 	if (chain_mode) {
-		priv->hw->chain = &chain_mode_ops;
+		priv->hw->mode = &chain_mode_ops;
 		pr_info(" Chain mode enabled\n");
 		priv->mode = STMMAC_CHAIN_MODE;
 	} else {
-		priv->hw->ring = &ring_mode_ops;
+		priv->hw->mode = &ring_mode_ops;
 		pr_info(" Ring mode enabled\n");
 		priv->mode = STMMAC_RING_MODE;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 5884a7d..8fb32a8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -33,6 +33,11 @@
 #ifdef CONFIG_DWMAC_SUNXI
 	{ .compatible = "allwinner,sun7i-a20-gmac", .data = &sun7i_gmac_data},
 #endif
+#ifdef CONFIG_DWMAC_STI
+	{ .compatible = "st,stih415-dwmac", .data = &sti_gmac_data},
+	{ .compatible = "st,stih416-dwmac", .data = &sti_gmac_data},
+	{ .compatible = "st,stid127-dwmac", .data = &sti_gmac_data},
+#endif
 	/* SoC specific glue layers should come before generic bindings */
 	{ .compatible = "st,spear600-gmac"},
 	{ .compatible = "snps,dwmac-3.610"},
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index bde63e3..7d6d8ec 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -554,7 +554,7 @@
 		 * common for both the interface as the interface shares
 		 * the same hardware resource.
 		 */
-		for (i = 0; i <= priv->data.slaves; i++)
+		for (i = 0; i < priv->data.slaves; i++)
 			if (priv->slaves[i].ndev->flags & IFF_PROMISC)
 				flag = true;
 
@@ -578,7 +578,7 @@
 			unsigned long timeout = jiffies + HZ;
 
 			/* Disable Learn for all ports */
-			for (i = 0; i <= priv->data.slaves; i++) {
+			for (i = 0; i < priv->data.slaves; i++) {
 				cpsw_ale_control_set(ale, i,
 						     ALE_PORT_NOLEARN, 1);
 				cpsw_ale_control_set(ale, i,
@@ -606,7 +606,7 @@
 			cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 0);
 
 			/* Enable Learn for all ports */
-			for (i = 0; i <= priv->data.slaves; i++) {
+			for (i = 0; i < priv->data.slaves; i++) {
 				cpsw_ale_control_set(ale, i,
 						     ALE_PORT_NOLEARN, 0);
 				cpsw_ale_control_set(ale, i,
@@ -1164,11 +1164,17 @@
 
 static void cpsw_slave_stop(struct cpsw_slave *slave, struct cpsw_priv *priv)
 {
+	u32 slave_port;
+
+	slave_port = cpsw_get_slave_port(priv, slave->slave_num);
+
 	if (!slave->phy)
 		return;
 	phy_stop(slave->phy);
 	phy_disconnect(slave->phy);
 	slave->phy = NULL;
+	cpsw_ale_control_set(priv->ale, slave_port,
+			     ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
 }
 
 static int cpsw_ndo_open(struct net_device *ndev)
@@ -1878,14 +1884,29 @@
 		mdio_node = of_find_node_by_phandle(be32_to_cpup(parp));
 		phyid = be32_to_cpup(parp+1);
 		mdio = of_find_device_by_node(mdio_node);
-		snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
-			 PHY_ID_FMT, mdio->name, phyid);
+
+		if (strncmp(mdio->name, "gpio", 4) == 0) {
+			/* GPIO bitbang MDIO driver attached */
+			struct mii_bus *bus = dev_get_drvdata(&mdio->dev);
+
+			snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
+				 PHY_ID_FMT, bus->id, phyid);
+		} else {
+			/* davinci MDIO driver attached */
+			snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
+				 PHY_ID_FMT, mdio->name, phyid);
+		}
 
 		mac_addr = of_get_mac_address(slave_node);
 		if (mac_addr)
 			memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN);
 
 		slave_data->phy_if = of_get_phy_mode(slave_node);
+		if (slave_data->phy_if < 0) {
+			pr_err("Missing or malformed slave[%d] phy-mode property\n",
+			       i);
+			return slave_data->phy_if;
+		}
 
 		if (data->dual_emac) {
 			if (of_property_read_u32(slave_node, "dual_emac_res_vlan",
@@ -2208,10 +2229,6 @@
 		goto clean_ale_ret;
 	}
 
-	if (cpts_register(&pdev->dev, priv->cpts,
-			  data->cpts_clock_mult, data->cpts_clock_shift))
-		dev_err(priv->dev, "error registering cpts device\n");
-
 	cpsw_notice(priv, probe, "initialized device (regs %pa, irq %d)\n",
 		    &ss_res->start, ndev->irq);
 
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 364d0c7..88ef270 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -355,7 +355,7 @@
 	int i;
 
 	spin_lock_irqsave(&ctlr->lock, flags);
-	if (ctlr->state != CPDMA_STATE_ACTIVE) {
+	if (ctlr->state == CPDMA_STATE_TEARDOWN) {
 		spin_unlock_irqrestore(&ctlr->lock, flags);
 		return -EINVAL;
 	}
@@ -891,7 +891,7 @@
 	unsigned		timeout;
 
 	spin_lock_irqsave(&chan->lock, flags);
-	if (chan->state != CPDMA_STATE_ACTIVE) {
+	if (chan->state == CPDMA_STATE_TEARDOWN) {
 		spin_unlock_irqrestore(&chan->lock, flags);
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index cd9b164..8f0e69c 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1532,9 +1532,9 @@
 	struct device *emac_dev = &ndev->dev;
 	u32 cnt;
 	struct resource *res;
-	int ret;
+	int q, m, ret;
+	int res_num = 0, irq_num = 0;
 	int i = 0;
-	int k = 0;
 	struct emac_priv *priv = netdev_priv(ndev);
 
 	pm_runtime_get(&priv->pdev->dev);
@@ -1564,15 +1564,24 @@
 	}
 
 	/* Request IRQ */
+	while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ,
+					    res_num))) {
+		for (irq_num = res->start; irq_num <= res->end; irq_num++) {
+			dev_err(emac_dev, "Request IRQ %d\n", irq_num);
+			if (request_irq(irq_num, emac_irq, 0, ndev->name,
+					ndev)) {
+				dev_err(emac_dev,
+					"DaVinci EMAC: request_irq() failed\n");
+				ret = -EBUSY;
 
-	while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, k))) {
-		for (i = res->start; i <= res->end; i++) {
-			if (devm_request_irq(&priv->pdev->dev, i, emac_irq,
-					     0, ndev->name, ndev))
 				goto rollback;
+			}
 		}
-		k++;
+		res_num++;
 	}
+	/* prepare counters for rollback in case of an error */
+	res_num--;
+	irq_num--;
 
 	/* Start/Enable EMAC hardware */
 	emac_hw_enable(priv);
@@ -1639,11 +1648,23 @@
 
 	return 0;
 
-rollback:
-
-	dev_err(emac_dev, "DaVinci EMAC: devm_request_irq() failed");
-	ret = -EBUSY;
 err:
+	emac_int_disable(priv);
+	napi_disable(&priv->napi);
+
+rollback:
+	for (q = res_num; q >= 0; q--) {
+		res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, q);
+		/* at the first iteration, irq_num is already set to the
+		 * right value
+		 */
+		if (q != res_num)
+			irq_num = res->end;
+
+		for (m = irq_num; m >= res->start; m--)
+			free_irq(m, ndev);
+	}
+	cpdma_ctlr_stop(priv->dma);
 	pm_runtime_put(&priv->pdev->dev);
 	return ret;
 }
@@ -1659,6 +1680,9 @@
  */
 static int emac_dev_stop(struct net_device *ndev)
 {
+	struct resource *res;
+	int i = 0;
+	int irq_num;
 	struct emac_priv *priv = netdev_priv(ndev);
 	struct device *emac_dev = &ndev->dev;
 
@@ -1674,6 +1698,13 @@
 	if (priv->phydev)
 		phy_disconnect(priv->phydev);
 
+	/* Free IRQ */
+	while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, i))) {
+		for (irq_num = res->start; irq_num <= res->end; irq_num++)
+			free_irq(irq_num, priv->ndev);
+		i++;
+	}
+
 	if (netif_msg_drv(priv))
 		dev_notice(emac_dev, "DaVinci EMAC: %s stopped\n", ndev->name);
 
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 023237a..17503da 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -2071,7 +2071,7 @@
 
 /* Return subqueue id on this core (one per core). */
 static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb,
-				 void *accel_priv)
+				 void *accel_priv, select_queue_fallback_t fallback)
 {
 	return smp_processor_id();
 }
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index ef312bc..6ac20a6 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -923,7 +923,7 @@
 	if (rc) {
 		dev_err(&pdev->dev,
 			"32-bit PCI DMA addresses not supported by the card!?\n");
-		goto err_out;
+		goto err_out_pci_disable;
 	}
 
 	/* sanity check */
@@ -931,7 +931,7 @@
 	    (pci_resource_len(pdev, 1) < io_size)) {
 		rc = -EIO;
 		dev_err(&pdev->dev, "Insufficient PCI resources, aborting\n");
-		goto err_out;
+		goto err_out_pci_disable;
 	}
 
 	pioaddr = pci_resource_start(pdev, 0);
@@ -942,7 +942,7 @@
 	dev = alloc_etherdev(sizeof(struct rhine_private));
 	if (!dev) {
 		rc = -ENOMEM;
-		goto err_out;
+		goto err_out_pci_disable;
 	}
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
@@ -1084,6 +1084,8 @@
 	pci_release_regions(pdev);
 err_out_free_netdev:
 	free_netdev(dev);
+err_out_pci_disable:
+	pci_disable_device(pdev);
 err_out:
 	return rc;
 }
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 1ec65fe..4bfdf8c 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -26,6 +26,7 @@
 #include <linux/netdevice.h>
 #include <linux/of_mdio.h>
 #include <linux/of_platform.h>
+#include <linux/of_irq.h>
 #include <linux/of_address.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
@@ -600,7 +601,8 @@
 		size += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
 		packets++;
 
-		lp->tx_bd_ci = ++lp->tx_bd_ci % TX_BD_NUM;
+		++lp->tx_bd_ci;
+		lp->tx_bd_ci %= TX_BD_NUM;
 		cur_p = &lp->tx_bd_v[lp->tx_bd_ci];
 		status = cur_p->status;
 	}
@@ -686,7 +688,8 @@
 				     skb_headlen(skb), DMA_TO_DEVICE);
 
 	for (ii = 0; ii < num_frag; ii++) {
-		lp->tx_bd_tail = ++lp->tx_bd_tail % TX_BD_NUM;
+		++lp->tx_bd_tail;
+		lp->tx_bd_tail %= TX_BD_NUM;
 		cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
 		frag = &skb_shinfo(skb)->frags[ii];
 		cur_p->phys = dma_map_single(ndev->dev.parent,
@@ -702,7 +705,8 @@
 	tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail;
 	/* Start the transfer */
 	axienet_dma_out32(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p);
-	lp->tx_bd_tail = ++lp->tx_bd_tail % TX_BD_NUM;
+	++lp->tx_bd_tail;
+	lp->tx_bd_tail %= TX_BD_NUM;
 
 	return NETDEV_TX_OK;
 }
@@ -774,7 +778,8 @@
 		cur_p->status = 0;
 		cur_p->sw_id_offset = (u32) new_skb;
 
-		lp->rx_bd_ci = ++lp->rx_bd_ci % RX_BD_NUM;
+		++lp->rx_bd_ci;
+		lp->rx_bd_ci %= RX_BD_NUM;
 		cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
 	}
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 7756118..d6fce97 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -88,8 +88,12 @@
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
 	struct hv_device *device_obj = net_device_ctx->device_ctx;
+	struct netvsc_device *nvdev;
+	struct rndis_device *rdev;
 	int ret = 0;
 
+	netif_carrier_off(net);
+
 	/* Open up the device */
 	ret = rndis_filter_open(device_obj);
 	if (ret != 0) {
@@ -99,6 +103,11 @@
 
 	netif_start_queue(net);
 
+	nvdev = hv_get_drvdata(device_obj);
+	rdev = nvdev->extension;
+	if (!rdev->link_state)
+		netif_carrier_on(net);
+
 	return ret;
 }
 
@@ -229,23 +238,24 @@
 	struct net_device *net;
 	struct net_device_context *ndev_ctx;
 	struct netvsc_device *net_device;
+	struct rndis_device *rdev;
 
 	net_device = hv_get_drvdata(device_obj);
+	rdev = net_device->extension;
+
+	rdev->link_state = status != 1;
+
 	net = net_device->ndev;
 
-	if (!net) {
-		netdev_err(net, "got link status but net device "
-				"not initialized yet\n");
+	if (!net || net->reg_state != NETREG_REGISTERED)
 		return;
-	}
 
+	ndev_ctx = netdev_priv(net);
 	if (status == 1) {
-		netif_carrier_on(net);
-		ndev_ctx = netdev_priv(net);
 		schedule_delayed_work(&ndev_ctx->dwork, 0);
 		schedule_delayed_work(&ndev_ctx->dwork, msecs_to_jiffies(20));
 	} else {
-		netif_carrier_off(net);
+		schedule_delayed_work(&ndev_ctx->dwork, 0);
 	}
 }
 
@@ -388,17 +398,35 @@
  * current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, add
  * another netif_notify_peers() into a delayed work, otherwise GARP packet
  * will not be sent after quick migration, and cause network disconnection.
+ * Also, we update the carrier status here.
  */
-static void netvsc_send_garp(struct work_struct *w)
+static void netvsc_link_change(struct work_struct *w)
 {
 	struct net_device_context *ndev_ctx;
 	struct net_device *net;
 	struct netvsc_device *net_device;
+	struct rndis_device *rdev;
+	bool notify;
+
+	rtnl_lock();
 
 	ndev_ctx = container_of(w, struct net_device_context, dwork.work);
 	net_device = hv_get_drvdata(ndev_ctx->device_ctx);
+	rdev = net_device->extension;
 	net = net_device->ndev;
-	netdev_notify_peers(net);
+
+	if (rdev->link_state) {
+		netif_carrier_off(net);
+		notify = false;
+	} else {
+		netif_carrier_on(net);
+		notify = true;
+	}
+
+	rtnl_unlock();
+
+	if (notify)
+		netdev_notify_peers(net);
 }
 
 
@@ -414,13 +442,12 @@
 	if (!net)
 		return -ENOMEM;
 
-	/* Set initial state */
 	netif_carrier_off(net);
 
 	net_device_ctx = netdev_priv(net);
 	net_device_ctx->device_ctx = dev;
 	hv_set_drvdata(dev, net);
-	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_send_garp);
+	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
 	INIT_WORK(&net_device_ctx->work, do_set_multicast);
 
 	net->netdev_ops = &device_ops;
@@ -443,13 +470,13 @@
 	}
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
-	netif_carrier_on(net);
-
 	ret = register_netdev(net);
 	if (ret != 0) {
 		pr_err("Unable to register netdev.\n");
 		rndis_filter_device_remove(dev);
 		free_netdev(net);
+	} else {
+		schedule_delayed_work(&net_device_ctx->dwork, 0);
 	}
 
 	return ret;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 1084e5d..b54fd25 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -243,6 +243,22 @@
 	return ret;
 }
 
+static void rndis_set_link_state(struct rndis_device *rdev,
+				 struct rndis_request *request)
+{
+	u32 link_status;
+	struct rndis_query_complete *query_complete;
+
+	query_complete = &request->response_msg.msg.query_complete;
+
+	if (query_complete->status == RNDIS_STATUS_SUCCESS &&
+	    query_complete->info_buflen == sizeof(u32)) {
+		memcpy(&link_status, (void *)((unsigned long)query_complete +
+		       query_complete->info_buf_offset), sizeof(u32));
+		rdev->link_state = link_status != 0;
+	}
+}
+
 static void rndis_filter_receive_response(struct rndis_device *dev,
 				       struct rndis_message *resp)
 {
@@ -272,6 +288,10 @@
 		    sizeof(struct rndis_message) + RNDIS_EXT_LEN) {
 			memcpy(&request->response_msg, resp,
 			       resp->msg_len);
+			if (request->request_msg.ndis_msg_type ==
+			    RNDIS_MSG_QUERY && request->request_msg.msg.
+			    query_req.oid == RNDIS_OID_GEN_MEDIA_CONNECT_STATUS)
+				rndis_set_link_state(dev, request);
 		} else {
 			netdev_err(ndev,
 				"rndis response buffer overflow "
@@ -620,7 +640,6 @@
 	ret = rndis_filter_query_device(dev,
 				      RNDIS_OID_GEN_MEDIA_CONNECT_STATUS,
 				      &link_status, &size);
-	dev->link_state = (link_status != 0) ? true : false;
 
 	return ret;
 }
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index ab31544..a30258a 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -546,12 +546,12 @@
 	int rc;
 	unsigned long flags;
 
-	spin_lock(&lp->lock);
+	spin_lock_irqsave(&lp->lock, flags);
 	if  (lp->irq_busy) {
-		spin_unlock(&lp->lock);
+		spin_unlock_irqrestore(&lp->lock, flags);
 		return -EBUSY;
 	}
-	spin_unlock(&lp->lock);
+	spin_unlock_irqrestore(&lp->lock, flags);
 
 	might_sleep();
 
@@ -725,10 +725,11 @@
 static irqreturn_t at86rf230_isr(int irq, void *data)
 {
 	struct at86rf230_local *lp = data;
+	unsigned long flags;
 
-	spin_lock(&lp->lock);
+	spin_lock_irqsave(&lp->lock, flags);
 	lp->irq_busy = 1;
-	spin_unlock(&lp->lock);
+	spin_unlock_irqrestore(&lp->lock, flags);
 
 	schedule_work(&lp->irqwork);
 
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index c14d39b..d7b2e94 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -180,7 +180,8 @@
 	dev->tx_queue_len = TX_Q_LIMIT;
 
 	dev->features |= IFB_FEATURES;
-	dev->vlan_features |= IFB_FEATURES;
+	dev->vlan_features |= IFB_FEATURES & ~(NETIF_F_HW_VLAN_CTAG_TX |
+					       NETIF_F_HW_VLAN_STAG_TX);
 
 	dev->flags |= IFF_NOARP;
 	dev->flags &= ~IFF_MULTICAST;
diff --git a/drivers/net/irda/Kconfig b/drivers/net/irda/Kconfig
index 2dc82f1..3da44d5 100644
--- a/drivers/net/irda/Kconfig
+++ b/drivers/net/irda/Kconfig
@@ -210,13 +210,6 @@
 	  To compile it as a module, choose M here: the module will be called
 	  kingsun-sir.
 
-config EP7211_DONGLE
-	tristate "Cirrus Logic clps711x I/R support"
-	depends on IRTTY_SIR && ARCH_CLPS711X && IRDA
-	help
-	  Say Y here if you want to build support for the Cirrus logic
-	  EP7211 chipset's infrared module.
-
 config KSDAZZLE_DONGLE
 	tristate "KingSun Dazzle IrDA-USB dongle"
 	depends on IRDA && USB
diff --git a/drivers/net/irda/Makefile b/drivers/net/irda/Makefile
index dfc6453..be8ab5b 100644
--- a/drivers/net/irda/Makefile
+++ b/drivers/net/irda/Makefile
@@ -35,7 +35,6 @@
 obj-$(CONFIG_ACT200L_DONGLE)	+= act200l-sir.o
 obj-$(CONFIG_MA600_DONGLE)	+= ma600-sir.o
 obj-$(CONFIG_TOIM3232_DONGLE)	+= toim3232-sir.o
-obj-$(CONFIG_EP7211_DONGLE)	+= ep7211-sir.o
 obj-$(CONFIG_KINGSUN_DONGLE)	+= kingsun-sir.o
 obj-$(CONFIG_KSDAZZLE_DONGLE)	+= ksdazzle-sir.o
 obj-$(CONFIG_KS959_DONGLE)    	+= ks959-sir.o
diff --git a/drivers/net/irda/ep7211-sir.c b/drivers/net/irda/ep7211-sir.c
deleted file mode 100644
index 5fe1f4d..0000000
--- a/drivers/net/irda/ep7211-sir.c
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * IR port driver for the Cirrus Logic CLPS711X processors
- *
- * Copyright 2001, Blue Mug Inc.  All rights reserved.
- * Copyright 2007, Samuel Ortiz <samuel@sortiz.org>
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-
-#include <mach/hardware.h>
-
-#include "sir-dev.h"
-
-static int clps711x_dongle_open(struct sir_dev *dev)
-{
-	unsigned int syscon;
-
-	/* Turn on the SIR encoder. */
-	syscon = clps_readl(SYSCON1);
-	syscon |= SYSCON1_SIREN;
-	clps_writel(syscon, SYSCON1);
-
-	return 0;
-}
-
-static int clps711x_dongle_close(struct sir_dev *dev)
-{
-	unsigned int syscon;
-
-	/* Turn off the SIR encoder. */
-	syscon = clps_readl(SYSCON1);
-	syscon &= ~SYSCON1_SIREN;
-	clps_writel(syscon, SYSCON1);
-
-	return 0;
-}
-
-static struct dongle_driver clps711x_dongle = {
-	.owner		= THIS_MODULE,
-	.driver_name	= "EP7211 IR driver",
-	.type		= IRDA_EP7211_DONGLE,
-	.open		= clps711x_dongle_open,
-	.close		= clps711x_dongle_close,
-};
-
-static int clps711x_sir_probe(struct platform_device *pdev)
-{
-	return irda_register_dongle(&clps711x_dongle);
-}
-
-static int clps711x_sir_remove(struct platform_device *pdev)
-{
-	return irda_unregister_dongle(&clps711x_dongle);
-}
-
-static struct platform_driver clps711x_sir_driver = {
-	.driver	= {
-		.name	= "sir-clps711x",
-		.owner	= THIS_MODULE,
-	},
-	.probe	= clps711x_sir_probe,
-	.remove	= clps711x_sir_remove,
-};
-module_platform_driver(clps711x_sir_driver);
-
-MODULE_AUTHOR("Samuel Ortiz <samuel@sortiz.org>");
-MODULE_DESCRIPTION("EP7211 IR dongle driver");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("irda-dongle-13"); /* IRDA_EP7211_DONGLE */
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index 177441a..24b6ddd 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -522,7 +522,6 @@
 	sirdev_put_instance(priv->dev);
 
 	/* Stop tty */
-	irtty_stop_receiver(tty, TRUE);
 	clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
 	if (tty->ops->stop)
 		tty->ops->stop(tty);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 8433de4..1831fb7 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -506,6 +506,9 @@
 static struct lock_class_key macvlan_netdev_xmit_lock_key;
 static struct lock_class_key macvlan_netdev_addr_lock_key;
 
+#define ALWAYS_ON_FEATURES \
+	(NETIF_F_SG | NETIF_F_GEN_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX)
+
 #define MACVLAN_FEATURES \
 	(NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
 	 NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \
@@ -539,7 +542,7 @@
 	dev->state		= (dev->state & ~MACVLAN_STATE_MASK) |
 				  (lowerdev->state & MACVLAN_STATE_MASK);
 	dev->features 		= lowerdev->features & MACVLAN_FEATURES;
-	dev->features		|= NETIF_F_LLTX;
+	dev->features		|= ALWAYS_ON_FEATURES;
 	dev->gso_max_size	= lowerdev->gso_max_size;
 	dev->iflink		= lowerdev->ifindex;
 	dev->hard_header_len	= lowerdev->hard_header_len;
@@ -699,7 +702,7 @@
 	features = netdev_increment_features(vlan->lowerdev->features,
 					     features,
 					     mask);
-	features |= NETIF_F_LLTX;
+	features |= ALWAYS_ON_FEATURES;
 
 	return features;
 }
@@ -879,14 +882,15 @@
 	dev->priv_flags |= IFF_MACVLAN;
 	err = netdev_upper_dev_link(lowerdev, dev);
 	if (err)
-		goto destroy_port;
-
+		goto unregister_netdev;
 
 	list_add_tail_rcu(&vlan->list, &port->vlans);
 	netif_stacked_transfer_operstate(lowerdev, dev);
 
 	return 0;
 
+unregister_netdev:
+	unregister_netdevice(dev);
 destroy_port:
 	port->count -= 1;
 	if (!port->count)
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 547725f..98e7cbf 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -437,7 +437,10 @@
 		if (on) {
 			gpio_num = gpio_tab[EXTTS0_GPIO + index];
 			evnt |= (gpio_num & EVNT_GPIO_MASK) << EVNT_GPIO_SHIFT;
-			evnt |= EVNT_RISE;
+			if (rq->extts.flags & PTP_FALLING_EDGE)
+				evnt |= EVNT_FALL;
+			else
+				evnt |= EVNT_RISE;
 		}
 		ext_write(0, phydev, PAGE5, PTP_EVNT, evnt);
 		return 0;
@@ -1003,11 +1006,6 @@
 	} else
 		list_add_tail(&dp83640->list, &clock->phylist);
 
-	if (clock->chosen && !list_empty(&clock->phylist))
-		recalibrate(clock);
-	else
-		enable_broadcast(dp83640->phydev, clock->page, 1);
-
 	dp83640_clock_put(clock);
 	return 0;
 
@@ -1058,6 +1056,21 @@
 	kfree(dp83640);
 }
 
+static int dp83640_config_init(struct phy_device *phydev)
+{
+	struct dp83640_private *dp83640 = phydev->priv;
+	struct dp83640_clock *clock = dp83640->clock;
+
+	if (clock->chosen && !list_empty(&clock->phylist))
+		recalibrate(clock);
+	else
+		enable_broadcast(phydev, clock->page, 1);
+
+	enable_status_frames(phydev, true);
+	ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+	return 0;
+}
+
 static int dp83640_ack_interrupt(struct phy_device *phydev)
 {
 	int err = phy_read(phydev, MII_DP83640_MISR);
@@ -1195,11 +1208,6 @@
 
 	mutex_lock(&dp83640->clock->extreg_lock);
 
-	if (dp83640->hwts_tx_en || dp83640->hwts_rx_en) {
-		enable_status_frames(phydev, true);
-		ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
-	}
-
 	ext_write(0, phydev, PAGE5, PTP_TXCFG0, txcfg0);
 	ext_write(0, phydev, PAGE5, PTP_RXCFG0, rxcfg0);
 
@@ -1281,6 +1289,7 @@
 		}
 		/* fall through */
 	case HWTSTAMP_TX_ON:
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		skb_queue_tail(&dp83640->tx_queue, skb);
 		schedule_work(&dp83640->ts_work);
 		break;
@@ -1330,6 +1339,7 @@
 	.flags		= PHY_HAS_INTERRUPT,
 	.probe		= dp83640_probe,
 	.remove		= dp83640_remove,
+	.config_init	= dp83640_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt  = dp83640_ack_interrupt,
diff --git a/drivers/net/phy/mdio-sun4i.c b/drivers/net/phy/mdio-sun4i.c
index bb88bc7..9367acc 100644
--- a/drivers/net/phy/mdio-sun4i.c
+++ b/drivers/net/phy/mdio-sun4i.c
@@ -170,6 +170,9 @@
 }
 
 static const struct of_device_id sun4i_mdio_dt_ids[] = {
+	{ .compatible = "allwinner,sun4i-a10-mdio" },
+
+	/* Deprecated */
 	{ .compatible = "allwinner,sun4i-mdio" },
 	{ }
 };
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 19c9eca..76d96b9 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -164,9 +164,9 @@
  *   of that setting.  Returns the index of the last setting if
  *   none of the others match.
  */
-static inline int phy_find_setting(int speed, int duplex)
+static inline unsigned int phy_find_setting(int speed, int duplex)
 {
-	int idx = 0;
+	unsigned int idx = 0;
 
 	while (idx < ARRAY_SIZE(settings) &&
 	       (settings[idx].speed != speed || settings[idx].duplex != duplex))
@@ -185,7 +185,7 @@
  *   the mask in features.  Returns the index of the last setting
  *   if nothing else matches.
  */
-static inline int phy_find_valid(int idx, u32 features)
+static inline unsigned int phy_find_valid(unsigned int idx, u32 features)
 {
 	while (idx < MAX_NUM_SETTINGS && !(settings[idx].setting & features))
 		idx++;
@@ -204,7 +204,7 @@
 static void phy_sanitize_settings(struct phy_device *phydev)
 {
 	u32 features = phydev->supported;
-	int idx;
+	unsigned int idx;
 
 	/* Sanitize settings based on PHY capabilities */
 	if ((features & SUPPORTED_Autoneg) == 0)
@@ -954,7 +954,8 @@
 	    (phydev->interface == PHY_INTERFACE_MODE_RGMII))) {
 		int eee_lp, eee_cap, eee_adv;
 		u32 lp, cap, adv;
-		int idx, status;
+		int status;
+		unsigned int idx;
 
 		/* Read phy status to properly get the right settings */
 		status = phy_read_status(phydev);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 4b03e63..2f6989b 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -683,10 +683,9 @@
 int phy_suspend(struct phy_device *phydev)
 {
 	struct phy_driver *phydrv = to_phy_driver(phydev->dev.driver);
-	struct ethtool_wolinfo wol;
+	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
 
 	/* If the device has WOL enabled, we cannot suspend the PHY */
-	wol.cmd = ETHTOOL_GWOL;
 	phy_ethtool_get_wol(phydev, &wol);
 	if (wol.wolopts)
 		return -EBUSY;
@@ -719,7 +718,7 @@
 static int genphy_config_advert(struct phy_device *phydev)
 {
 	u32 advertise;
-	int oldadv, adv;
+	int oldadv, adv, bmsr;
 	int err, changed = 0;
 
 	/* Only allow advertising what this PHY supports */
@@ -744,26 +743,36 @@
 		changed = 1;
 	}
 
+	bmsr = phy_read(phydev, MII_BMSR);
+	if (bmsr < 0)
+		return bmsr;
+
+	/* Per 802.3-2008, Section 22.2.4.2.16 Extended status all
+	 * 1000Mbits/sec capable PHYs shall have the BMSR_ESTATEN bit set to a
+	 * logical 1.
+	 */
+	if (!(bmsr & BMSR_ESTATEN))
+		return changed;
+
 	/* Configure gigabit if it's supported */
+	adv = phy_read(phydev, MII_CTRL1000);
+	if (adv < 0)
+		return adv;
+
+	oldadv = adv;
+	adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF);
+
 	if (phydev->supported & (SUPPORTED_1000baseT_Half |
 				 SUPPORTED_1000baseT_Full)) {
-		adv = phy_read(phydev, MII_CTRL1000);
-		if (adv < 0)
-			return adv;
-
-		oldadv = adv;
-		adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF);
 		adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
-
-		if (adv != oldadv) {
-			err = phy_write(phydev, MII_CTRL1000, adv);
-
-			if (err < 0)
-				return err;
+		if (adv != oldadv)
 			changed = 1;
-		}
 	}
 
+	err = phy_write(phydev, MII_CTRL1000, adv);
+	if (err < 0)
+		return err;
+
 	return changed;
 }
 
@@ -906,6 +915,8 @@
 	int err;
 	int lpa;
 	int lpagb = 0;
+	int common_adv;
+	int common_adv_gb = 0;
 
 	/* Update the link, but return if there was an error */
 	err = genphy_update_link(phydev);
@@ -927,7 +938,7 @@
 
 			phydev->lp_advertising =
 				mii_stat1000_to_ethtool_lpa_t(lpagb);
-			lpagb &= adv << 2;
+			common_adv_gb = lpagb & adv << 2;
 		}
 
 		lpa = phy_read(phydev, MII_LPA);
@@ -940,25 +951,25 @@
 		if (adv < 0)
 			return adv;
 
-		lpa &= adv;
+		common_adv = lpa & adv;
 
 		phydev->speed = SPEED_10;
 		phydev->duplex = DUPLEX_HALF;
 		phydev->pause = 0;
 		phydev->asym_pause = 0;
 
-		if (lpagb & (LPA_1000FULL | LPA_1000HALF)) {
+		if (common_adv_gb & (LPA_1000FULL | LPA_1000HALF)) {
 			phydev->speed = SPEED_1000;
 
-			if (lpagb & LPA_1000FULL)
+			if (common_adv_gb & LPA_1000FULL)
 				phydev->duplex = DUPLEX_FULL;
-		} else if (lpa & (LPA_100FULL | LPA_100HALF)) {
+		} else if (common_adv & (LPA_100FULL | LPA_100HALF)) {
 			phydev->speed = SPEED_100;
 
-			if (lpa & LPA_100FULL)
+			if (common_adv & LPA_100FULL)
 				phydev->duplex = DUPLEX_FULL;
 		} else
-			if (lpa & LPA_10FULL)
+			if (common_adv & LPA_10FULL)
 				phydev->duplex = DUPLEX_FULL;
 
 		if (phydev->duplex == DUPLEX_FULL) {
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2840742..c8624a8 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1648,7 +1648,7 @@
 }
 
 static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv)
+			     void *accel_priv, select_queue_fallback_t fallback)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 44c4db8..26f8635 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -366,7 +366,7 @@
  * hope the rxq no. may help here.
  */
 static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv)
+			    void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 	struct tun_flow_entry *e;
@@ -1686,7 +1686,9 @@
 				   TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
 				   NETIF_F_HW_VLAN_STAG_TX;
 		dev->features = dev->hw_features;
-		dev->vlan_features = dev->features;
+		dev->vlan_features = dev->features &
+				     ~(NETIF_F_HW_VLAN_CTAG_TX |
+				       NETIF_F_HW_VLAN_STAG_TX);
 
 		INIT_LIST_HEAD(&tun->disabled);
 		err = tun_attach(tun, file, false);
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 6b638a0..7e7269f 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -292,6 +292,21 @@
 	  This option adds support for CoreChip-sz SR9700 based USB 1.1
 	  10/100 Ethernet adapters.
 
+config USB_NET_SR9800
+	tristate "CoreChip-sz SR9800 based USB 2.0 10/100 ethernet devices"
+	depends on USB_USBNET
+	select CRC32
+	---help---
+	  Say Y if you want to use one of the following 100Mbps USB Ethernet
+	  device based on the CoreChip-sz SR9800 chip.
+
+	  This driver makes the adapter appear as a normal Ethernet interface,
+	  typically on eth0, if it is the only ethernet device, or perhaps on
+	  eth1, if you have a PCI or ISA ethernet card installed.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called sr9800.
+
 config USB_NET_SMSC75XX
 	tristate "SMSC LAN75XX based USB 2.0 gigabit ethernet devices"
 	depends on USB_USBNET
diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile
index b17b5e8..e2797f1 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -11,10 +11,11 @@
 obj-$(CONFIG_USB_NET_AX8817X)	+= asix.o
 asix-y := asix_devices.o asix_common.o ax88172a.o
 obj-$(CONFIG_USB_NET_AX88179_178A)      += ax88179_178a.o
-obj-$(CONFIG_USB_NET_CDCETHER)	+= cdc_ether.o r815x.o
+obj-$(CONFIG_USB_NET_CDCETHER)	+= cdc_ether.o
 obj-$(CONFIG_USB_NET_CDC_EEM)	+= cdc_eem.o
 obj-$(CONFIG_USB_NET_DM9601)	+= dm9601.o
 obj-$(CONFIG_USB_NET_SR9700)	+= sr9700.o
+obj-$(CONFIG_USB_NET_SR9800)	+= sr9800.o
 obj-$(CONFIG_USB_NET_SMSC75XX)	+= smsc75xx.o
 obj-$(CONFIG_USB_NET_SMSC95XX)	+= smsc95xx.o
 obj-$(CONFIG_USB_NET_GL620A)	+= gl620a.o
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 9765a7d..5d19409 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -917,7 +917,8 @@
 	.status = asix_status,
 	.link_reset = ax88178_link_reset,
 	.reset = ax88178_reset,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
+		 FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 };
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index d6f64da..054e59c 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1029,20 +1029,12 @@
 	dev->mii.phy_id = 0x03;
 	dev->mii.supports_gmii = 1;
 
-	if (usb_device_no_sg_constraint(dev->udev))
-		dev->can_dma_sg = 1;
-
 	dev->net->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			      NETIF_F_RXCSUM;
 
 	dev->net->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 				 NETIF_F_RXCSUM;
 
-	if (dev->can_dma_sg) {
-		dev->net->features |= NETIF_F_SG | NETIF_F_TSO;
-		dev->net->hw_features |= NETIF_F_SG | NETIF_F_TSO;
-	}
-
 	/* Enable checksum offload */
 	*tmp = AX_RXCOE_IP | AX_RXCOE_TCP | AX_RXCOE_UDP |
 	       AX_RXCOE_TCPV6 | AX_RXCOE_UDPV6;
@@ -1118,6 +1110,10 @@
 	u16 hdr_off;
 	u32 *pkt_hdr;
 
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	skb_trim(skb, skb->len - 4);
 	memcpy(&rx_hdr, skb_tail_pointer(skb), 4);
 	le32_to_cpus(&rx_hdr);
@@ -1391,6 +1387,19 @@
 	.tx_fixup = ax88179_tx_fixup,
 };
 
+static const struct driver_info dlink_dub1312_info = {
+	.description = "D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter",
+	.bind = ax88179_bind,
+	.unbind = ax88179_unbind,
+	.status = ax88179_status,
+	.link_reset = ax88179_link_reset,
+	.reset = ax88179_reset,
+	.stop = ax88179_stop,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.rx_fixup = ax88179_rx_fixup,
+	.tx_fixup = ax88179_tx_fixup,
+};
+
 static const struct driver_info sitecom_info = {
 	.description = "Sitecom USB 3.0 to Gigabit Adapter",
 	.bind = ax88179_bind,
@@ -1417,6 +1426,19 @@
 	.tx_fixup = ax88179_tx_fixup,
 };
 
+static const struct driver_info lenovo_info = {
+	.description = "Lenovo OneLinkDock Gigabit LAN",
+	.bind = ax88179_bind,
+	.unbind = ax88179_unbind,
+	.status = ax88179_status,
+	.link_reset = ax88179_link_reset,
+	.reset = ax88179_reset,
+	.stop = ax88179_stop,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.rx_fixup = ax88179_rx_fixup,
+	.tx_fixup = ax88179_tx_fixup,
+};
+
 static const struct usb_device_id products[] = {
 {
 	/* ASIX AX88179 10/100/1000 */
@@ -1427,6 +1449,10 @@
 	USB_DEVICE(0x0b95, 0x178a),
 	.driver_info = (unsigned long)&ax88178a_info,
 }, {
+	/* D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter */
+	USB_DEVICE(0x2001, 0x4a00),
+	.driver_info = (unsigned long)&dlink_dub1312_info,
+}, {
 	/* Sitecom USB 3.0 to Gigabit Adapter */
 	USB_DEVICE(0x0df6, 0x0072),
 	.driver_info = (unsigned long)&sitecom_info,
@@ -1434,6 +1460,10 @@
 	/* Samsung USB Ethernet Adapter */
 	USB_DEVICE(0x04e8, 0xa100),
 	.driver_info = (unsigned long)&samsung_info,
+}, {
+	/* Lenovo OneLinkDock Gigabit LAN */
+	USB_DEVICE(0x17ef, 0x304b),
+	.driver_info = (unsigned long)&lenovo_info,
 },
 	{ },
 };
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 42e1769..bd363b2 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -652,6 +652,13 @@
 	.driver_info = 0,
 },
 
+/* Samsung USB Ethernet Adapters */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, 0xa101, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* WHITELIST!!!
  *
  * CDC Ether uses two interfaces, not necessarily consecutive.
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index dbff290..d350d27 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -68,7 +68,6 @@
 static int cdc_ncm_setup(struct usbnet *dev)
 {
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
-	struct usb_cdc_ncm_ntb_parameters ncm_parm;
 	u32 val;
 	u8 flags;
 	u8 iface_no;
@@ -82,22 +81,22 @@
 	err = usbnet_read_cmd(dev, USB_CDC_GET_NTB_PARAMETERS,
 			      USB_TYPE_CLASS | USB_DIR_IN
 			      |USB_RECIP_INTERFACE,
-			      0, iface_no, &ncm_parm,
-			      sizeof(ncm_parm));
+			      0, iface_no, &ctx->ncm_parm,
+			      sizeof(ctx->ncm_parm));
 	if (err < 0) {
 		dev_err(&dev->intf->dev, "failed GET_NTB_PARAMETERS\n");
 		return err; /* GET_NTB_PARAMETERS is required */
 	}
 
 	/* read correct set of parameters according to device mode */
-	ctx->rx_max = le32_to_cpu(ncm_parm.dwNtbInMaxSize);
-	ctx->tx_max = le32_to_cpu(ncm_parm.dwNtbOutMaxSize);
-	ctx->tx_remainder = le16_to_cpu(ncm_parm.wNdpOutPayloadRemainder);
-	ctx->tx_modulus = le16_to_cpu(ncm_parm.wNdpOutDivisor);
-	ctx->tx_ndp_modulus = le16_to_cpu(ncm_parm.wNdpOutAlignment);
+	ctx->rx_max = le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize);
+	ctx->tx_max = le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize);
+	ctx->tx_remainder = le16_to_cpu(ctx->ncm_parm.wNdpOutPayloadRemainder);
+	ctx->tx_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutDivisor);
+	ctx->tx_ndp_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutAlignment);
 	/* devices prior to NCM Errata shall set this field to zero */
-	ctx->tx_max_datagrams = le16_to_cpu(ncm_parm.wNtbOutMaxDatagrams);
-	ntb_fmt_supported = le16_to_cpu(ncm_parm.bmNtbFormatsSupported);
+	ctx->tx_max_datagrams = le16_to_cpu(ctx->ncm_parm.wNtbOutMaxDatagrams);
+	ntb_fmt_supported = le16_to_cpu(ctx->ncm_parm.bmNtbFormatsSupported);
 
 	/* there are some minor differences in NCM and MBIM defaults */
 	if (cdc_ncm_comm_intf_is_mbim(ctx->control->cur_altsetting)) {
@@ -146,7 +145,7 @@
 	}
 
 	/* inform device about NTB input size changes */
-	if (ctx->rx_max != le32_to_cpu(ncm_parm.dwNtbInMaxSize)) {
+	if (ctx->rx_max != le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize)) {
 		__le32 dwNtbInMaxSize = cpu_to_le32(ctx->rx_max);
 
 		err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_INPUT_SIZE,
@@ -162,14 +161,6 @@
 		dev_dbg(&dev->intf->dev, "Using default maximum transmit length=%d\n",
 			CDC_NCM_NTB_MAX_SIZE_TX);
 		ctx->tx_max = CDC_NCM_NTB_MAX_SIZE_TX;
-
-		/* Adding a pad byte here simplifies the handling in
-		 * cdc_ncm_fill_tx_frame, by making tx_max always
-		 * represent the real skb max size.
-		 */
-		if (ctx->tx_max % usb_maxpacket(dev->udev, dev->out, 1) == 0)
-			ctx->tx_max++;
-
 	}
 
 	/*
@@ -439,6 +430,10 @@
 		goto error2;
 	}
 
+	/* initialize data interface */
+	if (cdc_ncm_setup(dev))
+		goto error2;
+
 	/* configure data interface */
 	temp = usb_set_interface(dev->udev, iface_no, data_altsetting);
 	if (temp) {
@@ -453,12 +448,6 @@
 		goto error2;
 	}
 
-	/* initialize data interface */
-	if (cdc_ncm_setup(dev))	{
-		dev_dbg(&intf->dev, "cdc_ncm_setup() failed\n");
-		goto error2;
-	}
-
 	usb_set_intfdata(ctx->data, dev);
 	usb_set_intfdata(ctx->control, dev);
 
@@ -475,6 +464,15 @@
 	dev->hard_mtu = ctx->tx_max;
 	dev->rx_urb_size = ctx->rx_max;
 
+	/* cdc_ncm_setup will override dwNtbOutMaxSize if it is
+	 * outside the sane range. Adding a pad byte here if necessary
+	 * simplifies the handling in cdc_ncm_fill_tx_frame, making
+	 * tx_max always represent the real skb max size.
+	 */
+	if (ctx->tx_max != le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) &&
+	    ctx->tx_max % usb_maxpacket(dev->udev, dev->out, 1) == 0)
+		ctx->tx_max++;
+
 	return 0;
 
 error2:
diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c
index e4a8a93..1cc24e6 100644
--- a/drivers/net/usb/gl620a.c
+++ b/drivers/net/usb/gl620a.c
@@ -84,6 +84,10 @@
 	u32			size;
 	u32			count;
 
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	header = (struct gl_header *) skb->data;
 
 	// get the packet count of the received skb
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 1a48234..660bd5e 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -1201,16 +1201,18 @@
 	struct hso_serial *serial = urb->context;
 	int status = urb->status;
 
+	D4("\n--- Got serial_read_bulk callback %02x ---", status);
+
 	/* sanity check */
 	if (!serial) {
 		D1("serial == NULL");
 		return;
-	} else if (status) {
+	}
+	if (status) {
 		handle_usb_error(status, __func__, serial->parent);
 		return;
 	}
 
-	D4("\n--- Got serial_read_bulk callback %02x ---", status);
 	D1("Actual length = %d\n", urb->actual_length);
 	DUMP1(urb->transfer_buffer, urb->actual_length);
 
@@ -1218,25 +1220,13 @@
 	if (serial->port.count == 0)
 		return;
 
-	if (status == 0) {
-		if (serial->parent->port_spec & HSO_INFO_CRC_BUG)
-			fix_crc_bug(urb, serial->in_endp->wMaxPacketSize);
-		/* Valid data, handle RX data */
-		spin_lock(&serial->serial_lock);
-		serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 1;
-		put_rxbuf_data_and_resubmit_bulk_urb(serial);
-		spin_unlock(&serial->serial_lock);
-	} else if (status == -ENOENT || status == -ECONNRESET) {
-		/* Unlinked - check for throttled port. */
-		D2("Port %d, successfully unlinked urb", serial->minor);
-		spin_lock(&serial->serial_lock);
-		serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 0;
-		hso_resubmit_rx_bulk_urb(serial, urb);
-		spin_unlock(&serial->serial_lock);
-	} else {
-		D2("Port %d, status = %d for read urb", serial->minor, status);
-		return;
-	}
+	if (serial->parent->port_spec & HSO_INFO_CRC_BUG)
+		fix_crc_bug(urb, serial->in_endp->wMaxPacketSize);
+	/* Valid data, handle RX data */
+	spin_lock(&serial->serial_lock);
+	serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 1;
+	put_rxbuf_data_and_resubmit_bulk_urb(serial);
+	spin_unlock(&serial->serial_lock);
 }
 
 /*
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index a305a7b..82d844a 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -526,8 +526,9 @@
 {
 	u8 status;
 
-	if (skb->len == 0) {
-		dev_err(&dev->udev->dev, "unexpected empty rx frame\n");
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len) {
+		dev_err(&dev->udev->dev, "unexpected tiny rx frame\n");
 		return 0;
 	}
 
diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c
index 0a85d92..4cbdb13 100644
--- a/drivers/net/usb/net1080.c
+++ b/drivers/net/usb/net1080.c
@@ -364,6 +364,10 @@
 	struct nc_trailer	*trailer;
 	u16			hdr_len, packet_len;
 
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	if (!(skb->len & 0x01)) {
 		netdev_dbg(dev->net, "rx framesize %d range %d..%d mtu %d\n",
 			   skb->len, dev->net->hard_header_len, dev->hard_mtu,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 23bdd5b..313cb6c 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -80,10 +80,10 @@
 {
 	__be16 proto;
 
-	/* usbnet rx_complete guarantees that skb->len is at least
-	 * hard_header_len, so we can inspect the dest address without
-	 * checking skb->len
-	 */
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	switch (skb->data[0] & 0xf0) {
 	case 0x40:
 		proto = htons(ETH_P_IP);
@@ -712,6 +712,7 @@
 	{QMI_FIXED_INTF(0x19d2, 0x1255, 3)},
 	{QMI_FIXED_INTF(0x19d2, 0x1255, 4)},
 	{QMI_FIXED_INTF(0x19d2, 0x1256, 4)},
+	{QMI_FIXED_INTF(0x19d2, 0x1270, 5)},	/* ZTE MF667 */
 	{QMI_FIXED_INTF(0x19d2, 0x1401, 2)},
 	{QMI_FIXED_INTF(0x19d2, 0x1402, 2)},	/* ZTE MF60 */
 	{QMI_FIXED_INTF(0x19d2, 0x1424, 2)},
@@ -723,6 +724,7 @@
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 8)},	/* Sierra Wireless MC7710 in QMI mode */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 19)},	/* Sierra Wireless MC7710 in QMI mode */
 	{QMI_FIXED_INTF(0x1199, 0x901c, 8)},    /* Sierra Wireless EM7700 */
+	{QMI_FIXED_INTF(0x1199, 0x9051, 8)},	/* Netgear AirCard 340U */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
@@ -730,6 +732,7 @@
 	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc005, 6)},    /* Olivetti Olicard 200 */
 	{QMI_FIXED_INTF(0x1e2d, 0x0060, 4)},	/* Cinterion PLxx */
+	{QMI_FIXED_INTF(0x1e2d, 0x0053, 4)},	/* Cinterion PHxx,PXxx */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index e8fac73..adb12f3 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -449,9 +449,6 @@
 #define MCU_TYPE_PLA			0x0100
 #define MCU_TYPE_USB			0x0000
 
-#define REALTEK_USB_DEVICE(vend, prod)	\
-	USB_DEVICE_INTERFACE_CLASS(vend, prod, USB_CLASS_VENDOR_SPEC)
-
 struct rx_desc {
 	__le32 opts1;
 #define RX_LEN_MASK			0x7fff
@@ -2273,15 +2270,6 @@
 	struct r8152 *tp = netdev_priv(netdev);
 	int res = 0;
 
-	res = usb_submit_urb(tp->intr_urb, GFP_KERNEL);
-	if (res) {
-		if (res == -ENODEV)
-			netif_device_detach(tp->netdev);
-		netif_warn(tp, ifup, netdev, "intr_urb submit failed: %d\n",
-			   res);
-		return res;
-	}
-
 	rtl8152_set_speed(tp, AUTONEG_ENABLE,
 			  tp->mii.supports_gmii ? SPEED_1000 : SPEED_100,
 			  DUPLEX_FULL);
@@ -2289,6 +2277,14 @@
 	netif_carrier_off(netdev);
 	netif_start_queue(netdev);
 	set_bit(WORK_ENABLE, &tp->flags);
+	res = usb_submit_urb(tp->intr_urb, GFP_KERNEL);
+	if (res) {
+		if (res == -ENODEV)
+			netif_device_detach(tp->netdev);
+		netif_warn(tp, ifup, netdev, "intr_urb submit failed: %d\n",
+			   res);
+	}
+
 
 	return res;
 }
@@ -2298,8 +2294,8 @@
 	struct r8152 *tp = netdev_priv(netdev);
 	int res = 0;
 
-	usb_kill_urb(tp->intr_urb);
 	clear_bit(WORK_ENABLE, &tp->flags);
+	usb_kill_urb(tp->intr_urb);
 	cancel_delayed_work_sync(&tp->schedule);
 	netif_stop_queue(netdev);
 	tasklet_disable(&tp->tl);
@@ -2740,6 +2736,12 @@
 	struct net_device *netdev;
 	int ret;
 
+	if (udev->actconfig->desc.bConfigurationValue != 1) {
+		usb_driver_set_configuration(udev, 1);
+		return -ENODEV;
+	}
+
+	usb_reset_device(udev);
 	netdev = alloc_etherdev(sizeof(struct r8152));
 	if (!netdev) {
 		dev_err(&intf->dev, "Out of memory\n");
@@ -2820,9 +2822,9 @@
 
 /* table of devices that work with this driver */
 static struct usb_device_id rtl8152_table[] = {
-	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8152)},
-	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8153)},
-	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, PRODUCT_ID_SAMSUNG)},
+	{USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8152)},
+	{USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8153)},
+	{USB_DEVICE(VENDOR_ID_SAMSUNG, PRODUCT_ID_SAMSUNG)},
 	{}
 };
 
diff --git a/drivers/net/usb/r815x.c b/drivers/net/usb/r815x.c
deleted file mode 100644
index f0a8791..0000000
--- a/drivers/net/usb/r815x.c
+++ /dev/null
@@ -1,248 +0,0 @@
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/mii.h>
-#include <linux/usb.h>
-#include <linux/usb/cdc.h>
-#include <linux/usb/usbnet.h>
-
-#define RTL815x_REQT_READ	0xc0
-#define RTL815x_REQT_WRITE	0x40
-#define RTL815x_REQ_GET_REGS	0x05
-#define RTL815x_REQ_SET_REGS	0x05
-
-#define MCU_TYPE_PLA		0x0100
-#define OCP_BASE		0xe86c
-#define BASE_MII		0xa400
-
-#define BYTE_EN_DWORD		0xff
-#define BYTE_EN_WORD		0x33
-#define BYTE_EN_BYTE		0x11
-
-#define R815x_PHY_ID		32
-#define REALTEK_VENDOR_ID	0x0bda
-
-
-static int pla_read_word(struct usb_device *udev, u16 index)
-{
-	int ret;
-	u8 shift = index & 2;
-	__le32 *tmp;
-
-	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
-
-	index &= ~3;
-
-	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
-			      RTL815x_REQ_GET_REGS, RTL815x_REQT_READ,
-			      index, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
-	if (ret < 0)
-		goto out2;
-
-	ret = __le32_to_cpu(*tmp);
-	ret >>= (shift * 8);
-	ret &= 0xffff;
-
-out2:
-	kfree(tmp);
-	return ret;
-}
-
-static int pla_write_word(struct usb_device *udev, u16 index, u32 data)
-{
-	__le32 *tmp;
-	u32 mask = 0xffff;
-	u16 byen = BYTE_EN_WORD;
-	u8 shift = index & 2;
-	int ret;
-
-	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
-
-	data &= mask;
-
-	if (shift) {
-		byen <<= shift;
-		mask <<= (shift * 8);
-		data <<= (shift * 8);
-		index &= ~3;
-	}
-
-	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
-			      RTL815x_REQ_GET_REGS, RTL815x_REQT_READ,
-			      index, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
-	if (ret < 0)
-		goto out3;
-
-	data |= __le32_to_cpu(*tmp) & ~mask;
-	*tmp = __cpu_to_le32(data);
-
-	ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
-			      RTL815x_REQ_SET_REGS, RTL815x_REQT_WRITE,
-			      index, MCU_TYPE_PLA | byen, tmp, sizeof(*tmp),
-			      500);
-
-out3:
-	kfree(tmp);
-	return ret;
-}
-
-static int ocp_reg_read(struct usbnet *dev, u16 addr)
-{
-	u16 ocp_base, ocp_index;
-	int ret;
-
-	ocp_base = addr & 0xf000;
-	ret = pla_write_word(dev->udev, OCP_BASE, ocp_base);
-	if (ret < 0)
-		goto out;
-
-	ocp_index = (addr & 0x0fff) | 0xb000;
-	ret = pla_read_word(dev->udev, ocp_index);
-
-out:
-	return ret;
-}
-
-static int ocp_reg_write(struct usbnet *dev, u16 addr, u16 data)
-{
-	u16 ocp_base, ocp_index;
-	int ret;
-
-	ocp_base = addr & 0xf000;
-	ret = pla_write_word(dev->udev, OCP_BASE, ocp_base);
-	if (ret < 0)
-		goto out1;
-
-	ocp_index = (addr & 0x0fff) | 0xb000;
-	ret = pla_write_word(dev->udev, ocp_index, data);
-
-out1:
-	return ret;
-}
-
-static int r815x_mdio_read(struct net_device *netdev, int phy_id, int reg)
-{
-	struct usbnet *dev = netdev_priv(netdev);
-	int ret;
-
-	if (phy_id != R815x_PHY_ID)
-		return -EINVAL;
-
-	if (usb_autopm_get_interface(dev->intf) < 0)
-		return -ENODEV;
-
-	ret = ocp_reg_read(dev, BASE_MII + reg * 2);
-
-	usb_autopm_put_interface(dev->intf);
-	return ret;
-}
-
-static
-void r815x_mdio_write(struct net_device *netdev, int phy_id, int reg, int val)
-{
-	struct usbnet *dev = netdev_priv(netdev);
-
-	if (phy_id != R815x_PHY_ID)
-		return;
-
-	if (usb_autopm_get_interface(dev->intf) < 0)
-		return;
-
-	ocp_reg_write(dev, BASE_MII + reg * 2, val);
-
-	usb_autopm_put_interface(dev->intf);
-}
-
-static int r8153_bind(struct usbnet *dev, struct usb_interface *intf)
-{
-	int status;
-
-	status = usbnet_cdc_bind(dev, intf);
-	if (status < 0)
-		return status;
-
-	dev->mii.dev = dev->net;
-	dev->mii.mdio_read = r815x_mdio_read;
-	dev->mii.mdio_write = r815x_mdio_write;
-	dev->mii.phy_id_mask = 0x3f;
-	dev->mii.reg_num_mask = 0x1f;
-	dev->mii.phy_id = R815x_PHY_ID;
-	dev->mii.supports_gmii = 1;
-
-	return status;
-}
-
-static int r8152_bind(struct usbnet *dev, struct usb_interface *intf)
-{
-	int status;
-
-	status = usbnet_cdc_bind(dev, intf);
-	if (status < 0)
-		return status;
-
-	dev->mii.dev = dev->net;
-	dev->mii.mdio_read = r815x_mdio_read;
-	dev->mii.mdio_write = r815x_mdio_write;
-	dev->mii.phy_id_mask = 0x3f;
-	dev->mii.reg_num_mask = 0x1f;
-	dev->mii.phy_id = R815x_PHY_ID;
-	dev->mii.supports_gmii = 0;
-
-	return status;
-}
-
-static const struct driver_info r8152_info = {
-	.description =	"RTL8152 ECM Device",
-	.flags =	FLAG_ETHER | FLAG_POINTTOPOINT,
-	.bind =		r8152_bind,
-	.unbind =	usbnet_cdc_unbind,
-	.status =	usbnet_cdc_status,
-	.manage_power =	usbnet_manage_power,
-};
-
-static const struct driver_info r8153_info = {
-	.description =	"RTL8153 ECM Device",
-	.flags =	FLAG_ETHER | FLAG_POINTTOPOINT,
-	.bind =		r8153_bind,
-	.unbind =	usbnet_cdc_unbind,
-	.status =	usbnet_cdc_status,
-	.manage_power =	usbnet_manage_power,
-};
-
-static const struct usb_device_id products[] = {
-{
-	USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8152, USB_CLASS_COMM,
-			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
-	.driver_info = (unsigned long) &r8152_info,
-},
-
-{
-	USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8153, USB_CLASS_COMM,
-			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
-	.driver_info = (unsigned long) &r8153_info,
-},
-
-	{ },		/* END */
-};
-MODULE_DEVICE_TABLE(usb, products);
-
-static struct usb_driver r815x_driver = {
-	.name =		"r815x",
-	.id_table =	products,
-	.probe =	usbnet_probe,
-	.disconnect =	usbnet_disconnect,
-	.suspend =	usbnet_suspend,
-	.resume =	usbnet_resume,
-	.reset_resume =	usbnet_resume,
-	.supports_autosuspend = 1,
-	.disable_hub_initiated_lpm = 1,
-};
-
-module_usb_driver(r815x_driver);
-
-MODULE_AUTHOR("Hayes Wang");
-MODULE_DESCRIPTION("Realtek USB ECM device");
-MODULE_LICENSE("GPL");
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index a48bc0f..524a47a 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -492,6 +492,10 @@
  */
 int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	/* peripheral may have batched packets to us... */
 	while (likely(skb->len)) {
 		struct rndis_data_hdr	*hdr = (void *)skb->data;
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index f17b9e0..d9e7892 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -2106,6 +2106,10 @@
 
 static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	while (skb->len > 0) {
 		u32 rx_cmd_a, rx_cmd_b, align_count, size;
 		struct sk_buff *ax_skb;
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 8dd54a0..424db65e 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1723,6 +1723,10 @@
 
 static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
 	while (skb->len > 0) {
 		u32 header, align_count;
 		struct sk_buff *ax_skb;
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c
new file mode 100644
index 0000000..b94a0fb
--- /dev/null
+++ b/drivers/net/usb/sr9800.c
@@ -0,0 +1,874 @@
+/* CoreChip-sz SR9800 one chip USB 2.0 Ethernet Devices
+ *
+ * Author : Liu Junliang <liujunliang_ljl@163.com>
+ *
+ * Based on asix_common.c, asix_devices.c
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.*
+ */
+
+#include <linux/module.h>
+#include <linux/kmod.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/workqueue.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/crc32.h>
+#include <linux/usb/usbnet.h>
+#include <linux/slab.h>
+#include <linux/if_vlan.h>
+
+#include "sr9800.h"
+
+static int sr_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
+			    u16 size, void *data)
+{
+	int err;
+
+	err = usbnet_read_cmd(dev, cmd, SR_REQ_RD_REG, value, index,
+			      data, size);
+	if ((err != size) && (err >= 0))
+		err = -EINVAL;
+
+	return err;
+}
+
+static int sr_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
+			     u16 size, void *data)
+{
+	int err;
+
+	err = usbnet_write_cmd(dev, cmd, SR_REQ_WR_REG, value, index,
+			      data, size);
+	if ((err != size) && (err >= 0))
+		err = -EINVAL;
+
+	return err;
+}
+
+static void
+sr_write_cmd_async(struct usbnet *dev, u8 cmd, u16 value, u16 index,
+		   u16 size, void *data)
+{
+	usbnet_write_cmd_async(dev, cmd, SR_REQ_WR_REG, value, index, data,
+			       size);
+}
+
+static int sr_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+{
+	int offset = 0;
+
+	/* This check is no longer done by usbnet */
+	if (skb->len < dev->net->hard_header_len)
+		return 0;
+
+	while (offset + sizeof(u32) < skb->len) {
+		struct sk_buff *sr_skb;
+		u16 size;
+		u32 header = get_unaligned_le32(skb->data + offset);
+
+		offset += sizeof(u32);
+		/* get the packet length */
+		size = (u16) (header & 0x7ff);
+		if (size != ((~header >> 16) & 0x07ff)) {
+			netdev_err(dev->net, "%s : Bad Header Length\n",
+				   __func__);
+			return 0;
+		}
+
+		if ((size > dev->net->mtu + ETH_HLEN + VLAN_HLEN) ||
+		    (size + offset > skb->len)) {
+			netdev_err(dev->net, "%s : Bad RX Length %d\n",
+				   __func__, size);
+			return 0;
+		}
+		sr_skb = netdev_alloc_skb_ip_align(dev->net, size);
+		if (!sr_skb)
+			return 0;
+
+		skb_put(sr_skb, size);
+		memcpy(sr_skb->data, skb->data + offset, size);
+		usbnet_skb_return(dev, sr_skb);
+
+		offset += (size + 1) & 0xfffe;
+	}
+
+	if (skb->len != offset) {
+		netdev_err(dev->net, "%s : Bad SKB Length %d\n", __func__,
+			   skb->len);
+		return 0;
+	}
+
+	return 1;
+}
+
+static struct sk_buff *sr_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
+					gfp_t flags)
+{
+	int headroom = skb_headroom(skb);
+	int tailroom = skb_tailroom(skb);
+	u32 padbytes = 0xffff0000;
+	u32 packet_len;
+	int padlen;
+
+	padlen = ((skb->len + 4) % (dev->maxpacket - 1)) ? 0 : 4;
+
+	if ((!skb_cloned(skb)) && ((headroom + tailroom) >= (4 + padlen))) {
+		if ((headroom < 4) || (tailroom < padlen)) {
+			skb->data = memmove(skb->head + 4, skb->data,
+					    skb->len);
+			skb_set_tail_pointer(skb, skb->len);
+		}
+	} else {
+		struct sk_buff *skb2;
+		skb2 = skb_copy_expand(skb, 4, padlen, flags);
+		dev_kfree_skb_any(skb);
+		skb = skb2;
+		if (!skb)
+			return NULL;
+	}
+
+	skb_push(skb, 4);
+	packet_len = (((skb->len - 4) ^ 0x0000ffff) << 16) + (skb->len - 4);
+	cpu_to_le32s(&packet_len);
+	skb_copy_to_linear_data(skb, &packet_len, sizeof(packet_len));
+
+	if (padlen) {
+		cpu_to_le32s(&padbytes);
+		memcpy(skb_tail_pointer(skb), &padbytes, sizeof(padbytes));
+		skb_put(skb, sizeof(padbytes));
+	}
+
+	return skb;
+}
+
+static void sr_status(struct usbnet *dev, struct urb *urb)
+{
+	struct sr9800_int_data *event;
+	int link;
+
+	if (urb->actual_length < 8)
+		return;
+
+	event = urb->transfer_buffer;
+	link = event->link & 0x01;
+	if (netif_carrier_ok(dev->net) != link) {
+		usbnet_link_change(dev, link, 1);
+		netdev_dbg(dev->net, "Link Status is: %d\n", link);
+	}
+
+	return;
+}
+
+static inline int sr_set_sw_mii(struct usbnet *dev)
+{
+	int ret;
+
+	ret = sr_write_cmd(dev, SR_CMD_SET_SW_MII, 0x0000, 0, 0, NULL);
+	if (ret < 0)
+		netdev_err(dev->net, "Failed to enable software MII access\n");
+	return ret;
+}
+
+static inline int sr_set_hw_mii(struct usbnet *dev)
+{
+	int ret;
+
+	ret = sr_write_cmd(dev, SR_CMD_SET_HW_MII, 0x0000, 0, 0, NULL);
+	if (ret < 0)
+		netdev_err(dev->net, "Failed to enable hardware MII access\n");
+	return ret;
+}
+
+static inline int sr_get_phy_addr(struct usbnet *dev)
+{
+	u8 buf[2];
+	int ret;
+
+	ret = sr_read_cmd(dev, SR_CMD_READ_PHY_ID, 0, 0, 2, buf);
+	if (ret < 0) {
+		netdev_err(dev->net, "%s : Error reading PHYID register:%02x\n",
+			   __func__, ret);
+		goto out;
+	}
+	netdev_dbg(dev->net, "%s : returning 0x%04x\n", __func__,
+		   *((__le16 *)buf));
+
+	ret = buf[1];
+
+out:
+	return ret;
+}
+
+static int sr_sw_reset(struct usbnet *dev, u8 flags)
+{
+	int ret;
+
+	ret = sr_write_cmd(dev, SR_CMD_SW_RESET, flags, 0, 0, NULL);
+	if (ret < 0)
+		netdev_err(dev->net, "Failed to send software reset:%02x\n",
+			   ret);
+
+	return ret;
+}
+
+static u16 sr_read_rx_ctl(struct usbnet *dev)
+{
+	__le16 v;
+	int ret;
+
+	ret = sr_read_cmd(dev, SR_CMD_READ_RX_CTL, 0, 0, 2, &v);
+	if (ret < 0) {
+		netdev_err(dev->net, "Error reading RX_CTL register:%02x\n",
+			   ret);
+		goto out;
+	}
+
+	ret = le16_to_cpu(v);
+out:
+	return ret;
+}
+
+static int sr_write_rx_ctl(struct usbnet *dev, u16 mode)
+{
+	int ret;
+
+	netdev_dbg(dev->net, "%s : mode = 0x%04x\n", __func__, mode);
+	ret = sr_write_cmd(dev, SR_CMD_WRITE_RX_CTL, mode, 0, 0, NULL);
+	if (ret < 0)
+		netdev_err(dev->net,
+			   "Failed to write RX_CTL mode to 0x%04x:%02x\n",
+			   mode, ret);
+
+	return ret;
+}
+
+static u16 sr_read_medium_status(struct usbnet *dev)
+{
+	__le16 v;
+	int ret;
+
+	ret = sr_read_cmd(dev, SR_CMD_READ_MEDIUM_STATUS, 0, 0, 2, &v);
+	if (ret < 0) {
+		netdev_err(dev->net,
+			   "Error reading Medium Status register:%02x\n", ret);
+		return ret;	/* TODO: callers not checking for error ret */
+	}
+
+	return le16_to_cpu(v);
+}
+
+static int sr_write_medium_mode(struct usbnet *dev, u16 mode)
+{
+	int ret;
+
+	netdev_dbg(dev->net, "%s : mode = 0x%04x\n", __func__, mode);
+	ret = sr_write_cmd(dev, SR_CMD_WRITE_MEDIUM_MODE, mode, 0, 0, NULL);
+	if (ret < 0)
+		netdev_err(dev->net,
+			   "Failed to write Medium Mode mode to 0x%04x:%02x\n",
+			   mode, ret);
+	return ret;
+}
+
+static int sr_write_gpio(struct usbnet *dev, u16 value, int sleep)
+{
+	int ret;
+
+	netdev_dbg(dev->net, "%s : value = 0x%04x\n", __func__, value);
+	ret = sr_write_cmd(dev, SR_CMD_WRITE_GPIOS, value, 0, 0, NULL);
+	if (ret < 0)
+		netdev_err(dev->net, "Failed to write GPIO value 0x%04x:%02x\n",
+			   value, ret);
+	if (sleep)
+		msleep(sleep);
+
+	return ret;
+}
+
+/* SR9800 have a 16-bit RX_CTL value */
+static void sr_set_multicast(struct net_device *net)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct sr_data *data = (struct sr_data *)&dev->data;
+	u16 rx_ctl = SR_DEFAULT_RX_CTL;
+
+	if (net->flags & IFF_PROMISC) {
+		rx_ctl |= SR_RX_CTL_PRO;
+	} else if (net->flags & IFF_ALLMULTI ||
+		   netdev_mc_count(net) > SR_MAX_MCAST) {
+		rx_ctl |= SR_RX_CTL_AMALL;
+	} else if (netdev_mc_empty(net)) {
+		/* just broadcast and directed */
+	} else {
+		/* We use the 20 byte dev->data
+		 * for our 8 byte filter buffer
+		 * to avoid allocating memory that
+		 * is tricky to free later
+		 */
+		struct netdev_hw_addr *ha;
+		u32 crc_bits;
+
+		memset(data->multi_filter, 0, SR_MCAST_FILTER_SIZE);
+
+		/* Build the multicast hash filter. */
+		netdev_for_each_mc_addr(ha, net) {
+			crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26;
+			data->multi_filter[crc_bits >> 3] |=
+			    1 << (crc_bits & 7);
+		}
+
+		sr_write_cmd_async(dev, SR_CMD_WRITE_MULTI_FILTER, 0, 0,
+				   SR_MCAST_FILTER_SIZE, data->multi_filter);
+
+		rx_ctl |= SR_RX_CTL_AM;
+	}
+
+	sr_write_cmd_async(dev, SR_CMD_WRITE_RX_CTL, rx_ctl, 0, 0, NULL);
+}
+
+static int sr_mdio_read(struct net_device *net, int phy_id, int loc)
+{
+	struct usbnet *dev = netdev_priv(net);
+	__le16 res;
+
+	mutex_lock(&dev->phy_mutex);
+	sr_set_sw_mii(dev);
+	sr_read_cmd(dev, SR_CMD_READ_MII_REG, phy_id, (__u16)loc, 2, &res);
+	sr_set_hw_mii(dev);
+	mutex_unlock(&dev->phy_mutex);
+
+	netdev_dbg(dev->net,
+		   "%s : phy_id=0x%02x, loc=0x%02x, returns=0x%04x\n", __func__,
+		   phy_id, loc, le16_to_cpu(res));
+
+	return le16_to_cpu(res);
+}
+
+static void
+sr_mdio_write(struct net_device *net, int phy_id, int loc, int val)
+{
+	struct usbnet *dev = netdev_priv(net);
+	__le16 res = cpu_to_le16(val);
+
+	netdev_dbg(dev->net,
+		   "%s : phy_id=0x%02x, loc=0x%02x, val=0x%04x\n", __func__,
+		   phy_id, loc, val);
+	mutex_lock(&dev->phy_mutex);
+	sr_set_sw_mii(dev);
+	sr_write_cmd(dev, SR_CMD_WRITE_MII_REG, phy_id, (__u16)loc, 2, &res);
+	sr_set_hw_mii(dev);
+	mutex_unlock(&dev->phy_mutex);
+}
+
+/* Get the PHY Identifier from the PHYSID1 & PHYSID2 MII registers */
+static u32 sr_get_phyid(struct usbnet *dev)
+{
+	int phy_reg;
+	u32 phy_id;
+	int i;
+
+	/* Poll for the rare case the FW or phy isn't ready yet.  */
+	for (i = 0; i < 100; i++) {
+		phy_reg = sr_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID1);
+		if (phy_reg != 0 && phy_reg != 0xFFFF)
+			break;
+		mdelay(1);
+	}
+
+	if (phy_reg <= 0 || phy_reg == 0xFFFF)
+		return 0;
+
+	phy_id = (phy_reg & 0xffff) << 16;
+
+	phy_reg = sr_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID2);
+	if (phy_reg < 0)
+		return 0;
+
+	phy_id |= (phy_reg & 0xffff);
+
+	return phy_id;
+}
+
+static void
+sr_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
+{
+	struct usbnet *dev = netdev_priv(net);
+	u8 opt;
+
+	if (sr_read_cmd(dev, SR_CMD_READ_MONITOR_MODE, 0, 0, 1, &opt) < 0) {
+		wolinfo->supported = 0;
+		wolinfo->wolopts = 0;
+		return;
+	}
+	wolinfo->supported = WAKE_PHY | WAKE_MAGIC;
+	wolinfo->wolopts = 0;
+	if (opt & SR_MONITOR_LINK)
+		wolinfo->wolopts |= WAKE_PHY;
+	if (opt & SR_MONITOR_MAGIC)
+		wolinfo->wolopts |= WAKE_MAGIC;
+}
+
+static int
+sr_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
+{
+	struct usbnet *dev = netdev_priv(net);
+	u8 opt = 0;
+
+	if (wolinfo->wolopts & WAKE_PHY)
+		opt |= SR_MONITOR_LINK;
+	if (wolinfo->wolopts & WAKE_MAGIC)
+		opt |= SR_MONITOR_MAGIC;
+
+	if (sr_write_cmd(dev, SR_CMD_WRITE_MONITOR_MODE,
+			 opt, 0, 0, NULL) < 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int sr_get_eeprom_len(struct net_device *net)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct sr_data *data = (struct sr_data *)&dev->data;
+
+	return data->eeprom_len;
+}
+
+static int sr_get_eeprom(struct net_device *net,
+			      struct ethtool_eeprom *eeprom, u8 *data)
+{
+	struct usbnet *dev = netdev_priv(net);
+	__le16 *ebuf = (__le16 *)data;
+	int ret;
+	int i;
+
+	/* Crude hack to ensure that we don't overwrite memory
+	 * if an odd length is supplied
+	 */
+	if (eeprom->len % 2)
+		return -EINVAL;
+
+	eeprom->magic = SR_EEPROM_MAGIC;
+
+	/* sr9800 returns 2 bytes from eeprom on read */
+	for (i = 0; i < eeprom->len / 2; i++) {
+		ret = sr_read_cmd(dev, SR_CMD_READ_EEPROM, eeprom->offset + i,
+				  0, 2, &ebuf[i]);
+		if (ret < 0)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static void sr_get_drvinfo(struct net_device *net,
+				 struct ethtool_drvinfo *info)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct sr_data *data = (struct sr_data *)&dev->data;
+
+	/* Inherit standard device info */
+	usbnet_get_drvinfo(net, info);
+	strncpy(info->driver, DRIVER_NAME, sizeof(info->driver));
+	strncpy(info->version, DRIVER_VERSION, sizeof(info->version));
+	info->eedump_len = data->eeprom_len;
+}
+
+static u32 sr_get_link(struct net_device *net)
+{
+	struct usbnet *dev = netdev_priv(net);
+
+	return mii_link_ok(&dev->mii);
+}
+
+static int sr_ioctl(struct net_device *net, struct ifreq *rq, int cmd)
+{
+	struct usbnet *dev = netdev_priv(net);
+
+	return generic_mii_ioctl(&dev->mii, if_mii(rq), cmd, NULL);
+}
+
+static int sr_set_mac_address(struct net_device *net, void *p)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct sr_data *data = (struct sr_data *)&dev->data;
+	struct sockaddr *addr = p;
+
+	if (netif_running(net))
+		return -EBUSY;
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(net->dev_addr, addr->sa_data, ETH_ALEN);
+
+	/* We use the 20 byte dev->data
+	 * for our 6 byte mac buffer
+	 * to avoid allocating memory that
+	 * is tricky to free later
+	 */
+	memcpy(data->mac_addr, addr->sa_data, ETH_ALEN);
+	sr_write_cmd_async(dev, SR_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN,
+			   data->mac_addr);
+
+	return 0;
+}
+
+static const struct ethtool_ops sr9800_ethtool_ops = {
+	.get_drvinfo	= sr_get_drvinfo,
+	.get_link	= sr_get_link,
+	.get_msglevel	= usbnet_get_msglevel,
+	.set_msglevel	= usbnet_set_msglevel,
+	.get_wol	= sr_get_wol,
+	.set_wol	= sr_set_wol,
+	.get_eeprom_len	= sr_get_eeprom_len,
+	.get_eeprom	= sr_get_eeprom,
+	.get_settings	= usbnet_get_settings,
+	.set_settings	= usbnet_set_settings,
+	.nway_reset	= usbnet_nway_reset,
+};
+
+static int sr9800_link_reset(struct usbnet *dev)
+{
+	struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET };
+	u16 mode;
+
+	mii_check_media(&dev->mii, 1, 1);
+	mii_ethtool_gset(&dev->mii, &ecmd);
+	mode = SR9800_MEDIUM_DEFAULT;
+
+	if (ethtool_cmd_speed(&ecmd) != SPEED_100)
+		mode &= ~SR_MEDIUM_PS;
+
+	if (ecmd.duplex != DUPLEX_FULL)
+		mode &= ~SR_MEDIUM_FD;
+
+	netdev_dbg(dev->net, "%s : speed: %u duplex: %d mode: 0x%04x\n",
+		   __func__, ethtool_cmd_speed(&ecmd), ecmd.duplex, mode);
+
+	sr_write_medium_mode(dev, mode);
+
+	return 0;
+}
+
+
+static int sr9800_set_default_mode(struct usbnet *dev)
+{
+	u16 rx_ctl;
+	int ret;
+
+	sr_mdio_write(dev->net, dev->mii.phy_id, MII_BMCR, BMCR_RESET);
+	sr_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE,
+		      ADVERTISE_ALL | ADVERTISE_CSMA);
+	mii_nway_restart(&dev->mii);
+
+	ret = sr_write_medium_mode(dev, SR9800_MEDIUM_DEFAULT);
+	if (ret < 0)
+		goto out;
+
+	ret = sr_write_cmd(dev, SR_CMD_WRITE_IPG012,
+				SR9800_IPG0_DEFAULT | SR9800_IPG1_DEFAULT,
+				SR9800_IPG2_DEFAULT, 0, NULL);
+	if (ret < 0) {
+		netdev_dbg(dev->net, "Write IPG,IPG1,IPG2 failed: %d\n", ret);
+		goto out;
+	}
+
+	/* Set RX_CTL to default values with 2k buffer, and enable cactus */
+	ret = sr_write_rx_ctl(dev, SR_DEFAULT_RX_CTL);
+	if (ret < 0)
+		goto out;
+
+	rx_ctl = sr_read_rx_ctl(dev);
+	netdev_dbg(dev->net, "RX_CTL is 0x%04x after all initializations\n",
+		   rx_ctl);
+
+	rx_ctl = sr_read_medium_status(dev);
+	netdev_dbg(dev->net, "Medium Status:0x%04x after all initializations\n",
+		   rx_ctl);
+
+	return 0;
+out:
+	return ret;
+}
+
+static int sr9800_reset(struct usbnet *dev)
+{
+	struct sr_data *data = (struct sr_data *)&dev->data;
+	int ret, embd_phy;
+	u16 rx_ctl;
+
+	ret = sr_write_gpio(dev,
+			SR_GPIO_RSE | SR_GPIO_GPO_2 | SR_GPIO_GPO2EN, 5);
+	if (ret < 0)
+		goto out;
+
+	embd_phy = ((sr_get_phy_addr(dev) & 0x1f) == 0x10 ? 1 : 0);
+
+	ret = sr_write_cmd(dev, SR_CMD_SW_PHY_SELECT, embd_phy, 0, 0, NULL);
+	if (ret < 0) {
+		netdev_dbg(dev->net, "Select PHY #1 failed: %d\n", ret);
+		goto out;
+	}
+
+	ret = sr_sw_reset(dev, SR_SWRESET_IPPD | SR_SWRESET_PRL);
+	if (ret < 0)
+		goto out;
+
+	msleep(150);
+
+	ret = sr_sw_reset(dev, SR_SWRESET_CLEAR);
+	if (ret < 0)
+		goto out;
+
+	msleep(150);
+
+	if (embd_phy) {
+		ret = sr_sw_reset(dev, SR_SWRESET_IPRL);
+		if (ret < 0)
+			goto out;
+	} else {
+		ret = sr_sw_reset(dev, SR_SWRESET_PRTE);
+		if (ret < 0)
+			goto out;
+	}
+
+	msleep(150);
+	rx_ctl = sr_read_rx_ctl(dev);
+	netdev_dbg(dev->net, "RX_CTL is 0x%04x after software reset\n", rx_ctl);
+	ret = sr_write_rx_ctl(dev, 0x0000);
+	if (ret < 0)
+		goto out;
+
+	rx_ctl = sr_read_rx_ctl(dev);
+	netdev_dbg(dev->net, "RX_CTL is 0x%04x setting to 0x0000\n", rx_ctl);
+
+	ret = sr_sw_reset(dev, SR_SWRESET_PRL);
+	if (ret < 0)
+		goto out;
+
+	msleep(150);
+
+	ret = sr_sw_reset(dev, SR_SWRESET_IPRL | SR_SWRESET_PRL);
+	if (ret < 0)
+		goto out;
+
+	msleep(150);
+
+	ret = sr9800_set_default_mode(dev);
+	if (ret < 0)
+		goto out;
+
+	/* Rewrite MAC address */
+	memcpy(data->mac_addr, dev->net->dev_addr, ETH_ALEN);
+	ret = sr_write_cmd(dev, SR_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN,
+							data->mac_addr);
+	if (ret < 0)
+		goto out;
+
+	return 0;
+
+out:
+	return ret;
+}
+
+static const struct net_device_ops sr9800_netdev_ops = {
+	.ndo_open		= usbnet_open,
+	.ndo_stop		= usbnet_stop,
+	.ndo_start_xmit		= usbnet_start_xmit,
+	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_set_mac_address	= sr_set_mac_address,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_do_ioctl		= sr_ioctl,
+	.ndo_set_rx_mode        = sr_set_multicast,
+};
+
+static int sr9800_phy_powerup(struct usbnet *dev)
+{
+	int ret;
+
+	/* set the embedded Ethernet PHY in power-down state */
+	ret = sr_sw_reset(dev, SR_SWRESET_IPPD | SR_SWRESET_IPRL);
+	if (ret < 0) {
+		netdev_err(dev->net, "Failed to power down PHY : %d\n", ret);
+		return ret;
+	}
+	msleep(20);
+
+	/* set the embedded Ethernet PHY in power-up state */
+	ret = sr_sw_reset(dev, SR_SWRESET_IPRL);
+	if (ret < 0) {
+		netdev_err(dev->net, "Failed to reset PHY: %d\n", ret);
+		return ret;
+	}
+	msleep(600);
+
+	/* set the embedded Ethernet PHY in reset state */
+	ret = sr_sw_reset(dev, SR_SWRESET_CLEAR);
+	if (ret < 0) {
+		netdev_err(dev->net, "Failed to power up PHY: %d\n", ret);
+		return ret;
+	}
+	msleep(20);
+
+	/* set the embedded Ethernet PHY in power-up state */
+	ret = sr_sw_reset(dev, SR_SWRESET_IPRL);
+	if (ret < 0) {
+		netdev_err(dev->net, "Failed to reset PHY: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+	struct sr_data *data = (struct sr_data *)&dev->data;
+	u16 led01_mux, led23_mux;
+	int ret, embd_phy;
+	u32 phyid;
+	u16 rx_ctl;
+
+	data->eeprom_len = SR9800_EEPROM_LEN;
+
+	usbnet_get_endpoints(dev, intf);
+
+	/* LED Setting Rule :
+	 * AABB:CCDD
+	 * AA : MFA0(LED0)
+	 * BB : MFA1(LED1)
+	 * CC : MFA2(LED2), Reserved for SR9800
+	 * DD : MFA3(LED3), Reserved for SR9800
+	 */
+	led01_mux = (SR_LED_MUX_LINK_ACTIVE << 8) | SR_LED_MUX_LINK;
+	led23_mux = (SR_LED_MUX_LINK_ACTIVE << 8) | SR_LED_MUX_TX_ACTIVE;
+	ret = sr_write_cmd(dev, SR_CMD_LED_MUX, led01_mux, led23_mux, 0, NULL);
+	if (ret < 0) {
+			netdev_err(dev->net, "set LINK LED failed : %d\n", ret);
+			goto out;
+	}
+
+	/* Get the MAC address */
+	ret = sr_read_cmd(dev, SR_CMD_READ_NODE_ID, 0, 0, ETH_ALEN,
+			  dev->net->dev_addr);
+	if (ret < 0) {
+		netdev_dbg(dev->net, "Failed to read MAC address: %d\n", ret);
+		return ret;
+	}
+	netdev_dbg(dev->net, "mac addr : %pM\n", dev->net->dev_addr);
+
+	/* Initialize MII structure */
+	dev->mii.dev = dev->net;
+	dev->mii.mdio_read = sr_mdio_read;
+	dev->mii.mdio_write = sr_mdio_write;
+	dev->mii.phy_id_mask = 0x1f;
+	dev->mii.reg_num_mask = 0x1f;
+	dev->mii.phy_id = sr_get_phy_addr(dev);
+
+	dev->net->netdev_ops = &sr9800_netdev_ops;
+	dev->net->ethtool_ops = &sr9800_ethtool_ops;
+
+	embd_phy = ((dev->mii.phy_id & 0x1f) == 0x10 ? 1 : 0);
+	/* Reset the PHY to normal operation mode */
+	ret = sr_write_cmd(dev, SR_CMD_SW_PHY_SELECT, embd_phy, 0, 0, NULL);
+	if (ret < 0) {
+		netdev_dbg(dev->net, "Select PHY #1 failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Init PHY routine */
+	ret = sr9800_phy_powerup(dev);
+	if (ret < 0)
+		goto out;
+
+	rx_ctl = sr_read_rx_ctl(dev);
+	netdev_dbg(dev->net, "RX_CTL is 0x%04x after software reset\n", rx_ctl);
+	ret = sr_write_rx_ctl(dev, 0x0000);
+	if (ret < 0)
+		goto out;
+
+	rx_ctl = sr_read_rx_ctl(dev);
+	netdev_dbg(dev->net, "RX_CTL is 0x%04x setting to 0x0000\n", rx_ctl);
+
+	/* Read PHYID register *AFTER* the PHY was reset properly */
+	phyid = sr_get_phyid(dev);
+	netdev_dbg(dev->net, "PHYID=0x%08x\n", phyid);
+
+	/* medium mode setting */
+	ret = sr9800_set_default_mode(dev);
+	if (ret < 0)
+		goto out;
+
+	if (dev->udev->speed == USB_SPEED_HIGH) {
+		ret = sr_write_cmd(dev, SR_CMD_BULKIN_SIZE,
+			SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_4K].byte_cnt,
+			SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_4K].threshold,
+			0, NULL);
+		if (ret < 0) {
+			netdev_err(dev->net, "Reset RX_CTL failed: %d\n", ret);
+			goto out;
+		}
+		dev->rx_urb_size =
+			SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_4K].size;
+	} else {
+		ret = sr_write_cmd(dev, SR_CMD_BULKIN_SIZE,
+			SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_2K].byte_cnt,
+			SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_2K].threshold,
+			0, NULL);
+		if (ret < 0) {
+			netdev_err(dev->net, "Reset RX_CTL failed: %d\n", ret);
+			goto out;
+		}
+		dev->rx_urb_size =
+			SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_2K].size;
+	}
+	netdev_dbg(dev->net, "%s : setting rx_urb_size with : %zu\n", __func__,
+		   dev->rx_urb_size);
+	return 0;
+
+out:
+	return ret;
+}
+
+static const struct driver_info sr9800_driver_info = {
+	.description	= "CoreChip SR9800 USB 2.0 Ethernet",
+	.bind		= sr9800_bind,
+	.status		= sr_status,
+	.link_reset	= sr9800_link_reset,
+	.reset		= sr9800_reset,
+	.flags		= DRIVER_FLAG,
+	.rx_fixup	= sr_rx_fixup,
+	.tx_fixup	= sr_tx_fixup,
+};
+
+static const struct usb_device_id	products[] = {
+	{
+		USB_DEVICE(0x0fe6, 0x9800),	/* SR9800 Device  */
+		.driver_info = (unsigned long) &sr9800_driver_info,
+	},
+	{},		/* END */
+};
+
+MODULE_DEVICE_TABLE(usb, products);
+
+static struct usb_driver sr_driver = {
+	.name		= DRIVER_NAME,
+	.id_table	= products,
+	.probe		= usbnet_probe,
+	.suspend	= usbnet_suspend,
+	.resume		= usbnet_resume,
+	.disconnect	= usbnet_disconnect,
+	.supports_autosuspend = 1,
+};
+
+module_usb_driver(sr_driver);
+
+MODULE_AUTHOR("Liu Junliang <liujunliang_ljl@163.com");
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_DESCRIPTION("SR9800 USB 2.0 USB2NET Dev : http://www.corechip-sz.com");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/usb/sr9800.h b/drivers/net/usb/sr9800.h
new file mode 100644
index 0000000..18f6702
--- /dev/null
+++ b/drivers/net/usb/sr9800.h
@@ -0,0 +1,202 @@
+/* CoreChip-sz SR9800 one chip USB 2.0 Ethernet Devices
+ *
+ * Author : Liu Junliang <liujunliang_ljl@163.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef	_SR9800_H
+#define	_SR9800_H
+
+/* SR9800 spec. command table on Linux Platform */
+
+/* command : Software Station Management Control Reg */
+#define SR_CMD_SET_SW_MII		0x06
+/* command : PHY Read Reg */
+#define SR_CMD_READ_MII_REG		0x07
+/* command : PHY Write Reg */
+#define SR_CMD_WRITE_MII_REG		0x08
+/* command : Hardware Station Management Control Reg */
+#define SR_CMD_SET_HW_MII		0x0a
+/* command : SROM Read Reg */
+#define SR_CMD_READ_EEPROM		0x0b
+/* command : SROM Write Reg */
+#define SR_CMD_WRITE_EEPROM		0x0c
+/* command : SROM Write Enable Reg */
+#define SR_CMD_WRITE_ENABLE		0x0d
+/* command : SROM Write Disable Reg */
+#define SR_CMD_WRITE_DISABLE		0x0e
+/* command : RX Control Read Reg */
+#define SR_CMD_READ_RX_CTL		0x0f
+#define		SR_RX_CTL_PRO			(1 << 0)
+#define		SR_RX_CTL_AMALL			(1 << 1)
+#define		SR_RX_CTL_SEP			(1 << 2)
+#define		SR_RX_CTL_AB			(1 << 3)
+#define		SR_RX_CTL_AM			(1 << 4)
+#define		SR_RX_CTL_AP			(1 << 5)
+#define		SR_RX_CTL_ARP			(1 << 6)
+#define		SR_RX_CTL_SO			(1 << 7)
+#define		SR_RX_CTL_RH1M			(1 << 8)
+#define		SR_RX_CTL_RH2M			(1 << 9)
+#define		SR_RX_CTL_RH3M			(1 << 10)
+/* command : RX Control Write Reg */
+#define SR_CMD_WRITE_RX_CTL		0x10
+/* command : IPG0/IPG1/IPG2 Control Read Reg */
+#define SR_CMD_READ_IPG012		0x11
+/* command : IPG0/IPG1/IPG2 Control Write Reg */
+#define SR_CMD_WRITE_IPG012		0x12
+/* command : Node ID Read Reg */
+#define SR_CMD_READ_NODE_ID		0x13
+/* command : Node ID Write Reg */
+#define SR_CMD_WRITE_NODE_ID		0x14
+/* command : Multicast Filter Array Read Reg */
+#define	SR_CMD_READ_MULTI_FILTER	0x15
+/* command : Multicast Filter Array Write Reg */
+#define SR_CMD_WRITE_MULTI_FILTER	0x16
+/* command : Eth/HomePNA PHY Address Reg */
+#define SR_CMD_READ_PHY_ID		0x19
+/* command : Medium Status Read Reg */
+#define SR_CMD_READ_MEDIUM_STATUS	0x1a
+#define		SR_MONITOR_LINK			(1 << 1)
+#define		SR_MONITOR_MAGIC		(1 << 2)
+#define		SR_MONITOR_HSFS			(1 << 4)
+/* command : Medium Status Write Reg */
+#define SR_CMD_WRITE_MEDIUM_MODE	0x1b
+#define		SR_MEDIUM_GM			(1 << 0)
+#define		SR_MEDIUM_FD			(1 << 1)
+#define		SR_MEDIUM_AC			(1 << 2)
+#define		SR_MEDIUM_ENCK			(1 << 3)
+#define		SR_MEDIUM_RFC			(1 << 4)
+#define		SR_MEDIUM_TFC			(1 << 5)
+#define		SR_MEDIUM_JFE			(1 << 6)
+#define		SR_MEDIUM_PF			(1 << 7)
+#define		SR_MEDIUM_RE			(1 << 8)
+#define		SR_MEDIUM_PS			(1 << 9)
+#define		SR_MEDIUM_RSV			(1 << 10)
+#define		SR_MEDIUM_SBP			(1 << 11)
+#define		SR_MEDIUM_SM			(1 << 12)
+/* command : Monitor Mode Status Read Reg */
+#define SR_CMD_READ_MONITOR_MODE	0x1c
+/* command : Monitor Mode Status Write Reg */
+#define SR_CMD_WRITE_MONITOR_MODE	0x1d
+/* command : GPIO Status Read Reg */
+#define SR_CMD_READ_GPIOS		0x1e
+#define		SR_GPIO_GPO0EN		(1 << 0) /* GPIO0 Output enable */
+#define		SR_GPIO_GPO_0		(1 << 1) /* GPIO0 Output value */
+#define		SR_GPIO_GPO1EN		(1 << 2) /* GPIO1 Output enable */
+#define		SR_GPIO_GPO_1		(1 << 3) /* GPIO1 Output value */
+#define		SR_GPIO_GPO2EN		(1 << 4) /* GPIO2 Output enable */
+#define		SR_GPIO_GPO_2		(1 << 5) /* GPIO2 Output value */
+#define		SR_GPIO_RESERVED	(1 << 6) /* Reserved */
+#define		SR_GPIO_RSE		(1 << 7) /* Reload serial EEPROM */
+/* command : GPIO Status Write Reg */
+#define SR_CMD_WRITE_GPIOS		0x1f
+/* command : Eth PHY Power and Reset Control Reg */
+#define SR_CMD_SW_RESET			0x20
+#define		SR_SWRESET_CLEAR		0x00
+#define		SR_SWRESET_RR			(1 << 0)
+#define		SR_SWRESET_RT			(1 << 1)
+#define		SR_SWRESET_PRTE			(1 << 2)
+#define		SR_SWRESET_PRL			(1 << 3)
+#define		SR_SWRESET_BZ			(1 << 4)
+#define		SR_SWRESET_IPRL			(1 << 5)
+#define		SR_SWRESET_IPPD			(1 << 6)
+/* command : Software Interface Selection Status Read Reg */
+#define SR_CMD_SW_PHY_STATUS		0x21
+/* command : Software Interface Selection Status Write Reg */
+#define SR_CMD_SW_PHY_SELECT		0x22
+/* command : BULK in Buffer Size Reg */
+#define	SR_CMD_BULKIN_SIZE		0x2A
+/* command : LED_MUX Control Reg */
+#define	SR_CMD_LED_MUX			0x70
+#define		SR_LED_MUX_TX_ACTIVE		(1 << 0)
+#define		SR_LED_MUX_RX_ACTIVE		(1 << 1)
+#define		SR_LED_MUX_COLLISION		(1 << 2)
+#define		SR_LED_MUX_DUP_COL		(1 << 3)
+#define		SR_LED_MUX_DUP			(1 << 4)
+#define		SR_LED_MUX_SPEED		(1 << 5)
+#define		SR_LED_MUX_LINK_ACTIVE		(1 << 6)
+#define		SR_LED_MUX_LINK			(1 << 7)
+
+/* Register Access Flags */
+#define SR_REQ_RD_REG   (USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE)
+#define SR_REQ_WR_REG   (USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE)
+
+/* Multicast Filter Array size & Max Number */
+#define	SR_MCAST_FILTER_SIZE		8
+#define	SR_MAX_MCAST			64
+
+/* IPG0/1/2 Default Value */
+#define	SR9800_IPG0_DEFAULT		0x15
+#define	SR9800_IPG1_DEFAULT		0x0c
+#define	SR9800_IPG2_DEFAULT		0x12
+
+/* Medium Status Default Mode */
+#define SR9800_MEDIUM_DEFAULT	\
+	(SR_MEDIUM_FD | SR_MEDIUM_RFC | \
+	 SR_MEDIUM_TFC | SR_MEDIUM_PS | \
+	 SR_MEDIUM_AC | SR_MEDIUM_RE)
+
+/* RX Control Default Setting */
+#define SR_DEFAULT_RX_CTL	\
+	(SR_RX_CTL_SO | SR_RX_CTL_AB | SR_RX_CTL_RH1M)
+
+/* EEPROM Magic Number & EEPROM Size */
+#define SR_EEPROM_MAGIC			0xdeadbeef
+#define SR9800_EEPROM_LEN		0xff
+
+/* SR9800 Driver Version and Driver Name */
+#define DRIVER_VERSION			"11-Nov-2013"
+#define DRIVER_NAME			"CoreChips"
+#define	DRIVER_FLAG		\
+	(FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |  FLAG_MULTI_PACKET)
+
+/* SR9800 BULKIN Buffer Size */
+#define SR9800_MAX_BULKIN_2K		0
+#define SR9800_MAX_BULKIN_4K		1
+#define SR9800_MAX_BULKIN_6K		2
+#define SR9800_MAX_BULKIN_8K		3
+#define SR9800_MAX_BULKIN_16K		4
+#define SR9800_MAX_BULKIN_20K		5
+#define SR9800_MAX_BULKIN_24K		6
+#define SR9800_MAX_BULKIN_32K		7
+
+struct {unsigned short size, byte_cnt, threshold; } SR9800_BULKIN_SIZE[] = {
+	/* 2k */
+	{2048, 0x8000, 0x8001},
+	/* 4k */
+	{4096, 0x8100, 0x8147},
+	/* 6k */
+	{6144, 0x8200, 0x81EB},
+	/* 8k */
+	{8192, 0x8300, 0x83D7},
+	/* 16 */
+	{16384, 0x8400, 0x851E},
+	/* 20k */
+	{20480, 0x8500, 0x8666},
+	/* 24k */
+	{24576, 0x8600, 0x87AE},
+	/* 32k */
+	{32768, 0x8700, 0x8A3D},
+};
+
+/* This structure cannot exceed sizeof(unsigned long [5]) AKA 20 bytes */
+struct sr_data {
+	u8 multi_filter[SR_MCAST_FILTER_SIZE];
+	u8 mac_addr[ETH_ALEN];
+	u8 phymode;
+	u8 ledmode;
+	u8 eeprom_len;
+};
+
+struct sr9800_int_data {
+	__le16 res1;
+	u8 link;
+	__le16 res2;
+	u8 status;
+	__le16 res3;
+} __packed;
+
+#endif	/* _SR9800_H */
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 4671da7..f9e96c4 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -542,17 +542,19 @@
 	}
 	// else network stack removes extra byte if we forced a short packet
 
-	if (skb->len) {
-		/* all data was already cloned from skb inside the driver */
-		if (dev->driver_info->flags & FLAG_MULTI_PACKET)
-			dev_kfree_skb_any(skb);
-		else
-			usbnet_skb_return(dev, skb);
+	/* all data was already cloned from skb inside the driver */
+	if (dev->driver_info->flags & FLAG_MULTI_PACKET)
+		goto done;
+
+	if (skb->len < ETH_HLEN) {
+		dev->net->stats.rx_errors++;
+		dev->net->stats.rx_length_errors++;
+		netif_dbg(dev, rx_err, dev->net, "rx length %d\n", skb->len);
+	} else {
+		usbnet_skb_return(dev, skb);
 		return;
 	}
 
-	netif_dbg(dev, rx_err, dev->net, "drop\n");
-	dev->net->stats.rx_errors++;
 done:
 	skb_queue_tail(&dev->done, skb);
 }
@@ -574,13 +576,6 @@
 	switch (urb_status) {
 	/* success */
 	case 0:
-		if (skb->len < dev->net->hard_header_len) {
-			state = rx_cleanup;
-			dev->net->stats.rx_errors++;
-			dev->net->stats.rx_length_errors++;
-			netif_dbg(dev, rx_err, dev->net,
-				  "rx length %d\n", skb->len);
-		}
 		break;
 
 	/* stalls need manual reset. this is rare ... except that
@@ -757,14 +752,12 @@
 // precondition: never called in_interrupt
 static void usbnet_terminate_urbs(struct usbnet *dev)
 {
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(unlink_wakeup);
 	DECLARE_WAITQUEUE(wait, current);
 	int temp;
 
 	/* ensure there are no more active urbs */
-	add_wait_queue(&unlink_wakeup, &wait);
+	add_wait_queue(&dev->wait, &wait);
 	set_current_state(TASK_UNINTERRUPTIBLE);
-	dev->wait = &unlink_wakeup;
 	temp = unlink_urbs(dev, &dev->txq) +
 		unlink_urbs(dev, &dev->rxq);
 
@@ -778,15 +771,14 @@
 				  "waited for %d urb completions\n", temp);
 	}
 	set_current_state(TASK_RUNNING);
-	dev->wait = NULL;
-	remove_wait_queue(&unlink_wakeup, &wait);
+	remove_wait_queue(&dev->wait, &wait);
 }
 
 int usbnet_stop (struct net_device *net)
 {
 	struct usbnet		*dev = netdev_priv(net);
 	struct driver_info	*info = dev->driver_info;
-	int			retval;
+	int			retval, pm;
 
 	clear_bit(EVENT_DEV_OPEN, &dev->flags);
 	netif_stop_queue (net);
@@ -796,6 +788,8 @@
 		   net->stats.rx_packets, net->stats.tx_packets,
 		   net->stats.rx_errors, net->stats.tx_errors);
 
+	/* to not race resume */
+	pm = usb_autopm_get_interface(dev->intf);
 	/* allow minidriver to stop correctly (wireless devices to turn off
 	 * radio etc) */
 	if (info->stop) {
@@ -822,6 +816,9 @@
 	dev->flags = 0;
 	del_timer_sync (&dev->delay);
 	tasklet_kill (&dev->bh);
+	if (!pm)
+		usb_autopm_put_interface(dev->intf);
+
 	if (info->manage_power &&
 	    !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags))
 		info->manage_power(dev, 0);
@@ -1442,11 +1439,12 @@
 	/* restart RX again after disabling due to high error rate */
 	clear_bit(EVENT_RX_KILL, &dev->flags);
 
-	// waiting for all pending urbs to complete?
-	if (dev->wait) {
-		if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) {
-			wake_up (dev->wait);
-		}
+	/* waiting for all pending urbs to complete?
+	 * only then can we forgo submitting anew
+	 */
+	if (waitqueue_active(&dev->wait)) {
+		if (dev->txq.qlen + dev->rxq.qlen + dev->done.qlen == 0)
+			wake_up_all(&dev->wait);
 
 	// or are we maybe short a few urbs?
 	} else if (netif_running (dev->net) &&
@@ -1585,6 +1583,7 @@
 	dev->driver_name = name;
 	dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
 				| NETIF_MSG_PROBE | NETIF_MSG_LINK);
+	init_waitqueue_head(&dev->wait);
 	skb_queue_head_init (&dev->rxq);
 	skb_queue_head_init (&dev->txq);
 	skb_queue_head_init (&dev->done);
@@ -1796,9 +1795,10 @@
 		spin_unlock_irq(&dev->txq.lock);
 
 		if (test_bit(EVENT_DEV_OPEN, &dev->flags)) {
-			/* handle remote wakeup ASAP */
-			if (!dev->wait &&
-				netif_device_present(dev->net) &&
+			/* handle remote wakeup ASAP
+			 * we cannot race against stop
+			 */
+			if (netif_device_present(dev->net) &&
 				!timer_pending(&dev->delay) &&
 				!test_bit(EVENT_RX_HALT, &dev->flags))
 					rx_alloc_submit(dev, GFP_NOIO);
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 2ec2041..c0e7c64 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -285,7 +285,11 @@
 	dev->ethtool_ops = &veth_ethtool_ops;
 	dev->features |= NETIF_F_LLTX;
 	dev->features |= VETH_FEATURES;
-	dev->vlan_features = dev->features;
+	dev->vlan_features = dev->features &
+			     ~(NETIF_F_HW_VLAN_CTAG_TX |
+			       NETIF_F_HW_VLAN_STAG_TX |
+			       NETIF_F_HW_VLAN_CTAG_RX |
+			       NETIF_F_HW_VLAN_STAG_RX);
 	dev->destructor = veth_dev_free;
 
 	dev->hw_features = VETH_FEATURES;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d75f8ed..841b608 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -671,8 +671,7 @@
 		if (err)
 			break;
 	} while (rq->vq->num_free);
-	if (unlikely(!virtqueue_kick(rq->vq)))
-		return false;
+	virtqueue_kick(rq->vq);
 	return !oom;
 }
 
@@ -877,7 +876,7 @@
 	err = xmit_skb(sq, skb);
 
 	/* This should not happen! */
-	if (unlikely(err) || unlikely(!virtqueue_kick(sq->vq))) {
+	if (unlikely(err)) {
 		dev->stats.tx_fifo_errors++;
 		if (net_ratelimit())
 			dev_warn(&dev->dev,
@@ -886,6 +885,7 @@
 		kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
+	virtqueue_kick(sq->vq);
 
 	/* Don't wait up for transmitted skbs to be freed. */
 	skb_orphan(skb);
@@ -1711,7 +1711,8 @@
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
 	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
-	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
 		vi->big_packets = true;
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 3be786f..0fa3b44 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1762,11 +1762,20 @@
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 
-	if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE)
-		vmxnet3_disable_all_intrs(adapter);
-
-	vmxnet3_do_poll(adapter, adapter->rx_queue[0].rx_ring[0].size);
-	vmxnet3_enable_all_intrs(adapter);
+	switch (adapter->intr.type) {
+#ifdef CONFIG_PCI_MSI
+	case VMXNET3_IT_MSIX: {
+		int i;
+		for (i = 0; i < adapter->num_rx_queues; i++)
+			vmxnet3_msix_rx(0, &adapter->rx_queue[i]);
+		break;
+	}
+#endif
+	case VMXNET3_IT_MSI:
+	default:
+		vmxnet3_intr(0, adapter->netdev);
+		break;
+	}
 
 }
 #endif	/* CONFIG_NET_POLL_CONTROLLER */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 026a313..1236812 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -469,7 +469,6 @@
 /* Look up Ethernet address in forwarding table */
 static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan,
 					const u8 *mac)
-
 {
 	struct hlist_head *head = vxlan_fdb_head(vxlan, mac);
 	struct vxlan_fdb *f;
@@ -596,10 +595,8 @@
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
-		goto found;
 	}
 
-found:
 	type = eh->h_proto;
 
 	rcu_read_lock();
@@ -1321,6 +1318,9 @@
 
 		neigh_release(n);
 
+		if (reply == NULL)
+			goto out;
+
 		skb_reset_mac_header(reply);
 		__skb_pull(reply, skb_network_offset(reply));
 		reply->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1342,15 +1342,103 @@
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
+
+static struct sk_buff *vxlan_na_create(struct sk_buff *request,
+	struct neighbour *n, bool isrouter)
+{
+	struct net_device *dev = request->dev;
+	struct sk_buff *reply;
+	struct nd_msg *ns, *na;
+	struct ipv6hdr *pip6;
+	u8 *daddr;
+	int na_olen = 8; /* opt hdr + ETH_ALEN for target */
+	int ns_olen;
+	int i, len;
+
+	if (dev == NULL)
+		return NULL;
+
+	len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
+		sizeof(*na) + na_olen + dev->needed_tailroom;
+	reply = alloc_skb(len, GFP_ATOMIC);
+	if (reply == NULL)
+		return NULL;
+
+	reply->protocol = htons(ETH_P_IPV6);
+	reply->dev = dev;
+	skb_reserve(reply, LL_RESERVED_SPACE(request->dev));
+	skb_push(reply, sizeof(struct ethhdr));
+	skb_set_mac_header(reply, 0);
+
+	ns = (struct nd_msg *)skb_transport_header(request);
+
+	daddr = eth_hdr(request)->h_source;
+	ns_olen = request->len - skb_transport_offset(request) - sizeof(*ns);
+	for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
+		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
+			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+			break;
+		}
+	}
+
+	/* Ethernet header */
+	ether_addr_copy(eth_hdr(reply)->h_dest, daddr);
+	ether_addr_copy(eth_hdr(reply)->h_source, n->ha);
+	eth_hdr(reply)->h_proto = htons(ETH_P_IPV6);
+	reply->protocol = htons(ETH_P_IPV6);
+
+	skb_pull(reply, sizeof(struct ethhdr));
+	skb_set_network_header(reply, 0);
+	skb_put(reply, sizeof(struct ipv6hdr));
+
+	/* IPv6 header */
+
+	pip6 = ipv6_hdr(reply);
+	memset(pip6, 0, sizeof(struct ipv6hdr));
+	pip6->version = 6;
+	pip6->priority = ipv6_hdr(request)->priority;
+	pip6->nexthdr = IPPROTO_ICMPV6;
+	pip6->hop_limit = 255;
+	pip6->daddr = ipv6_hdr(request)->saddr;
+	pip6->saddr = *(struct in6_addr *)n->primary_key;
+
+	skb_pull(reply, sizeof(struct ipv6hdr));
+	skb_set_transport_header(reply, 0);
+
+	na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen);
+
+	/* Neighbor Advertisement */
+	memset(na, 0, sizeof(*na)+na_olen);
+	na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
+	na->icmph.icmp6_router = isrouter;
+	na->icmph.icmp6_override = 1;
+	na->icmph.icmp6_solicited = 1;
+	na->target = ns->target;
+	ether_addr_copy(&na->opt[2], n->ha);
+	na->opt[0] = ND_OPT_TARGET_LL_ADDR;
+	na->opt[1] = na_olen >> 3;
+
+	na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr,
+		&pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6,
+		csum_partial(na, sizeof(*na)+na_olen, 0));
+
+	pip6->payload_len = htons(sizeof(*na)+na_olen);
+
+	skb_push(reply, sizeof(struct ipv6hdr));
+
+	reply->ip_summed = CHECKSUM_UNNECESSARY;
+
+	return reply;
+}
+
 static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct neighbour *n;
-	union vxlan_addr ipa;
+	struct nd_msg *msg;
 	const struct ipv6hdr *iphdr;
 	const struct in6_addr *saddr, *daddr;
-	struct nd_msg *msg;
-	struct inet6_dev *in6_dev = NULL;
+	struct neighbour *n;
+	struct inet6_dev *in6_dev;
 
 	in6_dev = __in6_dev_get(dev);
 	if (!in6_dev)
@@ -1363,19 +1451,20 @@
 	saddr = &iphdr->saddr;
 	daddr = &iphdr->daddr;
 
-	if (ipv6_addr_loopback(daddr) ||
-	    ipv6_addr_is_multicast(daddr))
-		goto out;
-
 	msg = (struct nd_msg *)skb_transport_header(skb);
 	if (msg->icmph.icmp6_code != 0 ||
 	    msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
 		goto out;
 
-	n = neigh_lookup(ipv6_stub->nd_tbl, daddr, dev);
+	if (ipv6_addr_loopback(daddr) ||
+	    ipv6_addr_is_multicast(&msg->target))
+		goto out;
+
+	n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev);
 
 	if (n) {
 		struct vxlan_fdb *f;
+		struct sk_buff *reply;
 
 		if (!(n->nud_state & NUD_CONNECTED)) {
 			neigh_release(n);
@@ -1389,13 +1478,23 @@
 			goto out;
 		}
 
-		ipv6_stub->ndisc_send_na(dev, n, saddr, &msg->target,
-					 !!in6_dev->cnf.forwarding,
-					 true, false, false);
+		reply = vxlan_na_create(skb, n,
+					!!(f ? f->flags & NTF_ROUTER : 0));
+
 		neigh_release(n);
+
+		if (reply == NULL)
+			goto out;
+
+		if (netif_rx_ni(reply) == NET_RX_DROP)
+			dev->stats.rx_dropped++;
+
 	} else if (vxlan->flags & VXLAN_F_L3MISS) {
-		ipa.sin6.sin6_addr = *daddr;
-		ipa.sa.sa_family = AF_INET6;
+		union vxlan_addr ipa = {
+			.sin6.sin6_addr = msg->target,
+			.sa.sa_family = AF_INET6,
+		};
+
 		vxlan_ip_miss(dev, &ipa);
 	}
 
diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index 0d1c759..19f7cb2 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -71,12 +71,9 @@
 		       const void *saddr, unsigned len)
 {
 	struct frhdr		hdr;
-	struct dlci_local	*dlp;
 	unsigned int		hlen;
 	char			*dest;
 
-	dlp = netdev_priv(dev);
-
 	hdr.control = FRAD_I_UI;
 	switch (type)
 	{
@@ -107,11 +104,9 @@
 
 static void dlci_receive(struct sk_buff *skb, struct net_device *dev)
 {
-	struct dlci_local *dlp;
 	struct frhdr		*hdr;
 	int					process, header;
 
-	dlp = netdev_priv(dev);
 	if (!pskb_may_pull(skb, sizeof(*hdr))) {
 		netdev_notice(dev, "invalid data no header\n");
 		dev->stats.rx_errors++;
diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c
index 8aa20df..507d9a9 100644
--- a/drivers/net/wireless/ath/ar5523/ar5523.c
+++ b/drivers/net/wireless/ath/ar5523/ar5523.c
@@ -1764,7 +1764,7 @@
 	AR5523_DEVICE_UG(0x07d1, 0x3a07),	/* D-Link / WUA-2340 rev A1 */
 	AR5523_DEVICE_UG(0x1690, 0x0712),	/* Gigaset / AR5523 */
 	AR5523_DEVICE_UG(0x1690, 0x0710),	/* Gigaset / SMCWUSBTG */
-	AR5523_DEVICE_UG(0x129b, 0x160c),	/* Gigaset / USB stick 108
+	AR5523_DEVICE_UG(0x129b, 0x160b),	/* Gigaset / USB stick 108
 						   (CyberTAN Technology) */
 	AR5523_DEVICE_UG(0x16ab, 0x7801),	/* Globalsun / AR5523_1 */
 	AR5523_DEVICE_UX(0x16ab, 0x7811),	/* Globalsun / AR5523_2 */
diff --git a/drivers/net/wireless/ath/ath5k/phy.c b/drivers/net/wireless/ath/ath5k/phy.c
index d6bc7cb..1a2973b 100644
--- a/drivers/net/wireless/ath/ath5k/phy.c
+++ b/drivers/net/wireless/ath/ath5k/phy.c
@@ -110,7 +110,7 @@
 		ath5k_hw_reg_write(ah, 0x00010000, AR5K_PHY(0x20));
 
 	if (ah->ah_version == AR5K_AR5210) {
-		srev = ath5k_hw_reg_read(ah, AR5K_PHY(256) >> 28) & 0xf;
+		srev = (ath5k_hw_reg_read(ah, AR5K_PHY(256)) >> 28) & 0xf;
 		ret = (u16)ath5k_hw_bitswap(srev, 4) + 1;
 	} else {
 		srev = (ath5k_hw_reg_read(ah, AR5K_PHY(0x100)) >> 24) & 0xff;
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index 25243cb..b8daff7 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -5065,6 +5065,10 @@
 			break;
 		}
 	}
+
+	if (is2GHz && !twiceMaxEdgePower)
+		twiceMaxEdgePower = 60;
+
 	return twiceMaxEdgePower;
 }
 
diff --git a/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h b/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
index 1cc1356..1b6b4d0 100644
--- a/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
@@ -57,7 +57,7 @@
 	{0x00009e14, 0x37b95d5e, 0x37b9605e, 0x3236605e, 0x32365a5e},
 	{0x00009e18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x00009e1c, 0x0001cf9c, 0x0001cf9c, 0x00021f9c, 0x00021f9c},
-	{0x00009e20, 0x000003b5, 0x000003b5, 0x000003ce, 0x000003ce},
+	{0x00009e20, 0x000003a5, 0x000003a5, 0x000003a5, 0x000003a5},
 	{0x00009e2c, 0x0000001c, 0x0000001c, 0x00000021, 0x00000021},
 	{0x00009e3c, 0xcf946220, 0xcf946220, 0xcfd5c782, 0xcfd5c282},
 	{0x00009e44, 0x62321e27, 0x62321e27, 0xfe291e27, 0xfe291e27},
@@ -96,7 +96,7 @@
 	{0x0000ae04, 0x001c0000, 0x001c0000, 0x001c0000, 0x00100000},
 	{0x0000ae18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x0000ae1c, 0x0000019c, 0x0000019c, 0x0000019c, 0x0000019c},
-	{0x0000ae20, 0x000001b5, 0x000001b5, 0x000001ce, 0x000001ce},
+	{0x0000ae20, 0x000001a6, 0x000001a6, 0x000001aa, 0x000001aa},
 	{0x0000b284, 0x00000000, 0x00000000, 0x00000550, 0x00000550},
 };
 
diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h
index 58da346..99a2031 100644
--- a/drivers/net/wireless/ath/ath9k/htc.h
+++ b/drivers/net/wireless/ath/ath9k/htc.h
@@ -262,6 +262,8 @@
 struct ath9k_htc_sta {
 	u8 index;
 	enum tid_aggr_state tid_state[ATH9K_HTC_MAX_TID];
+	struct work_struct rc_update_work;
+	struct ath9k_htc_priv *htc_priv;
 };
 
 #define ATH9K_HTC_RXBUF 256
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index f4e1de2..c57d6b8 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -34,6 +34,10 @@
 module_param_named(btcoex_enable, ath9k_htc_btcoex_enable, int, 0444);
 MODULE_PARM_DESC(btcoex_enable, "Enable wifi-BT coexistence");
 
+static int ath9k_ps_enable;
+module_param_named(ps_enable, ath9k_ps_enable, int, 0444);
+MODULE_PARM_DESC(ps_enable, "Enable WLAN PowerSave");
+
 #define CHAN2G(_freq, _idx)  { \
 	.center_freq = (_freq), \
 	.hw_value = (_idx), \
@@ -725,12 +729,14 @@
 		IEEE80211_HW_SPECTRUM_MGMT |
 		IEEE80211_HW_HAS_RATE_CONTROL |
 		IEEE80211_HW_RX_INCLUDES_FCS |
-		IEEE80211_HW_SUPPORTS_PS |
 		IEEE80211_HW_PS_NULLFUNC_STACK |
 		IEEE80211_HW_REPORTS_TX_ACK_STATUS |
 		IEEE80211_HW_MFP_CAPABLE |
 		IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING;
 
+	if (ath9k_ps_enable)
+		hw->flags |= IEEE80211_HW_SUPPORTS_PS;
+
 	hw->wiphy->interface_modes =
 		BIT(NL80211_IFTYPE_STATION) |
 		BIT(NL80211_IFTYPE_ADHOC) |
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 608d739..c9254a6 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -1270,18 +1270,50 @@
 	mutex_unlock(&priv->mutex);
 }
 
+static void ath9k_htc_sta_rc_update_work(struct work_struct *work)
+{
+	struct ath9k_htc_sta *ista =
+	    container_of(work, struct ath9k_htc_sta, rc_update_work);
+	struct ieee80211_sta *sta =
+	    container_of((void *)ista, struct ieee80211_sta, drv_priv);
+	struct ath9k_htc_priv *priv = ista->htc_priv;
+	struct ath_common *common = ath9k_hw_common(priv->ah);
+	struct ath9k_htc_target_rate trate;
+
+	mutex_lock(&priv->mutex);
+	ath9k_htc_ps_wakeup(priv);
+
+	memset(&trate, 0, sizeof(struct ath9k_htc_target_rate));
+	ath9k_htc_setup_rate(priv, sta, &trate);
+	if (!ath9k_htc_send_rate_cmd(priv, &trate))
+		ath_dbg(common, CONFIG,
+			"Supported rates for sta: %pM updated, rate caps: 0x%X\n",
+			sta->addr, be32_to_cpu(trate.capflags));
+	else
+		ath_dbg(common, CONFIG,
+			"Unable to update supported rates for sta: %pM\n",
+			sta->addr);
+
+	ath9k_htc_ps_restore(priv);
+	mutex_unlock(&priv->mutex);
+}
+
 static int ath9k_htc_sta_add(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif,
 			     struct ieee80211_sta *sta)
 {
 	struct ath9k_htc_priv *priv = hw->priv;
+	struct ath9k_htc_sta *ista = (struct ath9k_htc_sta *) sta->drv_priv;
 	int ret;
 
 	mutex_lock(&priv->mutex);
 	ath9k_htc_ps_wakeup(priv);
 	ret = ath9k_htc_add_station(priv, vif, sta);
-	if (!ret)
+	if (!ret) {
+		INIT_WORK(&ista->rc_update_work, ath9k_htc_sta_rc_update_work);
+		ista->htc_priv = priv;
 		ath9k_htc_init_rate(priv, sta);
+	}
 	ath9k_htc_ps_restore(priv);
 	mutex_unlock(&priv->mutex);
 
@@ -1293,12 +1325,13 @@
 				struct ieee80211_sta *sta)
 {
 	struct ath9k_htc_priv *priv = hw->priv;
-	struct ath9k_htc_sta *ista;
+	struct ath9k_htc_sta *ista = (struct ath9k_htc_sta *) sta->drv_priv;
 	int ret;
 
+	cancel_work_sync(&ista->rc_update_work);
+
 	mutex_lock(&priv->mutex);
 	ath9k_htc_ps_wakeup(priv);
-	ista = (struct ath9k_htc_sta *) sta->drv_priv;
 	htc_sta_drain(priv->htc, ista->index);
 	ret = ath9k_htc_remove_station(priv, vif, sta);
 	ath9k_htc_ps_restore(priv);
@@ -1311,28 +1344,12 @@
 				    struct ieee80211_vif *vif,
 				    struct ieee80211_sta *sta, u32 changed)
 {
-	struct ath9k_htc_priv *priv = hw->priv;
-	struct ath_common *common = ath9k_hw_common(priv->ah);
-	struct ath9k_htc_target_rate trate;
+	struct ath9k_htc_sta *ista = (struct ath9k_htc_sta *) sta->drv_priv;
 
-	mutex_lock(&priv->mutex);
-	ath9k_htc_ps_wakeup(priv);
+	if (!(changed & IEEE80211_RC_SUPP_RATES_CHANGED))
+		return;
 
-	if (changed & IEEE80211_RC_SUPP_RATES_CHANGED) {
-		memset(&trate, 0, sizeof(struct ath9k_htc_target_rate));
-		ath9k_htc_setup_rate(priv, sta, &trate);
-		if (!ath9k_htc_send_rate_cmd(priv, &trate))
-			ath_dbg(common, CONFIG,
-				"Supported rates for sta: %pM updated, rate caps: 0x%X\n",
-				sta->addr, be32_to_cpu(trate.capflags));
-		else
-			ath_dbg(common, CONFIG,
-				"Unable to update supported rates for sta: %pM\n",
-				sta->addr);
-	}
-
-	ath9k_htc_ps_restore(priv);
-	mutex_unlock(&priv->mutex);
+	schedule_work(&ista->rc_update_work);
 }
 
 static int ath9k_htc_conf_tx(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index fbf43c0..9078a6c 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1316,7 +1316,7 @@
 	if (AR_SREV_9300_20_OR_LATER(ah))
 		udelay(50);
 	else if (AR_SREV_9100(ah))
-		udelay(10000);
+		mdelay(10);
 	else
 		udelay(100);
 
@@ -1534,7 +1534,7 @@
 bool ath9k_hw_check_alive(struct ath_hw *ah)
 {
 	int count = 50;
-	u32 reg;
+	u32 reg, last_val;
 
 	if (AR_SREV_9300(ah))
 		return !ath9k_hw_detect_mac_hang(ah);
@@ -1542,9 +1542,14 @@
 	if (AR_SREV_9285_12_OR_LATER(ah))
 		return true;
 
+	last_val = REG_READ(ah, AR_OBS_BUS_1);
 	do {
 		reg = REG_READ(ah, AR_OBS_BUS_1);
+		if (reg != last_val)
+			return true;
 
+		udelay(1);
+		last_val = reg;
 		if ((reg & 0x7E7FFFEF) == 0x00702400)
 			continue;
 
@@ -2051,9 +2056,8 @@
 
 	REG_SET_BIT(ah, AR_RTC_FORCE_WAKE,
 		    AR_RTC_FORCE_WAKE_EN);
-
 	if (AR_SREV_9100(ah))
-		udelay(10000);
+		mdelay(10);
 	else
 		udelay(50);
 
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index c36de30..1fc2e5a 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -57,6 +57,10 @@
 module_param_named(bt_ant_diversity, ath9k_bt_ant_diversity, int, 0444);
 MODULE_PARM_DESC(bt_ant_diversity, "Enable WLAN/BT RX antenna diversity");
 
+static int ath9k_ps_enable;
+module_param_named(ps_enable, ath9k_ps_enable, int, 0444);
+MODULE_PARM_DESC(ps_enable, "Enable WLAN PowerSave");
+
 bool is_ath9k_unloaded;
 /* We use the hw_value as an index into our private channel structure */
 
@@ -903,13 +907,15 @@
 	hw->flags = IEEE80211_HW_RX_INCLUDES_FCS |
 		IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING |
 		IEEE80211_HW_SIGNAL_DBM |
-		IEEE80211_HW_SUPPORTS_PS |
 		IEEE80211_HW_PS_NULLFUNC_STACK |
 		IEEE80211_HW_SPECTRUM_MGMT |
 		IEEE80211_HW_REPORTS_TX_ACK_STATUS |
 		IEEE80211_HW_SUPPORTS_RC_TABLE |
 		IEEE80211_HW_SUPPORTS_HT_CCK_RATES;
 
+	if (ath9k_ps_enable)
+		hw->flags |= IEEE80211_HW_SUPPORTS_PS;
+
 	if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_HT) {
 		hw->flags |= IEEE80211_HW_AMPDU_AGGREGATION;
 
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index a0ebdd0..82e340d 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -732,11 +732,18 @@
 			return NULL;
 
 		/*
-		 * mark descriptor as zero-length and set the 'more'
-		 * flag to ensure that both buffers get discarded
+		 * Re-check previous descriptor, in case it has been filled
+		 * in the mean time.
 		 */
-		rs->rs_datalen = 0;
-		rs->rs_more = true;
+		ret = ath9k_hw_rxprocdesc(ah, ds, rs);
+		if (ret == -EINPROGRESS) {
+			/*
+			 * mark descriptor as zero-length and set the 'more'
+			 * flag to ensure that both buffers get discarded
+			 */
+			rs->rs_datalen = 0;
+			rs->rs_more = true;
+		}
 	}
 
 	list_del(&bf->list);
@@ -985,32 +992,32 @@
 	struct ath_common *common = ath9k_hw_common(ah);
 	struct ieee80211_hdr *hdr;
 	bool discard_current = sc->rx.discard_next;
-	int ret = 0;
 
 	/*
 	 * Discard corrupt descriptors which are marked in
 	 * ath_get_next_rx_buf().
 	 */
-	sc->rx.discard_next = rx_stats->rs_more;
 	if (discard_current)
-		return -EINVAL;
+		goto corrupt;
+
+	sc->rx.discard_next = false;
 
 	/*
 	 * Discard zero-length packets.
 	 */
 	if (!rx_stats->rs_datalen) {
 		RX_STAT_INC(rx_len_err);
-		return -EINVAL;
+		goto corrupt;
 	}
 
-        /*
-         * rs_status follows rs_datalen so if rs_datalen is too large
-         * we can take a hint that hardware corrupted it, so ignore
-         * those frames.
-         */
+	/*
+	 * rs_status follows rs_datalen so if rs_datalen is too large
+	 * we can take a hint that hardware corrupted it, so ignore
+	 * those frames.
+	 */
 	if (rx_stats->rs_datalen > (common->rx_bufsize - ah->caps.rx_status_len)) {
 		RX_STAT_INC(rx_len_err);
-		return -EINVAL;
+		goto corrupt;
 	}
 
 	/* Only use status info from the last fragment */
@@ -1024,10 +1031,8 @@
 	 * This is different from the other corrupt descriptor
 	 * condition handled above.
 	 */
-	if (rx_stats->rs_status & ATH9K_RXERR_CORRUPT_DESC) {
-		ret = -EINVAL;
-		goto exit;
-	}
+	if (rx_stats->rs_status & ATH9K_RXERR_CORRUPT_DESC)
+		goto corrupt;
 
 	hdr = (struct ieee80211_hdr *) (skb->data + ah->caps.rx_status_len);
 
@@ -1043,18 +1048,15 @@
 		if (ath_process_fft(sc, hdr, rx_stats, rx_status->mactime))
 			RX_STAT_INC(rx_spectral);
 
-		ret = -EINVAL;
-		goto exit;
+		return -EINVAL;
 	}
 
 	/*
 	 * everything but the rate is checked here, the rate check is done
 	 * separately to avoid doing two lookups for a rate for each frame.
 	 */
-	if (!ath9k_rx_accept(common, hdr, rx_status, rx_stats, decrypt_error)) {
-		ret = -EINVAL;
-		goto exit;
-	}
+	if (!ath9k_rx_accept(common, hdr, rx_status, rx_stats, decrypt_error))
+		return -EINVAL;
 
 	if (ath_is_mybeacon(common, hdr)) {
 		RX_STAT_INC(rx_beacons);
@@ -1064,15 +1066,11 @@
 	/*
 	 * This shouldn't happen, but have a safety check anyway.
 	 */
-	if (WARN_ON(!ah->curchan)) {
-		ret = -EINVAL;
-		goto exit;
-	}
+	if (WARN_ON(!ah->curchan))
+		return -EINVAL;
 
-	if (ath9k_process_rate(common, hw, rx_stats, rx_status)) {
-		ret =-EINVAL;
-		goto exit;
-	}
+	if (ath9k_process_rate(common, hw, rx_stats, rx_status))
+		return -EINVAL;
 
 	ath9k_process_rssi(common, hw, rx_stats, rx_status);
 
@@ -1087,9 +1085,11 @@
 		sc->rx.num_pkts++;
 #endif
 
-exit:
-	sc->rx.discard_next = false;
-	return ret;
+	return 0;
+
+corrupt:
+	sc->rx.discard_next = rx_stats->rs_more;
+	return -EINVAL;
 }
 
 static void ath9k_rx_skb_postprocess(struct ath_common *common,
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 0a75e2f..55897d5 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1444,14 +1444,16 @@
 	for (tidno = 0, tid = &an->tid[tidno];
 	     tidno < IEEE80211_NUM_TIDS; tidno++, tid++) {
 
-		if (!tid->sched)
-			continue;
-
 		ac = tid->ac;
 		txq = ac->txq;
 
 		ath_txq_lock(sc, txq);
 
+		if (!tid->sched) {
+			ath_txq_unlock(sc, txq);
+			continue;
+		}
+
 		buffered = ath_tid_has_buffered(tid);
 
 		tid->sched = false;
@@ -2061,7 +2063,7 @@
 
 	ATH_TXBUF_RESET(bf);
 
-	if (tid) {
+	if (tid && ieee80211_is_data_present(hdr->frame_control)) {
 		fragno = le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_FRAG;
 		seqno = tid->seq_next;
 		hdr->seq_ctrl = cpu_to_le16(tid->seq_next << IEEE80211_SEQ_SEQ_SHIFT);
@@ -2184,14 +2186,15 @@
 		txq->stopped = true;
 	}
 
+	if (txctl->an && ieee80211_is_data_present(hdr->frame_control))
+		tid = ath_get_skb_tid(sc, txctl->an, skb);
+
 	if (info->flags & IEEE80211_TX_CTL_PS_RESPONSE) {
 		ath_txq_unlock(sc, txq);
 		txq = sc->tx.uapsdq;
 		ath_txq_lock(sc, txq);
 	} else if (txctl->an &&
 		   ieee80211_is_data_present(hdr->frame_control)) {
-		tid = ath_get_skb_tid(sc, txctl->an, skb);
-
 		WARN_ON(tid->ac->txq != txctl->txq);
 
 		if (info->flags & IEEE80211_TX_CTL_CLEAR_PS_FILT)
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
index 3e99189..ddaa9ef 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
@@ -457,7 +457,6 @@
 
 	u8 tx_hdrlen;		/* sdio bus header length for tx packet */
 	bool txglom;		/* host tx glomming enable flag */
-	struct sk_buff *txglom_sgpad;	/* scatter-gather padding buffer */
 	u16 head_align;		/* buffer pointer alignment */
 	u16 sgentry_align;	/* scatter-gather buffer alignment */
 };
@@ -1944,19 +1943,21 @@
 	if (lastfrm && chain_pad)
 		tail_pad += blksize - chain_pad;
 	if (skb_tailroom(pkt) < tail_pad && pkt->len > blksize) {
-		pkt_pad = bus->txglom_sgpad;
-		if (pkt_pad == NULL)
-			  brcmu_pkt_buf_get_skb(tail_pad + tail_chop);
+		pkt_pad = brcmu_pkt_buf_get_skb(tail_pad + tail_chop +
+						bus->head_align);
 		if (pkt_pad == NULL)
 			return -ENOMEM;
 		ret = brcmf_sdio_txpkt_hdalign(bus, pkt_pad);
-		if (unlikely(ret < 0))
+		if (unlikely(ret < 0)) {
+			kfree_skb(pkt_pad);
 			return ret;
+		}
 		memcpy(pkt_pad->data,
 		       pkt->data + pkt->len - tail_chop,
 		       tail_chop);
 		*(u32 *)(pkt_pad->cb) = ALIGN_SKB_FLAG + tail_chop;
 		skb_trim(pkt, pkt->len - tail_chop);
+		skb_trim(pkt_pad, tail_pad + tail_chop);
 		__skb_queue_after(pktq, pkt, pkt_pad);
 	} else {
 		ntail = pkt->data_len + tail_pad -
@@ -2011,7 +2012,7 @@
 			return ret;
 		head_pad = (u16)ret;
 		if (head_pad)
-			memset(pkt_next->data, 0, head_pad + bus->tx_hdrlen);
+			memset(pkt_next->data + bus->tx_hdrlen, 0, head_pad);
 
 		total_len += pkt_next->len;
 
@@ -3486,10 +3487,6 @@
 		bus->txglom = false;
 		value = 1;
 		pad_size = bus->sdiodev->func[2]->cur_blksize << 1;
-		bus->txglom_sgpad = brcmu_pkt_buf_get_skb(pad_size);
-		if (!bus->txglom_sgpad)
-			brcmf_err("allocating txglom padding skb failed, reduced performance\n");
-
 		err = brcmf_iovar_data_set(bus->sdiodev->dev, "bus:rxglom",
 					   &value, sizeof(u32));
 		if (err < 0) {
@@ -4053,7 +4050,6 @@
 			brcmf_sdio_chip_detach(&bus->ci);
 		}
 
-		brcmu_pkt_buf_free_skb(bus->txglom_sgpad);
 		kfree(bus->rxbuf);
 		kfree(bus->hdrbuf);
 		kfree(bus);
diff --git a/drivers/net/wireless/hostap/hostap_ap.c b/drivers/net/wireless/hostap/hostap_ap.c
index d36e252..5965255 100644
--- a/drivers/net/wireless/hostap/hostap_ap.c
+++ b/drivers/net/wireless/hostap/hostap_ap.c
@@ -147,7 +147,7 @@
 
 	if (!sta->ap && sta->u.sta.challenge)
 		kfree(sta->u.sta.challenge);
-	del_timer(&sta->timer);
+	del_timer_sync(&sta->timer);
 #endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
 
 	kfree(sta);
diff --git a/drivers/net/wireless/hostap/hostap_proc.c b/drivers/net/wireless/hostap/hostap_proc.c
index aa7ad3a..4e5c0f8 100644
--- a/drivers/net/wireless/hostap/hostap_proc.c
+++ b/drivers/net/wireless/hostap/hostap_proc.c
@@ -496,7 +496,7 @@
 
 void hostap_remove_proc(local_info_t *local)
 {
-	remove_proc_subtree(local->ddev->name, hostap_proc);
+	proc_remove(local->proc);
 }
 
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
index c24d1d3..73086c1 100644
--- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
@@ -696,6 +696,24 @@
 	return ret;
 }
 
+static inline bool iwl_enable_rx_ampdu(const struct iwl_cfg *cfg)
+{
+	if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG)
+		return false;
+	return true;
+}
+
+static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg)
+{
+	if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG)
+		return false;
+	if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG)
+		return true;
+
+	/* disabled by default */
+	return false;
+}
+
 static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw,
 				   struct ieee80211_vif *vif,
 				   enum ieee80211_ampdu_mlme_action action,
@@ -717,7 +735,7 @@
 
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
-		if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG)
+		if (!iwl_enable_rx_ampdu(priv->cfg))
 			break;
 		IWL_DEBUG_HT(priv, "start Rx\n");
 		ret = iwl_sta_rx_agg_start(priv, sta, tid, *ssn);
@@ -729,7 +747,7 @@
 	case IEEE80211_AMPDU_TX_START:
 		if (!priv->trans->ops->txq_enable)
 			break;
-		if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG)
+		if (!iwl_enable_tx_ampdu(priv->cfg))
 			break;
 		IWL_DEBUG_HT(priv, "start Tx\n");
 		ret = iwlagn_tx_agg_start(priv, vif, sta, tid, ssn);
diff --git a/drivers/net/wireless/iwlwifi/dvm/sta.c b/drivers/net/wireless/iwlwifi/dvm/sta.c
index c0d070c..9cdd91c 100644
--- a/drivers/net/wireless/iwlwifi/dvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/dvm/sta.c
@@ -590,6 +590,7 @@
 			sizeof(priv->tid_data[sta_id][tid]));
 
 	priv->stations[sta_id].used &= ~IWL_STA_DRIVER_ACTIVE;
+	priv->stations[sta_id].used &= ~IWL_STA_UCODE_INPROGRESS;
 
 	priv->num_stations--;
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c
index a6839df..398dd09 100644
--- a/drivers/net/wireless/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/dvm/tx.c
@@ -1291,8 +1291,6 @@
 	struct iwl_compressed_ba_resp *ba_resp = (void *)pkt->data;
 	struct iwl_ht_agg *agg;
 	struct sk_buff_head reclaimed_skbs;
-	struct ieee80211_tx_info *info;
-	struct ieee80211_hdr *hdr;
 	struct sk_buff *skb;
 	int sta_id;
 	int tid;
@@ -1379,22 +1377,28 @@
 	freed = 0;
 
 	skb_queue_walk(&reclaimed_skbs, skb) {
-		hdr = (struct ieee80211_hdr *)skb->data;
+		struct ieee80211_hdr *hdr = (void *)skb->data;
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 
 		if (ieee80211_is_data_qos(hdr->frame_control))
 			freed++;
 		else
 			WARN_ON_ONCE(1);
 
-		info = IEEE80211_SKB_CB(skb);
 		iwl_trans_free_tx_cmd(priv->trans, info->driver_data[1]);
 
+		memset(&info->status, 0, sizeof(info->status));
+		/* Packet was transmitted successfully, failures come as single
+		 * frames because before failing a frame the firmware transmits
+		 * it without aggregation at least once.
+		 */
+		info->flags |= IEEE80211_TX_STAT_ACK;
+
 		if (freed == 1) {
 			/* this is the first skb we deliver in this batch */
 			/* put the rate scaling data there */
 			info = IEEE80211_SKB_CB(skb);
 			memset(&info->status, 0, sizeof(info->status));
-			info->flags |= IEEE80211_TX_STAT_ACK;
 			info->flags |= IEEE80211_TX_STAT_AMPDU;
 			info->status.ampdu_ack_len = ba_resp->txed_2_done;
 			info->status.ampdu_len = ba_resp->txed;
diff --git a/drivers/net/wireless/iwlwifi/iwl-drv.c b/drivers/net/wireless/iwlwifi/iwl-drv.c
index c372816..7510355 100644
--- a/drivers/net/wireless/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/iwlwifi/iwl-drv.c
@@ -1286,7 +1286,7 @@
 MODULE_PARM_DESC(swcrypto, "using crypto in software (default 0 [hardware])");
 module_param_named(11n_disable, iwlwifi_mod_params.disable_11n, uint, S_IRUGO);
 MODULE_PARM_DESC(11n_disable,
-	"disable 11n functionality, bitmap: 1: full, 2: agg TX, 4: agg RX");
+	"disable 11n functionality, bitmap: 1: full, 2: disable agg TX, 4: disable agg RX, 8 enable agg TX");
 module_param_named(amsdu_size_8K, iwlwifi_mod_params.amsdu_size_8K,
 		   int, S_IRUGO);
 MODULE_PARM_DESC(amsdu_size_8K, "enable 8K amsdu size (default 0)");
diff --git a/drivers/net/wireless/iwlwifi/iwl-modparams.h b/drivers/net/wireless/iwlwifi/iwl-modparams.h
index 0a84ade..b29075c 100644
--- a/drivers/net/wireless/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/iwlwifi/iwl-modparams.h
@@ -79,9 +79,12 @@
 	IWL_POWER_NUM
 };
 
-#define IWL_DISABLE_HT_ALL	BIT(0)
-#define IWL_DISABLE_HT_TXAGG	BIT(1)
-#define IWL_DISABLE_HT_RXAGG	BIT(2)
+enum iwl_disable_11n {
+	IWL_DISABLE_HT_ALL	 = BIT(0),
+	IWL_DISABLE_HT_TXAGG	 = BIT(1),
+	IWL_DISABLE_HT_RXAGG	 = BIT(2),
+	IWL_ENABLE_HT_TXAGG	 = BIT(3),
+};
 
 /**
  * struct iwl_mod_params
@@ -90,7 +93,7 @@
  *
  * @sw_crypto: using hardware encryption, default = 0
  * @disable_11n: disable 11n capabilities, default = 0,
- *	use IWL_DISABLE_HT_* constants
+ *	use IWL_[DIS,EN]ABLE_HT_* constants
  * @amsdu_size_8K: enable 8K amsdu size, default = 0
  * @restart_fw: restart firmware, default = 1
  * @wd_disable: enable stuck queue check, default = 0
diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
index f06f4cb..725e954 100644
--- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
@@ -182,6 +182,11 @@
 
 	for (ch_idx = 0; ch_idx < IWL_NUM_CHANNELS; ch_idx++) {
 		ch_flags = __le16_to_cpup(nvm_ch_flags + ch_idx);
+
+		if (ch_idx >= NUM_2GHZ_CHANNELS &&
+		    !data->sku_cap_band_52GHz_enable)
+			ch_flags &= ~NVM_CHANNEL_VALID;
+
 		if (!(ch_flags & NVM_CHANNEL_VALID)) {
 			IWL_DEBUG_EEPROM(dev,
 					 "Ch. %d Flags %x [%sGHz] - No traffic\n",
diff --git a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
index 76cde6c..18a895a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
+++ b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
@@ -872,8 +872,11 @@
 
 	lockdep_assert_held(&mvm->mutex);
 
-	/* Rssi update while not associated ?! */
-	if (WARN_ON_ONCE(mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT))
+	/*
+	 * Rssi update while not associated - can happen since the statistics
+	 * are handled asynchronously
+	 */
+	if (mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT)
 		return;
 
 	/* No BT - reports should be disabled */
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
index 73cbba7..9426905 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
@@ -504,6 +504,7 @@
  * @match_notify:	clients waiting for match found notification
  * @pass_match:		clients waiting for the results
  * @active_clients:	active clients bitmap - enum scan_framework_client
+ * @any_beacon_notify:	clients waiting for match notification without match
  */
 struct iwl_scan_offload_profile_cfg {
 	struct iwl_scan_offload_profile profiles[IWL_SCAN_MAX_PROFILES];
@@ -512,7 +513,8 @@
 	u8 match_notify;
 	u8 pass_match;
 	u8 active_clients;
-	u8 reserved[3];
+	u8 any_beacon_notify;
+	u8 reserved[2];
 } __packed;
 
 /**
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index c49b507..c35b866 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -246,7 +246,7 @@
 	else
 		hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
 
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_SCHED_SCAN) {
+	if (0 && mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_SCHED_SCAN) {
 		hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_SCHED_SCAN;
 		hw->wiphy->max_sched_scan_ssids = PROBE_OPTION_MAX;
 		hw->wiphy->max_match_sets = IWL_SCAN_MAX_PROFILES;
@@ -328,6 +328,24 @@
 	ieee80211_free_txskb(hw, skb);
 }
 
+static inline bool iwl_enable_rx_ampdu(const struct iwl_cfg *cfg)
+{
+	if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG)
+		return false;
+	return true;
+}
+
+static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg)
+{
+	if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG)
+		return false;
+	if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG)
+		return true;
+
+	/* enabled by default */
+	return true;
+}
+
 static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
 				    enum ieee80211_ampdu_mlme_action action,
@@ -347,7 +365,7 @@
 
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
-		if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG) {
+		if (!iwl_enable_rx_ampdu(mvm->cfg)) {
 			ret = -EINVAL;
 			break;
 		}
@@ -357,7 +375,7 @@
 		ret = iwl_mvm_sta_rx_agg(mvm, sta, tid, 0, false);
 		break;
 	case IEEE80211_AMPDU_TX_START:
-		if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG) {
+		if (!iwl_enable_tx_ampdu(mvm->cfg)) {
 			ret = -EINVAL;
 			break;
 		}
diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h
index e4ead86..2b0ba1f 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h
@@ -152,7 +152,7 @@
 	IWL_POWER_SCHEME_LP
 };
 
-#define IWL_CONN_MAX_LISTEN_INTERVAL	70
+#define IWL_CONN_MAX_LISTEN_INTERVAL	10
 #define IWL_UAPSD_AC_INFO		(IEEE80211_WMM_IE_STA_QOSINFO_AC_VO |\
 					 IEEE80211_WMM_IE_STA_QOSINFO_AC_VI |\
 					 IEEE80211_WMM_IE_STA_QOSINFO_AC_BK |\
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index 0e00079..742afc4 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -344,7 +344,8 @@
 
 	iwl_mvm_scan_fill_ssids(cmd, req, basic_ssid ? 1 : 0);
 
-	cmd->tx_cmd.tx_flags = cpu_to_le32(TX_CMD_FLG_SEQ_CTL);
+	cmd->tx_cmd.tx_flags = cpu_to_le32(TX_CMD_FLG_SEQ_CTL |
+					   TX_CMD_FLG_BT_DIS);
 	cmd->tx_cmd.sta_id = mvm->aux_sta.sta_id;
 	cmd->tx_cmd.life_time = cpu_to_le32(TX_CMD_LIFE_TIME_INFINITE);
 	cmd->tx_cmd.rate_n_flags =
@@ -807,6 +808,8 @@
 	profile_cfg->active_clients = SCAN_CLIENT_SCHED_SCAN;
 	profile_cfg->pass_match = SCAN_CLIENT_SCHED_SCAN;
 	profile_cfg->match_notify = SCAN_CLIENT_SCHED_SCAN;
+	if (!req->n_match_sets || !req->match_sets[0].ssid.ssid_len)
+		profile_cfg->any_beacon_notify = SCAN_CLIENT_SCHED_SCAN;
 
 	for (i = 0; i < req->n_match_sets; i++) {
 		profile = &profile_cfg->profiles[i];
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.c b/drivers/net/wireless/iwlwifi/mvm/sta.c
index ec18121..3397f59 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.c
@@ -652,7 +652,7 @@
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	static const u8 _baddr[] = {0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
-	static const u8 *baddr = _baddr;
+	const u8 *baddr = _baddr;
 
 	lockdep_assert_held(&mvm->mutex);
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index 90378c2..76ee486 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -659,8 +659,14 @@
 	rcu_read_lock();
 
 	sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]);
+	/*
+	 * sta can't be NULL otherwise it'd mean that the sta has been freed in
+	 * the firmware while we still have packets for it in the Tx queues.
+	 */
+	if (WARN_ON_ONCE(!sta))
+		goto out;
 
-	if (!IS_ERR_OR_NULL(sta)) {
+	if (!IS_ERR(sta)) {
 		mvmsta = iwl_mvm_sta_from_mac80211(sta);
 
 		if (tid != IWL_TID_NON_QOS) {
@@ -675,7 +681,6 @@
 			spin_unlock_bh(&mvmsta->lock);
 		}
 	} else {
-		sta = NULL;
 		mvmsta = NULL;
 	}
 
@@ -683,42 +688,38 @@
 	 * If the txq is not an AMPDU queue, there is no chance we freed
 	 * several skbs. Check that out...
 	 */
-	if (txq_id < mvm->first_agg_queue && !WARN_ON(skb_freed > 1) &&
-	    atomic_sub_and_test(skb_freed, &mvm->pending_frames[sta_id])) {
-		if (mvmsta) {
-			/*
-			 * If there are no pending frames for this STA, notify
-			 * mac80211 that this station can go to sleep in its
-			 * STA table.
-			 */
-			if (mvmsta->vif->type == NL80211_IFTYPE_AP)
-				ieee80211_sta_block_awake(mvm->hw, sta, false);
-			/*
-			 * We might very well have taken mvmsta pointer while
-			 * the station was being removed. The remove flow might
-			 * have seen a pending_frame (because we didn't take
-			 * the lock) even if now the queues are drained. So make
-			 * really sure now that this the station is not being
-			 * removed. If it is, run the drain worker to remove it.
-			 */
-			spin_lock_bh(&mvmsta->lock);
-			sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]);
-			if (!sta || PTR_ERR(sta) == -EBUSY) {
-				/*
-				 * Station disappeared in the meantime:
-				 * so we are draining.
-				 */
-				set_bit(sta_id, mvm->sta_drained);
-				schedule_work(&mvm->sta_drained_wk);
-			}
-			spin_unlock_bh(&mvmsta->lock);
-		} else if (!mvmsta && PTR_ERR(sta) == -EBUSY) {
-			/* Tx response without STA, so we are draining */
-			set_bit(sta_id, mvm->sta_drained);
-			schedule_work(&mvm->sta_drained_wk);
-		}
+	if (txq_id >= mvm->first_agg_queue)
+		goto out;
+
+	/* We can't free more than one frame at once on a shared queue */
+	WARN_ON(skb_freed > 1);
+
+	/* If we have still frames from this STA nothing to do here */
+	if (!atomic_sub_and_test(skb_freed, &mvm->pending_frames[sta_id]))
+		goto out;
+
+	if (mvmsta && mvmsta->vif->type == NL80211_IFTYPE_AP) {
+		/*
+		 * If there are no pending frames for this STA, notify
+		 * mac80211 that this station can go to sleep in its
+		 * STA table.
+		 * If mvmsta is not NULL, sta is valid.
+		 */
+		ieee80211_sta_block_awake(mvm->hw, sta, false);
 	}
 
+	if (PTR_ERR(sta) == -EBUSY || PTR_ERR(sta) == -ENOENT) {
+		/*
+		 * We are draining and this was the last packet - pre_rcu_remove
+		 * has been called already. We might be after the
+		 * synchronize_net already.
+		 * Don't rely on iwl_mvm_rm_sta to see the empty Tx queues.
+		 */
+		set_bit(sta_id, mvm->sta_drained);
+		schedule_work(&mvm->sta_drained_wk);
+	}
+
+out:
 	rcu_read_unlock();
 }
 
@@ -821,16 +822,12 @@
 	struct iwl_mvm_ba_notif *ba_notif = (void *)pkt->data;
 	struct sk_buff_head reclaimed_skbs;
 	struct iwl_mvm_tid_data *tid_data;
-	struct ieee80211_tx_info *info;
 	struct ieee80211_sta *sta;
 	struct iwl_mvm_sta *mvmsta;
-	struct ieee80211_hdr *hdr;
 	struct sk_buff *skb;
 	int sta_id, tid, freed;
-
 	/* "flow" corresponds to Tx queue */
 	u16 scd_flow = le16_to_cpu(ba_notif->scd_flow);
-
 	/* "ssn" is start of block-ack Tx window, corresponds to index
 	 * (in Tx queue's circular buffer) of first TFD/frame in window */
 	u16 ba_resp_scd_ssn = le16_to_cpu(ba_notif->scd_ssn);
@@ -887,22 +884,26 @@
 	freed = 0;
 
 	skb_queue_walk(&reclaimed_skbs, skb) {
-		hdr = (struct ieee80211_hdr *)skb->data;
+		struct ieee80211_hdr *hdr = (void *)skb->data;
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 
 		if (ieee80211_is_data_qos(hdr->frame_control))
 			freed++;
 		else
 			WARN_ON_ONCE(1);
 
-		info = IEEE80211_SKB_CB(skb);
 		iwl_trans_free_tx_cmd(mvm->trans, info->driver_data[1]);
 
+		memset(&info->status, 0, sizeof(info->status));
+		/* Packet was transmitted successfully, failures come as single
+		 * frames because before failing a frame the firmware transmits
+		 * it without aggregation at least once.
+		 */
+		info->flags |= IEEE80211_TX_STAT_ACK;
+
 		if (freed == 1) {
 			/* this is the first skb we deliver in this batch */
 			/* put the rate scaling data there */
-			info = IEEE80211_SKB_CB(skb);
-			memset(&info->status, 0, sizeof(info->status));
-			info->flags |= IEEE80211_TX_STAT_ACK;
 			info->flags |= IEEE80211_TX_STAT_AMPDU;
 			info->status.ampdu_ack_len = ba_notif->txed_2_done;
 			info->status.ampdu_len = ba_notif->txed;
diff --git a/drivers/net/wireless/iwlwifi/mvm/utils.c b/drivers/net/wireless/iwlwifi/mvm/utils.c
index a4a5e25..86989df 100644
--- a/drivers/net/wireless/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/iwlwifi/mvm/utils.c
@@ -411,6 +411,8 @@
 			mvm->status, table.valid);
 	}
 
+	IWL_ERR(mvm, "Loaded firmware version: %s\n", mvm->fw->fw_version);
+
 	trace_iwlwifi_dev_ucode_error(trans->dev, table.error_id, table.tsf_low,
 				      table.data1, table.data2, table.data3,
 				      table.blink1, table.blink2, table.ilink1,
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 3040924..3872ead 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -359,20 +359,24 @@
 /* 7265 Series */
 	{IWL_PCI_DEVICE(0x095A, 0x5010, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5110, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5100, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5310, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_n_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5210, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x500A, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5412, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5400, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x1010, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5000, iwl7265_2n_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x500A, iwl7265_2n_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5200, iwl7265_2n_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5002, iwl7265_n_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5202, iwl7265_n_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9010, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9012, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9110, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9112, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9210, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9510, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9310, iwl7265_2ac_cfg)},
diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c
index 32f7500..cb6d189 100644
--- a/drivers/net/wireless/libertas/cfg.c
+++ b/drivers/net/wireless/libertas/cfg.c
@@ -621,7 +621,7 @@
 			id = *pos++;
 			elen = *pos++;
 			left -= 2;
-			if (elen > left || elen == 0) {
+			if (elen > left) {
 				lbs_deb_scan("scan response: invalid IE fmt\n");
 				goto done;
 			}
diff --git a/drivers/net/wireless/mwifiex/11ac.c b/drivers/net/wireless/mwifiex/11ac.c
index 5e0eec4..5d9a808 100644
--- a/drivers/net/wireless/mwifiex/11ac.c
+++ b/drivers/net/wireless/mwifiex/11ac.c
@@ -189,8 +189,7 @@
 		vht_cap->header.len  =
 				cpu_to_le16(sizeof(struct ieee80211_vht_cap));
 		memcpy((u8 *)vht_cap + sizeof(struct mwifiex_ie_types_header),
-		       (u8 *)bss_desc->bcn_vht_cap +
-		       sizeof(struct ieee_types_header),
+		       (u8 *)bss_desc->bcn_vht_cap,
 		       le16_to_cpu(vht_cap->header.len));
 
 		mwifiex_fill_vht_cap_tlv(priv, vht_cap, bss_desc->bss_band);
diff --git a/drivers/net/wireless/mwifiex/11n.c b/drivers/net/wireless/mwifiex/11n.c
index 6261f8c..7db1a89 100644
--- a/drivers/net/wireless/mwifiex/11n.c
+++ b/drivers/net/wireless/mwifiex/11n.c
@@ -308,8 +308,7 @@
 		ht_cap->header.len =
 				cpu_to_le16(sizeof(struct ieee80211_ht_cap));
 		memcpy((u8 *) ht_cap + sizeof(struct mwifiex_ie_types_header),
-		       (u8 *) bss_desc->bcn_ht_cap +
-		       sizeof(struct ieee_types_header),
+		       (u8 *)bss_desc->bcn_ht_cap,
 		       le16_to_cpu(ht_cap->header.len));
 
 		mwifiex_fill_cap_info(priv, radio_type, ht_cap);
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 4d79761..9d3d275 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -748,7 +748,7 @@
 
 static u16
 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
-				void *accel_priv)
+				void *accel_priv, select_queue_fallback_t fallback)
 {
 	skb->priority = cfg80211_classify8021d(skb, NULL);
 	return mwifiex_1d_to_wmm_queue[skb->priority];
diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c
index 03688aa..7fe7b53 100644
--- a/drivers/net/wireless/mwifiex/pcie.c
+++ b/drivers/net/wireless/mwifiex/pcie.c
@@ -1211,6 +1211,12 @@
 		rd_index = card->rxbd_rdptr & reg->rx_mask;
 		skb_data = card->rx_buf_list[rd_index];
 
+		/* If skb allocation was failed earlier for Rx packet,
+		 * rx_buf_list[rd_index] would have been left with a NULL.
+		 */
+		if (!skb_data)
+			return -ENOMEM;
+
 		MWIFIEX_SKB_PACB(skb_data, &buf_pa);
 		pci_unmap_single(card->dev, buf_pa, MWIFIEX_RX_DATA_BUF_SIZE,
 				 PCI_DMA_FROMDEVICE);
@@ -1525,6 +1531,14 @@
 		if (adapter->ps_state == PS_STATE_SLEEP_CFM) {
 			mwifiex_process_sleep_confirm_resp(adapter, skb->data,
 							   skb->len);
+			mwifiex_pcie_enable_host_int(adapter);
+			if (mwifiex_write_reg(adapter,
+					      PCIE_CPU_INT_EVENT,
+					      CPU_INTR_SLEEP_CFM_DONE)) {
+				dev_warn(adapter->dev,
+					 "Write register failed\n");
+				return -1;
+			}
 			while (reg->sleep_cookie && (count++ < 10) &&
 			       mwifiex_pcie_ok_to_access_hw(adapter))
 				usleep_range(50, 60);
@@ -1993,23 +2007,9 @@
 		adapter->int_status |= pcie_ireg;
 		spin_unlock_irqrestore(&adapter->int_lock, flags);
 
-		if (pcie_ireg & HOST_INTR_CMD_DONE) {
-			if ((adapter->ps_state == PS_STATE_SLEEP_CFM) ||
-			    (adapter->ps_state == PS_STATE_SLEEP)) {
-				mwifiex_pcie_enable_host_int(adapter);
-				if (mwifiex_write_reg(adapter,
-						      PCIE_CPU_INT_EVENT,
-						      CPU_INTR_SLEEP_CFM_DONE)
-						      ) {
-					dev_warn(adapter->dev,
-						 "Write register failed\n");
-					return;
-
-				}
-			}
-		} else if (!adapter->pps_uapsd_mode &&
-			   adapter->ps_state == PS_STATE_SLEEP &&
-			   mwifiex_pcie_ok_to_access_hw(adapter)) {
+		if (!adapter->pps_uapsd_mode &&
+		    adapter->ps_state == PS_STATE_SLEEP &&
+		    mwifiex_pcie_ok_to_access_hw(adapter)) {
 				/* Potentially for PCIe we could get other
 				 * interrupts like shared. Don't change power
 				 * state until cookie is set */
diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c
index 0a8a26e..668547c 100644
--- a/drivers/net/wireless/mwifiex/scan.c
+++ b/drivers/net/wireless/mwifiex/scan.c
@@ -2101,12 +2101,12 @@
 			 curr_bss->ht_info_offset);
 
 	if (curr_bss->bcn_vht_cap)
-		curr_bss->bcn_ht_cap = (void *)(curr_bss->beacon_buf +
-						curr_bss->vht_cap_offset);
+		curr_bss->bcn_vht_cap = (void *)(curr_bss->beacon_buf +
+						 curr_bss->vht_cap_offset);
 
 	if (curr_bss->bcn_vht_oper)
-		curr_bss->bcn_ht_oper = (void *)(curr_bss->beacon_buf +
-						 curr_bss->vht_info_offset);
+		curr_bss->bcn_vht_oper = (void *)(curr_bss->beacon_buf +
+						  curr_bss->vht_info_offset);
 
 	if (curr_bss->bcn_bss_co_2040)
 		curr_bss->bcn_bss_co_2040 =
diff --git a/drivers/net/wireless/mwifiex/usb.c b/drivers/net/wireless/mwifiex/usb.c
index e8ebbd4..2087488 100644
--- a/drivers/net/wireless/mwifiex/usb.c
+++ b/drivers/net/wireless/mwifiex/usb.c
@@ -22,8 +22,6 @@
 
 #define USB_VERSION	"1.0"
 
-static const char usbdriver_name[] = "usb8xxx";
-
 static struct mwifiex_if_ops usb_ops;
 static struct semaphore add_remove_card_sem;
 static struct usb_card_rec *usb_card;
@@ -527,13 +525,6 @@
 						   MWIFIEX_BSS_ROLE_ANY),
 				  MWIFIEX_ASYNC_CMD);
 
-#ifdef CONFIG_PM
-	/* Resume handler may be called due to remote wakeup,
-	 * force to exit suspend anyway
-	 */
-	usb_disable_autosuspend(card->udev);
-#endif /* CONFIG_PM */
-
 	return 0;
 }
 
@@ -567,13 +558,12 @@
 }
 
 static struct usb_driver mwifiex_usb_driver = {
-	.name = usbdriver_name,
+	.name = "mwifiex_usb",
 	.probe = mwifiex_usb_probe,
 	.disconnect = mwifiex_usb_disconnect,
 	.id_table = mwifiex_usb_table,
 	.suspend = mwifiex_usb_suspend,
 	.resume = mwifiex_usb_resume,
-	.supports_autosuspend = 1,
 };
 
 static int mwifiex_usb_tx_init(struct mwifiex_adapter *adapter)
diff --git a/drivers/net/wireless/mwifiex/wmm.c b/drivers/net/wireless/mwifiex/wmm.c
index 13eaeed..981cf6e 100644
--- a/drivers/net/wireless/mwifiex/wmm.c
+++ b/drivers/net/wireless/mwifiex/wmm.c
@@ -559,7 +559,8 @@
 	mwifiex_wmm_delete_all_ralist(priv);
 	memcpy(tos_to_tid, ac_to_tid, sizeof(tos_to_tid));
 
-	if (priv->adapter->if_ops.clean_pcie_ring)
+	if (priv->adapter->if_ops.clean_pcie_ring &&
+	    !priv->adapter->surprise_removed)
 		priv->adapter->if_ops.clean_pcie_ring(priv->adapter);
 	spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags);
 }
diff --git a/drivers/net/wireless/rt2x00/rt2500pci.c b/drivers/net/wireless/rt2x00/rt2500pci.c
index abc5f56..2f1cd92 100644
--- a/drivers/net/wireless/rt2x00/rt2500pci.c
+++ b/drivers/net/wireless/rt2x00/rt2500pci.c
@@ -1877,6 +1877,11 @@
 						   EEPROM_MAC_ADDR_0));
 
 	/*
+	 * Disable powersaving as default.
+	 */
+	rt2x00dev->hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
+
+	/*
 	 * Initialize hw_mode information.
 	 */
 	spec->supported_bands = SUPPORT_BAND_2GHZ;
diff --git a/drivers/net/wireless/rt2x00/rt2500usb.c b/drivers/net/wireless/rt2x00/rt2500usb.c
index 9f16824..d849d59 100644
--- a/drivers/net/wireless/rt2x00/rt2500usb.c
+++ b/drivers/net/wireless/rt2x00/rt2500usb.c
@@ -1706,6 +1706,11 @@
 	    IEEE80211_HW_SUPPORTS_PS |
 	    IEEE80211_HW_PS_NULLFUNC_STACK;
 
+	/*
+	 * Disable powersaving as default.
+	 */
+	rt2x00dev->hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
+
 	SET_IEEE80211_DEV(rt2x00dev->hw, rt2x00dev->dev);
 	SET_IEEE80211_PERM_ADDR(rt2x00dev->hw,
 				rt2x00_eeprom_addr(rt2x00dev,
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index b8f5b06..41d4a81 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -5460,14 +5460,15 @@
 
 	rt2800_bbp_write(rt2x00dev, 68, 0x0b);
 
-	rt2800_bbp_write(rt2x00dev, 69, 0x0d);
-	rt2800_bbp_write(rt2x00dev, 70, 0x06);
+	rt2800_bbp_write(rt2x00dev, 69, 0x12);
 	rt2800_bbp_write(rt2x00dev, 73, 0x13);
 	rt2800_bbp_write(rt2x00dev, 75, 0x46);
 	rt2800_bbp_write(rt2x00dev, 76, 0x28);
 
 	rt2800_bbp_write(rt2x00dev, 77, 0x59);
 
+	rt2800_bbp_write(rt2x00dev, 70, 0x0a);
+
 	rt2800_bbp_write(rt2x00dev, 79, 0x13);
 	rt2800_bbp_write(rt2x00dev, 80, 0x05);
 	rt2800_bbp_write(rt2x00dev, 81, 0x33);
@@ -5510,7 +5511,6 @@
 	if (rt2x00_rt(rt2x00dev, RT5392)) {
 		rt2800_bbp_write(rt2x00dev, 134, 0xd0);
 		rt2800_bbp_write(rt2x00dev, 135, 0xf6);
-		rt2800_bbp_write(rt2x00dev, 148, 0x84);
 	}
 
 	rt2800_disable_unused_dac_adc(rt2x00dev);
@@ -7458,10 +7458,9 @@
 	u32 reg;
 
 	/*
-	 * Disable powersaving as default on PCI devices.
+	 * Disable powersaving as default.
 	 */
-	if (rt2x00_is_pci(rt2x00dev) || rt2x00_is_soc(rt2x00dev))
-		rt2x00dev->hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
+	rt2x00dev->hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
 
 	/*
 	 * Initialize all hw fields.
diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c
index caddc1b..42a2e06 100644
--- a/drivers/net/wireless/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/rt2x00/rt2800usb.c
@@ -764,7 +764,7 @@
 	/*
 	 * Overwrite TX done handler
 	 */
-	PREPARE_WORK(&rt2x00dev->txdone_work, rt2800usb_work_txdone);
+	INIT_WORK(&rt2x00dev->txdone_work, rt2800usb_work_txdone);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/rtl818x/rtl8180/dev.c b/drivers/net/wireless/rtl818x/rtl8180/dev.c
index 8ec17aa..3867d14 100644
--- a/drivers/net/wireless/rtl818x/rtl8180/dev.c
+++ b/drivers/net/wireless/rtl818x/rtl8180/dev.c
@@ -107,6 +107,7 @@
 	struct rtl8180_priv *priv = dev->priv;
 	unsigned int count = 32;
 	u8 signal, agc, sq;
+	dma_addr_t mapping;
 
 	while (count--) {
 		struct rtl8180_rx_desc *entry = &priv->rx_ring[priv->rx_idx];
@@ -128,6 +129,17 @@
 			if (unlikely(!new_skb))
 				goto done;
 
+			mapping = pci_map_single(priv->pdev,
+					       skb_tail_pointer(new_skb),
+					       MAX_RX_SIZE, PCI_DMA_FROMDEVICE);
+
+			if (pci_dma_mapping_error(priv->pdev, mapping)) {
+				kfree_skb(new_skb);
+				dev_err(&priv->pdev->dev, "RX DMA map error\n");
+
+				goto done;
+			}
+
 			pci_unmap_single(priv->pdev,
 					 *((dma_addr_t *)skb->cb),
 					 MAX_RX_SIZE, PCI_DMA_FROMDEVICE);
@@ -158,9 +170,7 @@
 
 			skb = new_skb;
 			priv->rx_buf[priv->rx_idx] = skb;
-			*((dma_addr_t *) skb->cb) =
-				pci_map_single(priv->pdev, skb_tail_pointer(skb),
-					       MAX_RX_SIZE, PCI_DMA_FROMDEVICE);
+			*((dma_addr_t *) skb->cb) = mapping;
 		}
 
 	done:
@@ -266,6 +276,13 @@
 	mapping = pci_map_single(priv->pdev, skb->data,
 				 skb->len, PCI_DMA_TODEVICE);
 
+	if (pci_dma_mapping_error(priv->pdev, mapping)) {
+		kfree_skb(skb);
+		dev_err(&priv->pdev->dev, "TX DMA mapping error\n");
+		return;
+
+	}
+
 	tx_flags = RTL818X_TX_DESC_FLAG_OWN | RTL818X_TX_DESC_FLAG_FS |
 		   RTL818X_TX_DESC_FLAG_LS |
 		   (ieee80211_get_tx_rate(dev, info)->hw_value << 24) |
diff --git a/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h b/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h
index 56aee06..a6ad79f 100644
--- a/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h
+++ b/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h
@@ -15,6 +15,8 @@
 #ifndef RTL8187_H
 #define RTL8187_H
 
+#include <linux/cache.h>
+
 #include "rtl818x.h"
 #include "leds.h"
 
@@ -139,7 +141,10 @@
 	u8 aifsn[4];
 	u8 rfkill_mask;
 	struct {
-		__le64 buf;
+		union {
+			__le64 buf;
+			u8 dummy1[L1_CACHE_BYTES];
+		} ____cacheline_aligned;
 		struct sk_buff_head queue;
 	} b_tx_status; /* This queue is used by both -b and non-b devices */
 	struct mutex io_mutex;
@@ -147,7 +152,8 @@
 		u8 bits8;
 		__le16 bits16;
 		__le32 bits32;
-	} *io_dmabuf;
+		u8 dummy2[L1_CACHE_BYTES];
+	} *io_dmabuf ____cacheline_aligned;
 	bool rfkill_off;
 	u16 seqno;
 };
diff --git a/drivers/net/wireless/rtlwifi/ps.c b/drivers/net/wireless/rtlwifi/ps.c
index deedae3..d1c0191 100644
--- a/drivers/net/wireless/rtlwifi/ps.c
+++ b/drivers/net/wireless/rtlwifi/ps.c
@@ -48,7 +48,7 @@
 
 	/*<2> Enable Adapter */
 	if (rtlpriv->cfg->ops->hw_init(hw))
-		return 1;
+		return false;
 	RT_CLEAR_PS_LEVEL(ppsc, RT_RF_OFF_LEVL_HALT_NIC);
 
 	/*<3> Enable Interrupt */
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
index a82b30a..2eb0b38 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
@@ -937,14 +937,26 @@
 	bool is92c;
 	int err;
 	u8 tmp_u1b;
+	unsigned long flags;
 
 	rtlpci->being_init_adapter = true;
+
+	/* Since this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 	rtstatus = _rtl92ce_init_mac(hw);
 	if (!rtstatus) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 
 	err = rtl92c_download_fw(hw);
@@ -952,7 +964,7 @@
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 
 	rtlhal->last_hmeboxnum = 0;
@@ -1032,6 +1044,8 @@
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE, "under 1.5V\n");
 	}
 	rtl92c_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpci->being_init_adapter = false;
 	return err;
 }
diff --git a/drivers/net/wireless/ti/wl1251/rx.c b/drivers/net/wireless/ti/wl1251/rx.c
index 123c4bb..cde0eaf 100644
--- a/drivers/net/wireless/ti/wl1251/rx.c
+++ b/drivers/net/wireless/ti/wl1251/rx.c
@@ -180,7 +180,7 @@
 	wl1251_mem_read(wl, rx_packet_ring_addr, rx_buffer, length);
 
 	/* The actual length doesn't include the target's alignment */
-	skb->len = desc->length  - PLCP_HEADER_LENGTH;
+	skb_trim(skb, desc->length - PLCP_HEADER_LENGTH);
 
 	fc = (u16 *)skb->data;
 
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 4c76bcb..ae413a2 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -143,11 +143,7 @@
 	char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
 	struct xen_netif_rx_back_ring rx;
 	struct sk_buff_head rx_queue;
-	bool rx_queue_stopped;
-	/* Set when the RX interrupt is triggered by the frontend.
-	 * The worker thread may need to wake the queue.
-	 */
-	bool rx_event;
+	RING_IDX rx_last_skb_slots;
 
 	/* This array is allocated seperately as it is large */
 	struct gnttab_copy *grant_copy_op;
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index b9de31e..301cc03 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -100,7 +100,6 @@
 {
 	struct xenvif *vif = dev_id;
 
-	vif->rx_event = true;
 	xenvif_kick_thread(vif);
 
 	return IRQ_HANDLED;
@@ -133,8 +132,7 @@
 	/* If the skb is GSO then we'll also need an extra slot for the
 	 * metadata.
 	 */
-	if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
-	    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+	if (skb_is_gso(skb))
 		min_slots_needed++;
 
 	/* If the skb can't possibly fit in the remaining slots
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 6b62c3e..438d0c0 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -240,7 +240,7 @@
 	struct gnttab_copy *copy_gop;
 	struct xenvif_rx_meta *meta;
 	unsigned long bytes;
-	int gso_type;
+	int gso_type = XEN_NETIF_GSO_TYPE_NONE;
 
 	/* Data must not cross a page boundary. */
 	BUG_ON(size + offset > PAGE_SIZE<<compound_order(page));
@@ -299,12 +299,12 @@
 		}
 
 		/* Leave a gap for the GSO descriptor. */
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
-			gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
-		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
-			gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
-		else
-			gso_type = XEN_NETIF_GSO_TYPE_NONE;
+		if (skb_is_gso(skb)) {
+			if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+				gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
+			else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+				gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
+		}
 
 		if (*head && ((1 << gso_type) & vif->gso_mask))
 			vif->rx.req_cons++;
@@ -338,19 +338,15 @@
 	int head = 1;
 	int old_meta_prod;
 	int gso_type;
-	int gso_size;
 
 	old_meta_prod = npo->meta_prod;
 
-	if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
-		gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
-		gso_size = skb_shinfo(skb)->gso_size;
-	} else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) {
-		gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
-		gso_size = skb_shinfo(skb)->gso_size;
-	} else {
-		gso_type = XEN_NETIF_GSO_TYPE_NONE;
-		gso_size = 0;
+	gso_type = XEN_NETIF_GSO_TYPE_NONE;
+	if (skb_is_gso(skb)) {
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+			gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
+		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+			gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
 	}
 
 	/* Set up a GSO prefix descriptor, if necessary */
@@ -358,7 +354,7 @@
 		req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
 		meta = npo->meta + npo->meta_prod++;
 		meta->gso_type = gso_type;
-		meta->gso_size = gso_size;
+		meta->gso_size = skb_shinfo(skb)->gso_size;
 		meta->size = 0;
 		meta->id = req->id;
 	}
@@ -368,7 +364,7 @@
 
 	if ((1 << gso_type) & vif->gso_mask) {
 		meta->gso_type = gso_type;
-		meta->gso_size = gso_size;
+		meta->gso_size = skb_shinfo(skb)->gso_size;
 	} else {
 		meta->gso_type = XEN_NETIF_GSO_TYPE_NONE;
 		meta->gso_size = 0;
@@ -476,7 +472,6 @@
 	unsigned long offset;
 	struct skb_cb_overlay *sco;
 	bool need_to_notify = false;
-	bool ring_full = false;
 
 	struct netrx_pending_operations npo = {
 		.copy  = vif->grant_copy_op,
@@ -486,7 +481,7 @@
 	skb_queue_head_init(&rxq);
 
 	while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) {
-		int max_slots_needed;
+		RING_IDX max_slots_needed;
 		int i;
 
 		/* We need a cheap worse case estimate for the number of
@@ -501,17 +496,19 @@
 			size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
 			max_slots_needed += DIV_ROUND_UP(size, PAGE_SIZE);
 		}
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
-		    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+		if (skb_is_gso(skb) &&
+		   (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
+		    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6))
 			max_slots_needed++;
 
 		/* If the skb may not fit then bail out now */
 		if (!xenvif_rx_ring_slots_available(vif, max_slots_needed)) {
 			skb_queue_head(&vif->rx_queue, skb);
 			need_to_notify = true;
-			ring_full = true;
+			vif->rx_last_skb_slots = max_slots_needed;
 			break;
-		}
+		} else
+			vif->rx_last_skb_slots = 0;
 
 		sco = (struct skb_cb_overlay *)skb->cb;
 		sco->meta_slots_used = xenvif_gop_skb(skb, &npo);
@@ -522,8 +519,6 @@
 
 	BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta));
 
-	vif->rx_queue_stopped = !npo.copy_prod && ring_full;
-
 	if (!npo.copy_prod)
 		goto done;
 
@@ -1473,8 +1468,8 @@
 
 static inline int rx_work_todo(struct xenvif *vif)
 {
-	return (!skb_queue_empty(&vif->rx_queue) && !vif->rx_queue_stopped) ||
-		vif->rx_event;
+	return !skb_queue_empty(&vif->rx_queue) &&
+	       xenvif_rx_ring_slots_available(vif, vif->rx_last_skb_slots);
 }
 
 static inline int tx_work_todo(struct xenvif *vif)
@@ -1560,8 +1555,6 @@
 		if (!skb_queue_empty(&vif->rx_queue))
 			xenvif_rx_action(vif);
 
-		vif->rx_event = false;
-
 		if (skb_queue_empty(&vif->rx_queue) &&
 		    netif_queue_stopped(vif->dev))
 			xenvif_start_queue(vif);
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index ff04d4f..e30d800 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -907,6 +907,7 @@
 
 		/* Ethernet work: Delayed to here as it peeks the header. */
 		skb->protocol = eth_type_trans(skb, dev);
+		skb_reset_network_header(skb);
 
 		if (checksum_setup(dev, skb)) {
 			kfree_skb(skb);
@@ -1832,7 +1833,6 @@
 	case XenbusStateReconfiguring:
 	case XenbusStateReconfigured:
 	case XenbusStateUnknown:
-	case XenbusStateClosed:
 		break;
 
 	case XenbusStateInitWait:
@@ -1847,6 +1847,10 @@
 		netdev_notify_peers(netdev);
 		break;
 
+	case XenbusStateClosed:
+		if (dev->state == XenbusStateClosed)
+			break;
+		/* Missed the backend's CLOSING state -- fallthrough */
 	case XenbusStateClosing:
 		xenbus_frontend_closed(dev);
 		break;
diff --git a/drivers/of/address.c b/drivers/of/address.c
index d3dd41c..1a54f1f 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -99,11 +99,12 @@
 static int of_bus_pci_match(struct device_node *np)
 {
 	/*
+ 	 * "pciex" is PCI Express
 	 * "vci" is for the /chaos bridge on 1st-gen PCI powermacs
 	 * "ht" is hypertransport
 	 */
-	return !strcmp(np->type, "pci") || !strcmp(np->type, "vci") ||
-		!strcmp(np->type, "ht");
+	return !strcmp(np->type, "pci") || !strcmp(np->type, "pciex") ||
+		!strcmp(np->type, "vci") || !strcmp(np->type, "ht");
 }
 
 static void of_bus_pci_count_cells(struct device_node *np,
diff --git a/drivers/of/base.c b/drivers/of/base.c
index ff85450..89e888a 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -342,27 +342,72 @@
 }
 EXPORT_SYMBOL(of_get_cpu_node);
 
-/** Checks if the given "compat" string matches one of the strings in
- * the device's "compatible" property
+/**
+ * __of_device_is_compatible() - Check if the node matches given constraints
+ * @device: pointer to node
+ * @compat: required compatible string, NULL or "" for any match
+ * @type: required device_type value, NULL or "" for any match
+ * @name: required node name, NULL or "" for any match
+ *
+ * Checks if the given @compat, @type and @name strings match the
+ * properties of the given @device. A constraints can be skipped by
+ * passing NULL or an empty string as the constraint.
+ *
+ * Returns 0 for no match, and a positive integer on match. The return
+ * value is a relative score with larger values indicating better
+ * matches. The score is weighted for the most specific compatible value
+ * to get the highest score. Matching type is next, followed by matching
+ * name. Practically speaking, this results in the following priority
+ * order for matches:
+ *
+ * 1. specific compatible && type && name
+ * 2. specific compatible && type
+ * 3. specific compatible && name
+ * 4. specific compatible
+ * 5. general compatible && type && name
+ * 6. general compatible && type
+ * 7. general compatible && name
+ * 8. general compatible
+ * 9. type && name
+ * 10. type
+ * 11. name
  */
 static int __of_device_is_compatible(const struct device_node *device,
-				     const char *compat)
+				     const char *compat, const char *type, const char *name)
 {
-	const char* cp;
-	int cplen, l;
+	struct property *prop;
+	const char *cp;
+	int index = 0, score = 0;
 
-	cp = __of_get_property(device, "compatible", &cplen);
-	if (cp == NULL)
-		return 0;
-	while (cplen > 0) {
-		if (of_compat_cmp(cp, compat, strlen(compat)) == 0)
-			return 1;
-		l = strlen(cp) + 1;
-		cp += l;
-		cplen -= l;
+	/* Compatible match has highest priority */
+	if (compat && compat[0]) {
+		prop = __of_find_property(device, "compatible", NULL);
+		for (cp = of_prop_next_string(prop, NULL); cp;
+		     cp = of_prop_next_string(prop, cp), index++) {
+			if (of_compat_cmp(cp, compat, strlen(compat)) == 0) {
+				score = INT_MAX/2 - (index << 2);
+				break;
+			}
+		}
+		if (!score)
+			return 0;
 	}
 
-	return 0;
+	/* Matching type is better than matching name */
+	if (type && type[0]) {
+		if (!device->type || of_node_cmp(type, device->type))
+			return 0;
+		score += 2;
+	}
+
+	/* Matching name is a bit better than not */
+	if (name && name[0]) {
+		if (!device->name || of_node_cmp(name, device->name))
+			return 0;
+		score++;
+	}
+
+	return score;
 }
 
 /** Checks if the given "compat" string matches one of the strings in
@@ -375,7 +420,7 @@
 	int res;
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
-	res = __of_device_is_compatible(device, compat);
+	res = __of_device_is_compatible(device, compat, NULL, NULL);
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return res;
 }
@@ -681,10 +726,7 @@
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 	np = from ? from->allnext : of_allnodes;
 	for (; np; np = np->allnext) {
-		if (type
-		    && !(np->type && (of_node_cmp(np->type, type) == 0)))
-			continue;
-		if (__of_device_is_compatible(np, compatible) &&
+		if (__of_device_is_compatible(np, compatible, type, NULL) &&
 		    of_node_get(np))
 			break;
 	}
@@ -734,43 +776,22 @@
 const struct of_device_id *__of_match_node(const struct of_device_id *matches,
 					   const struct device_node *node)
 {
-	const char *cp;
-	int cplen, l;
+	const struct of_device_id *best_match = NULL;
+	int score, best_score = 0;
 
 	if (!matches)
 		return NULL;
 
-	cp = __of_get_property(node, "compatible", &cplen);
-	do {
-		const struct of_device_id *m = matches;
-
-		/* Check against matches with current compatible string */
-		while (m->name[0] || m->type[0] || m->compatible[0]) {
-			int match = 1;
-			if (m->name[0])
-				match &= node->name
-					&& !strcmp(m->name, node->name);
-			if (m->type[0])
-				match &= node->type
-					&& !strcmp(m->type, node->type);
-			if (m->compatible[0])
-				match &= cp
-					&& !of_compat_cmp(m->compatible, cp,
-							strlen(m->compatible));
-			if (match)
-				return m;
-			m++;
+	for (; matches->name[0] || matches->type[0] || matches->compatible[0]; matches++) {
+		score = __of_device_is_compatible(node, matches->compatible,
+						  matches->type, matches->name);
+		if (score > best_score) {
+			best_match = matches;
+			best_score = score;
 		}
+	}
 
-		/* Get node's next compatible string */ 
-		if (cp) {
-			l = strlen(cp) + 1;
-			cp += l;
-			cplen -= l;
-		}
-	} while (cp && (cplen > 0));
-
-	return NULL;
+	return best_match;
 }
 
 /**
@@ -778,10 +799,7 @@
  *	@matches:	array of of device match structures to search in
  *	@node:		the of device structure to match against
  *
- *	Low level utility function used by device matching. Matching order
- *	is to compare each of the node's compatibles with all given matches
- *	first. This implies node's compatible is sorted from specific to
- *	generic while matches can be in any order.
+ *	Low level utility function used by device matching.
  */
 const struct of_device_id *of_match_node(const struct of_device_id *matches,
 					 const struct device_node *node)
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 875b7b6..5b3c24f 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -24,7 +24,11 @@
 
 static void of_set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	phydev->supported |= PHY_DEFAULT_FEATURES;
+	/* The default values for phydev->supported are provided by the PHY
+	 * driver "features" member, we want to reset to sane defaults fist
+	 * before supporting higher speeds.
+	 */
+	phydev->supported &= PHY_DEFAULT_FEATURES;
 
 	switch (max_speed) {
 	default:
@@ -44,7 +48,7 @@
 {
 	struct phy_device *phy;
 	bool is_c45;
-	int rc, prev_irq;
+	int rc;
 	u32 max_speed = 0;
 
 	is_c45 = of_device_is_compatible(child,
@@ -54,12 +58,14 @@
 	if (!phy || IS_ERR(phy))
 		return 1;
 
-	if (mdio->irq) {
-		prev_irq = mdio->irq[addr];
-		mdio->irq[addr] =
-			irq_of_parse_and_map(child, 0);
-		if (!mdio->irq[addr])
-			mdio->irq[addr] = prev_irq;
+	rc = irq_of_parse_and_map(child, 0);
+	if (rc > 0) {
+		phy->irq = rc;
+		if (mdio->irq)
+			mdio->irq[addr] = rc;
+	} else {
+		if (mdio->irq)
+			phy->irq = mdio->irq[addr];
 	}
 
 	/* Associate the OF node with the device structure so it
diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c
index e21012b..6643d19 100644
--- a/drivers/of/selftest.c
+++ b/drivers/of/selftest.c
@@ -300,6 +300,72 @@
 	of_node_put(np);
 }
 
+static struct of_device_id match_node_table[] = {
+	{ .data = "A", .name = "name0", }, /* Name alone is lowest priority */
+	{ .data = "B", .type = "type1", }, /* followed by type alone */
+
+	{ .data = "Ca", .name = "name2", .type = "type1", }, /* followed by both together */
+	{ .data = "Cb", .name = "name2", }, /* Only match when type doesn't match */
+	{ .data = "Cc", .name = "name2", .type = "type2", },
+
+	{ .data = "E", .compatible = "compat3" },
+	{ .data = "G", .compatible = "compat2", },
+	{ .data = "H", .compatible = "compat2", .name = "name5", },
+	{ .data = "I", .compatible = "compat2", .type = "type1", },
+	{ .data = "J", .compatible = "compat2", .type = "type1", .name = "name8", },
+	{ .data = "K", .compatible = "compat2", .name = "name9", },
+	{}
+};
+
+static struct {
+	const char *path;
+	const char *data;
+} match_node_tests[] = {
+	{ .path = "/testcase-data/match-node/name0", .data = "A", },
+	{ .path = "/testcase-data/match-node/name1", .data = "B", },
+	{ .path = "/testcase-data/match-node/a/name2", .data = "Ca", },
+	{ .path = "/testcase-data/match-node/b/name2", .data = "Cb", },
+	{ .path = "/testcase-data/match-node/c/name2", .data = "Cc", },
+	{ .path = "/testcase-data/match-node/name3", .data = "E", },
+	{ .path = "/testcase-data/match-node/name4", .data = "G", },
+	{ .path = "/testcase-data/match-node/name5", .data = "H", },
+	{ .path = "/testcase-data/match-node/name6", .data = "G", },
+	{ .path = "/testcase-data/match-node/name7", .data = "I", },
+	{ .path = "/testcase-data/match-node/name8", .data = "J", },
+	{ .path = "/testcase-data/match-node/name9", .data = "K", },
+};
+
+static void __init of_selftest_match_node(void)
+{
+	struct device_node *np;
+	const struct of_device_id *match;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(match_node_tests); i++) {
+		np = of_find_node_by_path(match_node_tests[i].path);
+		if (!np) {
+			selftest(0, "missing testcase node %s\n",
+				match_node_tests[i].path);
+			continue;
+		}
+
+		match = of_match_node(match_node_table, np);
+		if (!match) {
+			selftest(0, "%s didn't match anything\n",
+				match_node_tests[i].path);
+			continue;
+		}
+
+		if (strcmp(match->data, match_node_tests[i].data) != 0) {
+			selftest(0, "%s got wrong match. expected %s, got %s\n",
+				match_node_tests[i].path, match_node_tests[i].data,
+				(const char *)match->data);
+			continue;
+		}
+		selftest(1, "passed");
+	}
+}
+
 static int __init of_selftest(void)
 {
 	struct device_node *np;
@@ -316,6 +382,7 @@
 	of_selftest_property_match_string();
 	of_selftest_parse_interrupts();
 	of_selftest_parse_interrupts_extended();
+	of_selftest_match_node();
 	pr_info("end of selftest - %i passed, %i failed\n",
 		selftest_results.passed, selftest_results.failed);
 	return 0;
diff --git a/drivers/of/testcase-data/testcases.dtsi b/drivers/of/testcase-data/testcases.dtsi
new file mode 100644
index 0000000..3a5b75a
--- /dev/null
+++ b/drivers/of/testcase-data/testcases.dtsi
@@ -0,0 +1,3 @@
+#include "tests-phandle.dtsi"
+#include "tests-interrupts.dtsi"
+#include "tests-match.dtsi"
diff --git a/arch/arm/boot/dts/testcases/tests-interrupts.dtsi b/drivers/of/testcase-data/tests-interrupts.dtsi
similarity index 100%
rename from arch/arm/boot/dts/testcases/tests-interrupts.dtsi
rename to drivers/of/testcase-data/tests-interrupts.dtsi
diff --git a/drivers/of/testcase-data/tests-match.dtsi b/drivers/of/testcase-data/tests-match.dtsi
new file mode 100644
index 0000000..c9e5411
--- /dev/null
+++ b/drivers/of/testcase-data/tests-match.dtsi
@@ -0,0 +1,19 @@
+
+/ {
+	testcase-data {
+		match-node {
+			name0 { };
+			name1 { device_type = "type1"; };
+			a { name2 { device_type = "type1"; }; };
+			b { name2 { }; };
+			c { name2 { device_type = "type2"; }; };
+			name3 { compatible = "compat3"; };
+			name4 { compatible = "compat2", "compat3"; };
+			name5 { compatible = "compat2", "compat3"; };
+			name6 { compatible = "compat1", "compat2", "compat3"; };
+			name7 { compatible = "compat2"; device_type = "type1"; };
+			name8 { compatible = "compat2"; device_type = "type1"; };
+			name9 { compatible = "compat2"; };
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/testcases/tests-phandle.dtsi b/drivers/of/testcase-data/tests-phandle.dtsi
similarity index 100%
rename from arch/arm/boot/dts/testcases/tests-phandle.dtsi
rename to drivers/of/testcase-data/tests-phandle.dtsi
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 00660cc..3890166 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -162,8 +162,6 @@
 
 		avail = *r;
 		pci_clip_resource_to_region(bus, &avail, region);
-		if (!resource_size(&avail))
-			continue;
 
 		/*
 		 * "min" is typically PCIBIOS_MIN_IO or PCIBIOS_MIN_MEM to
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index 13478ec..0e79665 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -60,14 +60,6 @@
 #define PCIE_DEBUG_CTRL         0x1a60
 #define  PCIE_DEBUG_SOFT_RESET		BIT(20)
 
-/*
- * This product ID is registered by Marvell, and used when the Marvell
- * SoC is not the root complex, but an endpoint on the PCIe bus. It is
- * therefore safe to re-use this PCI ID for our emulated PCI-to-PCI
- * bridge.
- */
-#define MARVELL_EMULATED_PCI_PCI_BRIDGE_ID 0x7846
-
 /* PCI configuration space of a PCI-to-PCI bridge */
 struct mvebu_sw_pci_bridge {
 	u16 vendor;
@@ -388,7 +380,8 @@
 
 	bridge->class = PCI_CLASS_BRIDGE_PCI;
 	bridge->vendor = PCI_VENDOR_ID_MARVELL;
-	bridge->device = MARVELL_EMULATED_PCI_PCI_BRIDGE_ID;
+	bridge->device = mvebu_readl(port, PCIE_DEV_ID_OFF) >> 16;
+	bridge->revision = mvebu_readl(port, PCIE_DEV_REV_OFF) & 0xff;
 	bridge->header_type = PCI_HEADER_TYPE_BRIDGE;
 	bridge->cache_line_size = 0x10;
 
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index cd929ae..7c7a388 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -210,10 +210,29 @@
 	}
 }
 
+static void dock_event(acpi_handle handle, u32 type, void *data)
+{
+	struct acpiphp_context *context;
+
+	mutex_lock(&acpiphp_context_lock);
+	context = acpiphp_get_context(handle);
+	if (!context || WARN_ON(context->handle != handle)
+	    || context->func.parent->is_going_away) {
+		mutex_unlock(&acpiphp_context_lock);
+		return;
+	}
+	get_bridge(context->func.parent);
+	acpiphp_put_context(context);
+	mutex_unlock(&acpiphp_context_lock);
+
+	hotplug_event(handle, type, data);
+
+	put_bridge(context->func.parent);
+}
 
 static const struct acpi_dock_ops acpiphp_dock_ops = {
 	.fixup = post_dock_fixups,
-	.handler = hotplug_event,
+	.handler = dock_event,
 };
 
 /* Check whether the PCI device is managed by native PCIe hotplug driver */
@@ -441,7 +460,9 @@
 	list_del(&bridge->list);
 	mutex_unlock(&bridge_mutex);
 
+	mutex_lock(&acpiphp_context_lock);
 	bridge->is_going_away = true;
+	mutex_unlock(&acpiphp_context_lock);
 }
 
 /**
@@ -709,6 +730,17 @@
 	return (unsigned int)sta;
 }
 
+static inline bool device_status_valid(unsigned int sta)
+{
+	/*
+	 * ACPI spec says that _STA may return bit 0 clear with bit 3 set
+	 * if the device is valid but does not require a device driver to be
+	 * loaded (Section 6.3.7 of ACPI 5.0A).
+	 */
+	unsigned int mask = ACPI_STA_DEVICE_ENABLED | ACPI_STA_DEVICE_FUNCTIONING;
+	return (sta & mask) == mask;
+}
+
 /**
  * trim_stale_devices - remove PCI devices that are not responding.
  * @dev: PCI device to start walking the hierarchy from.
@@ -724,7 +756,7 @@
 		unsigned long long sta;
 
 		status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
-		alive = (ACPI_SUCCESS(status) && sta == ACPI_STA_ALL)
+		alive = (ACPI_SUCCESS(status) && device_status_valid(sta))
 			|| acpiphp_no_hotplug(handle);
 	}
 	if (!alive) {
@@ -742,7 +774,7 @@
 
 		/* The device is a bridge. so check the bus below it. */
 		pm_runtime_get_sync(&dev->dev);
-		list_for_each_entry_safe(child, tmp, &bus->devices, bus_list)
+		list_for_each_entry_safe_reverse(child, tmp, &bus->devices, bus_list)
 			trim_stale_devices(child);
 
 		pm_runtime_put(&dev->dev);
@@ -771,10 +803,10 @@
 		mutex_lock(&slot->crit_sect);
 		if (slot_no_hotplug(slot)) {
 			; /* do nothing */
-		} else if (get_slot_status(slot) == ACPI_STA_ALL) {
+		} else if (device_status_valid(get_slot_status(slot))) {
 			/* remove stale devices if any */
-			list_for_each_entry_safe(dev, tmp, &bus->devices,
-						 bus_list)
+			list_for_each_entry_safe_reverse(dev, tmp,
+							 &bus->devices, bus_list)
 				if (PCI_SLOT(dev->devfn) == slot->device)
 					trim_stale_devices(dev);
 
@@ -805,7 +837,7 @@
 	int i;
 	unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM;
 
-	list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
+	list_for_each_entry_safe_reverse(dev, tmp, &bus->devices, bus_list) {
 		for (i=0; i<PCI_BRIDGE_RESOURCES; i++) {
 			struct resource *res = &dev->resource[i];
 			if ((res->flags & type_mask) && !res->start &&
@@ -829,7 +861,11 @@
 
 	bridge = acpiphp_handle_to_bridge(handle);
 	if (bridge) {
+		pci_lock_rescan_remove();
+
 		acpiphp_check_bridge(bridge);
+
+		pci_unlock_rescan_remove();
 		put_bridge(bridge);
 	}
 }
@@ -852,6 +888,7 @@
 
 	mutex_unlock(&acpiphp_context_lock);
 
+	pci_lock_rescan_remove();
 	acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
 
 	switch (type) {
@@ -905,6 +942,7 @@
 		break;
 	}
 
+	pci_unlock_rescan_remove();
 	if (bridge)
 		put_bridge(bridge);
 }
@@ -915,11 +953,9 @@
 	acpi_handle handle = context->handle;
 
 	acpi_scan_lock_acquire();
-	pci_lock_rescan_remove();
 
 	hotplug_event(handle, type, context);
 
-	pci_unlock_rescan_remove();
 	acpi_scan_lock_release();
 	acpi_evaluate_hotplug_ost(handle, type, ACPI_OST_SC_SUCCESS, NULL);
 	put_bridge(context->func.parent);
@@ -937,6 +973,7 @@
 {
 	struct acpiphp_context *context;
 	u32 ost_code = ACPI_OST_SC_SUCCESS;
+	acpi_status status;
 
 	switch (type) {
 	case ACPI_NOTIFY_BUS_CHECK:
@@ -972,13 +1009,20 @@
 
 	mutex_lock(&acpiphp_context_lock);
 	context = acpiphp_get_context(handle);
-	if (context && !WARN_ON(context->handle != handle)) {
-		get_bridge(context->func.parent);
-		acpiphp_put_context(context);
-		acpi_hotplug_execute(hotplug_event_work, context, type);
+	if (!context || WARN_ON(context->handle != handle)
+	    || context->func.parent->is_going_away)
+		goto err_out;
+
+	get_bridge(context->func.parent);
+	acpiphp_put_context(context);
+	status = acpi_hotplug_execute(hotplug_event_work, context, type);
+	if (ACPI_SUCCESS(status)) {
 		mutex_unlock(&acpiphp_context_lock);
 		return;
 	}
+	put_bridge(context->func.parent);
+
+ err_out:
 	mutex_unlock(&acpiphp_context_lock);
 	ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE;
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 7a0fec6..955ab79 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -545,9 +545,15 @@
 		return -ENOMEM;
 	list_for_each_entry(entry, &pdev->msi_list, list) {
 		char *name = kmalloc(20, GFP_KERNEL);
-		msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL);
-		if (!msi_dev_attr)
+		if (!name)
 			goto error_attrs;
+
+		msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL);
+		if (!msi_dev_attr) {
+			kfree(name);
+			goto error_attrs;
+		}
+
 		sprintf(name, "%d", entry->irq);
 		sysfs_attr_init(&msi_dev_attr->attr);
 		msi_dev_attr->attr.name = name;
@@ -589,6 +595,7 @@
 		++count;
 		msi_attr = msi_attrs[count];
 	}
+	kfree(msi_attrs);
 	return ret;
 }
 
@@ -959,7 +966,6 @@
 /**
  * pci_msix_vec_count - return the number of device's MSI-X table entries
  * @dev: pointer to the pci_dev data structure of MSI-X device function
-
  * This function returns the number of device's MSI-X table entries and
  * therefore the number of MSI-X vectors device is capable of sending.
  * It returns a negative errno if the device is not capable of sending MSI-X
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1febe90..fdbc294 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1181,6 +1181,8 @@
 static int do_pci_enable_device(struct pci_dev *dev, int bars)
 {
 	int err;
+	u16 cmd;
+	u8 pin;
 
 	err = pci_set_power_state(dev, PCI_D0);
 	if (err < 0 && err != -EIO)
@@ -1190,6 +1192,17 @@
 		return err;
 	pci_fixup_device(pci_fixup_enable, dev);
 
+	if (dev->msi_enabled || dev->msix_enabled)
+		return 0;
+
+	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+	if (pin) {
+		pci_read_config_word(dev, PCI_COMMAND, &cmd);
+		if (cmd & PCI_COMMAND_INTX_DISABLE)
+			pci_write_config_word(dev, PCI_COMMAND,
+					      cmd & ~PCI_COMMAND_INTX_DISABLE);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index afa2354..c7a551c 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -5,7 +5,7 @@
 menu "PHY Subsystem"
 
 config GENERIC_PHY
-	tristate "PHY Core"
+	bool "PHY Core"
 	help
 	  Generic PHY support.
 
@@ -61,6 +61,7 @@
 config BCM_KONA_USB2_PHY
 	tristate "Broadcom Kona USB2 PHY Driver"
 	depends on GENERIC_PHY
+	depends on HAS_IOMEM
 	help
 	  Enable this to support the Broadcom Kona USB 2.0 PHY.
 
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 645c867..6c73837 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -162,6 +162,9 @@
 {
 	int ret;
 
+	if (!phy)
+		return 0;
+
 	ret = phy_pm_runtime_get_sync(phy);
 	if (ret < 0 && ret != -ENOTSUPP)
 		return ret;
@@ -173,6 +176,8 @@
 			dev_err(&phy->dev, "phy init failed --> %d\n", ret);
 			goto out;
 		}
+	} else {
+		ret = 0; /* Override possible ret == -ENOTSUPP */
 	}
 	++phy->init_count;
 
@@ -187,6 +192,9 @@
 {
 	int ret;
 
+	if (!phy)
+		return 0;
+
 	ret = phy_pm_runtime_get_sync(phy);
 	if (ret < 0 && ret != -ENOTSUPP)
 		return ret;
@@ -212,6 +220,9 @@
 {
 	int ret;
 
+	if (!phy)
+		return 0;
+
 	ret = phy_pm_runtime_get_sync(phy);
 	if (ret < 0 && ret != -ENOTSUPP)
 		return ret;
@@ -223,6 +234,8 @@
 			dev_err(&phy->dev, "phy poweron failed --> %d\n", ret);
 			goto out;
 		}
+	} else {
+		ret = 0; /* Override possible ret == -ENOTSUPP */
 	}
 	++phy->power_count;
 	mutex_unlock(&phy->mutex);
@@ -240,6 +253,9 @@
 {
 	int ret;
 
+	if (!phy)
+		return 0;
+
 	mutex_lock(&phy->mutex);
 	if (phy->power_count == 1 && phy->ops->power_off) {
 		ret =  phy->ops->power_off(phy);
@@ -308,7 +324,7 @@
  */
 void phy_put(struct phy *phy)
 {
-	if (IS_ERR(phy))
+	if (!phy || IS_ERR(phy))
 		return;
 
 	module_put(phy->ops->owner);
@@ -328,6 +344,9 @@
 {
 	int r;
 
+	if (!phy)
+		return;
+
 	r = devres_destroy(dev, devm_phy_release, devm_phy_match, phy);
 	dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n");
 }
@@ -389,17 +408,11 @@
 		index = of_property_match_string(dev->of_node, "phy-names",
 			string);
 		phy = of_phy_get(dev, index);
-		if (IS_ERR(phy)) {
-			dev_err(dev, "unable to find phy\n");
-			return phy;
-		}
 	} else {
 		phy = phy_lookup(dev, string);
-		if (IS_ERR(phy)) {
-			dev_err(dev, "unable to find phy\n");
-			return phy;
-		}
 	}
+	if (IS_ERR(phy))
+		return phy;
 
 	if (!try_module_get(phy->ops->owner))
 		return ERR_PTR(-EPROBE_DEFER);
@@ -411,6 +424,27 @@
 EXPORT_SYMBOL_GPL(phy_get);
 
 /**
+ * phy_optional_get() - lookup and obtain a reference to an optional phy.
+ * @dev: device that requests this phy
+ * @string: the phy name as given in the dt data or the name of the controller
+ * port for non-dt case
+ *
+ * Returns the phy driver, after getting a refcount to it; or
+ * NULL if there is no such phy.  The caller is responsible for
+ * calling phy_put() to release that count.
+ */
+struct phy *phy_optional_get(struct device *dev, const char *string)
+{
+	struct phy *phy = phy_get(dev, string);
+
+	if (PTR_ERR(phy) == -ENODEV)
+		phy = NULL;
+
+	return phy;
+}
+EXPORT_SYMBOL_GPL(phy_optional_get);
+
+/**
  * devm_phy_get() - lookup and obtain a reference to a phy.
  * @dev: device that requests this phy
  * @string: the phy name as given in the dt data or phy device name
@@ -441,6 +475,30 @@
 EXPORT_SYMBOL_GPL(devm_phy_get);
 
 /**
+ * devm_phy_optional_get() - lookup and obtain a reference to an optional phy.
+ * @dev: device that requests this phy
+ * @string: the phy name as given in the dt data or phy device name
+ * for non-dt case
+ *
+ * Gets the phy using phy_get(), and associates a device with it using
+ * devres. On driver detach, release function is invoked on the devres
+ * data, then, devres data is freed. This differs to devm_phy_get() in
+ * that if the phy does not exist, it is not considered an error and
+ * -ENODEV will not be returned. Instead the NULL phy is returned,
+ * which can be passed to all other phy consumer calls.
+ */
+struct phy *devm_phy_optional_get(struct device *dev, const char *string)
+{
+	struct phy *phy = devm_phy_get(dev, string);
+
+	if (PTR_ERR(phy) == -ENODEV)
+		phy = NULL;
+
+	return phy;
+}
+EXPORT_SYMBOL_GPL(devm_phy_optional_get);
+
+/**
  * phy_create() - create a new phy
  * @dev: device that is creating the new phy
  * @ops: function pointers for performing phy operations
diff --git a/drivers/phy/phy-exynos-dp-video.c b/drivers/phy/phy-exynos-dp-video.c
index 1dbe6ce..0786fef 100644
--- a/drivers/phy/phy-exynos-dp-video.c
+++ b/drivers/phy/phy-exynos-dp-video.c
@@ -76,10 +76,6 @@
 	if (IS_ERR(state->regs))
 		return PTR_ERR(state->regs);
 
-	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
-
 	phy = devm_phy_create(dev, &exynos_dp_video_phy_ops, NULL);
 	if (IS_ERR(phy)) {
 		dev_err(dev, "failed to create Display Port PHY\n");
@@ -87,6 +83,10 @@
 	}
 	phy_set_drvdata(phy, state);
 
+	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+	if (IS_ERR(phy_provider))
+		return PTR_ERR(phy_provider);
+
 	return 0;
 }
 
diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c
index 0c5efab..7f13932 100644
--- a/drivers/phy/phy-exynos-mipi-video.c
+++ b/drivers/phy/phy-exynos-mipi-video.c
@@ -134,11 +134,6 @@
 	dev_set_drvdata(dev, state);
 	spin_lock_init(&state->slock);
 
-	phy_provider = devm_of_phy_provider_register(dev,
-					exynos_mipi_video_phy_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
-
 	for (i = 0; i < EXYNOS_MIPI_PHYS_NUM; i++) {
 		struct phy *phy = devm_phy_create(dev,
 					&exynos_mipi_video_phy_ops, NULL);
@@ -152,6 +147,11 @@
 		phy_set_drvdata(phy, &state->phys[i]);
 	}
 
+	phy_provider = devm_of_phy_provider_register(dev,
+					exynos_mipi_video_phy_xlate);
+	if (IS_ERR(phy_provider))
+		return PTR_ERR(phy_provider);
+
 	return 0;
 }
 
diff --git a/drivers/phy/phy-mvebu-sata.c b/drivers/phy/phy-mvebu-sata.c
index d43786f..d70ecd6 100644
--- a/drivers/phy/phy-mvebu-sata.c
+++ b/drivers/phy/phy-mvebu-sata.c
@@ -99,17 +99,17 @@
 	if (IS_ERR(priv->clk))
 		return PTR_ERR(priv->clk);
 
-	phy_provider = devm_of_phy_provider_register(&pdev->dev,
-						     of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
-
 	phy = devm_phy_create(&pdev->dev, &phy_mvebu_sata_ops, NULL);
 	if (IS_ERR(phy))
 		return PTR_ERR(phy);
 
 	phy_set_drvdata(phy, priv);
 
+	phy_provider = devm_of_phy_provider_register(&pdev->dev,
+						     of_phy_simple_xlate);
+	if (IS_ERR(phy_provider))
+		return PTR_ERR(phy_provider);
+
 	/* The boot loader may of left it on. Turn it off. */
 	phy_mvebu_sata_power_off(phy);
 
diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index bfc5c33..7699752 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -177,11 +177,6 @@
 	phy->phy.otg		= otg;
 	phy->phy.type		= USB_PHY_TYPE_USB2;
 
-	phy_provider = devm_of_phy_provider_register(phy->dev,
-			of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
-
 	control_node = of_parse_phandle(node, "ctrl-module", 0);
 	if (!control_node) {
 		dev_err(&pdev->dev, "Failed to get control device phandle\n");
@@ -214,6 +209,11 @@
 
 	phy_set_drvdata(generic_phy, phy);
 
+	phy_provider = devm_of_phy_provider_register(phy->dev,
+			of_phy_simple_xlate);
+	if (IS_ERR(phy_provider))
+		return PTR_ERR(phy_provider);
+
 	phy->wkupclk = devm_clk_get(phy->dev, "usb_phy_cm_clk32k");
 	if (IS_ERR(phy->wkupclk)) {
 		dev_err(&pdev->dev, "unable to get usb_phy_cm_clk32k\n");
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
index daf65e6..c3ace1d 100644
--- a/drivers/phy/phy-twl4030-usb.c
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -695,11 +695,6 @@
 	otg->set_host		= twl4030_set_host;
 	otg->set_peripheral	= twl4030_set_peripheral;
 
-	phy_provider = devm_of_phy_provider_register(twl->dev,
-		of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
-
 	phy = devm_phy_create(twl->dev, &ops, init_data);
 	if (IS_ERR(phy)) {
 		dev_dbg(&pdev->dev, "Failed to create PHY\n");
@@ -708,6 +703,11 @@
 
 	phy_set_drvdata(phy, twl);
 
+	phy_provider = devm_of_phy_provider_register(twl->dev,
+		of_phy_simple_xlate);
+	if (IS_ERR(phy_provider))
+		return PTR_ERR(phy_provider);
+
 	/* init spinlock for workqueue */
 	spin_lock_init(&twl->lock);
 
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index be361b7..1e4e693 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -217,7 +217,7 @@
 	select PINCTRL_MXS
 
 config PINCTRL_MSM
-	tristate
+	bool
 	select PINMUX
 	select PINCONF
 	select GENERIC_PINCONF
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 5ee61a4..c0fe609 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -851,7 +851,9 @@
 	kref_init(&p->users);
 
 	/* Add the pinctrl handle to the global list */
+	mutex_lock(&pinctrl_list_mutex);
 	list_add_tail(&p->node, &pinctrl_list);
+	mutex_unlock(&pinctrl_list_mutex);
 
 	return p;
 }
@@ -1642,8 +1644,10 @@
 			    device_root, pctldev, &pinctrl_groups_ops);
 	debugfs_create_file("gpio-ranges", S_IFREG | S_IRUGO,
 			    device_root, pctldev, &pinctrl_gpioranges_ops);
-	pinmux_init_device_debugfs(device_root, pctldev);
-	pinconf_init_device_debugfs(device_root, pctldev);
+	if (pctldev->desc->pmxops)
+		pinmux_init_device_debugfs(device_root, pctldev);
+	if (pctldev->desc->confops)
+		pinconf_init_device_debugfs(device_root, pctldev);
 }
 
 static void pinctrl_remove_device_debugfs(struct pinctrl_dev *pctldev)
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index 38c6f8b..d990e33 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -1286,22 +1286,22 @@
 
 	switch (type) {
 	case IRQ_TYPE_EDGE_RISING:
-		irq_set_handler(d->irq, handle_simple_irq);
+		__irq_set_handler_locked(d->irq, handle_simple_irq);
 		writel_relaxed(mask, pio + PIO_ESR);
 		writel_relaxed(mask, pio + PIO_REHLSR);
 		break;
 	case IRQ_TYPE_EDGE_FALLING:
-		irq_set_handler(d->irq, handle_simple_irq);
+		__irq_set_handler_locked(d->irq, handle_simple_irq);
 		writel_relaxed(mask, pio + PIO_ESR);
 		writel_relaxed(mask, pio + PIO_FELLSR);
 		break;
 	case IRQ_TYPE_LEVEL_LOW:
-		irq_set_handler(d->irq, handle_level_irq);
+		__irq_set_handler_locked(d->irq, handle_level_irq);
 		writel_relaxed(mask, pio + PIO_LSR);
 		writel_relaxed(mask, pio + PIO_FELLSR);
 		break;
 	case IRQ_TYPE_LEVEL_HIGH:
-		irq_set_handler(d->irq, handle_level_irq);
+		__irq_set_handler_locked(d->irq, handle_level_irq);
 		writel_relaxed(mask, pio + PIO_LSR);
 		writel_relaxed(mask, pio + PIO_REHLSR);
 		break;
@@ -1310,7 +1310,7 @@
 		 * disable additional interrupt modes:
 		 * fall back to default behavior
 		 */
-		irq_set_handler(d->irq, handle_simple_irq);
+		__irq_set_handler_locked(d->irq, handle_simple_irq);
 		writel_relaxed(mask, pio + PIO_AIMDR);
 		return 0;
 	case IRQ_TYPE_NONE:
diff --git a/drivers/pinctrl/pinctrl-capri.c b/drivers/pinctrl/pinctrl-capri.c
index 4669c53..eb25002 100644
--- a/drivers/pinctrl/pinctrl-capri.c
+++ b/drivers/pinctrl/pinctrl-capri.c
@@ -1435,7 +1435,7 @@
 }
 
 static struct of_device_id capri_pinctrl_of_match[] = {
-	{ .compatible = "brcm,capri-pinctrl", },
+	{ .compatible = "brcm,bcm11351-pinctrl", },
 	{ },
 };
 
diff --git a/drivers/pinctrl/pinctrl-imx1-core.c b/drivers/pinctrl/pinctrl-imx1-core.c
index 17aecde..815384b 100644
--- a/drivers/pinctrl/pinctrl-imx1-core.c
+++ b/drivers/pinctrl/pinctrl-imx1-core.c
@@ -45,7 +45,7 @@
 #define MX1_DDIR 0x00
 #define MX1_OCR 0x04
 #define MX1_ICONFA 0x0c
-#define MX1_ICONFB 0x10
+#define MX1_ICONFB 0x14
 #define MX1_GIUS 0x20
 #define MX1_GPR 0x38
 #define MX1_PUEN 0x40
@@ -97,13 +97,13 @@
 	u32 old_val;
 	u32 new_val;
 
-	dev_dbg(ipctl->dev, "write: register 0x%p offset %d value 0x%x\n",
-			reg, offset, value);
-
 	/* Use the next register if the pin's port pin number is >=16 */
 	if (pin_id % 32 >= 16)
 		reg += 0x04;
 
+	dev_dbg(ipctl->dev, "write: register 0x%p offset %d value 0x%x\n",
+			reg, offset, value);
+
 	/* Get current state of pins */
 	old_val = readl(reg);
 	old_val &= mask;
@@ -139,7 +139,7 @@
 		u32 reg_offset)
 {
 	void __iomem *reg = imx1_mem(ipctl, pin_id) + reg_offset;
-	int offset = pin_id % 16;
+	int offset = (pin_id % 16) * 2;
 
 	/* Use the next register if the pin's port pin number is >=16 */
 	if (pin_id % 32 >= 16)
diff --git a/drivers/pinctrl/pinctrl-sunxi.c b/drivers/pinctrl/pinctrl-sunxi.c
index 9ccf681..f9fabe9 100644
--- a/drivers/pinctrl/pinctrl-sunxi.c
+++ b/drivers/pinctrl/pinctrl-sunxi.c
@@ -14,6 +14,7 @@
 #include <linux/clk.h>
 #include <linux/gpio.h>
 #include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -584,7 +585,7 @@
 	spin_lock_irqsave(&pctl->lock, flags);
 
 	regval = readl(pctl->membase + reg);
-	regval &= ~IRQ_CFG_IRQ_MASK;
+	regval &= ~(IRQ_CFG_IRQ_MASK << index);
 	writel(regval | (mode << index), pctl->membase + reg);
 
 	spin_unlock_irqrestore(&pctl->lock, flags);
@@ -665,6 +666,7 @@
 
 static void sunxi_pinctrl_irq_handler(unsigned irq, struct irq_desc *desc)
 {
+	struct irq_chip *chip = irq_get_chip(irq);
 	struct sunxi_pinctrl *pctl = irq_get_handler_data(irq);
 	const unsigned long reg = readl(pctl->membase + IRQ_STATUS_REG);
 
@@ -674,10 +676,12 @@
 	if (reg) {
 		int irqoffset;
 
+		chained_irq_enter(chip, desc);
 		for_each_set_bit(irqoffset, &reg, SUNXI_IRQ_NUMBER) {
 			int pin_irq = irq_find_mapping(pctl->domain, irqoffset);
 			generic_handle_irq(pin_irq);
 		}
+		chained_irq_exit(chip, desc);
 	}
 }
 
diff --git a/drivers/pinctrl/pinctrl-sunxi.h b/drivers/pinctrl/pinctrl-sunxi.h
index 01c494f..552b0e9 100644
--- a/drivers/pinctrl/pinctrl-sunxi.h
+++ b/drivers/pinctrl/pinctrl-sunxi.h
@@ -511,7 +511,7 @@
 
 static inline u32 sunxi_irq_cfg_reg(u16 irq)
 {
-	u8 reg = irq / IRQ_CFG_IRQ_PER_REG;
+	u8 reg = irq / IRQ_CFG_IRQ_PER_REG * 0x04;
 	return reg + IRQ_CFG_REG;
 }
 
@@ -523,7 +523,7 @@
 
 static inline u32 sunxi_irq_ctrl_reg(u16 irq)
 {
-	u8 reg = irq / IRQ_CTRL_IRQ_PER_REG;
+	u8 reg = irq / IRQ_CTRL_IRQ_PER_REG * 0x04;
 	return reg + IRQ_CTRL_REG;
 }
 
@@ -535,7 +535,7 @@
 
 static inline u32 sunxi_irq_status_reg(u16 irq)
 {
-	u8 reg = irq / IRQ_STATUS_IRQ_PER_REG;
+	u8 reg = irq / IRQ_STATUS_IRQ_PER_REG * 0x04;
 	return reg + IRQ_STATUS_REG;
 }
 
diff --git a/drivers/pinctrl/pinctrl-tegra.c b/drivers/pinctrl/pinctrl-tegra.c
index a2e93a2..e767355 100644
--- a/drivers/pinctrl/pinctrl-tegra.c
+++ b/drivers/pinctrl/pinctrl-tegra.c
@@ -645,7 +645,7 @@
 				 GFP_KERNEL);
 	if (!pmx->regs) {
 		dev_err(&pdev->dev, "Can't alloc regs pointer\n");
-		return -ENODEV;
+		return -ENOMEM;
 	}
 
 	for (i = 0; i < pmx->nbanks; i++) {
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
index 77d103f..567d691 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
@@ -89,7 +89,8 @@
 
 	/* GPSR6 */
 	FN_IP13_10, FN_IP13_11, FN_IP13_12, FN_IP13_13, FN_IP13_14,
-	FN_IP13_15, FN_IP13_18_16, FN_IP13_21_19, FN_IP13_22, FN_IP13_24_23,
+	FN_IP13_15, FN_IP13_18_16, FN_IP13_21_19,
+	FN_IP13_22, FN_IP13_24_23, FN_SD1_CLK,
 	FN_IP13_25, FN_IP13_26, FN_IP13_27, FN_IP13_30_28, FN_IP14_1_0,
 	FN_IP14_2, FN_IP14_3, FN_IP14_4, FN_IP14_5, FN_IP14_6, FN_IP14_7,
 	FN_IP14_10_8, FN_IP14_13_11, FN_IP14_16_14, FN_IP14_19_17,
@@ -788,6 +789,7 @@
 	PINMUX_DATA(USB1_PWEN_MARK, FN_USB1_PWEN),
 	PINMUX_DATA(USB1_OVC_MARK, FN_USB1_OVC),
 	PINMUX_DATA(DU0_DOTCLKIN_MARK, FN_DU0_DOTCLKIN),
+	PINMUX_DATA(SD1_CLK_MARK, FN_SD1_CLK),
 
 	/* IPSR0 */
 	PINMUX_IPSR_DATA(IP0_0, D0),
@@ -3825,7 +3827,7 @@
 		GP_6_11_FN, FN_IP13_25,
 		GP_6_10_FN, FN_IP13_24_23,
 		GP_6_9_FN, FN_IP13_22,
-		0, 0,
+		GP_6_8_FN, FN_SD1_CLK,
 		GP_6_7_FN, FN_IP13_21_19,
 		GP_6_6_FN, FN_IP13_18_16,
 		GP_6_5_FN, FN_IP13_15,
diff --git a/drivers/pinctrl/sirf/pinctrl-prima2.c b/drivers/pinctrl/sirf/pinctrl-prima2.c
index 37b4265..dde0285 100644
--- a/drivers/pinctrl/sirf/pinctrl-prima2.c
+++ b/drivers/pinctrl/sirf/pinctrl-prima2.c
@@ -413,7 +413,7 @@
 	.funcval = 0,
 };
 
-static const unsigned ac97_pins[] = { 33, 34, 35, 36 };
+static const unsigned ac97_pins[] = { 43, 44, 45, 46 };
 
 static const struct sirfsoc_muxmask spi1_muxmask[] = {
 	{
diff --git a/drivers/pinctrl/sirf/pinctrl-sirf.c b/drivers/pinctrl/sirf/pinctrl-sirf.c
index a0d6152..617a491 100644
--- a/drivers/pinctrl/sirf/pinctrl-sirf.c
+++ b/drivers/pinctrl/sirf/pinctrl-sirf.c
@@ -598,7 +598,7 @@
 {
 	struct sirfsoc_gpio_bank *bank = irq_data_get_irq_chip_data(d);
 
-	if (gpio_lock_as_irq(&bank->chip.gc, d->hwirq))
+	if (gpio_lock_as_irq(&bank->chip.gc, d->hwirq % SIRFSOC_GPIO_BANK_SIZE))
 		dev_err(bank->chip.gc.dev,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			d->hwirq);
@@ -611,7 +611,7 @@
 	struct sirfsoc_gpio_bank *bank = irq_data_get_irq_chip_data(d);
 
 	sirfsoc_gpio_irq_mask(d);
-	gpio_unlock_as_irq(&bank->chip.gc, d->hwirq);
+	gpio_unlock_as_irq(&bank->chip.gc, d->hwirq % SIRFSOC_GPIO_BANK_SIZE);
 }
 
 static struct irq_chip sirfsoc_irq_chip = {
diff --git a/drivers/pinctrl/vt8500/pinctrl-wmt.c b/drivers/pinctrl/vt8500/pinctrl-wmt.c
index b28d1af..9802b67 100644
--- a/drivers/pinctrl/vt8500/pinctrl-wmt.c
+++ b/drivers/pinctrl/vt8500/pinctrl-wmt.c
@@ -276,7 +276,20 @@
 	if (!configs)
 		return -ENOMEM;
 
-	configs[0] = pull;
+	switch (pull) {
+	case 0:
+		configs[0] = PIN_CONFIG_BIAS_DISABLE;
+		break;
+	case 1:
+		configs[0] = PIN_CONFIG_BIAS_PULL_DOWN;
+		break;
+	case 2:
+		configs[0] = PIN_CONFIG_BIAS_PULL_UP;
+		break;
+	default:
+		configs[0] = PIN_CONFIG_BIAS_DISABLE;
+		dev_err(data->dev, "invalid pull state %d - disabling\n", pull);
+	}
 
 	map->type = PIN_MAP_TYPE_CONFIGS_PIN;
 	map->data.configs.group_or_pin = data->groups[group];
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 167f3d0..66977eb 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -183,9 +183,7 @@
 	struct resource r = {0};
 	int i, flags;
 
-	if (acpi_dev_resource_memory(res, &r)
-	    || acpi_dev_resource_io(res, &r)
-	    || acpi_dev_resource_address_space(res, &r)
+	if (acpi_dev_resource_address_space(res, &r)
 	    || acpi_dev_resource_ext_address_space(res, &r)) {
 		pnp_add_resource(dev, &r);
 		return AE_OK;
@@ -217,6 +215,17 @@
 	}
 
 	switch (res->type) {
+	case ACPI_RESOURCE_TYPE_MEMORY24:
+	case ACPI_RESOURCE_TYPE_MEMORY32:
+	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
+		if (acpi_dev_resource_memory(res, &r))
+			pnp_add_resource(dev, &r);
+		break;
+	case ACPI_RESOURCE_TYPE_IO:
+	case ACPI_RESOURCE_TYPE_FIXED_IO:
+		if (acpi_dev_resource_io(res, &r))
+			pnp_add_resource(dev, &r);
+		break;
 	case ACPI_RESOURCE_TYPE_DMA:
 		dma = &res->data.dma;
 		if (dma->channel_count > 0 && dma->channels[0] != (u8) -1)
diff --git a/drivers/pnp/pnpbios/bioscalls.c b/drivers/pnp/pnpbios/bioscalls.c
index 769d265..deb7f4b 100644
--- a/drivers/pnp/pnpbios/bioscalls.c
+++ b/drivers/pnp/pnpbios/bioscalls.c
@@ -21,7 +21,7 @@
 
 #include "pnpbios.h"
 
-static struct {
+__visible struct {
 	u16 offset;
 	u16 segment;
 } pnp_bios_callpoint;
@@ -41,6 +41,7 @@
 
 __asm__(".text			\n"
 	__ALIGN_STR "\n"
+	".globl pnp_bios_callfunc\n"
 	"pnp_bios_callfunc:\n"
 	"	pushl %edx	\n"
 	"	pushl %ecx	\n"
@@ -66,9 +67,9 @@
  * after PnP BIOS oopses.
  */
 
-u32 pnp_bios_fault_esp;
-u32 pnp_bios_fault_eip;
-u32 pnp_bios_is_utter_crap = 0;
+__visible u32 pnp_bios_fault_esp;
+__visible u32 pnp_bios_fault_eip;
+__visible u32 pnp_bios_is_utter_crap = 0;
 
 static spinlock_t pnp_bios_lock;
 
diff --git a/drivers/power/ds2782_battery.c b/drivers/power/ds2782_battery.c
index 5631748..041f9b6 100644
--- a/drivers/power/ds2782_battery.c
+++ b/drivers/power/ds2782_battery.c
@@ -192,7 +192,7 @@
 
 	/*
 	 * Voltage is measured in units of 1.22mV. The voltage is stored as
-	 * a 10-bit number plus sign, in the upper bits of a 16-bit register
+	 * a 12-bit number plus sign, in the upper bits of a 16-bit register
 	 */
 	err = ds278x_read_reg16(info, DS278x_REG_VOLT_MSB, &raw);
 	if (err)
diff --git a/drivers/power/isp1704_charger.c b/drivers/power/isp1704_charger.c
index 80edb7d..0b4cf9d 100644
--- a/drivers/power/isp1704_charger.c
+++ b/drivers/power/isp1704_charger.c
@@ -444,8 +444,6 @@
 		ret = PTR_ERR(isp->phy);
 		goto fail0;
 	}
-	if (!isp->phy)
-		goto fail0;
 
 	isp->dev = &pdev->dev;
 	platform_set_drvdata(pdev, isp);
diff --git a/drivers/power/max17040_battery.c b/drivers/power/max17040_battery.c
index c7ff6d6..0fbac86 100644
--- a/drivers/power/max17040_battery.c
+++ b/drivers/power/max17040_battery.c
@@ -148,7 +148,7 @@
 {
 	struct max17040_chip *chip = i2c_get_clientdata(client);
 
-	if (chip->pdata->battery_online)
+	if (chip->pdata && chip->pdata->battery_online)
 		chip->online = chip->pdata->battery_online();
 	else
 		chip->online = 1;
@@ -158,7 +158,8 @@
 {
 	struct max17040_chip *chip = i2c_get_clientdata(client);
 
-	if (!chip->pdata->charger_online || !chip->pdata->charger_enable) {
+	if (!chip->pdata || !chip->pdata->charger_online
+			|| !chip->pdata->charger_enable) {
 		chip->status = POWER_SUPPLY_STATUS_UNKNOWN;
 		return;
 	}
diff --git a/drivers/ps3/ps3-vuart.c b/drivers/ps3/ps3-vuart.c
index fb73008..bc1e513 100644
--- a/drivers/ps3/ps3-vuart.c
+++ b/drivers/ps3/ps3-vuart.c
@@ -699,8 +699,6 @@
 
 	BUG_ON(!bytes);
 
-	PREPARE_WORK(&priv->rx_list.work.work, ps3_vuart_work);
-
 	spin_lock_irqsave(&priv->rx_list.lock, flags);
 	if (priv->rx_list.bytes_held >= bytes) {
 		dev_dbg(&dev->core, "%s:%d: schedule_work %xh bytes\n",
@@ -1052,7 +1050,7 @@
 	INIT_LIST_HEAD(&priv->rx_list.head);
 	spin_lock_init(&priv->rx_list.lock);
 
-	INIT_WORK(&priv->rx_list.work.work, NULL);
+	INIT_WORK(&priv->rx_list.work.work, ps3_vuart_work);
 	priv->rx_list.work.trigger = 0;
 	priv->rx_list.work.dev = dev;
 
diff --git a/drivers/pwm/pwm-lp3943.c b/drivers/pwm/pwm-lp3943.c
index 8a843a0..a40b9c3 100644
--- a/drivers/pwm/pwm-lp3943.c
+++ b/drivers/pwm/pwm-lp3943.c
@@ -52,8 +52,10 @@
 		offset = pwm_map->output[i];
 
 		/* Return an error if the pin is already assigned */
-		if (test_and_set_bit(offset, &lp3943->pin_used))
+		if (test_and_set_bit(offset, &lp3943->pin_used)) {
+			kfree(pwm_map);
 			return ERR_PTR(-EBUSY);
+		}
 	}
 
 	return pwm_map;
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
index b4b0d83..7061ac0 100644
--- a/drivers/rapidio/devices/tsi721.h
+++ b/drivers/rapidio/devices/tsi721.h
@@ -678,6 +678,7 @@
 	struct list_head	free_list;
 	dma_cookie_t		completed_cookie;
 	struct tasklet_struct	tasklet;
+	bool			active;
 };
 
 #endif /* CONFIG_RAPIDIO_DMA_ENGINE */
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index 502663f..91245f5 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -206,8 +206,8 @@
 {
 	/* Disable BDMA channel interrupts */
 	iowrite32(0, bdma_chan->regs + TSI721_DMAC_INTE);
-
-	tasklet_schedule(&bdma_chan->tasklet);
+	if (bdma_chan->active)
+		tasklet_schedule(&bdma_chan->tasklet);
 }
 
 #ifdef CONFIG_PCI_MSI
@@ -562,7 +562,7 @@
 	}
 #endif /* CONFIG_PCI_MSI */
 
-	tasklet_enable(&bdma_chan->tasklet);
+	bdma_chan->active = true;
 	tsi721_bdma_interrupt_enable(bdma_chan, 1);
 
 	return bdma_chan->bd_num - 1;
@@ -576,9 +576,7 @@
 static void tsi721_free_chan_resources(struct dma_chan *dchan)
 {
 	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
-#ifdef CONFIG_PCI_MSI
 	struct tsi721_device *priv = to_tsi721(dchan->device);
-#endif
 	LIST_HEAD(list);
 
 	dev_dbg(dchan->device->dev, "%s: Entry\n", __func__);
@@ -589,14 +587,25 @@
 	BUG_ON(!list_empty(&bdma_chan->active_list));
 	BUG_ON(!list_empty(&bdma_chan->queue));
 
-	tasklet_disable(&bdma_chan->tasklet);
+	tsi721_bdma_interrupt_enable(bdma_chan, 0);
+	bdma_chan->active = false;
+
+#ifdef CONFIG_PCI_MSI
+	if (priv->flags & TSI721_USING_MSIX) {
+		synchronize_irq(priv->msix[TSI721_VECT_DMA0_DONE +
+					   bdma_chan->id].vector);
+		synchronize_irq(priv->msix[TSI721_VECT_DMA0_INT +
+					   bdma_chan->id].vector);
+	} else
+#endif
+	synchronize_irq(priv->pdev->irq);
+
+	tasklet_kill(&bdma_chan->tasklet);
 
 	spin_lock_bh(&bdma_chan->lock);
 	list_splice_init(&bdma_chan->free_list, &list);
 	spin_unlock_bh(&bdma_chan->lock);
 
-	tsi721_bdma_interrupt_enable(bdma_chan, 0);
-
 #ifdef CONFIG_PCI_MSI
 	if (priv->flags & TSI721_USING_MSIX) {
 		free_irq(priv->msix[TSI721_VECT_DMA0_DONE +
@@ -790,6 +799,7 @@
 		bdma_chan->dchan.cookie = 1;
 		bdma_chan->dchan.chan_id = i;
 		bdma_chan->id = i;
+		bdma_chan->active = false;
 
 		spin_lock_init(&bdma_chan->lock);
 
@@ -799,7 +809,6 @@
 
 		tasklet_init(&bdma_chan->tasklet, tsi721_dma_tasklet,
 			     (unsigned long)bdma_chan);
-		tasklet_disable(&bdma_chan->tasklet);
 		list_add_tail(&bdma_chan->dchan.device_node,
 			      &mport->dma.channels);
 	}
diff --git a/drivers/regulator/ab3100.c b/drivers/regulator/ab3100.c
index 77b46d0..e10febe 100644
--- a/drivers/regulator/ab3100.c
+++ b/drivers/regulator/ab3100.c
@@ -498,7 +498,7 @@
 				     struct ab3100_platform_data *plfdata,
 				     struct regulator_init_data *init_data,
 				     struct device_node *np,
-				     int id)
+				     unsigned long id)
 {
 	struct regulator_desc *desc;
 	struct ab3100_regulator *reg;
@@ -646,7 +646,7 @@
 		err = ab3100_regulator_register(
 			pdev, NULL, ab3100_regulator_matches[i].init_data,
 			ab3100_regulator_matches[i].of_node,
-			(int) ab3100_regulator_matches[i].driver_data);
+			(unsigned long)ab3100_regulator_matches[i].driver_data);
 		if (err) {
 			ab3100_regulators_remove(pdev);
 			return err;
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index b38a6b6..afca1bc 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -953,6 +953,8 @@
 	return 0;
 }
 
+static int _regulator_do_enable(struct regulator_dev *rdev);
+
 /**
  * set_machine_constraints - sets regulator constraints
  * @rdev: regulator source
@@ -1013,10 +1015,9 @@
 	/* If the constraints say the regulator should be on at this point
 	 * and we have control then make sure it is enabled.
 	 */
-	if ((rdev->constraints->always_on || rdev->constraints->boot_on) &&
-	    ops->enable) {
-		ret = ops->enable(rdev);
-		if (ret < 0) {
+	if (rdev->constraints->always_on || rdev->constraints->boot_on) {
+		ret = _regulator_do_enable(rdev);
+		if (ret < 0 && ret != -EINVAL) {
 			rdev_err(rdev, "failed to enable\n");
 			goto out;
 		}
@@ -1272,6 +1273,8 @@
 				if (r->dev.parent &&
 					node == r->dev.of_node)
 					return r;
+			*ret = -EPROBE_DEFER;
+			return NULL;
 		} else {
 			/*
 			 * If we couldn't even get the node then it's
@@ -1312,7 +1315,7 @@
 	struct regulator_dev *rdev;
 	struct regulator *regulator = ERR_PTR(-EPROBE_DEFER);
 	const char *devname = NULL;
-	int ret = -EPROBE_DEFER;
+	int ret;
 
 	if (id == NULL) {
 		pr_err("get() with no identifier\n");
@@ -1322,6 +1325,11 @@
 	if (dev)
 		devname = dev_name(dev);
 
+	if (have_full_constraints())
+		ret = -ENODEV;
+	else
+		ret = -EPROBE_DEFER;
+
 	mutex_lock(&regulator_list_mutex);
 
 	rdev = regulator_dev_lookup(dev, id, &ret);
@@ -1352,7 +1360,7 @@
 		goto found;
 	/* Don't log an error when called from regulator_get_optional() */
 	} else if (!have_full_constraints() || exclusive) {
-		dev_err(dev, "dummy supplies not allowed\n");
+		dev_warn(dev, "dummy supplies not allowed\n");
 	}
 
 	mutex_unlock(&regulator_list_mutex);
@@ -1900,8 +1908,6 @@
 
 	trace_regulator_disable_complete(rdev_get_name(rdev));
 
-	_notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
-			     NULL);
 	return 0;
 }
 
@@ -1925,6 +1931,8 @@
 				rdev_err(rdev, "failed to disable\n");
 				return ret;
 			}
+			_notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
+					NULL);
 		}
 
 		rdev->use_count = 0;
@@ -1977,20 +1985,16 @@
 {
 	int ret = 0;
 
-	/* force disable */
-	if (rdev->desc->ops->disable) {
-		/* ah well, who wants to live forever... */
-		ret = rdev->desc->ops->disable(rdev);
-		if (ret < 0) {
-			rdev_err(rdev, "failed to force disable\n");
-			return ret;
-		}
-		/* notify other consumers that power has been forced off */
-		_notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
-			REGULATOR_EVENT_DISABLE, NULL);
+	ret = _regulator_do_disable(rdev);
+	if (ret < 0) {
+		rdev_err(rdev, "failed to force disable\n");
+		return ret;
 	}
 
-	return ret;
+	_notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
+			REGULATOR_EVENT_DISABLE, NULL);
+
+	return 0;
 }
 
 /**
@@ -3623,23 +3627,18 @@
 
 	mutex_lock(&regulator_list_mutex);
 	list_for_each_entry(rdev, &regulator_list, list) {
-		struct regulator_ops *ops = rdev->desc->ops;
-
 		mutex_lock(&rdev->mutex);
-		if ((rdev->use_count > 0  || rdev->constraints->always_on) &&
-				ops->enable) {
-			error = ops->enable(rdev);
+		if (rdev->use_count > 0  || rdev->constraints->always_on) {
+			error = _regulator_do_enable(rdev);
 			if (error)
 				ret = error;
 		} else {
 			if (!have_full_constraints())
 				goto unlock;
-			if (!ops->disable)
-				goto unlock;
 			if (!_regulator_is_enabled(rdev))
 				goto unlock;
 
-			error = ops->disable(rdev);
+			error = _regulator_do_disable(rdev);
 			if (error)
 				ret = error;
 		}
@@ -3813,7 +3812,7 @@
 		ops = rdev->desc->ops;
 		c = rdev->constraints;
 
-		if (!ops->disable || (c && c->always_on))
+		if (c && c->always_on)
 			continue;
 
 		mutex_lock(&rdev->mutex);
@@ -3834,7 +3833,7 @@
 			/* We log since this may kill the system if it
 			 * goes wrong. */
 			rdev_info(rdev, "disabling\n");
-			ret = ops->disable(rdev);
+			ret = _regulator_do_disable(rdev);
 			if (ret != 0)
 				rdev_err(rdev, "couldn't disable: %d\n", ret);
 		} else {
diff --git a/drivers/regulator/da9055-regulator.c b/drivers/regulator/da9055-regulator.c
index 7f34020..b14ebda 100644
--- a/drivers/regulator/da9055-regulator.c
+++ b/drivers/regulator/da9055-regulator.c
@@ -576,7 +576,9 @@
 	/* Only LDO 5 and 6 has got the over current interrupt */
 	if (pdev->id == DA9055_ID_LDO5 || pdev->id ==  DA9055_ID_LDO6) {
 		irq = platform_get_irq_byname(pdev, "REGULATOR");
-		irq = regmap_irq_get_virq(da9055->irq_data, irq);
+		if (irq < 0)
+			return irq;
+
 		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
 						da9055_ldo5_6_oc_irq,
 						IRQF_TRIGGER_HIGH |
diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c
index 56727eb..91e99a2 100644
--- a/drivers/regulator/da9063-regulator.c
+++ b/drivers/regulator/da9063-regulator.c
@@ -1,3 +1,4 @@
+
 /*
  * Regulator driver for DA9063 PMIC series
  *
@@ -60,7 +61,8 @@
 	.desc.ops = &da9063_ldo_ops, \
 	.desc.min_uV = (min_mV) * 1000, \
 	.desc.uV_step = (step_mV) * 1000, \
-	.desc.n_voltages = (((max_mV) - (min_mV))/(step_mV) + 1), \
+	.desc.n_voltages = (((max_mV) - (min_mV))/(step_mV) + 1 \
+		+ (DA9063_V##regl_name##_BIAS)), \
 	.desc.enable_reg = DA9063_REG_##regl_name##_CONT, \
 	.desc.enable_mask = DA9063_LDO_EN, \
 	.desc.vsel_reg = DA9063_REG_V##regl_name##_A, \
diff --git a/drivers/regulator/max14577.c b/drivers/regulator/max14577.c
index b1078ba3..e061952 100644
--- a/drivers/regulator/max14577.c
+++ b/drivers/regulator/max14577.c
@@ -166,12 +166,14 @@
 
 	ret = of_regulator_match(&pdev->dev, np, max14577_regulator_matches,
 			MAX14577_REG_MAX);
-	if (ret < 0) {
+	if (ret < 0)
 		dev_err(&pdev->dev, "Error parsing regulator init data: %d\n", ret);
-		return ret;
-	}
+	else
+		ret = 0;
 
-	return 0;
+	of_node_put(np);
+
+	return ret;
 }
 
 static inline struct regulator_init_data *match_init_data(int index)
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index d9e5579..cd0b9e3 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -441,6 +441,7 @@
 	for (i = 0; i < S2MPS11_REGULATOR_MAX; i++) {
 		if (!reg_np) {
 			config.init_data = pdata->regulators[i].initdata;
+			config.of_node = pdata->regulators[i].reg_node;
 		} else {
 			config.init_data = rdata[i].init_data;
 			config.of_node = rdata[i].of_node;
diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index d7164bb..d958dfa 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -535,7 +535,7 @@
 		return -ENODEV;
 	}
 
-	regulators_np = of_find_node_by_name(pmic_np, "regulators");
+	regulators_np = of_get_child_by_name(pmic_np, "regulators");
 	if (!regulators_np) {
 		dev_err(iodev->dev, "could not find regulators sub-node\n");
 		return -EINVAL;
@@ -591,6 +591,8 @@
 		rmode++;
 	}
 
+	of_node_put(regulators_np);
+
 	if (of_get_property(pmic_np, "s5m8767,pmic-buck2-uses-gpio-dvs", NULL)) {
 		pdata->buck2_gpiodvs = true;
 
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 7afd373..c4cde9c 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -580,10 +580,12 @@
 
 	clk_enable(rtc_clk);
 	/* save TICNT for anyone using periodic interrupts */
-	ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT);
 	if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
 		ticnt_en_save = readw(s3c_rtc_base + S3C2410_RTCCON);
 		ticnt_en_save &= S3C64XX_RTCCON_TICEN;
+		ticnt_save = readl(s3c_rtc_base + S3C2410_TICNT);
+	} else {
+		ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT);
 	}
 	s3c_rtc_enable(pdev, 0);
 
@@ -605,10 +607,15 @@
 
 	clk_enable(rtc_clk);
 	s3c_rtc_enable(pdev, 1);
-	writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
-	if (s3c_rtc_cpu_type == TYPE_S3C64XX && ticnt_en_save) {
-		tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
-		writew(tmp | ticnt_en_save, s3c_rtc_base + S3C2410_RTCCON);
+	if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
+		writel(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
+		if (ticnt_en_save) {
+			tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
+			writew(tmp | ticnt_en_save,
+					s3c_rtc_base + S3C2410_RTCCON);
+		}
+	} else {
+		writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
 	}
 
 	if (device_may_wakeup(dev) && wake_en) {
diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index eb5d227..5af7f0b 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -922,7 +922,7 @@
 		raw3215_freelist = req;
 	}
 
-	cdev = ccw_device_probe_console();
+	cdev = ccw_device_create_console(&raw3215_ccw_driver);
 	if (IS_ERR(cdev))
 		return -ENODEV;
 
@@ -932,6 +932,12 @@
 	cdev->handler = raw3215_irq;
 
 	raw->flags |= RAW3215_FIXED;
+	if (ccw_device_enable_console(cdev)) {
+		ccw_device_destroy_console(cdev);
+		raw3215_free_info(raw);
+		raw3215[0] = NULL;
+		return -ENODEV;
+	}
 
 	/* Request the console irq */
 	if (raw3215_startup(raw) != 0) {
diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c
index 699fd3e..75ffe99 100644
--- a/drivers/s390/char/con3270.c
+++ b/drivers/s390/char/con3270.c
@@ -7,6 +7,7 @@
  *     Copyright IBM Corp. 2003, 2009
  */
 
+#include <linux/module.h>
 #include <linux/console.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -30,6 +31,9 @@
 
 static struct raw3270_fn con3270_fn;
 
+static bool auto_update = 1;
+module_param(auto_update, bool, 0);
+
 /*
  * Main 3270 console view data structure.
  */
@@ -204,6 +208,8 @@
 	struct string *s, *n;
 	int rc;
 
+	if (!auto_update && !raw3270_view_active(&cp->view))
+		return;
 	if (cp->view.dev)
 		raw3270_activate_view(&cp->view);
 
@@ -529,6 +535,7 @@
 	if (!cp->view.dev)
 		return;
 	raw3270_pm_unfreeze(&cp->view);
+	raw3270_activate_view(&cp->view);
 	spin_lock_irqsave(&cp->view.lock, flags);
 	con3270_wait_write(cp);
 	cp->nr_up = 0;
@@ -576,7 +583,6 @@
 static int __init
 con3270_init(void)
 {
-	struct ccw_device *cdev;
 	struct raw3270 *rp;
 	void *cbuf;
 	int i;
@@ -591,10 +597,7 @@
 		cpcmd("TERM AUTOCR OFF", NULL, 0, NULL);
 	}
 
-	cdev = ccw_device_probe_console();
-	if (IS_ERR(cdev))
-		return -ENODEV;
-	rp = raw3270_setup_console(cdev);
+	rp = raw3270_setup_console();
 	if (IS_ERR(rp))
 		return PTR_ERR(rp);
 
diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c
index 2cdec21..9f849df 100644
--- a/drivers/s390/char/raw3270.c
+++ b/drivers/s390/char/raw3270.c
@@ -276,6 +276,15 @@
 }
 
 int
+raw3270_view_active(struct raw3270_view *view)
+{
+	struct raw3270 *rp = view->dev;
+
+	return rp && rp->view == view &&
+		!test_bit(RAW3270_FLAGS_FROZEN, &rp->flags);
+}
+
+int
 raw3270_start(struct raw3270_view *view, struct raw3270_request *rq)
 {
 	unsigned long flags;
@@ -776,22 +785,37 @@
 }
 
 #ifdef CONFIG_TN3270_CONSOLE
+/* Tentative definition - see below for actual definition. */
+static struct ccw_driver raw3270_ccw_driver;
+
 /*
  * Setup 3270 device configured as console.
  */
-struct raw3270 __init *raw3270_setup_console(struct ccw_device *cdev)
+struct raw3270 __init *raw3270_setup_console(void)
 {
+	struct ccw_device *cdev;
 	unsigned long flags;
 	struct raw3270 *rp;
 	char *ascebc;
 	int rc;
 
+	cdev = ccw_device_create_console(&raw3270_ccw_driver);
+	if (IS_ERR(cdev))
+		return ERR_CAST(cdev);
+
 	rp = kzalloc(sizeof(struct raw3270), GFP_KERNEL | GFP_DMA);
 	ascebc = kzalloc(256, GFP_KERNEL);
 	rc = raw3270_setup_device(cdev, rp, ascebc);
 	if (rc)
 		return ERR_PTR(rc);
 	set_bit(RAW3270_FLAGS_CONSOLE, &rp->flags);
+
+	rc = ccw_device_enable_console(cdev);
+	if (rc) {
+		ccw_device_destroy_console(cdev);
+		return ERR_PTR(rc);
+	}
+
 	spin_lock_irqsave(get_ccwdev_lock(rp->cdev), flags);
 	do {
 		__raw3270_reset_device(rp);
diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h
index 7b73ff8..e1e41c2 100644
--- a/drivers/s390/char/raw3270.h
+++ b/drivers/s390/char/raw3270.h
@@ -173,6 +173,7 @@
 int raw3270_start_irq(struct raw3270_view *, struct raw3270_request *);
 int raw3270_reset(struct raw3270_view *);
 struct raw3270_view *raw3270_view(struct raw3270_view *);
+int raw3270_view_active(struct raw3270_view *);
 
 /* Reference count inliner for view structures. */
 static inline void
@@ -190,7 +191,7 @@
 		wake_up(&raw3270_wait_queue);
 }
 
-struct raw3270 *raw3270_setup_console(struct ccw_device *cdev);
+struct raw3270 *raw3270_setup_console(void);
 void raw3270_wait_cons_dev(struct raw3270 *);
 
 /* Notifier for device addition/removal */
diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index 82f2c38..14196ea 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -20,7 +20,9 @@
 	struct	sccb_header header;	/* 0-7 */
 	u16	rnmax;			/* 8-9 */
 	u8	rnsize;			/* 10 */
-	u8	_reserved0[24 - 11];	/* 11-15 */
+	u8	_reserved0[16 - 11];	/* 11-15 */
+	u16	ncpurl;			/* 16-17 */
+	u8	_reserved7[24 - 18];	/* 18-23 */
 	u8	loadparm[8];		/* 24-31 */
 	u8	_reserved1[48 - 32];	/* 32-47 */
 	u64	facilities;		/* 48-55 */
@@ -32,13 +34,16 @@
 	u8	_reserved4[100 - 92];	/* 92-99 */
 	u32	rnsize2;		/* 100-103 */
 	u64	rnmax2;			/* 104-111 */
-	u8	_reserved5[4096 - 112];	/* 112-4095 */
+	u8	_reserved5[120 - 112];	/* 112-119 */
+	u16	hcpua;			/* 120-121 */
+	u8	_reserved6[4096 - 122];	/* 122-4095 */
 } __packed __aligned(PAGE_SIZE);
 
 static char sccb_early[PAGE_SIZE] __aligned(PAGE_SIZE) __initdata;
 static unsigned int sclp_con_has_vt220 __initdata;
 static unsigned int sclp_con_has_linemode __initdata;
 static unsigned long sclp_hsa_size;
+static unsigned int sclp_max_cpu;
 static struct sclp_ipl_info sclp_ipl_info;
 
 u64 sclp_facilities;
@@ -102,6 +107,15 @@
 	sclp_rzm = sccb->rnsize ? sccb->rnsize : sccb->rnsize2;
 	sclp_rzm <<= 20;
 
+	if (!sccb->hcpua) {
+		if (MACHINE_IS_VM)
+			sclp_max_cpu = 64;
+		else
+			sclp_max_cpu = sccb->ncpurl;
+	} else {
+		sclp_max_cpu = sccb->hcpua + 1;
+	}
+
 	/* Save IPL information */
 	sclp_ipl_info.is_valid = 1;
 	if (sccb->flags & 0x2)
@@ -129,6 +143,11 @@
 	return sclp_rzm;
 }
 
+unsigned int sclp_get_max_cpu(void)
+{
+	return sclp_max_cpu;
+}
+
 /*
  * This function will be called after sclp_facilities_detect(), which gets
  * called from early.c code. The sclp_facilities_detect() function retrieves
@@ -184,9 +203,9 @@
 	sccb_init_eq_size(sccb);
 	if (sclp_cmd_early(SCLP_CMDW_WRITE_EVENT_DATA, sccb))
 		return -EIO;
-	if (sccb->evbuf.blk_cnt != 0)
-		return (sccb->evbuf.blk_cnt - 1) * PAGE_SIZE;
-	return 0;
+	if (sccb->evbuf.blk_cnt == 0)
+		return 0;
+	return (sccb->evbuf.blk_cnt - 1) * PAGE_SIZE;
 }
 
 static long __init sclp_hsa_copy_wait(struct sccb_header *sccb)
@@ -195,6 +214,8 @@
 	sccb->length = PAGE_SIZE;
 	if (sclp_cmd_early(SCLP_CMDW_READ_EVENT_DATA, sccb))
 		return -EIO;
+	if (((struct sdias_sccb *) sccb)->evbuf.blk_cnt == 0)
+		return 0;
 	return (((struct sdias_sccb *) sccb)->evbuf.blk_cnt - 1) * PAGE_SIZE;
 }
 
diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c
index f055df0..445564c 100644
--- a/drivers/s390/cio/airq.c
+++ b/drivers/s390/cio/airq.c
@@ -186,55 +186,71 @@
 EXPORT_SYMBOL(airq_iv_release);
 
 /**
- * airq_iv_alloc_bit - allocate an irq bit from an interrupt vector
+ * airq_iv_alloc - allocate irq bits from an interrupt vector
  * @iv: pointer to an interrupt vector structure
+ * @num: number of consecutive irq bits to allocate
  *
- * Returns the bit number of the allocated irq, or -1UL if no bit
- * is available or the AIRQ_IV_ALLOC flag has not been specified
+ * Returns the bit number of the first irq in the allocated block of irqs,
+ * or -1UL if no bit is available or the AIRQ_IV_ALLOC flag has not been
+ * specified
  */
-unsigned long airq_iv_alloc_bit(struct airq_iv *iv)
+unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num)
 {
-	unsigned long bit;
+	unsigned long bit, i;
 
-	if (!iv->avail)
+	if (!iv->avail || num == 0)
 		return -1UL;
 	spin_lock(&iv->lock);
 	bit = find_first_bit_inv(iv->avail, iv->bits);
-	if (bit < iv->bits) {
-		clear_bit_inv(bit, iv->avail);
-		if (bit >= iv->end)
-			iv->end = bit + 1;
-	} else
+	while (bit + num <= iv->bits) {
+		for (i = 1; i < num; i++)
+			if (!test_bit_inv(bit + i, iv->avail))
+				break;
+		if (i >= num) {
+			/* Found a suitable block of irqs */
+			for (i = 0; i < num; i++)
+				clear_bit_inv(bit + i, iv->avail);
+			if (bit + num >= iv->end)
+				iv->end = bit + num + 1;
+			break;
+		}
+		bit = find_next_bit_inv(iv->avail, iv->bits, bit + i + 1);
+	}
+	if (bit + num > iv->bits)
 		bit = -1UL;
 	spin_unlock(&iv->lock);
 	return bit;
 
 }
-EXPORT_SYMBOL(airq_iv_alloc_bit);
+EXPORT_SYMBOL(airq_iv_alloc);
 
 /**
- * airq_iv_free_bit - free an irq bit of an interrupt vector
+ * airq_iv_free - free irq bits of an interrupt vector
  * @iv: pointer to interrupt vector structure
- * @bit: number of the irq bit to free
+ * @bit: number of the first irq bit to free
+ * @num: number of consecutive irq bits to free
  */
-void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit)
+void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num)
 {
-	if (!iv->avail)
+	unsigned long i;
+
+	if (!iv->avail || num == 0)
 		return;
 	spin_lock(&iv->lock);
-	/* Clear (possibly left over) interrupt bit */
-	clear_bit_inv(bit, iv->vector);
-	/* Make the bit position available again */
-	set_bit_inv(bit, iv->avail);
-	if (bit == iv->end - 1) {
+	for (i = 0; i < num; i++) {
+		/* Clear (possibly left over) interrupt bit */
+		clear_bit_inv(bit + i, iv->vector);
+		/* Make the bit positions available again */
+		set_bit_inv(bit + i, iv->avail);
+	}
+	if (bit + num >= iv->end) {
 		/* Find new end of bit-field */
-		while (--iv->end > 0)
-			if (!test_bit_inv(iv->end - 1, iv->avail))
-				break;
+		while (iv->end > 0 && !test_bit_inv(iv->end - 1, iv->avail))
+			iv->end--;
 	}
 	spin_unlock(&iv->lock);
 }
-EXPORT_SYMBOL(airq_iv_free_bit);
+EXPORT_SYMBOL(airq_iv_free);
 
 /**
  * airq_iv_scan - scan interrupt vector for non-zero bits
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index f6b9188..9f0ea6c 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -610,6 +610,7 @@
 		css_wait_for_slow_path();
 		for_each_subchannel_staged(__s390_process_res_acc, NULL,
 					   &link);
+		css_schedule_reprobe();
 	}
 }
 
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index 7b29d0b..1d3661a 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -173,8 +173,7 @@
 
 static int __init chsc_init_dbfs(void)
 {
-	chsc_debug_msg_id = debug_register("chsc_msg", 16, 1,
-					   16 * sizeof(long));
+	chsc_debug_msg_id = debug_register("chsc_msg", 8, 1, 4 * sizeof(long));
 	if (!chsc_debug_msg_id)
 		goto out;
 	debug_register_view(chsc_debug_msg_id, &debug_sprintf_view);
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 5154513..d691e6a 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -54,7 +54,7 @@
  */
 static int __init cio_debug_init(void)
 {
-	cio_debug_msg_id = debug_register("cio_msg", 16, 1, 16 * sizeof(long));
+	cio_debug_msg_id = debug_register("cio_msg", 16, 1, 11 * sizeof(long));
 	if (!cio_debug_msg_id)
 		goto out_unregister;
 	debug_register_view(cio_debug_msg_id, &debug_sprintf_view);
@@ -64,7 +64,7 @@
 		goto out_unregister;
 	debug_register_view(cio_debug_trace_id, &debug_hex_ascii_view);
 	debug_set_level(cio_debug_trace_id, 2);
-	cio_debug_crw_id = debug_register("cio_crw", 16, 1, 16 * sizeof(long));
+	cio_debug_crw_id = debug_register("cio_crw", 8, 1, 8 * sizeof(long));
 	if (!cio_debug_crw_id)
 		goto out_unregister;
 	debug_register_view(cio_debug_crw_id, &debug_sprintf_view);
@@ -342,8 +342,9 @@
  */
 int cio_commit_config(struct subchannel *sch)
 {
-	struct schib schib;
 	int ccode, retry, ret = 0;
+	struct schib schib;
+	struct irb irb;
 
 	if (stsch_err(sch->schid, &schib) || !css_sch_is_valid(&schib))
 		return -ENODEV;
@@ -367,7 +368,10 @@
 			ret = -EAGAIN;
 			break;
 		case 1: /* status pending */
-			return -EBUSY;
+			ret = -EBUSY;
+			if (tsch(sch->schid, &irb))
+				return ret;
+			break;
 		case 2: /* busy */
 			udelay(100); /* allow for recovery */
 			ret = -EBUSY;
@@ -403,7 +407,6 @@
  */
 int cio_enable_subchannel(struct subchannel *sch, u32 intparm)
 {
-	int retry;
 	int ret;
 
 	CIO_TRACE_EVENT(2, "ensch");
@@ -418,20 +421,14 @@
 	sch->config.isc = sch->isc;
 	sch->config.intparm = intparm;
 
-	for (retry = 0; retry < 3; retry++) {
+	ret = cio_commit_config(sch);
+	if (ret == -EIO) {
+		/*
+		 * Got a program check in msch. Try without
+		 * the concurrent sense bit the next time.
+		 */
+		sch->config.csense = 0;
 		ret = cio_commit_config(sch);
-		if (ret == -EIO) {
-			/*
-			 * Got a program check in msch. Try without
-			 * the concurrent sense bit the next time.
-			 */
-			sch->config.csense = 0;
-		} else if (ret == -EBUSY) {
-			struct irb irb;
-			if (tsch(sch->schid, &irb) != 0)
-				break;
-		} else
-			break;
 	}
 	CIO_HEX_EVENT(2, &ret, sizeof(ret));
 	return ret;
@@ -444,7 +441,6 @@
  */
 int cio_disable_subchannel(struct subchannel *sch)
 {
-	int retry;
 	int ret;
 
 	CIO_TRACE_EVENT(2, "dissch");
@@ -456,16 +452,8 @@
 		return -ENODEV;
 
 	sch->config.ena = 0;
+	ret = cio_commit_config(sch);
 
-	for (retry = 0; retry < 3; retry++) {
-		ret = cio_commit_config(sch);
-		if (ret == -EBUSY) {
-			struct irb irb;
-			if (tsch(sch->schid, &irb) != 0)
-				break;
-		} else
-			break;
-	}
 	CIO_HEX_EVENT(2, &ret, sizeof(ret));
 	return ret;
 }
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index e9d7835..d8d9b5b 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -1571,12 +1571,27 @@
 	return rc;
 }
 
-#ifdef CONFIG_CCW_CONSOLE
-static int ccw_device_console_enable(struct ccw_device *cdev,
-				     struct subchannel *sch)
+static void ccw_device_set_int_class(struct ccw_device *cdev)
 {
+	struct ccw_driver *cdrv = cdev->drv;
+
+	/* Note: we interpret class 0 in this context as an uninitialized
+	 * field since it translates to a non-I/O interrupt class. */
+	if (cdrv->int_class != 0)
+		cdev->private->int_class = cdrv->int_class;
+	else
+		cdev->private->int_class = IRQIO_CIO;
+}
+
+#ifdef CONFIG_CCW_CONSOLE
+int __init ccw_device_enable_console(struct ccw_device *cdev)
+{
+	struct subchannel *sch = to_subchannel(cdev->dev.parent);
 	int rc;
 
+	if (!cdev->drv || !cdev->handler)
+		return -EINVAL;
+
 	io_subchannel_init_fields(sch);
 	rc = cio_commit_config(sch);
 	if (rc)
@@ -1609,12 +1624,11 @@
 	return rc;
 }
 
-struct ccw_device *ccw_device_probe_console(void)
+struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv)
 {
 	struct io_subchannel_private *io_priv;
 	struct ccw_device *cdev;
 	struct subchannel *sch;
-	int ret;
 
 	sch = cio_probe_console();
 	if (IS_ERR(sch))
@@ -1631,18 +1645,23 @@
 		kfree(io_priv);
 		return cdev;
 	}
+	cdev->drv = drv;
 	set_io_private(sch, io_priv);
-	ret = ccw_device_console_enable(cdev, sch);
-	if (ret) {
-		set_io_private(sch, NULL);
-		put_device(&sch->dev);
-		put_device(&cdev->dev);
-		kfree(io_priv);
-		return ERR_PTR(ret);
-	}
+	ccw_device_set_int_class(cdev);
 	return cdev;
 }
 
+void __init ccw_device_destroy_console(struct ccw_device *cdev)
+{
+	struct subchannel *sch = to_subchannel(cdev->dev.parent);
+	struct io_subchannel_private *io_priv = to_io_private(sch);
+
+	set_io_private(sch, NULL);
+	put_device(&sch->dev);
+	put_device(&cdev->dev);
+	kfree(io_priv);
+}
+
 /**
  * ccw_device_wait_idle() - busy wait for device to become idle
  * @cdev: ccw device
@@ -1726,15 +1745,8 @@
 	int ret;
 
 	cdev->drv = cdrv; /* to let the driver call _set_online */
-	/* Note: we interpret class 0 in this context as an uninitialized
-	 * field since it translates to a non-I/O interrupt class. */
-	if (cdrv->int_class != 0)
-		cdev->private->int_class = cdrv->int_class;
-	else
-		cdev->private->int_class = IRQIO_CIO;
-
+	ccw_device_set_int_class(cdev);
 	ret = cdrv->probe ? cdrv->probe(cdev) : -ENODEV;
-
 	if (ret) {
 		cdev->drv = NULL;
 		cdev->private->int_class = IRQIO_CIO;
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index 8acaae1..a563e4c 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -359,14 +359,12 @@
 #define need_siga_sync_out_after_pci(q)	\
 	(unlikely(q->irq_ptr->siga_flag.sync_out_after_pci))
 
-#define for_each_input_queue(irq_ptr, q, i)	\
-	for (i = 0, q = irq_ptr->input_qs[0];	\
-		i < irq_ptr->nr_input_qs;	\
-		q = irq_ptr->input_qs[++i])
-#define for_each_output_queue(irq_ptr, q, i)	\
-	for (i = 0, q = irq_ptr->output_qs[0];	\
-		i < irq_ptr->nr_output_qs;	\
-		q = irq_ptr->output_qs[++i])
+#define for_each_input_queue(irq_ptr, q, i)		\
+	for (i = 0; i < irq_ptr->nr_input_qs &&		\
+		({ q = irq_ptr->input_qs[i]; 1; }); i++)
+#define for_each_output_queue(irq_ptr, q, i)		\
+	for (i = 0; i < irq_ptr->nr_output_qs &&	\
+		({ q = irq_ptr->output_qs[i]; 1; }); i++)
 
 #define prev_buf(bufnr)	\
 	((bufnr + QDIO_MAX_BUFFERS_MASK) & QDIO_MAX_BUFFERS_MASK)
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index c883a08..77466c4 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -996,7 +996,7 @@
 		}
 	}
 
-	if (!pci_out_supported(q))
+	if (!(irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED))
 		return;
 
 	for_each_output_queue(irq_ptr, q, i) {
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index dc542e0..0bc91e4 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -311,7 +311,7 @@
 	} __packed * msg = ap_msg->message;
 
 	int rcblen = CEIL4(xcRB->request_control_blk_length);
-	int replylen;
+	int replylen, req_sumlen, resp_sumlen;
 	char *req_data = ap_msg->message + sizeof(struct type6_hdr) + rcblen;
 	char *function_code;
 
@@ -321,12 +321,34 @@
 		xcRB->request_data_length;
 	if (ap_msg->length > MSGTYPE06_MAX_MSG_SIZE)
 		return -EINVAL;
+
+	/* Overflow check
+	   sum must be greater (or equal) than the largest operand */
+	req_sumlen = CEIL4(xcRB->request_control_blk_length) +
+			xcRB->request_data_length;
+	if ((CEIL4(xcRB->request_control_blk_length) <=
+						xcRB->request_data_length) ?
+		(req_sumlen < xcRB->request_data_length) :
+		(req_sumlen < CEIL4(xcRB->request_control_blk_length))) {
+		return -EINVAL;
+	}
+
 	replylen = sizeof(struct type86_fmt2_msg) +
 		CEIL4(xcRB->reply_control_blk_length) +
 		xcRB->reply_data_length;
 	if (replylen > MSGTYPE06_MAX_MSG_SIZE)
 		return -EINVAL;
 
+	/* Overflow check
+	   sum must be greater (or equal) than the largest operand */
+	resp_sumlen = CEIL4(xcRB->reply_control_blk_length) +
+			xcRB->reply_data_length;
+	if ((CEIL4(xcRB->reply_control_blk_length) <= xcRB->reply_data_length) ?
+		(resp_sumlen < xcRB->reply_data_length) :
+		(resp_sumlen < CEIL4(xcRB->reply_control_blk_length))) {
+		return -EINVAL;
+	}
+
 	/* prepare type6 header */
 	msg->hdr = static_type6_hdrX;
 	memcpy(msg->hdr.agent_id , &(xcRB->agent_ID), sizeof(xcRB->agent_ID));
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index c3a83df..a0aff2e 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -33,8 +33,8 @@
 	/*                   N  P  A    M  L  V                      H  */
 	[QETH_DBF_SETUP] = {"qeth_setup",
 				8, 1,   8, 5, &debug_hex_ascii_view, NULL},
-	[QETH_DBF_MSG]   = {"qeth_msg",
-				8, 1, 128, 3, &debug_sprintf_view,   NULL},
+	[QETH_DBF_MSG]	 = {"qeth_msg", 8, 1, 11 * sizeof(long), 3,
+			    &debug_sprintf_view, NULL},
 	[QETH_DBF_CTRL]  = {"qeth_control",
 		8, 1, QETH_DBF_CTRL_LEN, 5, &debug_hex_ascii_view, NULL},
 };
@@ -1660,7 +1660,6 @@
 				QDIO_FLAG_CLEANUP_USING_CLEAR);
 		if (rc)
 			QETH_CARD_TEXT_(card, 3, "1err%d", rc);
-		qdio_free(CARD_DDEV(card));
 		atomic_set(&card->qdio.state, QETH_QDIO_ALLOCATED);
 		break;
 	case QETH_QDIO_CLEANING:
@@ -2605,6 +2604,7 @@
 	return 0;
 out_qdio:
 	qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD);
+	qdio_free(CARD_DDEV(card));
 	return rc;
 }
 
@@ -4906,9 +4906,11 @@
 	if (retries < 3)
 		QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n",
 			dev_name(&card->gdev->dev));
+	rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD);
 	ccw_device_set_offline(CARD_DDEV(card));
 	ccw_device_set_offline(CARD_WDEV(card));
 	ccw_device_set_offline(CARD_RDEV(card));
+	qdio_free(CARD_DDEV(card));
 	rc = ccw_device_set_online(CARD_RDEV(card));
 	if (rc)
 		goto retriable;
@@ -4918,7 +4920,6 @@
 	rc = ccw_device_set_online(CARD_DDEV(card));
 	if (rc)
 		goto retriable;
-	rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD);
 retriable:
 	if (rc == -ERESTARTSYS) {
 		QETH_DBF_TEXT(SETUP, 2, "break1");
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 0710550..908d825 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1091,6 +1091,7 @@
 	ccw_device_set_offline(CARD_DDEV(card));
 	ccw_device_set_offline(CARD_WDEV(card));
 	ccw_device_set_offline(CARD_RDEV(card));
+	qdio_free(CARD_DDEV(card));
 	if (recover_flag == CARD_STATE_RECOVER)
 		card->state = CARD_STATE_RECOVER;
 	else
@@ -1132,6 +1133,7 @@
 		rc = (rc2) ? rc2 : rc3;
 	if (rc)
 		QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc);
+	qdio_free(CARD_DDEV(card));
 	if (recover_flag == CARD_STATE_UP)
 		card->state = CARD_STATE_RECOVER;
 	/* let user_space know that device is offline */
@@ -1194,6 +1196,7 @@
 		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
 	qeth_qdio_clear_card(card, 0);
 	qeth_clear_qdio_buffers(card);
+	qdio_free(CARD_DDEV(card));
 }
 
 static int qeth_l2_pm_suspend(struct ccwgroup_device *gdev)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 0f43042..3524d34 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3447,6 +3447,7 @@
 	ccw_device_set_offline(CARD_DDEV(card));
 	ccw_device_set_offline(CARD_WDEV(card));
 	ccw_device_set_offline(CARD_RDEV(card));
+	qdio_free(CARD_DDEV(card));
 	if (recover_flag == CARD_STATE_RECOVER)
 		card->state = CARD_STATE_RECOVER;
 	else
@@ -3493,6 +3494,7 @@
 		rc = (rc2) ? rc2 : rc3;
 	if (rc)
 		QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc);
+	qdio_free(CARD_DDEV(card));
 	if (recover_flag == CARD_STATE_UP)
 		card->state = CARD_STATE_RECOVER;
 	/* let user_space know that device is offline */
@@ -3545,6 +3547,7 @@
 		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
 	qeth_qdio_clear_card(card, 0);
 	qeth_clear_qdio_buffers(card);
+	qdio_free(CARD_DDEV(card));
 }
 
 static int qeth_l3_pm_suspend(struct ccwgroup_device *gdev)
diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c
index 6b4678a..4ccb5d8 100644
--- a/drivers/sbus/char/jsflash.c
+++ b/drivers/sbus/char/jsflash.c
@@ -507,7 +507,6 @@
 	}
 
 	/* Let us be really paranoid for modifications to probing code. */
-	/* extern enum sparc_cpu sparc_cpu_model; */ /* in <asm/system.h> */
 	if (sparc_cpu_model != sun4m) {
 		/* We must be on sun4m because we use MMU Bypass ASI. */
 		return -ENXIO;
diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c
index a3e6c8a..296c936 100644
--- a/drivers/scsi/atari_scsi.c
+++ b/drivers/scsi/atari_scsi.c
@@ -90,6 +90,7 @@
 #include <linux/init.h>
 #include <linux/nvram.h>
 #include <linux/bitops.h>
+#include <linux/wait.h>
 
 #include <asm/setup.h>
 #include <asm/atarihw.h>
@@ -549,8 +550,10 @@
 
 	local_irq_save(flags);
 
-	while (!in_irq() && falcon_got_lock && stdma_others_waiting())
-		sleep_on(&falcon_fairness_wait);
+	wait_event_cmd(falcon_fairness_wait,
+		in_interrupt() || !falcon_got_lock || !stdma_others_waiting(),
+		local_irq_restore(flags),
+		local_irq_save(flags));
 
 	while (!falcon_got_lock) {
 		if (in_irq())
@@ -562,7 +565,10 @@
 			falcon_trying_lock = 0;
 			wake_up(&falcon_try_wait);
 		} else {
-			sleep_on(&falcon_try_wait);
+			wait_event_cmd(falcon_try_wait,
+				falcon_got_lock && !falcon_trying_lock,
+				local_irq_restore(flags),
+				local_irq_save(flags));
 		}
 	}
 
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 1f37505..5642a9b 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -325,7 +325,7 @@
 		if (!abrt_task->sc || abrt_task->state == ISCSI_TASK_FREE)
 			continue;
 
-		if (abrt_task->sc->device->lun != abrt_task->sc->device->lun)
+		if (sc->device->lun != abrt_task->sc->device->lun)
 			continue;
 
 		/* Invalidate WRB Posted for this Task */
diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index ed88089..e9279a8 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -594,13 +594,13 @@
 		mp_req->mp_resp_bd = NULL;
 	}
 	if (mp_req->req_buf) {
-		dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+		dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 				     mp_req->req_buf,
 				     mp_req->req_buf_dma);
 		mp_req->req_buf = NULL;
 	}
 	if (mp_req->resp_buf) {
-		dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+		dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 				     mp_req->resp_buf,
 				     mp_req->resp_buf_dma);
 		mp_req->resp_buf = NULL;
@@ -622,7 +622,7 @@
 
 	mp_req->req_len = sizeof(struct fcp_cmnd);
 	io_req->data_xfer_len = mp_req->req_len;
-	mp_req->req_buf = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+	mp_req->req_buf = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 					     &mp_req->req_buf_dma,
 					     GFP_ATOMIC);
 	if (!mp_req->req_buf) {
@@ -631,7 +631,7 @@
 		return FAILED;
 	}
 
-	mp_req->resp_buf = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+	mp_req->resp_buf = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 					      &mp_req->resp_buf_dma,
 					      GFP_ATOMIC);
 	if (!mp_req->resp_buf) {
@@ -639,8 +639,8 @@
 		bnx2fc_free_mp_resc(io_req);
 		return FAILED;
 	}
-	memset(mp_req->req_buf, 0, PAGE_SIZE);
-	memset(mp_req->resp_buf, 0, PAGE_SIZE);
+	memset(mp_req->req_buf, 0, CNIC_PAGE_SIZE);
+	memset(mp_req->resp_buf, 0, CNIC_PAGE_SIZE);
 
 	/* Allocate and map mp_req_bd and mp_resp_bd */
 	sz = sizeof(struct fcoe_bd_ctx);
@@ -665,7 +665,7 @@
 	mp_req_bd = mp_req->mp_req_bd;
 	mp_req_bd->buf_addr_lo = (u32)addr & 0xffffffff;
 	mp_req_bd->buf_addr_hi = (u32)((u64)addr >> 32);
-	mp_req_bd->buf_len = PAGE_SIZE;
+	mp_req_bd->buf_len = CNIC_PAGE_SIZE;
 	mp_req_bd->flags = 0;
 
 	/*
@@ -677,7 +677,7 @@
 	addr = mp_req->resp_buf_dma;
 	mp_resp_bd->buf_addr_lo = (u32)addr & 0xffffffff;
 	mp_resp_bd->buf_addr_hi = (u32)((u64)addr >> 32);
-	mp_resp_bd->buf_len = PAGE_SIZE;
+	mp_resp_bd->buf_len = CNIC_PAGE_SIZE;
 	mp_resp_bd->flags = 0;
 
 	return SUCCESS;
diff --git a/drivers/scsi/bnx2fc/bnx2fc_tgt.c b/drivers/scsi/bnx2fc/bnx2fc_tgt.c
index 4d93177..d9bae56 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_tgt.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_tgt.c
@@ -673,7 +673,8 @@
 
 	/* Allocate and map SQ */
 	tgt->sq_mem_size = tgt->max_sqes * BNX2FC_SQ_WQE_SIZE;
-	tgt->sq_mem_size = (tgt->sq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+	tgt->sq_mem_size = (tgt->sq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+			   CNIC_PAGE_MASK;
 
 	tgt->sq = dma_alloc_coherent(&hba->pcidev->dev, tgt->sq_mem_size,
 				     &tgt->sq_dma, GFP_KERNEL);
@@ -686,7 +687,8 @@
 
 	/* Allocate and map CQ */
 	tgt->cq_mem_size = tgt->max_cqes * BNX2FC_CQ_WQE_SIZE;
-	tgt->cq_mem_size = (tgt->cq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+	tgt->cq_mem_size = (tgt->cq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+			   CNIC_PAGE_MASK;
 
 	tgt->cq = dma_alloc_coherent(&hba->pcidev->dev, tgt->cq_mem_size,
 				     &tgt->cq_dma, GFP_KERNEL);
@@ -699,7 +701,8 @@
 
 	/* Allocate and map RQ and RQ PBL */
 	tgt->rq_mem_size = tgt->max_rqes * BNX2FC_RQ_WQE_SIZE;
-	tgt->rq_mem_size = (tgt->rq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+	tgt->rq_mem_size = (tgt->rq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+			   CNIC_PAGE_MASK;
 
 	tgt->rq = dma_alloc_coherent(&hba->pcidev->dev, tgt->rq_mem_size,
 					&tgt->rq_dma, GFP_KERNEL);
@@ -710,8 +713,9 @@
 	}
 	memset(tgt->rq, 0, tgt->rq_mem_size);
 
-	tgt->rq_pbl_size = (tgt->rq_mem_size / PAGE_SIZE) * sizeof(void *);
-	tgt->rq_pbl_size = (tgt->rq_pbl_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+	tgt->rq_pbl_size = (tgt->rq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *);
+	tgt->rq_pbl_size = (tgt->rq_pbl_size + (CNIC_PAGE_SIZE - 1)) &
+			   CNIC_PAGE_MASK;
 
 	tgt->rq_pbl = dma_alloc_coherent(&hba->pcidev->dev, tgt->rq_pbl_size,
 					 &tgt->rq_pbl_dma, GFP_KERNEL);
@@ -722,7 +726,7 @@
 	}
 
 	memset(tgt->rq_pbl, 0, tgt->rq_pbl_size);
-	num_pages = tgt->rq_mem_size / PAGE_SIZE;
+	num_pages = tgt->rq_mem_size / CNIC_PAGE_SIZE;
 	page = tgt->rq_dma;
 	pbl = (u32 *)tgt->rq_pbl;
 
@@ -731,13 +735,13 @@
 		pbl++;
 		*pbl = (u32)((u64)page >> 32);
 		pbl++;
-		page += PAGE_SIZE;
+		page += CNIC_PAGE_SIZE;
 	}
 
 	/* Allocate and map XFERQ */
 	tgt->xferq_mem_size = tgt->max_sqes * BNX2FC_XFERQ_WQE_SIZE;
-	tgt->xferq_mem_size = (tgt->xferq_mem_size + (PAGE_SIZE - 1)) &
-			       PAGE_MASK;
+	tgt->xferq_mem_size = (tgt->xferq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+			       CNIC_PAGE_MASK;
 
 	tgt->xferq = dma_alloc_coherent(&hba->pcidev->dev, tgt->xferq_mem_size,
 					&tgt->xferq_dma, GFP_KERNEL);
@@ -750,8 +754,8 @@
 
 	/* Allocate and map CONFQ & CONFQ PBL */
 	tgt->confq_mem_size = tgt->max_sqes * BNX2FC_CONFQ_WQE_SIZE;
-	tgt->confq_mem_size = (tgt->confq_mem_size + (PAGE_SIZE - 1)) &
-			       PAGE_MASK;
+	tgt->confq_mem_size = (tgt->confq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+			       CNIC_PAGE_MASK;
 
 	tgt->confq = dma_alloc_coherent(&hba->pcidev->dev, tgt->confq_mem_size,
 					&tgt->confq_dma, GFP_KERNEL);
@@ -763,9 +767,9 @@
 	memset(tgt->confq, 0, tgt->confq_mem_size);
 
 	tgt->confq_pbl_size =
-		(tgt->confq_mem_size / PAGE_SIZE) * sizeof(void *);
+		(tgt->confq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *);
 	tgt->confq_pbl_size =
-		(tgt->confq_pbl_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+		(tgt->confq_pbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
 
 	tgt->confq_pbl = dma_alloc_coherent(&hba->pcidev->dev,
 					    tgt->confq_pbl_size,
@@ -777,7 +781,7 @@
 	}
 
 	memset(tgt->confq_pbl, 0, tgt->confq_pbl_size);
-	num_pages = tgt->confq_mem_size / PAGE_SIZE;
+	num_pages = tgt->confq_mem_size / CNIC_PAGE_SIZE;
 	page = tgt->confq_dma;
 	pbl = (u32 *)tgt->confq_pbl;
 
@@ -786,7 +790,7 @@
 		pbl++;
 		*pbl = (u32)((u64)page >> 32);
 		pbl++;
-		page += PAGE_SIZE;
+		page += CNIC_PAGE_SIZE;
 	}
 
 	/* Allocate and map ConnDB */
@@ -805,8 +809,8 @@
 
 	/* Allocate and map LCQ */
 	tgt->lcq_mem_size = (tgt->max_sqes + 8) * BNX2FC_SQ_WQE_SIZE;
-	tgt->lcq_mem_size = (tgt->lcq_mem_size + (PAGE_SIZE - 1)) &
-			     PAGE_MASK;
+	tgt->lcq_mem_size = (tgt->lcq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+			     CNIC_PAGE_MASK;
 
 	tgt->lcq = dma_alloc_coherent(&hba->pcidev->dev, tgt->lcq_mem_size,
 				      &tgt->lcq_dma, GFP_KERNEL);
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index e4cf23d..b87a193 100644
--- a/drivers/scsi/bnx2i/bnx2i_hwi.c
+++ b/drivers/scsi/bnx2i/bnx2i_hwi.c
@@ -61,7 +61,7 @@
 	 * yield integral num of page buffers
 	 */
 	/* adjust SQ */
-	num_elements_per_pg = PAGE_SIZE / BNX2I_SQ_WQE_SIZE;
+	num_elements_per_pg = CNIC_PAGE_SIZE / BNX2I_SQ_WQE_SIZE;
 	if (hba->max_sqes < num_elements_per_pg)
 		hba->max_sqes = num_elements_per_pg;
 	else if (hba->max_sqes % num_elements_per_pg)
@@ -69,7 +69,7 @@
 				 ~(num_elements_per_pg - 1);
 
 	/* adjust CQ */
-	num_elements_per_pg = PAGE_SIZE / BNX2I_CQE_SIZE;
+	num_elements_per_pg = CNIC_PAGE_SIZE / BNX2I_CQE_SIZE;
 	if (hba->max_cqes < num_elements_per_pg)
 		hba->max_cqes = num_elements_per_pg;
 	else if (hba->max_cqes % num_elements_per_pg)
@@ -77,7 +77,7 @@
 				 ~(num_elements_per_pg - 1);
 
 	/* adjust RQ */
-	num_elements_per_pg = PAGE_SIZE / BNX2I_RQ_WQE_SIZE;
+	num_elements_per_pg = CNIC_PAGE_SIZE / BNX2I_RQ_WQE_SIZE;
 	if (hba->max_rqes < num_elements_per_pg)
 		hba->max_rqes = num_elements_per_pg;
 	else if (hba->max_rqes % num_elements_per_pg)
@@ -959,7 +959,7 @@
 
 	/* SQ page table */
 	memset(ep->qp.sq_pgtbl_virt, 0, ep->qp.sq_pgtbl_size);
-	num_pages = ep->qp.sq_mem_size / PAGE_SIZE;
+	num_pages = ep->qp.sq_mem_size / CNIC_PAGE_SIZE;
 	page = ep->qp.sq_phys;
 
 	if (cnic_dev_10g)
@@ -973,7 +973,7 @@
 			ptbl++;
 			*ptbl = (u32) ((u64) page >> 32);
 			ptbl++;
-			page += PAGE_SIZE;
+			page += CNIC_PAGE_SIZE;
 		} else {
 			/* PTE is written in big endian format for
 			 * 5706/5708/5709 devices */
@@ -981,13 +981,13 @@
 			ptbl++;
 			*ptbl = (u32) page;
 			ptbl++;
-			page += PAGE_SIZE;
+			page += CNIC_PAGE_SIZE;
 		}
 	}
 
 	/* RQ page table */
 	memset(ep->qp.rq_pgtbl_virt, 0, ep->qp.rq_pgtbl_size);
-	num_pages = ep->qp.rq_mem_size / PAGE_SIZE;
+	num_pages = ep->qp.rq_mem_size / CNIC_PAGE_SIZE;
 	page = ep->qp.rq_phys;
 
 	if (cnic_dev_10g)
@@ -1001,7 +1001,7 @@
 			ptbl++;
 			*ptbl = (u32) ((u64) page >> 32);
 			ptbl++;
-			page += PAGE_SIZE;
+			page += CNIC_PAGE_SIZE;
 		} else {
 			/* PTE is written in big endian format for
 			 * 5706/5708/5709 devices */
@@ -1009,13 +1009,13 @@
 			ptbl++;
 			*ptbl = (u32) page;
 			ptbl++;
-			page += PAGE_SIZE;
+			page += CNIC_PAGE_SIZE;
 		}
 	}
 
 	/* CQ page table */
 	memset(ep->qp.cq_pgtbl_virt, 0, ep->qp.cq_pgtbl_size);
-	num_pages = ep->qp.cq_mem_size / PAGE_SIZE;
+	num_pages = ep->qp.cq_mem_size / CNIC_PAGE_SIZE;
 	page = ep->qp.cq_phys;
 
 	if (cnic_dev_10g)
@@ -1029,7 +1029,7 @@
 			ptbl++;
 			*ptbl = (u32) ((u64) page >> 32);
 			ptbl++;
-			page += PAGE_SIZE;
+			page += CNIC_PAGE_SIZE;
 		} else {
 			/* PTE is written in big endian format for
 			 * 5706/5708/5709 devices */
@@ -1037,7 +1037,7 @@
 			ptbl++;
 			*ptbl = (u32) page;
 			ptbl++;
-			page += PAGE_SIZE;
+			page += CNIC_PAGE_SIZE;
 		}
 	}
 }
@@ -1064,11 +1064,11 @@
 	/* Allocate page table memory for SQ which is page aligned */
 	ep->qp.sq_mem_size = hba->max_sqes * BNX2I_SQ_WQE_SIZE;
 	ep->qp.sq_mem_size =
-		(ep->qp.sq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+		(ep->qp.sq_mem_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
 	ep->qp.sq_pgtbl_size =
-		(ep->qp.sq_mem_size / PAGE_SIZE) * sizeof(void *);
+		(ep->qp.sq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *);
 	ep->qp.sq_pgtbl_size =
-		(ep->qp.sq_pgtbl_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+		(ep->qp.sq_pgtbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
 
 	ep->qp.sq_pgtbl_virt =
 		dma_alloc_coherent(&hba->pcidev->dev, ep->qp.sq_pgtbl_size,
@@ -1101,11 +1101,11 @@
 	/* Allocate page table memory for CQ which is page aligned */
 	ep->qp.cq_mem_size = hba->max_cqes * BNX2I_CQE_SIZE;
 	ep->qp.cq_mem_size =
-		(ep->qp.cq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+		(ep->qp.cq_mem_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
 	ep->qp.cq_pgtbl_size =
-		(ep->qp.cq_mem_size / PAGE_SIZE) * sizeof(void *);
+		(ep->qp.cq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *);
 	ep->qp.cq_pgtbl_size =
-		(ep->qp.cq_pgtbl_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+		(ep->qp.cq_pgtbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
 
 	ep->qp.cq_pgtbl_virt =
 		dma_alloc_coherent(&hba->pcidev->dev, ep->qp.cq_pgtbl_size,
@@ -1144,11 +1144,11 @@
 	/* Allocate page table memory for RQ which is page aligned */
 	ep->qp.rq_mem_size = hba->max_rqes * BNX2I_RQ_WQE_SIZE;
 	ep->qp.rq_mem_size =
-		(ep->qp.rq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+		(ep->qp.rq_mem_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
 	ep->qp.rq_pgtbl_size =
-		(ep->qp.rq_mem_size / PAGE_SIZE) * sizeof(void *);
+		(ep->qp.rq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *);
 	ep->qp.rq_pgtbl_size =
-		(ep->qp.rq_pgtbl_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+		(ep->qp.rq_pgtbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
 
 	ep->qp.rq_pgtbl_virt =
 		dma_alloc_coherent(&hba->pcidev->dev, ep->qp.rq_pgtbl_size,
@@ -1270,7 +1270,7 @@
 	bnx2i_adjust_qp_size(hba);
 
 	iscsi_init.flags =
-		ISCSI_PAGE_SIZE_4K << ISCSI_KWQE_INIT1_PAGE_SIZE_SHIFT;
+		(CNIC_PAGE_BITS - 8) << ISCSI_KWQE_INIT1_PAGE_SIZE_SHIFT;
 	if (en_tcp_dack)
 		iscsi_init.flags |= ISCSI_KWQE_INIT1_DELAYED_ACK_ENABLE;
 	iscsi_init.reserved0 = 0;
@@ -1288,15 +1288,15 @@
 			((hba->num_ccell & 0xFFFF) | (hba->max_sqes << 16));
 	iscsi_init.num_ccells_per_conn = hba->num_ccell;
 	iscsi_init.num_tasks_per_conn = hba->max_sqes;
-	iscsi_init.sq_wqes_per_page = PAGE_SIZE / BNX2I_SQ_WQE_SIZE;
+	iscsi_init.sq_wqes_per_page = CNIC_PAGE_SIZE / BNX2I_SQ_WQE_SIZE;
 	iscsi_init.sq_num_wqes = hba->max_sqes;
 	iscsi_init.cq_log_wqes_per_page =
-		(u8) bnx2i_power_of2(PAGE_SIZE / BNX2I_CQE_SIZE);
+		(u8) bnx2i_power_of2(CNIC_PAGE_SIZE / BNX2I_CQE_SIZE);
 	iscsi_init.cq_num_wqes = hba->max_cqes;
 	iscsi_init.cq_num_pages = (hba->max_cqes * BNX2I_CQE_SIZE +
-				   (PAGE_SIZE - 1)) / PAGE_SIZE;
+				   (CNIC_PAGE_SIZE - 1)) / CNIC_PAGE_SIZE;
 	iscsi_init.sq_num_pages = (hba->max_sqes * BNX2I_SQ_WQE_SIZE +
-				   (PAGE_SIZE - 1)) / PAGE_SIZE;
+				   (CNIC_PAGE_SIZE - 1)) / CNIC_PAGE_SIZE;
 	iscsi_init.rq_buffer_size = BNX2I_RQ_WQE_SIZE;
 	iscsi_init.rq_num_wqes = hba->max_rqes;
 
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index 854dad7..c8b0aff 100644
--- a/drivers/scsi/bnx2i/bnx2i_iscsi.c
+++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c
@@ -525,7 +525,7 @@
 	struct iscsi_bd *mp_bdt;
 	u64 addr;
 
-	hba->mp_bd_tbl = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+	hba->mp_bd_tbl = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 					    &hba->mp_bd_dma, GFP_KERNEL);
 	if (!hba->mp_bd_tbl) {
 		printk(KERN_ERR "unable to allocate Middle Path BDT\n");
@@ -533,11 +533,12 @@
 		goto out;
 	}
 
-	hba->dummy_buffer = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+	hba->dummy_buffer = dma_alloc_coherent(&hba->pcidev->dev,
+					       CNIC_PAGE_SIZE,
 					       &hba->dummy_buf_dma, GFP_KERNEL);
 	if (!hba->dummy_buffer) {
 		printk(KERN_ERR "unable to alloc Middle Path Dummy Buffer\n");
-		dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+		dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 				  hba->mp_bd_tbl, hba->mp_bd_dma);
 		hba->mp_bd_tbl = NULL;
 		rc = -1;
@@ -548,7 +549,7 @@
 	addr = (unsigned long) hba->dummy_buf_dma;
 	mp_bdt->buffer_addr_lo = addr & 0xffffffff;
 	mp_bdt->buffer_addr_hi = addr >> 32;
-	mp_bdt->buffer_length = PAGE_SIZE;
+	mp_bdt->buffer_length = CNIC_PAGE_SIZE;
 	mp_bdt->flags = ISCSI_BD_LAST_IN_BD_CHAIN |
 			ISCSI_BD_FIRST_IN_BD_CHAIN;
 out:
@@ -565,12 +566,12 @@
 static void bnx2i_free_mp_bdt(struct bnx2i_hba *hba)
 {
 	if (hba->mp_bd_tbl) {
-		dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+		dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 				  hba->mp_bd_tbl, hba->mp_bd_dma);
 		hba->mp_bd_tbl = NULL;
 	}
 	if (hba->dummy_buffer) {
-		dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+		dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 				  hba->dummy_buffer, hba->dummy_buf_dma);
 		hba->dummy_buffer = NULL;
 	}
@@ -934,14 +935,14 @@
 					    struct bnx2i_conn *bnx2i_conn)
 {
 	if (bnx2i_conn->gen_pdu.resp_bd_tbl) {
-		dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+		dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 				  bnx2i_conn->gen_pdu.resp_bd_tbl,
 				  bnx2i_conn->gen_pdu.resp_bd_dma);
 		bnx2i_conn->gen_pdu.resp_bd_tbl = NULL;
 	}
 
 	if (bnx2i_conn->gen_pdu.req_bd_tbl) {
-		dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+		dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 				  bnx2i_conn->gen_pdu.req_bd_tbl,
 				  bnx2i_conn->gen_pdu.req_bd_dma);
 		bnx2i_conn->gen_pdu.req_bd_tbl = NULL;
@@ -998,13 +999,13 @@
 	bnx2i_conn->gen_pdu.resp_wr_ptr = bnx2i_conn->gen_pdu.resp_buf;
 
 	bnx2i_conn->gen_pdu.req_bd_tbl =
-		dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+		dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 				   &bnx2i_conn->gen_pdu.req_bd_dma, GFP_KERNEL);
 	if (bnx2i_conn->gen_pdu.req_bd_tbl == NULL)
 		goto login_req_bd_tbl_failure;
 
 	bnx2i_conn->gen_pdu.resp_bd_tbl =
-		dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+		dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 				   &bnx2i_conn->gen_pdu.resp_bd_dma,
 				   GFP_KERNEL);
 	if (bnx2i_conn->gen_pdu.resp_bd_tbl == NULL)
@@ -1013,7 +1014,7 @@
 	return 0;
 
 login_resp_bd_tbl_failure:
-	dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+	dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
 			  bnx2i_conn->gen_pdu.req_bd_tbl,
 			  bnx2i_conn->gen_pdu.req_bd_dma);
 	bnx2i_conn->gen_pdu.req_bd_tbl = NULL;
diff --git a/drivers/scsi/isci/host.h b/drivers/scsi/isci/host.h
index 4911310..22a9bb1 100644
--- a/drivers/scsi/isci/host.h
+++ b/drivers/scsi/isci/host.h
@@ -311,9 +311,8 @@
 }
 
 #define for_each_isci_host(id, ihost, pdev) \
-	for (id = 0, ihost = to_pci_info(pdev)->hosts[id]; \
-	     id < ARRAY_SIZE(to_pci_info(pdev)->hosts) && ihost; \
-	     ihost = to_pci_info(pdev)->hosts[++id])
+	for (id = 0; id < SCI_MAX_CONTROLLERS && \
+	     (ihost = to_pci_info(pdev)->hosts[id]); id++)
 
 static inline void wait_for_start(struct isci_host *ihost)
 {
diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c
index 85c77f6..ac87974 100644
--- a/drivers/scsi/isci/port_config.c
+++ b/drivers/scsi/isci/port_config.c
@@ -615,13 +615,6 @@
 					  SCIC_SDS_APC_WAIT_LINK_UP_NOTIFICATION);
 	} else {
 		/* the phy is already the part of the port */
-		u32 port_state = iport->sm.current_state_id;
-
-		/* if the PORT'S state is resetting then the link up is from
-		 * port hard reset in this case, we need to tell the port
-		 * that link up is recieved
-		 */
-		BUG_ON(port_state != SCI_PORT_RESETTING);
 		port_agent->phy_ready_mask |= 1 << phy_index;
 		sci_port_link_up(iport, iphy);
 	}
diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c
index 0d30ca8..5d6fda7 100644
--- a/drivers/scsi/isci/task.c
+++ b/drivers/scsi/isci/task.c
@@ -801,7 +801,7 @@
 		/* XXX: need to cleanup any ireqs targeting this
 		 * domain_device
 		 */
-		ret = TMF_RESP_FUNC_COMPLETE;
+		ret = -ENODEV;
 		goto out;
 	}
 
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index d289583..766098a 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -700,46 +700,26 @@
 
 }
 
-static bool sas_ata_flush_pm_eh(struct asd_sas_port *port, const char *func)
+static void sas_ata_flush_pm_eh(struct asd_sas_port *port, const char *func)
 {
 	struct domain_device *dev, *n;
-	bool retry = false;
 
 	list_for_each_entry_safe(dev, n, &port->dev_list, dev_list_node) {
-		int rc;
-
 		if (!dev_is_sata(dev))
 			continue;
 
 		sas_ata_wait_eh(dev);
-		rc = dev->sata_dev.pm_result;
-		if (rc == -EAGAIN)
-			retry = true;
-		else if (rc) {
-			/* since we don't have a
-			 * ->port_{suspend|resume} routine in our
-			 *  ata_port ops, and no entanglements with
-			 *  acpi, suspend should just be mechanical trip
-			 *  through eh, catch cases where these
-			 *  assumptions are invalidated
-			 */
-			WARN_ONCE(1, "failed %s %s error: %d\n", func,
-				 dev_name(&dev->rphy->dev), rc);
-		}
 
 		/* if libata failed to power manage the device, tear it down */
 		if (ata_dev_disabled(sas_to_ata_dev(dev)))
 			sas_fail_probe(dev, func, -ENODEV);
 	}
-
-	return retry;
 }
 
 void sas_suspend_sata(struct asd_sas_port *port)
 {
 	struct domain_device *dev;
 
- retry:
 	mutex_lock(&port->ha->disco_mutex);
 	list_for_each_entry(dev, &port->dev_list, dev_list_node) {
 		struct sata_device *sata;
@@ -751,20 +731,17 @@
 		if (sata->ap->pm_mesg.event == PM_EVENT_SUSPEND)
 			continue;
 
-		sata->pm_result = -EIO;
-		ata_sas_port_async_suspend(sata->ap, &sata->pm_result);
+		ata_sas_port_suspend(sata->ap);
 	}
 	mutex_unlock(&port->ha->disco_mutex);
 
-	if (sas_ata_flush_pm_eh(port, __func__))
-		goto retry;
+	sas_ata_flush_pm_eh(port, __func__);
 }
 
 void sas_resume_sata(struct asd_sas_port *port)
 {
 	struct domain_device *dev;
 
- retry:
 	mutex_lock(&port->ha->disco_mutex);
 	list_for_each_entry(dev, &port->dev_list, dev_list_node) {
 		struct sata_device *sata;
@@ -776,13 +753,11 @@
 		if (sata->ap->pm_mesg.event == PM_EVENT_ON)
 			continue;
 
-		sata->pm_result = -EIO;
-		ata_sas_port_async_resume(sata->ap, &sata->pm_result);
+		ata_sas_port_resume(sata->ap);
 	}
 	mutex_unlock(&port->ha->disco_mutex);
 
-	if (sas_ata_flush_pm_eh(port, __func__))
-		goto retry;
+	sas_ata_flush_pm_eh(port, __func__);
 }
 
 /**
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index e1fe95e..266724b 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2996,8 +2996,7 @@
 				IS_QLA82XX(ha) || IS_QLA83XX(ha) || \
 				IS_QLA8044(ha))
 #define IS_MSIX_NACK_CAPABLE(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha))
-#define IS_NOPOLLING_TYPE(ha)	((IS_QLA25XX(ha) || IS_QLA81XX(ha) || \
-			IS_QLA83XX(ha)) && (ha)->flags.msix_enabled)
+#define IS_NOPOLLING_TYPE(ha)	(IS_QLA81XX(ha) && (ha)->flags.msix_enabled)
 #define IS_FAC_REQUIRED(ha)	(IS_QLA81XX(ha) || IS_QLA83XX(ha))
 #define IS_NOCACHE_VPD_TYPE(ha)	(IS_QLA81XX(ha) || IS_QLA83XX(ha))
 #define IS_ALOGIO_CAPABLE(ha)	(IS_QLA23XX(ha) || IS_FWI2_CAPABLE(ha))
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 9bc86b9..0a1dcb4 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -2880,6 +2880,7 @@
 qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 {
 #define MIN_MSIX_COUNT	2
+#define ATIO_VECTOR	2
 	int i, ret;
 	struct msix_entry *entries;
 	struct qla_msix_entry *qentry;
@@ -2936,34 +2937,47 @@
 	}
 
 	/* Enable MSI-X vectors for the base queue */
-	for (i = 0; i < ha->msix_count; i++) {
+	for (i = 0; i < 2; i++) {
 		qentry = &ha->msix_entries[i];
-		if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) {
-			ret = request_irq(qentry->vector,
-				qla83xx_msix_entries[i].handler,
-				0, qla83xx_msix_entries[i].name, rsp);
-		} else if (IS_P3P_TYPE(ha)) {
+		if (IS_P3P_TYPE(ha))
 			ret = request_irq(qentry->vector,
 				qla82xx_msix_entries[i].handler,
 				0, qla82xx_msix_entries[i].name, rsp);
-		} else {
+		else
 			ret = request_irq(qentry->vector,
 				msix_entries[i].handler,
 				0, msix_entries[i].name, rsp);
-		}
-		if (ret) {
-			ql_log(ql_log_fatal, vha, 0x00cb,
-			    "MSI-X: unable to register handler -- %x/%d.\n",
-			    qentry->vector, ret);
-			qla24xx_disable_msix(ha);
-			ha->mqenable = 0;
-			goto msix_out;
-		}
+		if (ret)
+			goto msix_register_fail;
 		qentry->have_irq = 1;
 		qentry->rsp = rsp;
 		rsp->msix = qentry;
 	}
 
+	/*
+	 * If target mode is enable, also request the vector for the ATIO
+	 * queue.
+	 */
+	if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) {
+		qentry = &ha->msix_entries[ATIO_VECTOR];
+		ret = request_irq(qentry->vector,
+			qla83xx_msix_entries[ATIO_VECTOR].handler,
+			0, qla83xx_msix_entries[ATIO_VECTOR].name, rsp);
+		qentry->have_irq = 1;
+		qentry->rsp = rsp;
+		rsp->msix = qentry;
+	}
+
+msix_register_fail:
+	if (ret) {
+		ql_log(ql_log_fatal, vha, 0x00cb,
+		    "MSI-X: unable to register handler -- %x/%d.\n",
+		    qentry->vector, ret);
+		qla24xx_disable_msix(ha);
+		ha->mqenable = 0;
+		goto msix_out;
+	}
+
 	/* Enable MSI-X vector for response queue update for queue 0 */
 	if (IS_QLA83XX(ha)) {
 		if (ha->msixbase && ha->mqiobase &&
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 9e80d61..0cb7307 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -790,17 +790,32 @@
 }
 
 /* Called by tcm_qla2xxx configfs code */
-void qlt_stop_phase1(struct qla_tgt *tgt)
+int qlt_stop_phase1(struct qla_tgt *tgt)
 {
 	struct scsi_qla_host *vha = tgt->vha;
 	struct qla_hw_data *ha = tgt->ha;
 	unsigned long flags;
 
+	mutex_lock(&qla_tgt_mutex);
+	if (!vha->fc_vport) {
+		struct Scsi_Host *sh = vha->host;
+		struct fc_host_attrs *fc_host = shost_to_fc_host(sh);
+		bool npiv_vports;
+
+		spin_lock_irqsave(sh->host_lock, flags);
+		npiv_vports = (fc_host->npiv_vports_inuse);
+		spin_unlock_irqrestore(sh->host_lock, flags);
+
+		if (npiv_vports) {
+			mutex_unlock(&qla_tgt_mutex);
+			return -EPERM;
+		}
+	}
 	if (tgt->tgt_stop || tgt->tgt_stopped) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04e,
 		    "Already in tgt->tgt_stop or tgt_stopped state\n");
-		dump_stack();
-		return;
+		mutex_unlock(&qla_tgt_mutex);
+		return -EPERM;
 	}
 
 	ql_dbg(ql_dbg_tgt, vha, 0xe003, "Stopping target for host %ld(%p)\n",
@@ -815,6 +830,7 @@
 	qlt_clear_tgt_db(tgt, true);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	mutex_unlock(&vha->vha_tgt.tgt_mutex);
+	mutex_unlock(&qla_tgt_mutex);
 
 	flush_delayed_work(&tgt->sess_del_work);
 
@@ -841,6 +857,7 @@
 
 	/* Wait for sessions to clear out (just in case) */
 	wait_event(tgt->waitQ, test_tgt_sess_count(tgt));
+	return 0;
 }
 EXPORT_SYMBOL(qlt_stop_phase1);
 
@@ -2595,8 +2612,6 @@
 		return -ENOMEM;
 	}
 
-	INIT_LIST_HEAD(&cmd->cmd_list);
-
 	memcpy(&cmd->atio, atio, sizeof(*atio));
 	cmd->state = QLA_TGT_STATE_NEW;
 	cmd->tgt = vha->vha_tgt.qla_tgt;
@@ -3187,7 +3202,8 @@
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02c,
 		    "SRR cmd %p (se_cmd %p, tag %d, op %x), "
 		    "sg_cnt=%d, offset=%d", cmd, &cmd->se_cmd, cmd->tag,
-		    se_cmd->t_task_cdb[0], cmd->sg_cnt, cmd->offset);
+		    se_cmd->t_task_cdb ? se_cmd->t_task_cdb[0] : 0,
+		    cmd->sg_cnt, cmd->offset);
 
 		qlt_handle_srr(vha, sctio, imm);
 
@@ -4183,6 +4199,9 @@
 	tgt->datasegs_per_cmd = QLA_TGT_DATASEGS_PER_CMD_24XX;
 	tgt->datasegs_per_cont = QLA_TGT_DATASEGS_PER_CONT_24XX;
 
+	if (base_vha->fc_vport)
+		return 0;
+
 	mutex_lock(&qla_tgt_mutex);
 	list_add_tail(&tgt->tgt_list_entry, &qla_tgt_glist);
 	mutex_unlock(&qla_tgt_mutex);
@@ -4196,6 +4215,10 @@
 	if (!vha->vha_tgt.qla_tgt)
 		return 0;
 
+	if (vha->fc_vport) {
+		qlt_release(vha->vha_tgt.qla_tgt);
+		return 0;
+	}
 	mutex_lock(&qla_tgt_mutex);
 	list_del(&vha->vha_tgt.qla_tgt->tgt_list_entry);
 	mutex_unlock(&qla_tgt_mutex);
@@ -4267,6 +4290,12 @@
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 			continue;
 		}
+		if (tgt->tgt_stop) {
+			pr_debug("MODE_TARGET in shutdown on qla2xxx(%d)\n",
+				 host->host_no);
+			spin_unlock_irqrestore(&ha->hardware_lock, flags);
+			continue;
+		}
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 		if (!scsi_host_get(host)) {
@@ -4281,12 +4310,11 @@
 			scsi_host_put(host);
 			continue;
 		}
-		mutex_unlock(&qla_tgt_mutex);
-
 		rc = (*callback)(vha, target_lport_ptr, npiv_wwpn, npiv_wwnn);
 		if (rc != 0)
 			scsi_host_put(host);
 
+		mutex_unlock(&qla_tgt_mutex);
 		return rc;
 	}
 	mutex_unlock(&qla_tgt_mutex);
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 1d10eec..ce33d8c 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -855,7 +855,6 @@
 	uint16_t loop_id;	/* to save extra sess dereferences */
 	struct qla_tgt *tgt;	/* to save extra sess dereferences */
 	struct scsi_qla_host *vha;
-	struct list_head cmd_list;
 
 	struct atio_from_isp atio;
 };
@@ -1002,7 +1001,7 @@
 extern void qlt_probe_one_stage1(struct scsi_qla_host *, struct qla_hw_data *);
 extern int qlt_mem_alloc(struct qla_hw_data *);
 extern void qlt_mem_free(struct qla_hw_data *);
-extern void qlt_stop_phase1(struct qla_tgt *);
+extern int qlt_stop_phase1(struct qla_tgt *);
 extern void qlt_stop_phase2(struct qla_tgt *);
 extern irqreturn_t qla83xx_msix_atio_q(int, void *);
 extern void qlt_83xx_iospace_config(struct qla_hw_data *);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 75a141b..788c4fe 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -182,20 +182,6 @@
 	return 0;
 }
 
-static ssize_t tcm_qla2xxx_npiv_format_wwn(char *buf, size_t len,
-					u64 wwpn, u64 wwnn)
-{
-	u8 b[8], b2[8];
-
-	put_unaligned_be64(wwpn, b);
-	put_unaligned_be64(wwnn, b2);
-	return snprintf(buf, len,
-		"%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x,"
-		"%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x",
-		b[0], b[1], b[2], b[3], b[4], b[5], b[6], b[7],
-		b2[0], b2[1], b2[2], b2[3], b2[4], b2[5], b2[6], b2[7]);
-}
-
 static char *tcm_qla2xxx_npiv_get_fabric_name(void)
 {
 	return "qla2xxx_npiv";
@@ -227,15 +213,6 @@
 	return lport->lport_naa_name;
 }
 
-static char *tcm_qla2xxx_npiv_get_fabric_wwn(struct se_portal_group *se_tpg)
-{
-	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
-				struct tcm_qla2xxx_tpg, se_tpg);
-	struct tcm_qla2xxx_lport *lport = tpg->lport;
-
-	return &lport->lport_npiv_name[0];
-}
-
 static u16 tcm_qla2xxx_get_tag(struct se_portal_group *se_tpg)
 {
 	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
@@ -941,15 +918,41 @@
 			atomic_read(&tpg->lport_tpg_enabled));
 }
 
+static void tcm_qla2xxx_depend_tpg(struct work_struct *work)
+{
+	struct tcm_qla2xxx_tpg *base_tpg = container_of(work,
+				struct tcm_qla2xxx_tpg, tpg_base_work);
+	struct se_portal_group *se_tpg = &base_tpg->se_tpg;
+	struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha;
+
+	if (!configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
+				  &se_tpg->tpg_group.cg_item)) {
+		atomic_set(&base_tpg->lport_tpg_enabled, 1);
+		qlt_enable_vha(base_vha);
+	}
+	complete(&base_tpg->tpg_base_comp);
+}
+
+static void tcm_qla2xxx_undepend_tpg(struct work_struct *work)
+{
+	struct tcm_qla2xxx_tpg *base_tpg = container_of(work,
+				struct tcm_qla2xxx_tpg, tpg_base_work);
+	struct se_portal_group *se_tpg = &base_tpg->se_tpg;
+	struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha;
+
+	if (!qlt_stop_phase1(base_vha->vha_tgt.qla_tgt)) {
+		atomic_set(&base_tpg->lport_tpg_enabled, 0);
+		configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
+				       &se_tpg->tpg_group.cg_item);
+	}
+	complete(&base_tpg->tpg_base_comp);
+}
+
 static ssize_t tcm_qla2xxx_tpg_store_enable(
 	struct se_portal_group *se_tpg,
 	const char *page,
 	size_t count)
 {
-	struct se_wwn *se_wwn = se_tpg->se_tpg_wwn;
-	struct tcm_qla2xxx_lport *lport = container_of(se_wwn,
-			struct tcm_qla2xxx_lport, lport_wwn);
-	struct scsi_qla_host *vha = lport->qla_vha;
 	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
 			struct tcm_qla2xxx_tpg, se_tpg);
 	unsigned long op;
@@ -964,19 +967,28 @@
 		pr_err("Illegal value for tpg_enable: %lu\n", op);
 		return -EINVAL;
 	}
+	if (op) {
+		if (atomic_read(&tpg->lport_tpg_enabled))
+			return -EEXIST;
+
+		INIT_WORK(&tpg->tpg_base_work, tcm_qla2xxx_depend_tpg);
+	} else {
+		if (!atomic_read(&tpg->lport_tpg_enabled))
+			return count;
+
+		INIT_WORK(&tpg->tpg_base_work, tcm_qla2xxx_undepend_tpg);
+	}
+	init_completion(&tpg->tpg_base_comp);
+	schedule_work(&tpg->tpg_base_work);
+	wait_for_completion(&tpg->tpg_base_comp);
 
 	if (op) {
-		atomic_set(&tpg->lport_tpg_enabled, 1);
-		qlt_enable_vha(vha);
-	} else {
-		if (!vha->vha_tgt.qla_tgt) {
-			pr_err("struct qla_hw_data *vha->vha_tgt.qla_tgt is NULL\n");
+		if (!atomic_read(&tpg->lport_tpg_enabled))
 			return -ENODEV;
-		}
-		atomic_set(&tpg->lport_tpg_enabled, 0);
-		qlt_stop_phase1(vha->vha_tgt.qla_tgt);
+	} else {
+		if (atomic_read(&tpg->lport_tpg_enabled))
+			return -EPERM;
 	}
-
 	return count;
 }
 
@@ -1053,11 +1065,64 @@
 	/*
 	 * Clear local TPG=1 pointer for non NPIV mode.
 	 */
-		lport->tpg_1 = NULL;
-
+	lport->tpg_1 = NULL;
 	kfree(tpg);
 }
 
+static ssize_t tcm_qla2xxx_npiv_tpg_show_enable(
+	struct se_portal_group *se_tpg,
+	char *page)
+{
+	return tcm_qla2xxx_tpg_show_enable(se_tpg, page);
+}
+
+static ssize_t tcm_qla2xxx_npiv_tpg_store_enable(
+	struct se_portal_group *se_tpg,
+	const char *page,
+	size_t count)
+{
+	struct se_wwn *se_wwn = se_tpg->se_tpg_wwn;
+	struct tcm_qla2xxx_lport *lport = container_of(se_wwn,
+			struct tcm_qla2xxx_lport, lport_wwn);
+	struct scsi_qla_host *vha = lport->qla_vha;
+	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
+			struct tcm_qla2xxx_tpg, se_tpg);
+	unsigned long op;
+	int rc;
+
+	rc = kstrtoul(page, 0, &op);
+	if (rc < 0) {
+		pr_err("kstrtoul() returned %d\n", rc);
+		return -EINVAL;
+	}
+	if ((op != 1) && (op != 0)) {
+		pr_err("Illegal value for tpg_enable: %lu\n", op);
+		return -EINVAL;
+	}
+	if (op) {
+		if (atomic_read(&tpg->lport_tpg_enabled))
+			return -EEXIST;
+
+		atomic_set(&tpg->lport_tpg_enabled, 1);
+		qlt_enable_vha(vha);
+	} else {
+		if (!atomic_read(&tpg->lport_tpg_enabled))
+			return count;
+
+		atomic_set(&tpg->lport_tpg_enabled, 0);
+		qlt_stop_phase1(vha->vha_tgt.qla_tgt);
+	}
+
+	return count;
+}
+
+TF_TPG_BASE_ATTR(tcm_qla2xxx_npiv, enable, S_IRUGO | S_IWUSR);
+
+static struct configfs_attribute *tcm_qla2xxx_npiv_tpg_attrs[] = {
+        &tcm_qla2xxx_npiv_tpg_enable.attr,
+        NULL,
+};
+
 static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg(
 	struct se_wwn *wwn,
 	struct config_group *group,
@@ -1650,6 +1715,9 @@
 	struct scsi_qla_host *npiv_vha;
 	struct tcm_qla2xxx_lport *lport =
 			(struct tcm_qla2xxx_lport *)target_lport_ptr;
+	struct tcm_qla2xxx_lport *base_lport =
+			(struct tcm_qla2xxx_lport *)base_vha->vha_tgt.target_lport_ptr;
+	struct tcm_qla2xxx_tpg *base_tpg;
 	struct fc_vport_identifiers vport_id;
 
 	if (!qla_tgt_mode_enabled(base_vha)) {
@@ -1657,6 +1725,13 @@
 		return -EPERM;
 	}
 
+	if (!base_lport || !base_lport->tpg_1 ||
+	    !atomic_read(&base_lport->tpg_1->lport_tpg_enabled)) {
+		pr_err("qla2xxx base_lport or tpg_1 not available\n");
+		return -EPERM;
+	}
+	base_tpg = base_lport->tpg_1;
+
 	memset(&vport_id, 0, sizeof(vport_id));
 	vport_id.port_name = npiv_wwpn;
 	vport_id.node_name = npiv_wwnn;
@@ -1675,7 +1750,6 @@
 	npiv_vha = (struct scsi_qla_host *)vport->dd_data;
 	npiv_vha->vha_tgt.target_lport_ptr = target_lport_ptr;
 	lport->qla_vha = npiv_vha;
-
 	scsi_host_get(npiv_vha->host);
 	return 0;
 }
@@ -1714,8 +1788,6 @@
 	}
 	lport->lport_npiv_wwpn = npiv_wwpn;
 	lport->lport_npiv_wwnn = npiv_wwnn;
-	tcm_qla2xxx_npiv_format_wwn(&lport->lport_npiv_name[0],
-			TCM_QLA2XXX_NAMELEN, npiv_wwpn, npiv_wwnn);
 	sprintf(lport->lport_naa_name, "naa.%016llx", (unsigned long long) npiv_wwpn);
 
 	ret = tcm_qla2xxx_init_lport(lport);
@@ -1824,7 +1896,7 @@
 static struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = {
 	.get_fabric_name		= tcm_qla2xxx_npiv_get_fabric_name,
 	.get_fabric_proto_ident		= tcm_qla2xxx_get_fabric_proto_ident,
-	.tpg_get_wwn			= tcm_qla2xxx_npiv_get_fabric_wwn,
+	.tpg_get_wwn			= tcm_qla2xxx_get_fabric_wwn,
 	.tpg_get_tag			= tcm_qla2xxx_get_tag,
 	.tpg_get_default_depth		= tcm_qla2xxx_get_default_depth,
 	.tpg_get_pr_transport_id	= tcm_qla2xxx_get_pr_transport_id,
@@ -1935,7 +2007,7 @@
 	 */
 	npiv_fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs =
-	    tcm_qla2xxx_tpg_attrs;
+	    tcm_qla2xxx_npiv_tpg_attrs;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
index 275d8b9..33aaac8 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
@@ -4,8 +4,6 @@
 #define TCM_QLA2XXX_VERSION	"v0.1"
 /* length of ASCII WWPNs including pad */
 #define TCM_QLA2XXX_NAMELEN	32
-/* lenth of ASCII NPIV 'WWPN+WWNN' including pad */
-#define TCM_QLA2XXX_NPIV_NAMELEN 66
 
 #include "qla_target.h"
 
@@ -43,6 +41,9 @@
 	struct tcm_qla2xxx_tpg_attrib tpg_attrib;
 	/* Returned by tcm_qla2xxx_make_tpg() */
 	struct se_portal_group se_tpg;
+	/* Items for dealing with configfs_depend_item */
+	struct completion tpg_base_comp;
+	struct work_struct tpg_base_work;
 };
 
 struct tcm_qla2xxx_fc_loopid {
@@ -62,8 +63,6 @@
 	char lport_name[TCM_QLA2XXX_NAMELEN];
 	/* ASCII formatted naa WWPN for VPD page 83 etc */
 	char lport_naa_name[TCM_QLA2XXX_NAMELEN];
-	/* ASCII formatted WWPN+WWNN for NPIV FC Target Lport */
-	char lport_npiv_name[TCM_QLA2XXX_NPIV_NAMELEN];
 	/* map for fc_port pointers in 24-bit FC Port ID space */
 	struct btree_head32 lport_fcport_map;
 	/* vmalloc-ed memory for fc_port pointers for 16-bit FC loop ID */
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 7bd7f0d..62ec84b 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1684,7 +1684,7 @@
 
 	host_dev = scsi_get_device(shost);
 	if (host_dev && host_dev->dma_mask)
-		bounce_limit = dma_max_pfn(host_dev) << PAGE_SHIFT;
+		bounce_limit = (u64)dma_max_pfn(host_dev) << PAGE_SHIFT;
 
 	return bounce_limit;
 }
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 17d7404..9969fa1 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1419,6 +1419,9 @@
 {
 	struct stor_mem_pools *memp = sdevice->hostdata;
 
+	if (!memp)
+		return;
+
 	mempool_destroy(memp->request_mempool);
 	kmem_cache_destroy(memp->request_pool);
 	kfree(memp);
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index ba9310b..581ee2a 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -376,10 +376,10 @@
 	def_tristate SPI_PXA2XX && PCI
 
 config SPI_RSPI
-	tristate "Renesas RSPI controller"
+	tristate "Renesas RSPI/QSPI controller"
 	depends on (SUPERH && SH_DMAE_BASE) || ARCH_SHMOBILE
 	help
-	  SPI driver for Renesas RSPI blocks.
+	  SPI driver for Renesas RSPI and QSPI blocks.
 
 config SPI_S3C24XX
 	tristate "Samsung S3C24XX series SPI"
diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index 31534b5..c3b2fb9 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -132,9 +132,9 @@
 
 		flags = GPIOF_DIR_OUT;
 		if (spi->mode & SPI_CS_HIGH)
-			flags |= GPIOF_INIT_HIGH;
-		else
 			flags |= GPIOF_INIT_LOW;
+		else
+			flags |= GPIOF_INIT_HIGH;
 
 		status = gpio_request_one(cdata->gpio, flags,
 					  dev_name(&spi->dev));
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index b0842f7..5d7b07f 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1455,6 +1455,14 @@
 {
 	struct spi_master	*master = dev_get_drvdata(dev);
 	struct atmel_spi	*as = spi_master_get_devdata(master);
+	int ret;
+
+	/* Stop the queue running */
+	ret = spi_master_suspend(master);
+	if (ret) {
+		dev_warn(dev, "cannot suspend master\n");
+		return ret;
+	}
 
 	clk_disable_unprepare(as->clk);
 	return 0;
@@ -1464,9 +1472,16 @@
 {
 	struct spi_master	*master = dev_get_drvdata(dev);
 	struct atmel_spi	*as = spi_master_get_devdata(master);
+	int ret;
 
 	clk_prepare_enable(as->clk);
-	return 0;
+
+	/* Start the queue running */
+	ret = spi_master_resume(master);
+	if (ret)
+		dev_err(dev, "problem starting queue (%d)\n", ret);
+
+	return ret;
 }
 
 static SIMPLE_DEV_PM_OPS(atmel_spi_pm_ops, atmel_spi_suspend, atmel_spi_resume);
diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c
index cabed8f..28ae470 100644
--- a/drivers/spi/spi-coldfire-qspi.c
+++ b/drivers/spi/spi-coldfire-qspi.c
@@ -514,7 +514,8 @@
 #ifdef CONFIG_PM_RUNTIME
 static int mcfqspi_runtime_suspend(struct device *dev)
 {
-	struct mcfqspi *mcfqspi = dev_get_drvdata(dev);
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct mcfqspi *mcfqspi = spi_master_get_devdata(master);
 
 	clk_disable(mcfqspi->clk);
 
@@ -523,7 +524,8 @@
 
 static int mcfqspi_runtime_resume(struct device *dev)
 {
-	struct mcfqspi *mcfqspi = dev_get_drvdata(dev);
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct mcfqspi *mcfqspi = spi_master_get_devdata(master);
 
 	clk_enable(mcfqspi->clk);
 
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index ec79f72..a253920 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -420,7 +420,6 @@
 
 static int dspi_resume(struct device *dev)
 {
-
 	struct spi_master *master = dev_get_drvdata(dev);
 	struct fsl_dspi *dspi = spi_master_get_devdata(master);
 
@@ -504,7 +503,7 @@
 	clk_prepare_enable(dspi->clk);
 
 	init_waitqueue_head(&dspi->waitq);
-	platform_set_drvdata(pdev, dspi);
+	platform_set_drvdata(pdev, master);
 
 	ret = spi_bitbang_start(&dspi->bitbang);
 	if (ret != 0) {
@@ -525,7 +524,8 @@
 
 static int dspi_remove(struct platform_device *pdev)
 {
-	struct fsl_dspi *dspi = platform_get_drvdata(pdev);
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct fsl_dspi *dspi = spi_master_get_devdata(master);
 
 	/* Disconnect from the SPI framework */
 	spi_bitbang_stop(&dspi->bitbang);
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index a5474ef..47f15d9 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -948,8 +948,8 @@
 	spi_bitbang_stop(&spi_imx->bitbang);
 
 	writel(0, spi_imx->base + MXC_CSPICTRL);
-	clk_disable_unprepare(spi_imx->clk_ipg);
-	clk_disable_unprepare(spi_imx->clk_per);
+	clk_unprepare(spi_imx->clk_ipg);
+	clk_unprepare(spi_imx->clk_per);
 	spi_master_put(master);
 
 	return 0;
diff --git a/drivers/spi/spi-nuc900.c b/drivers/spi/spi-nuc900.c
index 5040630..bae97ff 100644
--- a/drivers/spi/spi-nuc900.c
+++ b/drivers/spi/spi-nuc900.c
@@ -361,6 +361,8 @@
 	init_completion(&hw->done);
 
 	master->mode_bits          = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	if (hw->pdata->lsb)
+		master->mode_bits |= SPI_LSB_FIRST;
 	master->num_chipselect     = hw->pdata->num_cs;
 	master->bus_num            = hw->pdata->bus_num;
 	hw->bitbang.master         = hw->master;
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index 2e7f38c..88eb57e 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -915,7 +915,7 @@
 	/* Set Tx DMA */
 	param = &dma->param_tx;
 	param->dma_dev = &dma_dev->dev;
-	param->chan_id = data->master->bus_num * 2; /* Tx = 0, 2 */
+	param->chan_id = data->ch * 2; /* Tx = 0, 2 */;
 	param->tx_reg = data->io_base_addr + PCH_SPDWR;
 	param->width = width;
 	chan = dma_request_channel(mask, pch_spi_filter, param);
@@ -930,7 +930,7 @@
 	/* Set Rx DMA */
 	param = &dma->param_rx;
 	param->dma_dev = &dma_dev->dev;
-	param->chan_id = data->master->bus_num * 2 + 1; /* Rx = Tx + 1 */
+	param->chan_id = data->ch * 2 + 1; /* Rx = Tx + 1 */;
 	param->rx_reg = data->io_base_addr + PCH_SPDRR;
 	param->width = width;
 	chan = dma_request_channel(mask, pch_spi_filter, param);
@@ -1452,6 +1452,11 @@
 
 	pch_spi_set_master_mode(master);
 
+	if (use_dma) {
+		dev_info(&plat_dev->dev, "Use DMA for data transfers\n");
+		pch_alloc_dma_buf(board_dat, data);
+	}
+
 	ret = spi_register_master(master);
 	if (ret != 0) {
 		dev_err(&plat_dev->dev,
@@ -1459,14 +1464,10 @@
 		goto err_spi_register_master;
 	}
 
-	if (use_dma) {
-		dev_info(&plat_dev->dev, "Use DMA for data transfers\n");
-		pch_alloc_dma_buf(board_dat, data);
-	}
-
 	return 0;
 
 err_spi_register_master:
+	pch_free_dma_buf(board_dat, data);
 	free_irq(board_dat->pdev->irq, data);
 err_request_irq:
 	pch_spi_free_resources(board_dat, data);
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 23756b0..d0b28bb 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -755,9 +755,7 @@
 	ret = master->transfer_one_message(master, master->cur_msg);
 	if (ret) {
 		dev_err(&master->dev,
-			"failed to transfer one message from queue: %d\n", ret);
-		master->cur_msg->status = ret;
-		spi_finalize_current_message(master);
+			"failed to transfer one message from queue\n");
 		return;
 	}
 }
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 23948f1..713a972 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -295,21 +295,29 @@
 
 	/* If size is not set, or set to 0, always return EOF. */
 	if (asma->size == 0)
-		goto out;
+		goto out_unlock;
 
 	if (!asma->file) {
 		ret = -EBADF;
-		goto out;
+		goto out_unlock;
 	}
 
+	mutex_unlock(&ashmem_mutex);
+
+	/*
+	 * asma and asma->file are used outside the lock here.  We assume
+	 * once asma->file is set it will never be changed, and will not
+	 * be destroyed until all references to the file are dropped and
+	 * ashmem_release is called.
+	 */
 	ret = asma->file->f_op->read(asma->file, buf, len, pos);
-	if (ret < 0)
-		goto out;
+	if (ret >= 0) {
+		/** Update backing file pos, since f_ops->read() doesn't */
+		asma->file->f_pos = *pos;
+	}
+	return ret;
 
-	/** Update backing file pos, since f_ops->read() doesn't */
-	asma->file->f_pos = *pos;
-
-out:
+out_unlock:
 	mutex_unlock(&ashmem_mutex);
 	return ret;
 }
@@ -498,6 +506,7 @@
 
 static int set_name(struct ashmem_area *asma, void __user *name)
 {
+	int len;
 	int ret = 0;
 	char local_name[ASHMEM_NAME_LEN];
 
@@ -510,21 +519,19 @@
 	 * variable that does not need protection and later copy the local
 	 * variable to the structure member with lock held.
 	 */
-	if (copy_from_user(local_name, name, ASHMEM_NAME_LEN))
-		return -EFAULT;
-
+	len = strncpy_from_user(local_name, name, ASHMEM_NAME_LEN);
+	if (len < 0)
+		return len;
+	if (len == ASHMEM_NAME_LEN)
+		local_name[ASHMEM_NAME_LEN - 1] = '\0';
 	mutex_lock(&ashmem_mutex);
 	/* cannot change an existing mapping's name */
-	if (unlikely(asma->file)) {
+	if (unlikely(asma->file))
 		ret = -EINVAL;
-		goto out;
-	}
-	memcpy(asma->name + ASHMEM_NAME_PREFIX_LEN,
-		local_name, ASHMEM_NAME_LEN);
-	asma->name[ASHMEM_FULL_NAME_LEN-1] = '\0';
-out:
-	mutex_unlock(&ashmem_mutex);
+	else
+		strcpy(asma->name + ASHMEM_NAME_PREFIX_LEN, local_name);
 
+	mutex_unlock(&ashmem_mutex);
 	return ret;
 }
 
diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
index eaec1da..1432d95 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/staging/android/binder.c
@@ -2904,7 +2904,7 @@
 		refs++;
 
 		if (!ref->death)
-			goto out;
+			continue;
 
 		death++;
 
@@ -2917,7 +2917,6 @@
 			BUG();
 	}
 
-out:
 	binder_debug(BINDER_DEBUG_DEAD_BINDER,
 		     "node %d now dead, refs %d, death %d\n",
 		     node->debug_id, refs, death);
diff --git a/drivers/staging/android/ion/compat_ion.c b/drivers/staging/android/ion/compat_ion.c
index af6cd37..ee3a738 100644
--- a/drivers/staging/android/ion/compat_ion.c
+++ b/drivers/staging/android/ion/compat_ion.c
@@ -35,9 +35,14 @@
 	compat_ulong_t arg;
 };
 
+struct compat_ion_handle_data {
+	compat_int_t handle;
+};
+
 #define COMPAT_ION_IOC_ALLOC	_IOWR(ION_IOC_MAGIC, 0, \
 				      struct compat_ion_allocation_data)
-#define COMPAT_ION_IOC_FREE	_IOWR(ION_IOC_MAGIC, 1, struct ion_handle_data)
+#define COMPAT_ION_IOC_FREE	_IOWR(ION_IOC_MAGIC, 1, \
+				      struct compat_ion_handle_data)
 #define COMPAT_ION_IOC_CUSTOM	_IOWR(ION_IOC_MAGIC, 6, \
 				      struct compat_ion_custom_data)
 
@@ -64,6 +69,19 @@
 	return err;
 }
 
+static int compat_get_ion_handle_data(
+			struct compat_ion_handle_data __user *data32,
+			struct ion_handle_data __user *data)
+{
+	compat_int_t i;
+	int err;
+
+	err = get_user(i, &data32->handle);
+	err |= put_user(i, &data->handle);
+
+	return err;
+}
+
 static int compat_put_ion_allocation_data(
 			struct compat_ion_allocation_data __user *data32,
 			struct ion_allocation_data __user *data)
@@ -132,8 +150,8 @@
 	}
 	case COMPAT_ION_IOC_FREE:
 	{
-		struct compat_ion_allocation_data __user *data32;
-		struct ion_allocation_data __user *data;
+		struct compat_ion_handle_data __user *data32;
+		struct ion_handle_data __user *data;
 		int err;
 
 		data32 = compat_ptr(arg);
@@ -141,7 +159,7 @@
 		if (data == NULL)
 			return -EFAULT;
 
-		err = compat_get_ion_allocation_data(data32, data);
+		err = compat_get_ion_handle_data(data32, data);
 		if (err)
 			return err;
 
diff --git a/drivers/staging/android/ion/ion_dummy_driver.c b/drivers/staging/android/ion/ion_dummy_driver.c
index 55b2002..01cdc8a 100644
--- a/drivers/staging/android/ion/ion_dummy_driver.c
+++ b/drivers/staging/android/ion/ion_dummy_driver.c
@@ -17,9 +17,11 @@
 #include <linux/err.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/init.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
 #include <linux/sizes.h>
+#include <linux/io.h>
 #include "ion.h"
 #include "ion_priv.h"
 
@@ -57,7 +59,7 @@
 };
 
 struct ion_platform_data dummy_ion_pdata = {
-	.nr = 4,
+	.nr = ARRAY_SIZE(dummy_heaps),
 	.heaps = dummy_heaps,
 };
 
@@ -69,7 +71,7 @@
 	heaps = kzalloc(sizeof(struct ion_heap *) * dummy_ion_pdata.nr,
 			GFP_KERNEL);
 	if (!heaps)
-		return PTR_ERR(heaps);
+		return -ENOMEM;
 
 
 	/* Allocate a dummy carveout heap */
@@ -128,6 +130,7 @@
 	}
 	return err;
 }
+device_initcall(ion_dummy_init);
 
 static void __exit ion_dummy_exit(void)
 {
@@ -152,7 +155,4 @@
 
 	return;
 }
-
-module_init(ion_dummy_init);
-module_exit(ion_dummy_exit);
-
+__exitcall(ion_dummy_exit);
diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c
index 296c74f..37e64d5 100644
--- a/drivers/staging/android/ion/ion_heap.c
+++ b/drivers/staging/android/ion/ion_heap.c
@@ -243,12 +243,12 @@
 	init_waitqueue_head(&heap->waitqueue);
 	heap->task = kthread_run(ion_heap_deferred_free, heap,
 				 "%s", heap->name);
-	sched_setscheduler(heap->task, SCHED_IDLE, &param);
 	if (IS_ERR(heap->task)) {
 		pr_err("%s: creating thread for deferred free failed\n",
 		       __func__);
 		return PTR_RET(heap->task);
 	}
+	sched_setscheduler(heap->task, SCHED_IDLE, &param);
 	return 0;
 }
 
diff --git a/drivers/staging/android/ion/ion_priv.h b/drivers/staging/android/ion/ion_priv.h
index d986739..fc2e4fc 100644
--- a/drivers/staging/android/ion/ion_priv.h
+++ b/drivers/staging/android/ion/ion_priv.h
@@ -17,6 +17,7 @@
 #ifndef _ION_PRIV_H
 #define _ION_PRIV_H
 
+#include <linux/device.h>
 #include <linux/dma-direction.h>
 #include <linux/kref.h>
 #include <linux/mm_types.h>
diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c
index 7f07291..9849f39 100644
--- a/drivers/staging/android/ion/ion_system_heap.c
+++ b/drivers/staging/android/ion/ion_system_heap.c
@@ -124,6 +124,7 @@
 
 		info->page = page;
 		info->order = orders[i];
+		INIT_LIST_HEAD(&info->list);
 		return info;
 	}
 	kfree(info);
@@ -145,12 +146,15 @@
 	struct list_head pages;
 	struct page_info *info, *tmp_info;
 	int i = 0;
-	long size_remaining = PAGE_ALIGN(size);
+	unsigned long size_remaining = PAGE_ALIGN(size);
 	unsigned int max_order = orders[0];
 
 	if (align > PAGE_SIZE)
 		return -EINVAL;
 
+	if (size / PAGE_SIZE > totalram_pages / 2)
+		return -ENOMEM;
+
 	INIT_LIST_HEAD(&pages);
 	while (size_remaining > 0) {
 		info = alloc_largest_available(sys_heap, buffer, size_remaining,
diff --git a/drivers/staging/android/sw_sync.h b/drivers/staging/android/sw_sync.h
index 585040b..5aaf71d 100644
--- a/drivers/staging/android/sw_sync.h
+++ b/drivers/staging/android/sw_sync.h
@@ -35,10 +35,27 @@
 	u32			value;
 };
 
+#if IS_ENABLED(CONFIG_SW_SYNC)
 struct sw_sync_timeline *sw_sync_timeline_create(const char *name);
 void sw_sync_timeline_inc(struct sw_sync_timeline *obj, u32 inc);
 
 struct sync_pt *sw_sync_pt_create(struct sw_sync_timeline *obj, u32 value);
+#else
+static inline struct sw_sync_timeline *sw_sync_timeline_create(const char *name)
+{
+	return NULL;
+}
+
+static inline void sw_sync_timeline_inc(struct sw_sync_timeline *obj, u32 inc)
+{
+}
+
+static inline struct sync_pt *sw_sync_pt_create(struct sw_sync_timeline *obj,
+		u32 value)
+{
+	return NULL;
+}
+#endif /* IS_ENABLED(CONFIG_SW_SYNC) */
 
 #endif /* __KERNEL __ */
 
diff --git a/drivers/staging/android/sync.c b/drivers/staging/android/sync.c
index 38e5d3b..3d05f662 100644
--- a/drivers/staging/android/sync.c
+++ b/drivers/staging/android/sync.c
@@ -79,27 +79,27 @@
 		container_of(kref, struct sync_timeline, kref);
 	unsigned long flags;
 
-	if (obj->ops->release_obj)
-		obj->ops->release_obj(obj);
-
 	spin_lock_irqsave(&sync_timeline_list_lock, flags);
 	list_del(&obj->sync_timeline_list);
 	spin_unlock_irqrestore(&sync_timeline_list_lock, flags);
 
+	if (obj->ops->release_obj)
+		obj->ops->release_obj(obj);
+
 	kfree(obj);
 }
 
 void sync_timeline_destroy(struct sync_timeline *obj)
 {
 	obj->destroyed = true;
+	smp_wmb();
 
 	/*
-	 * If this is not the last reference, signal any children
-	 * that their parent is going away.
+	 * signal any children that their parent is going away.
 	 */
+	sync_timeline_signal(obj);
 
-	if (!kref_put(&obj->kref, sync_timeline_free))
-		sync_timeline_signal(obj);
+	kref_put(&obj->kref, sync_timeline_free);
 }
 EXPORT_SYMBOL(sync_timeline_destroy);
 
diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c
index 8dfdd27..95a2358 100644
--- a/drivers/staging/bcm/Bcmnet.c
+++ b/drivers/staging/bcm/Bcmnet.c
@@ -40,7 +40,7 @@
 }
 
 static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv)
+			    void *accel_priv, select_queue_fallback_t fallback)
 {
 	return ClassifyPacket(netdev_priv(dev), skb);
 }
diff --git a/drivers/staging/comedi/drivers.c b/drivers/staging/comedi/drivers.c
index 2460803..5b15033 100644
--- a/drivers/staging/comedi/drivers.c
+++ b/drivers/staging/comedi/drivers.c
@@ -616,8 +616,6 @@
 	ret = driver->auto_attach(dev, context);
 	if (ret >= 0)
 		ret = comedi_device_postconfig(dev);
-	if (ret < 0)
-		comedi_device_detach(dev);
 	mutex_unlock(&dev->mutex);
 
 	if (ret < 0) {
diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c
index 593676c..d9ad2c0 100644
--- a/drivers/staging/comedi/drivers/adv_pci1710.c
+++ b/drivers/staging/comedi/drivers/adv_pci1710.c
@@ -494,6 +494,7 @@
 				 struct comedi_insn *insn, unsigned int *data)
 {
 	struct pci1710_private *devpriv = dev->private;
+	unsigned int val;
 	int n, chan, range, ofs;
 
 	chan = CR_CHAN(insn->chanspec);
@@ -509,11 +510,14 @@
 		outw(devpriv->da_ranges, dev->iobase + PCI171x_DAREF);
 		ofs = PCI171x_DA1;
 	}
+	val = devpriv->ao_data[chan];
 
-	for (n = 0; n < insn->n; n++)
-		outw(data[n], dev->iobase + ofs);
+	for (n = 0; n < insn->n; n++) {
+		val = data[n];
+		outw(val, dev->iobase + ofs);
+	}
 
-	devpriv->ao_data[chan] = data[n];
+	devpriv->ao_data[chan] = val;
 
 	return n;
 
@@ -679,6 +683,7 @@
 				 struct comedi_insn *insn, unsigned int *data)
 {
 	struct pci1710_private *devpriv = dev->private;
+	unsigned int val;
 	int n, rangereg, chan;
 
 	chan = CR_CHAN(insn->chanspec);
@@ -688,13 +693,15 @@
 		outb(rangereg, dev->iobase + PCI1720_RANGE);
 		devpriv->da_ranges = rangereg;
 	}
+	val = devpriv->ao_data[chan];
 
 	for (n = 0; n < insn->n; n++) {
-		outw(data[n], dev->iobase + PCI1720_DA0 + (chan << 1));
+		val = data[n];
+		outw(val, dev->iobase + PCI1720_DA0 + (chan << 1));
 		outb(0, dev->iobase + PCI1720_SYNCOUT);	/*  update outputs */
 	}
 
-	devpriv->ao_data[chan] = data[n];
+	devpriv->ao_data[chan] = val;
 
 	return n;
 }
diff --git a/drivers/staging/comedi/drivers/usbduxsigma.c b/drivers/staging/comedi/drivers/usbduxsigma.c
index 3beeb12..88c60b6 100644
--- a/drivers/staging/comedi/drivers/usbduxsigma.c
+++ b/drivers/staging/comedi/drivers/usbduxsigma.c
@@ -48,6 +48,7 @@
 #include <linux/usb.h>
 #include <linux/fcntl.h>
 #include <linux/compiler.h>
+#include <asm/unaligned.h>
 
 #include "comedi_fc.h"
 #include "../comedidev.h"
@@ -792,7 +793,8 @@
 		}
 
 		/* 32 bits big endian from the A/D converter */
-		val = be32_to_cpu(*((uint32_t *)((devpriv->insn_buf) + 1)));
+		val = be32_to_cpu(get_unaligned((uint32_t
+						 *)(devpriv->insn_buf + 1)));
 		val &= 0x00ffffff;	/* strip status byte */
 		val ^= 0x00800000;	/* convert to unsigned */
 
@@ -1357,7 +1359,7 @@
 		return ret;
 
 	/* 32 bits big endian from the A/D converter */
-	val = be32_to_cpu(*((uint32_t *)((devpriv->insn_buf)+1)));
+	val = be32_to_cpu(get_unaligned((uint32_t *)(devpriv->insn_buf + 1)));
 	val &= 0x00ffffff;	/* strip status byte */
 	val ^= 0x00800000;	/* convert to unsigned */
 
diff --git a/drivers/staging/cxt1e1/linux.c b/drivers/staging/cxt1e1/linux.c
index 4a08e16..79206cb 100644
--- a/drivers/staging/cxt1e1/linux.c
+++ b/drivers/staging/cxt1e1/linux.c
@@ -866,6 +866,8 @@
             _IOC_SIZE (iocmd));
 #endif
     iolen = _IOC_SIZE (iocmd);
+    if (iolen > sizeof(arg))
+        return -EFAULT;
     data = ifr->ifr_data + sizeof (iocmd);
     if (copy_from_user (&arg, data, iolen))
         return -EFAULT;
diff --git a/drivers/staging/dgrp/dgrp_net_ops.c b/drivers/staging/dgrp/dgrp_net_ops.c
index 1f61b89..33ac7fb 100644
--- a/drivers/staging/dgrp/dgrp_net_ops.c
+++ b/drivers/staging/dgrp/dgrp_net_ops.c
@@ -2232,177 +2232,6 @@
 	return rtn;
 }
 
-/*
- * Common Packet Handling code
- */
-
-static void handle_data_in_packet(struct nd_struct *nd, struct ch_struct *ch,
-				  long dlen, long plen, int n1, u8 *dbuf)
-{
-	char *error;
-	long n;
-	long remain;
-	u8 *buf;
-	u8 *b;
-
-	remain = nd->nd_remain;
-	nd->nd_tx_work = 1;
-
-	/*
-	 *  Otherwise data should appear only when we are
-	 *  in the CS_READY state.
-	 */
-
-	if (ch->ch_state < CS_READY) {
-		error = "Data received before RWIN established";
-		nd->nd_remain = 0;
-		nd->nd_state = NS_SEND_ERROR;
-		nd->nd_error = error;
-	}
-
-	/*
-	 *  Assure that the data received is within the
-	 *  allowable window.
-	 */
-
-	n = (ch->ch_s_rwin - ch->ch_s_rin) & 0xffff;
-
-	if (dlen > n) {
-		error = "Receive data overrun";
-		nd->nd_remain = 0;
-		nd->nd_state = NS_SEND_ERROR;
-		nd->nd_error = error;
-	}
-
-	/*
-	 *  If we received 3 or less characters,
-	 *  assume it is a human typing, and set RTIME
-	 *  to 10 milliseconds.
-	 *
-	 *  If we receive 10 or more characters,
-	 *  assume its not a human typing, and set RTIME
-	 *  to 100 milliseconds.
-	 */
-
-	if (ch->ch_edelay != DGRP_RTIME) {
-		if (ch->ch_rtime != ch->ch_edelay) {
-			ch->ch_rtime = ch->ch_edelay;
-			ch->ch_flag |= CH_PARAM;
-		}
-	} else if (dlen <= 3) {
-		if (ch->ch_rtime != 10) {
-			ch->ch_rtime = 10;
-			ch->ch_flag |= CH_PARAM;
-		}
-	} else {
-		if (ch->ch_rtime != DGRP_RTIME) {
-			ch->ch_rtime = DGRP_RTIME;
-			ch->ch_flag |= CH_PARAM;
-		}
-	}
-
-	/*
-	 *  If a portion of the packet is outside the
-	 *  buffer, shorten the effective length of the
-	 *  data packet to be the amount of data received.
-	 */
-
-	if (remain < plen)
-		dlen -= plen - remain;
-
-	/*
-	 *  Detect if receive flush is now complete.
-	 */
-
-	if ((ch->ch_flag & CH_RX_FLUSH) != 0 &&
-			((ch->ch_flush_seq - nd->nd_seq_out) & SEQ_MASK) >=
-			((nd->nd_seq_in    - nd->nd_seq_out) & SEQ_MASK)) {
-		ch->ch_flag &= ~CH_RX_FLUSH;
-	}
-
-	/*
-	 *  If we are ready to receive, move the data into
-	 *  the receive buffer.
-	 */
-
-	ch->ch_s_rin = (ch->ch_s_rin + dlen) & 0xffff;
-
-	if (ch->ch_state == CS_READY &&
-			(ch->ch_tun.un_open_count != 0) &&
-			(ch->ch_tun.un_flag & UN_CLOSING) == 0 &&
-			(ch->ch_cflag & CF_CREAD) != 0 &&
-			(ch->ch_flag & (CH_BAUD0 | CH_RX_FLUSH)) == 0 &&
-			(ch->ch_send & RR_RX_FLUSH) == 0) {
-
-		if (ch->ch_rin + dlen >= RBUF_MAX) {
-			n = RBUF_MAX - ch->ch_rin;
-
-			memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, n);
-
-			ch->ch_rin = 0;
-			dbuf += n;
-			dlen -= n;
-		}
-
-		memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, dlen);
-
-		ch->ch_rin += dlen;
-
-
-		/*
-		 *  If we are not in fastcook mode, or
-		 *  if there is a fastcook thread
-		 *  waiting for data, send the data to
-		 *  the line discipline.
-		 */
-
-		if ((ch->ch_flag & CH_FAST_READ) == 0 ||
-				ch->ch_inwait != 0) {
-			dgrp_input(ch);
-		}
-
-		/*
-		 *  If there is a read thread waiting
-		 *  in select, and we are in fastcook
-		 *  mode, wake him up.
-		 */
-
-		if (waitqueue_active(&ch->ch_tun.un_tty->read_wait) &&
-				(ch->ch_flag & CH_FAST_READ) != 0)
-			wake_up_interruptible(&ch->ch_tun.un_tty->read_wait);
-
-		/*
-		 * Wake any thread waiting in the
-		 * fastcook loop.
-		 */
-
-		if ((ch->ch_flag & CH_INPUT) != 0) {
-			ch->ch_flag &= ~CH_INPUT;
-			wake_up_interruptible(&ch->ch_flag_wait);
-		}
-	}
-
-	/*
-	 *  Fabricate and insert a data packet header to
-	 *  preced the remaining data when it comes in.
-	 */
-
-	if (remain < plen) {
-		dlen = plen - remain;
-		b = buf;
-
-		b[0] = 0x90 + n1;
-		put_unaligned_be16(dlen, b + 1);
-
-		remain = 3;
-		if (remain > 0 && b != buf)
-			memcpy(buf, b, remain);
-
-		nd->nd_remain = remain;
-		return;
-	}
-}
-
 /**
  * dgrp_receive() -- decode data packets received from the remote PortServer.
  * @nd: pointer to a node structure
@@ -2477,8 +2306,7 @@
 			plen = dlen + 1;
 
 			dbuf = b + 1;
-			handle_data_in_packet(nd, ch, dlen, plen, n1, dbuf);
-			break;
+			goto data;
 
 		/*
 		 *  Process 2-byte header data packet.
@@ -2492,8 +2320,7 @@
 			plen = dlen + 2;
 
 			dbuf = b + 2;
-			handle_data_in_packet(nd, ch, dlen, plen, n1, dbuf);
-			break;
+			goto data;
 
 		/*
 		 *  Process 3-byte header data packet.
@@ -2508,6 +2335,159 @@
 
 			dbuf = b + 3;
 
+		/*
+		 *  Common packet handling code.
+		 */
+
+data:
+			nd->nd_tx_work = 1;
+
+			/*
+			 *  Otherwise data should appear only when we are
+			 *  in the CS_READY state.
+			 */
+
+			if (ch->ch_state < CS_READY) {
+				error = "Data received before RWIN established";
+				goto prot_error;
+			}
+
+			/*
+			 *  Assure that the data received is within the
+			 *  allowable window.
+			 */
+
+			n = (ch->ch_s_rwin - ch->ch_s_rin) & 0xffff;
+
+			if (dlen > n) {
+				error = "Receive data overrun";
+				goto prot_error;
+			}
+
+			/*
+			 *  If we received 3 or less characters,
+			 *  assume it is a human typing, and set RTIME
+			 *  to 10 milliseconds.
+			 *
+			 *  If we receive 10 or more characters,
+			 *  assume its not a human typing, and set RTIME
+			 *  to 100 milliseconds.
+			 */
+
+			if (ch->ch_edelay != DGRP_RTIME) {
+				if (ch->ch_rtime != ch->ch_edelay) {
+					ch->ch_rtime = ch->ch_edelay;
+					ch->ch_flag |= CH_PARAM;
+				}
+			} else if (dlen <= 3) {
+				if (ch->ch_rtime != 10) {
+					ch->ch_rtime = 10;
+					ch->ch_flag |= CH_PARAM;
+				}
+			} else {
+				if (ch->ch_rtime != DGRP_RTIME) {
+					ch->ch_rtime = DGRP_RTIME;
+					ch->ch_flag |= CH_PARAM;
+				}
+			}
+
+			/*
+			 *  If a portion of the packet is outside the
+			 *  buffer, shorten the effective length of the
+			 *  data packet to be the amount of data received.
+			 */
+
+			if (remain < plen)
+				dlen -= plen - remain;
+
+			/*
+			 *  Detect if receive flush is now complete.
+			 */
+
+			if ((ch->ch_flag & CH_RX_FLUSH) != 0 &&
+			    ((ch->ch_flush_seq - nd->nd_seq_out) & SEQ_MASK) >=
+			    ((nd->nd_seq_in    - nd->nd_seq_out) & SEQ_MASK)) {
+				ch->ch_flag &= ~CH_RX_FLUSH;
+			}
+
+			/*
+			 *  If we are ready to receive, move the data into
+			 *  the receive buffer.
+			 */
+
+			ch->ch_s_rin = (ch->ch_s_rin + dlen) & 0xffff;
+
+			if (ch->ch_state == CS_READY &&
+			    (ch->ch_tun.un_open_count != 0) &&
+			    (ch->ch_tun.un_flag & UN_CLOSING) == 0 &&
+			    (ch->ch_cflag & CF_CREAD) != 0 &&
+			    (ch->ch_flag & (CH_BAUD0 | CH_RX_FLUSH)) == 0 &&
+			    (ch->ch_send & RR_RX_FLUSH) == 0) {
+
+				if (ch->ch_rin + dlen >= RBUF_MAX) {
+					n = RBUF_MAX - ch->ch_rin;
+
+					memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, n);
+
+					ch->ch_rin = 0;
+					dbuf += n;
+					dlen -= n;
+				}
+
+				memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, dlen);
+
+				ch->ch_rin += dlen;
+
+
+				/*
+				 *  If we are not in fastcook mode, or
+				 *  if there is a fastcook thread
+				 *  waiting for data, send the data to
+				 *  the line discipline.
+				 */
+
+				if ((ch->ch_flag & CH_FAST_READ) == 0 ||
+				    ch->ch_inwait != 0) {
+					dgrp_input(ch);
+				}
+
+				/*
+				 *  If there is a read thread waiting
+				 *  in select, and we are in fastcook
+				 *  mode, wake him up.
+				 */
+
+				if (waitqueue_active(&ch->ch_tun.un_tty->read_wait) &&
+				    (ch->ch_flag & CH_FAST_READ) != 0)
+					wake_up_interruptible(&ch->ch_tun.un_tty->read_wait);
+
+				/*
+				 * Wake any thread waiting in the
+				 * fastcook loop.
+				 */
+
+				if ((ch->ch_flag & CH_INPUT) != 0) {
+					ch->ch_flag &= ~CH_INPUT;
+
+					wake_up_interruptible(&ch->ch_flag_wait);
+				}
+			}
+
+			/*
+			 *  Fabricate and insert a data packet header to
+			 *  preced the remaining data when it comes in.
+			 */
+
+			if (remain < plen) {
+				dlen = plen - remain;
+				b = buf;
+
+				b[0] = 0x90 + n1;
+				put_unaligned_be16(dlen, b + 1);
+
+				remain = 3;
+				goto done;
+			}
 			break;
 
 		/*
diff --git a/drivers/staging/fwserial/fwserial.c b/drivers/staging/fwserial/fwserial.c
index 8af136e..b22142e 100644
--- a/drivers/staging/fwserial/fwserial.c
+++ b/drivers/staging/fwserial/fwserial.c
@@ -2036,6 +2036,13 @@
 		schedule_delayed_work(&peer->connect, CONNECT_RETRY_DELAY);
 }
 
+static void fwserial_peer_workfn(struct work_struct *work)
+{
+	struct fwtty_peer *peer = to_peer(work, work);
+
+	peer->workfn(work);
+}
+
 /**
  * fwserial_add_peer - add a newly probed 'serial' unit device as a 'peer'
  * @serial: aggregate representing the specific fw_card to add the peer to
@@ -2100,7 +2107,7 @@
 	peer->port = NULL;
 
 	init_timer(&peer->timer);
-	INIT_WORK(&peer->work, NULL);
+	INIT_WORK(&peer->work, fwserial_peer_workfn);
 	INIT_DELAYED_WORK(&peer->connect, fwserial_auto_connect);
 
 	/* associate peer with specific fw_card */
@@ -2702,7 +2709,7 @@
 
 		} else {
 			peer->work_params.plug_req = pkt->plug_req;
-			PREPARE_WORK(&peer->work, fwserial_handle_plug_req);
+			peer->workfn = fwserial_handle_plug_req;
 			queue_work(system_unbound_wq, &peer->work);
 		}
 		break;
@@ -2731,7 +2738,7 @@
 			fwtty_err(&peer->unit, "unplug req: busy\n");
 			rcode = RCODE_CONFLICT_ERROR;
 		} else {
-			PREPARE_WORK(&peer->work, fwserial_handle_unplug_req);
+			peer->workfn = fwserial_handle_unplug_req;
 			queue_work(system_unbound_wq, &peer->work);
 		}
 		break;
diff --git a/drivers/staging/fwserial/fwserial.h b/drivers/staging/fwserial/fwserial.h
index 54f7f9b..98b853d 100644
--- a/drivers/staging/fwserial/fwserial.h
+++ b/drivers/staging/fwserial/fwserial.h
@@ -91,6 +91,7 @@
 	struct rcu_head		rcu;
 
 	spinlock_t		lock;
+	work_func_t		workfn;
 	struct work_struct	work;
 	struct peer_work_params work_params;
 	struct timer_list	timer;
diff --git a/drivers/staging/gdm72xx/gdm_usb.c b/drivers/staging/gdm72xx/gdm_usb.c
index f8788bf..cdeffe7 100644
--- a/drivers/staging/gdm72xx/gdm_usb.c
+++ b/drivers/staging/gdm72xx/gdm_usb.c
@@ -635,11 +635,14 @@
 #endif /* CONFIG_WIMAX_GDM72XX_USB_PM */
 
 	ret = register_wimax_device(phy_dev, &intf->dev);
+	if (ret)
+		release_usb(udev);
 
 out:
 	if (ret) {
 		kfree(phy_dev);
 		kfree(udev);
+		usb_put_dev(usbdev);
 	} else {
 		usb_set_intfdata(intf, phy_dev);
 	}
diff --git a/drivers/staging/iio/Documentation/iio_utils.h b/drivers/staging/iio/Documentation/iio_utils.h
index 35154d6..c9fedb7 100644
--- a/drivers/staging/iio/Documentation/iio_utils.h
+++ b/drivers/staging/iio/Documentation/iio_utils.h
@@ -77,7 +77,6 @@
 	uint64_t mask;
 	unsigned be;
 	unsigned is_signed;
-	unsigned enabled;
 	unsigned location;
 };
 
@@ -335,6 +334,7 @@
 	while (ent = readdir(dp), ent != NULL) {
 		if (strcmp(ent->d_name + strlen(ent->d_name) - strlen("_en"),
 			   "_en") == 0) {
+			int current_enabled = 0;
 			current = &(*ci_array)[count++];
 			ret = asprintf(&filename,
 				       "%s/%s", scan_el_dir, ent->d_name);
@@ -350,10 +350,10 @@
 				ret = -errno;
 				goto error_cleanup_array;
 			}
-			fscanf(sysfsfp, "%u", &current->enabled);
+			fscanf(sysfsfp, "%u", &current_enabled);
 			fclose(sysfsfp);
 
-			if (!current->enabled) {
+			if (!current_enabled) {
 				free(filename);
 				count--;
 				continue;
diff --git a/drivers/staging/iio/adc/ad799x_core.c b/drivers/staging/iio/adc/ad799x_core.c
index 5ea3641..5708ffc 100644
--- a/drivers/staging/iio/adc/ad799x_core.c
+++ b/drivers/staging/iio/adc/ad799x_core.c
@@ -393,7 +393,7 @@
 	}, {
 		.type = IIO_EV_TYPE_THRESH,
 		.dir = IIO_EV_DIR_FALLING,
-		.mask_separate = BIT(IIO_EV_INFO_VALUE),
+		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
 			BIT(IIO_EV_INFO_ENABLE),
 	}, {
 		.type = IIO_EV_TYPE_THRESH,
@@ -409,7 +409,13 @@
 	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \
 	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \
 	.scan_index = (_index), \
-	.scan_type = IIO_ST('u', _realbits, 16, 12 - (_realbits)), \
+	.scan_type = { \
+		.sign = 'u', \
+		.realbits = (_realbits), \
+		.storagebits = 16, \
+		.shift = 12 - (_realbits), \
+		.endianness = IIO_BE, \
+	}, \
 	.event_spec = _ev_spec, \
 	.num_event_specs = _num_ev_spec, \
 }
@@ -588,7 +594,8 @@
 	return 0;
 
 error_free_irq:
-	free_irq(client->irq, indio_dev);
+	if (client->irq > 0)
+		free_irq(client->irq, indio_dev);
 error_cleanup_ring:
 	ad799x_ring_cleanup(indio_dev);
 error_disable_reg:
diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c
index df71669..514844e 100644
--- a/drivers/staging/iio/adc/mxs-lradc.c
+++ b/drivers/staging/iio/adc/mxs-lradc.c
@@ -757,6 +757,7 @@
 	}
 
 	/* if it is released, wait for the next touch via IRQ */
+	lradc->cur_plate = LRADC_TOUCH;
 	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ, LRADC_CTRL1);
 	mxs_lradc_reg_set(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, LRADC_CTRL1);
 }
@@ -1035,8 +1036,6 @@
 SHOW_SCALE_AVAILABLE_ATTR(5);
 SHOW_SCALE_AVAILABLE_ATTR(6);
 SHOW_SCALE_AVAILABLE_ATTR(7);
-SHOW_SCALE_AVAILABLE_ATTR(8);
-SHOW_SCALE_AVAILABLE_ATTR(9);
 SHOW_SCALE_AVAILABLE_ATTR(10);
 SHOW_SCALE_AVAILABLE_ATTR(11);
 SHOW_SCALE_AVAILABLE_ATTR(12);
@@ -1053,8 +1052,6 @@
 	&iio_dev_attr_in_voltage5_scale_available.dev_attr.attr,
 	&iio_dev_attr_in_voltage6_scale_available.dev_attr.attr,
 	&iio_dev_attr_in_voltage7_scale_available.dev_attr.attr,
-	&iio_dev_attr_in_voltage8_scale_available.dev_attr.attr,
-	&iio_dev_attr_in_voltage9_scale_available.dev_attr.attr,
 	&iio_dev_attr_in_voltage10_scale_available.dev_attr.attr,
 	&iio_dev_attr_in_voltage11_scale_available.dev_attr.attr,
 	&iio_dev_attr_in_voltage12_scale_available.dev_attr.attr,
@@ -1613,7 +1610,7 @@
 			 * of the array.
 			 */
 			scale_uv = ((u64)lradc->vref_mv[i] * 100000000) >>
-				   (iio->channels[i].scan_type.realbits - s);
+				   (LRADC_RESOLUTION - s);
 			lradc->scale_avail[i][s].nano =
 					do_div(scale_uv, 100000000) * 10;
 			lradc->scale_avail[i][s].integer = scale_uv;
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 0a4298b..2b96665 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -629,7 +629,7 @@
 	struct iio_buffer *buffer;
 
 	buffer = iio_kfifo_allocate(indio_dev);
-	if (buffer)
+	if (!buffer)
 		return -ENOMEM;
 
 	iio_device_attach_buffer(indio_dev, buffer);
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index 09ef5fb8..236ed66 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -88,9 +88,9 @@
 
 	imx_drm_device_put();
 
-	drm_vblank_cleanup(imxdrm->drm);
-	drm_kms_helper_poll_fini(imxdrm->drm);
-	drm_mode_config_cleanup(imxdrm->drm);
+	drm_vblank_cleanup(drm);
+	drm_kms_helper_poll_fini(drm);
+	drm_mode_config_cleanup(drm);
 
 	return 0;
 }
@@ -142,19 +142,19 @@
 
 int imx_drm_crtc_vblank_get(struct imx_drm_crtc *imx_drm_crtc)
 {
-	return drm_vblank_get(imx_drm_crtc->imxdrm->drm, imx_drm_crtc->pipe);
+	return drm_vblank_get(imx_drm_crtc->crtc->dev, imx_drm_crtc->pipe);
 }
 EXPORT_SYMBOL_GPL(imx_drm_crtc_vblank_get);
 
 void imx_drm_crtc_vblank_put(struct imx_drm_crtc *imx_drm_crtc)
 {
-	drm_vblank_put(imx_drm_crtc->imxdrm->drm, imx_drm_crtc->pipe);
+	drm_vblank_put(imx_drm_crtc->crtc->dev, imx_drm_crtc->pipe);
 }
 EXPORT_SYMBOL_GPL(imx_drm_crtc_vblank_put);
 
 void imx_drm_handle_vblank(struct imx_drm_crtc *imx_drm_crtc)
 {
-	drm_handle_vblank(imx_drm_crtc->imxdrm->drm, imx_drm_crtc->pipe);
+	drm_handle_vblank(imx_drm_crtc->crtc->dev, imx_drm_crtc->pipe);
 }
 EXPORT_SYMBOL_GPL(imx_drm_handle_vblank);
 
@@ -370,29 +370,6 @@
 }
 
 /*
- * register a crtc to the drm core
- */
-static int imx_drm_crtc_register(struct imx_drm_crtc *imx_drm_crtc)
-{
-	struct imx_drm_device *imxdrm = __imx_drm_device();
-	int ret;
-
-	ret = drm_mode_crtc_set_gamma_size(imx_drm_crtc->crtc, 256);
-	if (ret)
-		return ret;
-
-	drm_crtc_helper_add(imx_drm_crtc->crtc,
-			imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs);
-
-	drm_crtc_init(imxdrm->drm, imx_drm_crtc->crtc,
-			imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs);
-
-	drm_mode_group_reinit(imxdrm->drm);
-
-	return 0;
-}
-
-/*
  * Called by the CRTC driver when all CRTCs are registered. This
  * puts all the pieces together and initializes the driver.
  * Once this is called no more CRTCs can be registered since
@@ -424,15 +401,15 @@
 
 	mutex_lock(&imxdrm->mutex);
 
-	drm_kms_helper_poll_init(imxdrm->drm);
+	drm_kms_helper_poll_init(drm);
 
 	/* setup the grouping for the legacy output */
-	ret = drm_mode_group_init_legacy_group(imxdrm->drm,
-			&imxdrm->drm->primary->mode_group);
+	ret = drm_mode_group_init_legacy_group(drm,
+			&drm->primary->mode_group);
 	if (ret)
 		goto err_kms;
 
-	ret = drm_vblank_init(imxdrm->drm, MAX_CRTC);
+	ret = drm_vblank_init(drm, MAX_CRTC);
 	if (ret)
 		goto err_kms;
 
@@ -441,7 +418,7 @@
 	 * by drm timer once a current process gives up ownership of
 	 * vblank event.(after drm_vblank_put function is called)
 	 */
-	imxdrm->drm->vblank_disable_allowed = true;
+	drm->vblank_disable_allowed = true;
 
 	if (!imx_drm_device_get()) {
 		ret = -EINVAL;
@@ -536,10 +513,18 @@
 
 	*new_crtc = imx_drm_crtc;
 
-	ret = imx_drm_crtc_register(imx_drm_crtc);
+	ret = drm_mode_crtc_set_gamma_size(imx_drm_crtc->crtc, 256);
 	if (ret)
 		goto err_register;
 
+	drm_crtc_helper_add(crtc,
+			imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs);
+
+	drm_crtc_init(imxdrm->drm, crtc,
+			imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs);
+
+	drm_mode_group_reinit(imxdrm->drm);
+
 	imx_drm_update_possible_crtcs();
 
 	mutex_unlock(&imxdrm->mutex);
diff --git a/drivers/staging/imx-drm/imx-hdmi.c b/drivers/staging/imx-drm/imx-hdmi.c
index f3a1f5e..62ce0e8 100644
--- a/drivers/staging/imx-drm/imx-hdmi.c
+++ b/drivers/staging/imx-drm/imx-hdmi.c
@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/clk.h>
+#include <linux/hdmi.h>
 #include <linux/regmap.h>
 #include <linux/mfd/syscon.h>
 #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
@@ -52,11 +53,6 @@
 	YCbCr422_12B = 0x12,
 };
 
-enum hdmi_colorimetry {
-	ITU601,
-	ITU709,
-};
-
 enum imx_hdmi_devtype {
 	IMX6Q_HDMI,
 	IMX6DL_HDMI,
@@ -489,12 +485,12 @@
 
 	if (is_color_space_conversion(hdmi)) {
 		if (hdmi->hdmi_data.enc_out_format == RGB) {
-			if (hdmi->hdmi_data.colorimetry == ITU601)
+			if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601)
 				csc_coeff = &csc_coeff_rgb_out_eitu601;
 			else
 				csc_coeff = &csc_coeff_rgb_out_eitu709;
 		} else if (hdmi->hdmi_data.enc_in_format == RGB) {
-			if (hdmi->hdmi_data.colorimetry == ITU601)
+			if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601)
 				csc_coeff = &csc_coeff_rgb_in_eitu601;
 			else
 				csc_coeff = &csc_coeff_rgb_in_eitu709;
@@ -1140,16 +1136,16 @@
 	/* Set up colorimetry */
 	if (hdmi->hdmi_data.enc_out_format == XVYCC444) {
 		colorimetry = HDMI_FC_AVICONF1_COLORIMETRY_EXTENDED_INFO;
-		if (hdmi->hdmi_data.colorimetry == ITU601)
+		if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601)
 			ext_colorimetry =
 				HDMI_FC_AVICONF2_EXT_COLORIMETRY_XVYCC601;
-		else /* hdmi->hdmi_data.colorimetry == ITU709 */
+		else /*hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_709*/
 			ext_colorimetry =
 				HDMI_FC_AVICONF2_EXT_COLORIMETRY_XVYCC709;
 	} else if (hdmi->hdmi_data.enc_out_format != RGB) {
-		if (hdmi->hdmi_data.colorimetry == ITU601)
+		if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601)
 			colorimetry = HDMI_FC_AVICONF1_COLORIMETRY_SMPTE;
-		else /* hdmi->hdmi_data.colorimetry == ITU709 */
+		else /*hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_709*/
 			colorimetry = HDMI_FC_AVICONF1_COLORIMETRY_ITUR;
 		ext_colorimetry = HDMI_FC_AVICONF2_EXT_COLORIMETRY_XVYCC601;
 	} else { /* Carries no data */
@@ -1379,9 +1375,9 @@
 		(hdmi->vic == 21) || (hdmi->vic == 22) ||
 		(hdmi->vic == 2) || (hdmi->vic == 3) ||
 		(hdmi->vic == 17) || (hdmi->vic == 18))
-		hdmi->hdmi_data.colorimetry = ITU601;
+		hdmi->hdmi_data.colorimetry = HDMI_COLORIMETRY_ITU_601;
 	else
-		hdmi->hdmi_data.colorimetry = ITU709;
+		hdmi->hdmi_data.colorimetry = HDMI_COLORIMETRY_ITU_709;
 
 	if ((hdmi->vic == 10) || (hdmi->vic == 11) ||
 		(hdmi->vic == 12) || (hdmi->vic == 13) ||
diff --git a/drivers/staging/lustre/TODO b/drivers/staging/lustre/TODO
index 22742d6..0a2b6cb 100644
--- a/drivers/staging/lustre/TODO
+++ b/drivers/staging/lustre/TODO
@@ -9,5 +9,6 @@
 * Other minor misc cleanups...
 
 Please send any patches to Greg Kroah-Hartman <greg@kroah.com>, Andreas Dilger
-<andreas.dilger@intel.com> and Peng Tao <tao.peng@emc.com>. CCing
-hpdd-discuss <hpdd-discuss@lists.01.org> would be great too.
+<andreas.dilger@intel.com>, Oleg Drokin <oleg.drokin@intel.com> and
+Peng Tao <tao.peng@emc.com>. CCing hpdd-discuss <hpdd-discuss@lists.01.org>
+would be great too.
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h
index 596a15f..037ae8a 100644
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h
+++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h
@@ -61,6 +61,8 @@
 	__u16 kuc_msglen;     /* Including header */
 } __attribute__((aligned(sizeof(__u64))));
 
+#define KUC_CHANGELOG_MSG_MAXSIZE (sizeof(struct kuc_hdr)+CR_MAXSIZE)
+
 #define KUC_MAGIC  0x191C /*Lustre9etLinC */
 #define KUC_FL_BLOCK 0x01   /* Wait for send */
 
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h
index d0d942c..dddccca1 100644
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h
+++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h
@@ -120,7 +120,7 @@
 do {									    \
 	LASSERT(!in_interrupt() ||					    \
 		((size) <= LIBCFS_VMALLOC_SIZE &&			    \
-		 ((mask) & GFP_ATOMIC)) != 0);			    \
+		 ((mask) & __GFP_WAIT) == 0));				    \
 } while (0)
 
 #define LIBCFS_ALLOC_POST(ptr, size)					    \
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
index 9364863..6f58ead 100644
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
@@ -529,7 +529,7 @@
 {
 	struct page *page;
 
-	if (is_vmalloc_addr(vaddr)) {
+	if (is_vmalloc_addr((void *)vaddr)) {
 		page = vmalloc_to_page ((void *)vaddr);
 		LASSERT (page != NULL);
 		return page;
diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
index 68a4f52..b7b53b5 100644
--- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
@@ -924,7 +924,7 @@
 int
 ksocknal_send(lnet_ni_t *ni, void *private, lnet_msg_t *lntmsg)
 {
-	int	       mpflag = 0;
+	int	       mpflag = 1;
 	int	       type = lntmsg->msg_type;
 	lnet_process_id_t target = lntmsg->msg_target;
 	unsigned int      payload_niov = lntmsg->msg_niov;
@@ -993,8 +993,9 @@
 
 	/* The first fragment will be set later in pro_pack */
 	rc = ksocknal_launch_packet(ni, tx, target);
-	if (lntmsg->msg_vmflush)
+	if (!mpflag)
 		cfs_memory_pressure_restore(mpflag);
+
 	if (rc == 0)
 		return (0);
 
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
index 6b6c0240..7893d83 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
@@ -760,7 +760,8 @@
 	*flags |= (error << CLF_HSM_ERR_L);
 }
 
-#define CR_MAXSIZE cfs_size_round(2*NAME_MAX + 1 + sizeof(struct changelog_rec))
+#define CR_MAXSIZE cfs_size_round(2*NAME_MAX + 1 + \
+				  sizeof(struct changelog_ext_rec))
 
 struct changelog_rec {
 	__u16		 cr_namelen;
diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 22d0acc9..52b7731 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -1086,7 +1086,7 @@
 		break;
 	case Q_GETQUOTA:
 		if (((type == USRQUOTA &&
-		      uid_eq(current_euid(), make_kuid(&init_user_ns, id))) ||
+		      !uid_eq(current_euid(), make_kuid(&init_user_ns, id))) ||
 		     (type == GRPQUOTA &&
 		      !in_egroup_p(make_kgid(&init_user_ns, id)))) &&
 		    (!cfs_capable(CFS_CAP_SYS_ADMIN) ||
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c
index d1ad91c3..8301392 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_request.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -1430,7 +1430,7 @@
 {
 	struct kuc_hdr *lh = (struct kuc_hdr *)buf;
 
-	LASSERT(len <= CR_MAXSIZE);
+	LASSERT(len <= KUC_CHANGELOG_MSG_MAXSIZE);
 
 	lh->kuc_magic = KUC_MAGIC;
 	lh->kuc_transport = KUC_TRANSPORT_CHANGELOG;
@@ -1503,7 +1503,7 @@
 	CDEBUG(D_CHANGELOG, "changelog to fp=%p start "LPU64"\n",
 	       cs->cs_fp, cs->cs_startrec);
 
-	OBD_ALLOC(cs->cs_buf, CR_MAXSIZE);
+	OBD_ALLOC(cs->cs_buf, KUC_CHANGELOG_MSG_MAXSIZE);
 	if (cs->cs_buf == NULL)
 		GOTO(out, rc = -ENOMEM);
 
@@ -1540,7 +1540,7 @@
 	if (ctxt)
 		llog_ctxt_put(ctxt);
 	if (cs->cs_buf)
-		OBD_FREE(cs->cs_buf, CR_MAXSIZE);
+		OBD_FREE(cs->cs_buf, KUC_CHANGELOG_MSG_MAXSIZE);
 	OBD_FREE_PTR(cs);
 	return rc;
 }
diff --git a/drivers/staging/media/go7007/go7007-loader.c b/drivers/staging/media/go7007/go7007-loader.c
index 10bb41c..eecb1f2 100644
--- a/drivers/staging/media/go7007/go7007-loader.c
+++ b/drivers/staging/media/go7007/go7007-loader.c
@@ -59,7 +59,7 @@
 
 	if (usbdev->descriptor.bNumConfigurations != 1) {
 		dev_err(&interface->dev, "can't handle multiple config\n");
-		return -ENODEV;
+		goto failed2;
 	}
 
 	vendor = le16_to_cpu(usbdev->descriptor.idVendor);
@@ -108,6 +108,7 @@
 	return 0;
 
 failed2:
+	usb_put_dev(usbdev);
 	dev_err(&interface->dev, "probe failed\n");
 	return -ENODEV;
 }
@@ -115,6 +116,7 @@
 static void go7007_loader_disconnect(struct usb_interface *interface)
 {
 	dev_info(&interface->dev, "disconnect\n");
+	usb_put_dev(interface_to_usbdev(interface));
 	usb_set_intfdata(interface, NULL);
 }
 
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index eedffed..31b269a 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -307,7 +307,7 @@
 }
 
 static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
-				void *accel_priv)
+				void *accel_priv, select_queue_fallback_t fallback)
 {
 	return (u16)smp_processor_id();
 }
@@ -892,6 +892,11 @@
 	priv->mii_bus->write = xlr_mii_write;
 	priv->mii_bus->parent = &pdev->dev;
 	priv->mii_bus->irq = kmalloc(sizeof(int)*PHY_MAX_ADDR, GFP_KERNEL);
+	if (priv->mii_bus->irq == NULL) {
+		pr_err("irq alloc failed\n");
+		mdiobus_free(priv->mii_bus);
+		return -ENOMEM;
+	}
 	priv->mii_bus->irq[priv->phy_addr] = priv->ndev->irq;
 
 	/* Scan only the enabled address */
diff --git a/drivers/staging/octeon-usb/octeon-hcd.c b/drivers/staging/octeon-usb/octeon-hcd.c
index 47e0a91..5a001d9 100644
--- a/drivers/staging/octeon-usb/octeon-hcd.c
+++ b/drivers/staging/octeon-usb/octeon-hcd.c
@@ -275,13 +275,6 @@
  */
 #define MAX_TRANSFER_PACKETS	((1<<10)-1)
 
-enum {
-	USB_CLOCK_TYPE_REF_12,
-	USB_CLOCK_TYPE_REF_24,
-	USB_CLOCK_TYPE_REF_48,
-	USB_CLOCK_TYPE_CRYSTAL_12,
-};
-
 /**
  * Logical transactions may take numerous low level
  * transactions, especially when splits are concerned. This
@@ -471,19 +464,6 @@
 /* Returns the IO address to push/pop stuff data from the FIFOs */
 #define USB_FIFO_ADDRESS(channel, usb_index) (CVMX_USBCX_GOTGCTL(usb_index) + ((channel)+1)*0x1000)
 
-static int octeon_usb_get_clock_type(void)
-{
-	switch (cvmx_sysinfo_get()->board_type) {
-	case CVMX_BOARD_TYPE_BBGW_REF:
-	case CVMX_BOARD_TYPE_LANAI2_A:
-	case CVMX_BOARD_TYPE_LANAI2_U:
-	case CVMX_BOARD_TYPE_LANAI2_G:
-	case CVMX_BOARD_TYPE_UBNT_E100:
-		return USB_CLOCK_TYPE_CRYSTAL_12;
-	}
-	return USB_CLOCK_TYPE_REF_48;
-}
-
 /**
  * Read a USB 32bit CSR. It performs the necessary address swizzle
  * for 32bit CSRs and logs the value in a readable format if
@@ -582,37 +562,6 @@
 		return 0; /* Data0 */
 }
 
-
-/**
- * Return the number of USB ports supported by this Octeon
- * chip. If the chip doesn't support USB, or is not supported
- * by this API, a zero will be returned. Most Octeon chips
- * support one usb port, but some support two ports.
- * cvmx_usb_initialize() must be called on independent
- * struct cvmx_usb_state.
- *
- * Returns: Number of port, zero if usb isn't supported
- */
-static int cvmx_usb_get_num_ports(void)
-{
-	int arch_ports = 0;
-
-	if (OCTEON_IS_MODEL(OCTEON_CN56XX))
-		arch_ports = 1;
-	else if (OCTEON_IS_MODEL(OCTEON_CN52XX))
-		arch_ports = 2;
-	else if (OCTEON_IS_MODEL(OCTEON_CN50XX))
-		arch_ports = 1;
-	else if (OCTEON_IS_MODEL(OCTEON_CN31XX))
-		arch_ports = 1;
-	else if (OCTEON_IS_MODEL(OCTEON_CN30XX))
-		arch_ports = 1;
-	else
-		arch_ports = 0;
-
-	return arch_ports;
-}
-
 /**
  * Initialize a USB port for use. This must be called before any
  * other access to the Octeon USB port is made. The port starts
@@ -628,41 +577,16 @@
  * Returns: 0 or a negative error code.
  */
 static int cvmx_usb_initialize(struct cvmx_usb_state *usb,
-			       int usb_port_number)
+			       int usb_port_number,
+			       enum cvmx_usb_initialize_flags flags)
 {
 	union cvmx_usbnx_clk_ctl usbn_clk_ctl;
 	union cvmx_usbnx_usbp_ctl_status usbn_usbp_ctl_status;
-	enum cvmx_usb_initialize_flags flags = 0;
 	int i;
 
 	/* At first allow 0-1 for the usb port number */
 	if ((usb_port_number < 0) || (usb_port_number > 1))
 		return -EINVAL;
-	/* For all chips except 52XX there is only one port */
-	if (!OCTEON_IS_MODEL(OCTEON_CN52XX) && (usb_port_number > 0))
-		return -EINVAL;
-	/* Try to determine clock type automatically */
-	if (octeon_usb_get_clock_type() == USB_CLOCK_TYPE_CRYSTAL_12) {
-		/* Only 12 MHZ crystals are supported */
-		flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_XI;
-	} else {
-		flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_GND;
-
-		switch (octeon_usb_get_clock_type()) {
-		case USB_CLOCK_TYPE_REF_12:
-			flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_12MHZ;
-			break;
-		case USB_CLOCK_TYPE_REF_24:
-			flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_24MHZ;
-			break;
-		case USB_CLOCK_TYPE_REF_48:
-			flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_48MHZ;
-			break;
-		default:
-			return -EINVAL;
-			break;
-		}
-	}
 
 	memset(usb, 0, sizeof(*usb));
 	usb->init_flags = flags;
@@ -3431,7 +3355,6 @@
 	return 0;
 }
 
-
 static const struct hc_driver octeon_hc_driver = {
 	.description		= "Octeon USB",
 	.product_desc		= "Octeon Host Controller",
@@ -3448,15 +3371,74 @@
 	.hub_control		= octeon_usb_hub_control,
 };
 
-
-static int octeon_usb_driver_probe(struct device *dev)
+static int octeon_usb_probe(struct platform_device *pdev)
 {
 	int status;
-	int usb_num = to_platform_device(dev)->id;
-	int irq = platform_get_irq(to_platform_device(dev), 0);
+	int initialize_flags;
+	int usb_num;
+	struct resource *res_mem;
+	struct device_node *usbn_node;
+	int irq = platform_get_irq(pdev, 0);
+	struct device *dev = &pdev->dev;
 	struct octeon_hcd *priv;
 	struct usb_hcd *hcd;
 	unsigned long flags;
+	u32 clock_rate = 48000000;
+	bool is_crystal_clock = false;
+	const char *clock_type;
+	int i;
+
+	if (dev->of_node == NULL) {
+		dev_err(dev, "Error: empty of_node\n");
+		return -ENXIO;
+	}
+	usbn_node = dev->of_node->parent;
+
+	i = of_property_read_u32(usbn_node,
+				 "refclk-frequency", &clock_rate);
+	if (i) {
+		dev_err(dev, "No USBN \"refclk-frequency\"\n");
+		return -ENXIO;
+	}
+	switch (clock_rate) {
+	case 12000000:
+		initialize_flags = CVMX_USB_INITIALIZE_FLAGS_CLOCK_12MHZ;
+		break;
+	case 24000000:
+		initialize_flags = CVMX_USB_INITIALIZE_FLAGS_CLOCK_24MHZ;
+		break;
+	case 48000000:
+		initialize_flags = CVMX_USB_INITIALIZE_FLAGS_CLOCK_48MHZ;
+		break;
+	default:
+		dev_err(dev, "Illebal USBN \"refclk-frequency\" %u\n", clock_rate);
+		return -ENXIO;
+
+	}
+
+	i = of_property_read_string(usbn_node,
+				    "refclk-type", &clock_type);
+
+	if (!i && strcmp("crystal", clock_type) == 0)
+		is_crystal_clock = true;
+
+	if (is_crystal_clock)
+		initialize_flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_XI;
+	else
+		initialize_flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_GND;
+
+	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res_mem == NULL) {
+		dev_err(dev, "found no memory resource\n");
+		return -ENXIO;
+	}
+	usb_num = (res_mem->start >> 44) & 1;
+
+	if (irq < 0) {
+		/* Defective device tree, but we know how to fix it. */
+		irq_hw_number_t hwirq = usb_num ? (1 << 6) + 17 : 56;
+		irq = irq_create_mapping(NULL, hwirq);
+	}
 
 	/*
 	 * Set the DMA mask to 64bits so we get buffers already translated for
@@ -3465,90 +3447,6 @@
 	dev->coherent_dma_mask = ~0;
 	dev->dma_mask = &dev->coherent_dma_mask;
 
-	hcd = usb_create_hcd(&octeon_hc_driver, dev, dev_name(dev));
-	if (!hcd) {
-		dev_dbg(dev, "Failed to allocate memory for HCD\n");
-		return -1;
-	}
-	hcd->uses_new_polling = 1;
-	priv = (struct octeon_hcd *)hcd->hcd_priv;
-
-	spin_lock_init(&priv->lock);
-
-	tasklet_init(&priv->dequeue_tasklet, octeon_usb_urb_dequeue_work, (unsigned long)priv);
-	INIT_LIST_HEAD(&priv->dequeue_list);
-
-	status = cvmx_usb_initialize(&priv->usb, usb_num);
-	if (status) {
-		dev_dbg(dev, "USB initialization failed with %d\n", status);
-		kfree(hcd);
-		return -1;
-	}
-
-	/* This delay is needed for CN3010, but I don't know why... */
-	mdelay(10);
-
-	spin_lock_irqsave(&priv->lock, flags);
-	cvmx_usb_poll(&priv->usb);
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	status = usb_add_hcd(hcd, irq, IRQF_SHARED);
-	if (status) {
-		dev_dbg(dev, "USB add HCD failed with %d\n", status);
-		kfree(hcd);
-		return -1;
-	}
-	device_wakeup_enable(hcd->self.controller);
-
-	dev_dbg(dev, "Registered HCD for port %d on irq %d\n", usb_num, irq);
-
-	return 0;
-}
-
-static int octeon_usb_driver_remove(struct device *dev)
-{
-	int status;
-	struct usb_hcd *hcd = dev_get_drvdata(dev);
-	struct octeon_hcd *priv = hcd_to_octeon(hcd);
-	unsigned long flags;
-
-	usb_remove_hcd(hcd);
-	tasklet_kill(&priv->dequeue_tasklet);
-	spin_lock_irqsave(&priv->lock, flags);
-	status = cvmx_usb_shutdown(&priv->usb);
-	spin_unlock_irqrestore(&priv->lock, flags);
-	if (status)
-		dev_dbg(dev, "USB shutdown failed with %d\n", status);
-
-	kfree(hcd);
-
-	return 0;
-}
-
-static struct device_driver octeon_usb_driver = {
-	.name	= "OcteonUSB",
-	.bus	= &platform_bus_type,
-	.probe	= octeon_usb_driver_probe,
-	.remove	= octeon_usb_driver_remove,
-};
-
-
-#define MAX_USB_PORTS   10
-static struct platform_device *pdev_glob[MAX_USB_PORTS];
-static int octeon_usb_registered;
-static int __init octeon_usb_module_init(void)
-{
-	int num_devices = cvmx_usb_get_num_ports();
-	int device;
-
-	if (usb_disabled() || num_devices == 0)
-		return -ENODEV;
-
-	if (driver_register(&octeon_usb_driver))
-		return -ENOMEM;
-
-	octeon_usb_registered = 1;
-
 	/*
 	 * Only cn52XX and cn56XX have DWC_OTG USB hardware and the
 	 * IOB priority registers.  Under heavy network load USB
@@ -3569,41 +3467,102 @@
 		cvmx_write_csr(CVMX_IOB_N2C_L2C_PRI_CNT, pri_cnt.u64);
 	}
 
-	for (device = 0; device < num_devices; device++) {
-		struct resource irq_resource;
-		struct platform_device *pdev;
-		memset(&irq_resource, 0, sizeof(irq_resource));
-		irq_resource.start = (device == 0) ? OCTEON_IRQ_USB0 : OCTEON_IRQ_USB1;
-		irq_resource.end = irq_resource.start;
-		irq_resource.flags = IORESOURCE_IRQ;
-		pdev = platform_device_register_simple((char *)octeon_usb_driver.  name, device, &irq_resource, 1);
-		if (IS_ERR(pdev)) {
-			driver_unregister(&octeon_usb_driver);
-			octeon_usb_registered = 0;
-			return PTR_ERR(pdev);
-		}
-		if (device < MAX_USB_PORTS)
-			pdev_glob[device] = pdev;
-
+	hcd = usb_create_hcd(&octeon_hc_driver, dev, dev_name(dev));
+	if (!hcd) {
+		dev_dbg(dev, "Failed to allocate memory for HCD\n");
+		return -1;
 	}
+	hcd->uses_new_polling = 1;
+	priv = (struct octeon_hcd *)hcd->hcd_priv;
+
+	spin_lock_init(&priv->lock);
+
+	tasklet_init(&priv->dequeue_tasklet, octeon_usb_urb_dequeue_work, (unsigned long)priv);
+	INIT_LIST_HEAD(&priv->dequeue_list);
+
+	status = cvmx_usb_initialize(&priv->usb, usb_num, initialize_flags);
+	if (status) {
+		dev_dbg(dev, "USB initialization failed with %d\n", status);
+		kfree(hcd);
+		return -1;
+	}
+
+	/* This delay is needed for CN3010, but I don't know why... */
+	mdelay(10);
+
+	spin_lock_irqsave(&priv->lock, flags);
+	cvmx_usb_poll(&priv->usb);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	status = usb_add_hcd(hcd, irq, 0);
+	if (status) {
+		dev_dbg(dev, "USB add HCD failed with %d\n", status);
+		kfree(hcd);
+		return -1;
+	}
+	device_wakeup_enable(hcd->self.controller);
+
+	dev_info(dev, "Registered HCD for port %d on irq %d\n", usb_num, irq);
+
 	return 0;
 }
 
-static void __exit octeon_usb_module_cleanup(void)
+static int octeon_usb_remove(struct platform_device *pdev)
 {
-	int i;
+	int status;
+	struct device *dev = &pdev->dev;
+	struct usb_hcd *hcd = dev_get_drvdata(dev);
+	struct octeon_hcd *priv = hcd_to_octeon(hcd);
+	unsigned long flags;
 
-	for (i = 0; i < MAX_USB_PORTS; i++)
-		if (pdev_glob[i]) {
-			platform_device_unregister(pdev_glob[i]);
-			pdev_glob[i] = NULL;
-		}
-	if (octeon_usb_registered)
-		driver_unregister(&octeon_usb_driver);
+	usb_remove_hcd(hcd);
+	tasklet_kill(&priv->dequeue_tasklet);
+	spin_lock_irqsave(&priv->lock, flags);
+	status = cvmx_usb_shutdown(&priv->usb);
+	spin_unlock_irqrestore(&priv->lock, flags);
+	if (status)
+		dev_dbg(dev, "USB shutdown failed with %d\n", status);
+
+	kfree(hcd);
+
+	return 0;
 }
 
+static struct of_device_id octeon_usb_match[] = {
+	{
+		.compatible = "cavium,octeon-5750-usbc",
+	},
+	{},
+};
+
+static struct platform_driver octeon_usb_driver = {
+	.driver = {
+		.name       = "OcteonUSB",
+		.owner		= THIS_MODULE,
+		.of_match_table = octeon_usb_match,
+	},
+	.probe      = octeon_usb_probe,
+	.remove     = octeon_usb_remove,
+};
+
+static int __init octeon_usb_driver_init(void)
+{
+	if (usb_disabled())
+		return 0;
+
+	return platform_driver_register(&octeon_usb_driver);
+}
+module_init(octeon_usb_driver_init);
+
+static void __exit octeon_usb_driver_exit(void)
+{
+	if (usb_disabled())
+		return;
+
+	platform_driver_unregister(&octeon_usb_driver);
+}
+module_exit(octeon_usb_driver_exit);
+
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Cavium Networks <support@caviumnetworks.com>");
-MODULE_DESCRIPTION("Cavium Networks Octeon USB Host driver.");
-module_init(octeon_usb_module_init);
-module_exit(octeon_usb_module_cleanup);
+MODULE_AUTHOR("Cavium, Inc. <support@cavium.com>");
+MODULE_DESCRIPTION("Cavium Inc. OCTEON USB Host driver.");
diff --git a/drivers/staging/ozwpan/ozproto.c b/drivers/staging/ozwpan/ozproto.c
index cb06036..5d965cf 100644
--- a/drivers/staging/ozwpan/ozproto.c
+++ b/drivers/staging/ozwpan/ozproto.c
@@ -668,8 +668,8 @@
 	if (binding) {
 		binding->ptype.type = __constant_htons(OZ_ETHERTYPE);
 		binding->ptype.func = oz_pkt_recv;
-		memcpy(binding->name, net_dev, OZ_MAX_BINDING_LEN);
 		if (net_dev && *net_dev) {
+			memcpy(binding->name, net_dev, OZ_MAX_BINDING_LEN);
 			oz_dbg(ON, "Adding binding: %s\n", net_dev);
 			binding->ptype.dev =
 				dev_get_by_name(&init_net, net_dev);
@@ -680,6 +680,7 @@
 			}
 		} else {
 			oz_dbg(ON, "Binding to all netcards\n");
+			memset(binding->name, 0, OZ_MAX_BINDING_LEN);
 			binding->ptype.dev = NULL;
 		}
 		if (binding) {
diff --git a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c
index 153ec61..96df62f 100644
--- a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c
+++ b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c
@@ -912,12 +912,12 @@
 	unsigned char *pbuf;
 	u32 wpa_ielen = 0;
 	u8 *pbssid = GetAddr3Ptr(pframe);
-	u32 hidden_ssid = 0;
 	struct HT_info_element *pht_info = NULL;
 	struct rtw_ieee80211_ht_cap *pht_cap = NULL;
 	u32 bcn_channel;
 	unsigned short	ht_cap_info;
 	unsigned char	ht_info_infos_0;
+	int ssid_len;
 
 	if (is_client_associated_to_ap(Adapter) == false)
 		return true;
@@ -999,21 +999,15 @@
 	}
 
 	/* checking SSID */
+	ssid_len = 0;
 	p = rtw_get_ie(bssid->IEs + _FIXED_IE_LENGTH_, _SSID_IE_, &len, bssid->IELength - _FIXED_IE_LENGTH_);
-	if (p == NULL) {
-		DBG_88E("%s marc: cannot find SSID for survey event\n", __func__);
-		hidden_ssid = true;
-	} else {
-		hidden_ssid = false;
+	if (p) {
+		ssid_len = *(p + 1);
+		if (ssid_len > NDIS_802_11_LENGTH_SSID)
+			ssid_len = 0;
 	}
-
-	if ((NULL != p) && (false == hidden_ssid && (*(p + 1)))) {
-		memcpy(bssid->Ssid.Ssid, (p + 2), *(p + 1));
-		bssid->Ssid.SsidLength = *(p + 1);
-	} else {
-		bssid->Ssid.SsidLength = 0;
-		bssid->Ssid.Ssid[0] = '\0';
-	}
+	memcpy(bssid->Ssid.Ssid, (p + 2), ssid_len);
+	bssid->Ssid.SsidLength = ssid_len;
 
 	RT_TRACE(_module_rtl871x_mlme_c_, _drv_info_, ("%s bssid.Ssid.Ssid:%s bssid.Ssid.SsidLength:%d "
 				"cur_network->network.Ssid.Ssid:%s len:%d\n", __func__, bssid->Ssid.Ssid,
diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
index dec9925..4ad80ae 100644
--- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
+++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
@@ -2500,7 +2500,7 @@
 		 ("rtw_mp_ioctl_hdl: subcode [%d], len[%d], buffer_len[%d]\r\n",
 		  poidparam->subcode, poidparam->len, len));
 
-	if (poidparam->subcode >= MAX_MP_IOCTL_SUBCODE) {
+	if (poidparam->subcode >= ARRAY_SIZE(mp_ioctl_hdl)) {
 		RT_TRACE(_module_rtl871x_ioctl_os_c, _drv_err_, ("no matching drvext subcodes\r\n"));
 		ret = -EINVAL;
 		goto _rtw_mp_ioctl_hdl_exit;
@@ -3164,9 +3164,7 @@
 	u8 *p2pie;
 	uint p2pielen = 0, attr_contentlen = 0;
 	u8 attr_content[100] = {0x00};
-
-	u8 go_devadd_str[17 + 10] = {0x00};
-	/*  +10 is for the str "go_devadd =", we have to clear it at wrqu->data.pointer */
+	u8 go_devadd_str[17 + 12] = {};
 
 	/*	Commented by Albert 20121209 */
 	/*	The input data is the GO's interface address which the application wants to know its device address. */
@@ -3223,12 +3221,12 @@
 	spin_unlock_bh(&pmlmepriv->scanned_queue.lock);
 
 	if (!blnMatch)
-		sprintf(go_devadd_str, "\n\ndev_add = NULL");
+		snprintf(go_devadd_str, sizeof(go_devadd_str), "\n\ndev_add = NULL");
 	else
-		sprintf(go_devadd_str, "\n\ndev_add =%.2X:%.2X:%.2X:%.2X:%.2X:%.2X",
+		snprintf(go_devadd_str, sizeof(go_devadd_str), "\n\ndev_add =%.2X:%.2X:%.2X:%.2X:%.2X:%.2X",
 			attr_content[0], attr_content[1], attr_content[2], attr_content[3], attr_content[4], attr_content[5]);
 
-	if (copy_to_user(wrqu->data.pointer, go_devadd_str, 10 + 17))
+	if (copy_to_user(wrqu->data.pointer, go_devadd_str, sizeof(go_devadd_str)))
 		return -EFAULT;
 	return ret;
 }
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index 68f98fa..7c9ee58 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -653,7 +653,7 @@
 }
 
 static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv)
+			    void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct adapter	*padapter = rtw_netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
index 0a341d6..2f40ff5 100644
--- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
@@ -53,8 +53,9 @@
 	{USB_DEVICE(USB_VENDER_ID_REALTEK, 0x0179)}, /* 8188ETV */
 	/*=== Customer ID ===*/
 	/****** 8188EUS ********/
-	{USB_DEVICE(0x8179, 0x07B8)}, /* Abocom - Abocom */
+	{USB_DEVICE(0x07b8, 0x8179)}, /* Abocom - Abocom */
 	{USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */
+	{USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */
 	{}	/* Terminating entry */
 };
 
diff --git a/drivers/staging/rtl8821ae/Kconfig b/drivers/staging/rtl8821ae/Kconfig
index 2aa5dac2..abccc9d 100644
--- a/drivers/staging/rtl8821ae/Kconfig
+++ b/drivers/staging/rtl8821ae/Kconfig
@@ -1,6 +1,6 @@
 config R8821AE
 	tristate "RealTek RTL8821AE Wireless LAN NIC driver"
-	depends on PCI && WLAN
+	depends on PCI && WLAN && MAC80211
 	depends on m
 	select WIRELESS_EXT
 	select WEXT_PRIV
diff --git a/drivers/staging/rtl8821ae/wifi.h b/drivers/staging/rtl8821ae/wifi.h
index cfe88a1..76bef93 100644
--- a/drivers/staging/rtl8821ae/wifi.h
+++ b/drivers/staging/rtl8821ae/wifi.h
@@ -1414,7 +1414,7 @@
 
 
 	/*88e tx power tracking*/
-	u8 bb_swing_idx_ofdm[2];
+	u8 bb_swing_idx_ofdm[MAX_RF_PATH];
 	u8 bb_swing_idx_ofdm_current;
 	u8 bb_swing_idx_ofdm_base[MAX_RF_PATH];
 	bool bb_swing_flag_Ofdm;
diff --git a/drivers/staging/usbip/userspace/libsrc/names.c b/drivers/staging/usbip/userspace/libsrc/names.c
index 3c8d28b..81ff852 100644
--- a/drivers/staging/usbip/userspace/libsrc/names.c
+++ b/drivers/staging/usbip/userspace/libsrc/names.c
@@ -169,15 +169,15 @@
 	struct pool *p;
 
 	p = calloc(1, sizeof(struct pool));
-	if (!p) {
+	if (!p)
+		return NULL;
+
+	p->mem = calloc(1, size);
+	if (!p->mem) {
 		free(p);
 		return NULL;
 	}
 
-	p->mem = calloc(1, size);
-	if (!p->mem)
-		return NULL;
-
 	p->next = pool_head;
 	pool_head = p;
 
diff --git a/drivers/staging/usbip/vhci_sysfs.c b/drivers/staging/usbip/vhci_sysfs.c
index 9b51586..0141bc3 100644
--- a/drivers/staging/usbip/vhci_sysfs.c
+++ b/drivers/staging/usbip/vhci_sysfs.c
@@ -149,7 +149,8 @@
 	case USB_SPEED_WIRELESS:
 		break;
 	default:
-		pr_err("speed %d\n", speed);
+		pr_err("Failed attach request for unsupported USB speed: %s\n",
+			usb_speed_string(speed));
 		return -EINVAL;
 	}
 
diff --git a/drivers/staging/wlags49_h2/wl_wext.c b/drivers/staging/wlags49_h2/wl_wext.c
index 4a1ddaf..187fc06 100644
--- a/drivers/staging/wlags49_h2/wl_wext.c
+++ b/drivers/staging/wlags49_h2/wl_wext.c
@@ -1061,7 +1061,7 @@
 		goto out;
 	}
 
-	if (data->flags != 0 && data->length > HCF_MAX_NAME_LEN + 1) {
+	if (data->flags != 0 && data->length > HCF_MAX_NAME_LEN) {
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 7f1a7ce..b83ec37 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -785,7 +785,7 @@
 	spin_unlock_bh(&conn->cmd_lock);
 
 	list_for_each_entry_safe(cmd, cmd_p, &ack_list, i_conn_node) {
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		iscsit_free_cmd(cmd, false);
 	}
 }
@@ -3708,7 +3708,7 @@
 		break;
 	case ISTATE_REMOVE:
 		spin_lock_bh(&conn->cmd_lock);
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		iscsit_free_cmd(cmd, false);
@@ -4151,7 +4151,7 @@
 	spin_lock_bh(&conn->cmd_lock);
 	list_for_each_entry_safe(cmd, cmd_tmp, &conn->conn_cmd_list, i_conn_node) {
 
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		iscsit_increment_maxcmdsn(cmd, sess);
@@ -4196,6 +4196,10 @@
 	iscsit_stop_timers_for_cmds(conn);
 	iscsit_stop_nopin_response_timer(conn);
 	iscsit_stop_nopin_timer(conn);
+
+	if (conn->conn_transport->iscsit_wait_conn)
+		conn->conn_transport->iscsit_wait_conn(conn);
+
 	iscsit_free_queue_reqs_for_conn(conn);
 
 	/*
diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c
index e048d64..cda4d80 100644
--- a/drivers/target/iscsi/iscsi_target_erl1.c
+++ b/drivers/target/iscsi/iscsi_target_erl1.c
@@ -507,7 +507,9 @@
 	u32 last_statsn;
 	int found_cmd;
 
-	if (conn->exp_statsn > begrun) {
+	if (!begrun) {
+		begrun = conn->exp_statsn;
+	} else if (conn->exp_statsn > begrun) {
 		pr_err("Got Status SNACK Begrun: 0x%08x, RunLength:"
 			" 0x%08x but already got ExpStatSN: 0x%08x on CID:"
 			" %hu.\n", begrun, runlength, conn->exp_statsn,
diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c
index 33be1fb..4ca8fd2 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.c
+++ b/drivers/target/iscsi/iscsi_target_erl2.c
@@ -138,7 +138,7 @@
 		list_for_each_entry_safe(cmd, cmd_tmp,
 				&cr->conn_recovery_cmd_list, i_conn_node) {
 
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			cmd->conn = NULL;
 			spin_unlock(&cr->conn_recovery_cmd_lock);
 			iscsit_free_cmd(cmd, true);
@@ -160,7 +160,7 @@
 		list_for_each_entry_safe(cmd, cmd_tmp,
 				&cr->conn_recovery_cmd_list, i_conn_node) {
 
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			cmd->conn = NULL;
 			spin_unlock(&cr->conn_recovery_cmd_lock);
 			iscsit_free_cmd(cmd, true);
@@ -216,7 +216,7 @@
 	}
 	cr = cmd->cr;
 
-	list_del(&cmd->i_conn_node);
+	list_del_init(&cmd->i_conn_node);
 	return --cr->cmd_count;
 }
 
@@ -297,7 +297,7 @@
 		if (!(cmd->cmd_flags & ICF_OOO_CMDSN))
 			continue;
 
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 
 		spin_unlock_bh(&conn->cmd_lock);
 		iscsit_free_cmd(cmd, true);
@@ -335,7 +335,7 @@
 	/*
 	 * Only perform connection recovery on ISCSI_OP_SCSI_CMD or
 	 * ISCSI_OP_NOOP_OUT opcodes.  For all other opcodes call
-	 * list_del(&cmd->i_conn_node); to release the command to the
+	 * list_del_init(&cmd->i_conn_node); to release the command to the
 	 * session pool and remove it from the connection's list.
 	 *
 	 * Also stop the DataOUT timer, which will be restarted after
@@ -351,7 +351,7 @@
 				" CID: %hu\n", cmd->iscsi_opcode,
 				cmd->init_task_tag, cmd->cmd_sn, conn->cid);
 
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			spin_unlock_bh(&conn->cmd_lock);
 			iscsit_free_cmd(cmd, true);
 			spin_lock_bh(&conn->cmd_lock);
@@ -371,7 +371,7 @@
 		 */
 		if (!(cmd->cmd_flags & ICF_OOO_CMDSN) && !cmd->immediate_cmd &&
 		     iscsi_sna_gte(cmd->cmd_sn, conn->sess->exp_cmd_sn)) {
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			spin_unlock_bh(&conn->cmd_lock);
 			iscsit_free_cmd(cmd, true);
 			spin_lock_bh(&conn->cmd_lock);
@@ -393,7 +393,7 @@
 
 		cmd->sess = conn->sess;
 
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		iscsit_free_all_datain_reqs(cmd);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 3976183..44a5471 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -137,7 +137,7 @@
 	list_for_each_entry(tpg, &tiqn->tiqn_tpg_list, tpg_list) {
 
 		spin_lock(&tpg->tpg_state_lock);
-		if (tpg->tpg_state == TPG_STATE_FREE) {
+		if (tpg->tpg_state != TPG_STATE_ACTIVE) {
 			spin_unlock(&tpg->tpg_state_lock);
 			continue;
 		}
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 12da9b3..c3d9df6 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -500,7 +500,7 @@
 
 			if (segment_mult) {
 				u64 tmp = lba;
-				start_lba = sector_div(tmp, segment_size * segment_mult);
+				start_lba = do_div(tmp, segment_size * segment_mult);
 
 				last_lba = first_lba + segment_size - 1;
 				if (start_lba >= first_lba &&
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 2f5d779..3013287 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -2009,7 +2009,7 @@
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	unsigned char isid_buf[PR_REG_ISID_LEN], *isid_ptr = NULL;
 	sense_reason_t ret = TCM_NO_SENSE;
-	int pr_holder = 0;
+	int pr_holder = 0, type;
 
 	if (!se_sess || !se_lun) {
 		pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
@@ -2131,6 +2131,7 @@
 			ret = TCM_RESERVATION_CONFLICT;
 			goto out;
 		}
+		type = pr_reg->pr_res_type;
 
 		spin_lock(&pr_tmpl->registration_lock);
 		/*
@@ -2161,6 +2162,7 @@
 		 * Release the calling I_T Nexus registration now..
 		 */
 		__core_scsi3_free_registration(cmd->se_dev, pr_reg, NULL, 1);
+		pr_reg = NULL;
 
 		/*
 		 * From spc4r17, section 5.7.11.3 Unregistering
@@ -2174,8 +2176,8 @@
 		 * RESERVATIONS RELEASED.
 		 */
 		if (pr_holder &&
-		    (pr_reg->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_REGONLY ||
-		     pr_reg->pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_REGONLY)) {
+		    (type == PR_TYPE_WRITE_EXCLUSIVE_REGONLY ||
+		     type == PR_TYPE_EXCLUSIVE_ACCESS_REGONLY)) {
 			list_for_each_entry(pr_reg_p,
 					&pr_tmpl->registration_list,
 					pr_reg_list) {
@@ -2194,7 +2196,8 @@
 	ret = core_scsi3_update_and_write_aptpl(dev, aptpl);
 
 out:
-	core_scsi3_put_pr_reg(pr_reg);
+	if (pr_reg)
+		core_scsi3_put_pr_reg(pr_reg);
 	return ret;
 }
 
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index fa3cae3..77e6531 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -1074,23 +1074,36 @@
 	struct scatterlist *psg;
 	void *paddr, *addr;
 	unsigned int i, len, left;
+	unsigned int offset = sg_off;
 
 	left = sectors * dev->prot_length;
 
 	for_each_sg(cmd->t_prot_sg, psg, cmd->t_prot_nents, i) {
+		unsigned int psg_len, copied = 0;
 
-		len = min(psg->length, left);
 		paddr = kmap_atomic(sg_page(psg)) + psg->offset;
-		addr = kmap_atomic(sg_page(sg)) + sg_off;
+		psg_len = min(left, psg->length);
+		while (psg_len) {
+			len = min(psg_len, sg->length - offset);
+			addr = kmap_atomic(sg_page(sg)) + sg->offset + offset;
 
-		if (read)
-			memcpy(paddr, addr, len);
-		else
-			memcpy(addr, paddr, len);
+			if (read)
+				memcpy(paddr + copied, addr, len);
+			else
+				memcpy(addr, paddr + copied, len);
 
-		left -= len;
+			left -= len;
+			offset += len;
+			copied += len;
+			psg_len -= len;
+
+			if (offset >= sg->length) {
+				sg = sg_next(sg);
+				offset = 0;
+			}
+			kunmap_atomic(addr);
+		}
 		kunmap_atomic(paddr);
-		kunmap_atomic(addr);
 	}
 }
 
@@ -1155,7 +1168,7 @@
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_dif_v1_tuple *sdt;
-	struct scatterlist *dsg;
+	struct scatterlist *dsg, *psg = sg;
 	sector_t sector = start;
 	void *daddr, *paddr;
 	int i, j, offset = sg_off;
@@ -1163,14 +1176,14 @@
 
 	for_each_sg(cmd->t_data_sg, dsg, cmd->t_data_nents, i) {
 		daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
-		paddr = kmap_atomic(sg_page(sg)) + sg->offset;
+		paddr = kmap_atomic(sg_page(psg)) + sg->offset;
 
 		for (j = 0; j < dsg->length; j += dev->dev_attrib.block_size) {
 
-			if (offset >= sg->length) {
+			if (offset >= psg->length) {
 				kunmap_atomic(paddr);
-				sg = sg_next(sg);
-				paddr = kmap_atomic(sg_page(sg)) + sg->offset;
+				psg = sg_next(psg);
+				paddr = kmap_atomic(sg_page(psg)) + psg->offset;
 				offset = 0;
 			}
 
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 43c5ca98..3bebc71 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -440,8 +440,8 @@
 		padding = ((-scsi_target_len) & 3);
 		if (padding)
 			scsi_target_len += padding;
-		if (scsi_name_len > 256)
-			scsi_name_len = 256;
+		if (scsi_target_len > 256)
+			scsi_target_len = 256;
 
 		buf[off-1] = scsi_target_len;
 		off += scsi_target_len;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index c50fd9f..2956250 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -669,9 +669,6 @@
 		return;
 	}
 
-	if (!success)
-		cmd->transport_state |= CMD_T_FAILED;
-
 	/*
 	 * Check for case where an explicit ABORT_TASK has been received
 	 * and transport_wait_for_tasks() will be waiting for completion..
@@ -681,7 +678,7 @@
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 		complete(&cmd->t_transport_stop_comp);
 		return;
-	} else if (cmd->transport_state & CMD_T_FAILED) {
+	} else if (!success) {
 		INIT_WORK(&cmd->work, target_complete_failure_work);
 	} else {
 		INIT_WORK(&cmd->work, target_complete_ok_work);
@@ -1604,6 +1601,9 @@
 	case TCM_CHECK_CONDITION_ABORT_CMD:
 	case TCM_CHECK_CONDITION_UNIT_ATTENTION:
 	case TCM_CHECK_CONDITION_NOT_READY:
+	case TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED:
+	case TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED:
+	case TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED:
 		break;
 	case TCM_OUT_OF_RESOURCES:
 		sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 35c0664..5f88d76 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -136,6 +136,7 @@
 config RCAR_THERMAL
 	tristate "Renesas R-Car thermal driver"
 	depends on ARCH_SHMOBILE || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enable this to plug the R-Car thermal sensor driver into the Linux
 	  thermal framework.
@@ -210,8 +211,16 @@
 	tristate "ACPI INT3403 thermal driver"
 	depends on X86 && ACPI
 	help
-	  This driver uses ACPI INT3403 device objects. If present, it will
-	  register each INT3403 thermal sensor as a thermal zone.
+	  Newer laptops and tablets that use ACPI may have thermal sensors
+	  outside the core CPU/SOC for thermal safety reasons. These
+	  temperature sensors are also exposed for the OS to use via the so
+	  called INT3403 ACPI object. This driver will, on devices that have
+	  such sensors, expose the temperature information from these sensors
+	  to userspace via the normal thermal framework. This means that a wide
+	  range of applications and GUI widgets can show this information to
+	  the user or use this information for making decisions. For example,
+	  the Intel Thermal Daemon can use this information to allow the user
+	  to select his laptop to run without turning on the fans.
 
 menu "Texas Instruments thermal drivers"
 source "drivers/thermal/ti-soc-thermal/Kconfig"
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 338a88b..71b0ec0 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -56,10 +56,15 @@
 static DEFINE_MUTEX(thermal_list_lock);
 static DEFINE_MUTEX(thermal_governor_lock);
 
+static struct thermal_governor *def_governor;
+
 static struct thermal_governor *__find_governor(const char *name)
 {
 	struct thermal_governor *pos;
 
+	if (!name || !name[0])
+		return def_governor;
+
 	list_for_each_entry(pos, &thermal_governor_list, governor_list)
 		if (!strnicmp(name, pos->name, THERMAL_NAME_LENGTH))
 			return pos;
@@ -82,17 +87,23 @@
 	if (__find_governor(governor->name) == NULL) {
 		err = 0;
 		list_add(&governor->governor_list, &thermal_governor_list);
+		if (!def_governor && !strncmp(governor->name,
+			DEFAULT_THERMAL_GOVERNOR, THERMAL_NAME_LENGTH))
+			def_governor = governor;
 	}
 
 	mutex_lock(&thermal_list_lock);
 
 	list_for_each_entry(pos, &thermal_tz_list, node) {
+		/*
+		 * only thermal zones with specified tz->tzp->governor_name
+		 * may run with tz->govenor unset
+		 */
 		if (pos->governor)
 			continue;
-		if (pos->tzp)
-			name = pos->tzp->governor_name;
-		else
-			name = DEFAULT_THERMAL_GOVERNOR;
+
+		name = pos->tzp->governor_name;
+
 		if (!strnicmp(name, governor->name, THERMAL_NAME_LENGTH))
 			pos->governor = governor;
 	}
@@ -342,8 +353,8 @@
 static void handle_non_critical_trips(struct thermal_zone_device *tz,
 			int trip, enum thermal_trip_type trip_type)
 {
-	if (tz->governor)
-		tz->governor->throttle(tz, trip);
+	tz->governor ? tz->governor->throttle(tz, trip) :
+		       def_governor->throttle(tz, trip);
 }
 
 static void handle_critical_trips(struct thermal_zone_device *tz,
@@ -1107,7 +1118,7 @@
 	INIT_LIST_HEAD(&cdev->thermal_instances);
 	cdev->np = np;
 	cdev->ops = ops;
-	cdev->updated = true;
+	cdev->updated = false;
 	cdev->device.class = &thermal_class;
 	cdev->devdata = devdata;
 	dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
@@ -1533,7 +1544,7 @@
 	if (tz->tzp)
 		tz->governor = __find_governor(tz->tzp->governor_name);
 	else
-		tz->governor = __find_governor(DEFAULT_THERMAL_GOVERNOR);
+		tz->governor = def_governor;
 
 	mutex_unlock(&thermal_governor_lock);
 
diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c
index 972e1c7..081fd7e 100644
--- a/drivers/thermal/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/x86_pkg_temp_thermal.c
@@ -68,6 +68,10 @@
 	struct thermal_zone_device *tzone;
 };
 
+static const struct thermal_zone_params pkg_temp_tz_params = {
+	.no_hwmon	= true,
+};
+
 /* List maintaining number of package instances */
 static LIST_HEAD(phy_dev_list);
 static DEFINE_MUTEX(phy_dev_list_mutex);
@@ -394,7 +398,6 @@
 	int err;
 	u32 tj_max;
 	struct phy_dev_entry *phy_dev_entry;
-	char buffer[30];
 	int thres_count;
 	u32 eax, ebx, ecx, edx;
 	u8 *temp;
@@ -440,13 +443,11 @@
 	phy_dev_entry->first_cpu = cpu;
 	phy_dev_entry->tj_max = tj_max;
 	phy_dev_entry->ref_cnt = 1;
-	snprintf(buffer, sizeof(buffer), "pkg-temp-%d\n",
-					phy_dev_entry->phys_proc_id);
-	phy_dev_entry->tzone = thermal_zone_device_register(buffer,
+	phy_dev_entry->tzone = thermal_zone_device_register("x86_pkg_temp",
 			thres_count,
 			(thres_count == MAX_NUMBER_OF_TRIPS) ?
 				0x03 : 0x01,
-			phy_dev_entry, &tzone_ops, NULL, 0, 0);
+			phy_dev_entry, &tzone_ops, &pkg_temp_tz_params, 0, 0);
 	if (IS_ERR(phy_dev_entry->tzone)) {
 		err = PTR_ERR(phy_dev_entry->tzone);
 		goto err_ret_free;
diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c
index 6496872..b01659b 100644
--- a/drivers/tty/hvc/hvc_opal.c
+++ b/drivers/tty/hvc/hvc_opal.c
@@ -255,13 +255,7 @@
 	/* Register as a vio device to receive callbacks */
 	return platform_driver_register(&hvc_opal_driver);
 }
-module_init(hvc_opal_init);
-
-static void __exit hvc_opal_exit(void)
-{
-	platform_driver_unregister(&hvc_opal_driver);
-}
-module_exit(hvc_opal_exit);
+device_initcall(hvc_opal_init);
 
 static void udbg_opal_putc(char c)
 {
diff --git a/drivers/tty/hvc/hvc_rtas.c b/drivers/tty/hvc/hvc_rtas.c
index 0069bb8..08c8792 100644
--- a/drivers/tty/hvc/hvc_rtas.c
+++ b/drivers/tty/hvc/hvc_rtas.c
@@ -102,17 +102,7 @@
 
 	return 0;
 }
-module_init(hvc_rtas_init);
-
-/* This will tear down the tty portion of the driver */
-static void __exit hvc_rtas_exit(void)
-{
-	/* Really the fun isn't over until the worker thread breaks down and
-	 * the tty cleans up */
-	if (hvc_rtas_dev)
-		hvc_remove(hvc_rtas_dev);
-}
-module_exit(hvc_rtas_exit);
+device_initcall(hvc_rtas_init);
 
 /* This will happen prior to module init.  There is no tty at this time? */
 static int __init hvc_rtas_console_init(void)
diff --git a/drivers/tty/hvc/hvc_udbg.c b/drivers/tty/hvc/hvc_udbg.c
index 7222827..9cf573d 100644
--- a/drivers/tty/hvc/hvc_udbg.c
+++ b/drivers/tty/hvc/hvc_udbg.c
@@ -80,14 +80,7 @@
 
 	return 0;
 }
-module_init(hvc_udbg_init);
-
-static void __exit hvc_udbg_exit(void)
-{
-	if (hvc_udbg_dev)
-		hvc_remove(hvc_udbg_dev);
-}
-module_exit(hvc_udbg_exit);
+device_initcall(hvc_udbg_init);
 
 static int __init hvc_udbg_console_init(void)
 {
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 636c9ba..2dc2831 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -561,18 +561,7 @@
 #endif
 	return r;
 }
-
-static void __exit xen_hvc_fini(void)
-{
-	struct xencons_info *entry, *next;
-
-	if (list_empty(&xenconsoles))
-			return;
-
-	list_for_each_entry_safe(entry, next, &xenconsoles, list) {
-		xen_console_remove(entry);
-	}
-}
+device_initcall(xen_hvc_init);
 
 static int xen_cons_init(void)
 {
@@ -598,10 +587,6 @@
 	hvc_instantiate(HVC_COOKIE, 0, ops);
 	return 0;
 }
-
-
-module_init(xen_hvc_init);
-module_exit(xen_hvc_fini);
 console_initcall(xen_cons_init);
 
 #ifdef CONFIG_EARLY_PRINTK
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index f34461c..2ebe47b 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -1090,6 +1090,7 @@
 {
 	unsigned int addr = 0;
 	unsigned int modem = 0;
+	unsigned int brk = 0;
 	struct gsm_dlci *dlci;
 	int len = clen;
 	u8 *dp = data;
@@ -1116,6 +1117,16 @@
 		if (len == 0)
 			return;
 	}
+	len--;
+	if (len > 0) {
+		while (gsm_read_ea(&brk, *dp++) == 0) {
+			len--;
+			if (len == 0)
+				return;
+		}
+		modem <<= 7;
+		modem |= (brk & 0x7f);
+	}
 	tty = tty_port_tty_get(&dlci->port);
 	gsm_process_modem(tty, dlci, modem, clen);
 	if (tty) {
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index cb8017a..d15624c 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -817,8 +817,7 @@
 	struct n_tty_data *ldata = tty->disc_data;
 	size_t echoed;
 
-	if ((!L_ECHO(tty) && !L_ECHONL(tty)) ||
-	    ldata->echo_mark == ldata->echo_tail)
+	if (ldata->echo_mark == ldata->echo_tail)
 		return;
 
 	mutex_lock(&ldata->output_lock);
@@ -1244,7 +1243,8 @@
 	if (L_ECHO(tty)) {
 		echo_char(c, tty);
 		commit_echoes(tty);
-	}
+	} else
+		process_echoes(tty);
 	isig(signal, tty);
 	return;
 }
@@ -1274,7 +1274,7 @@
 	if (I_IXON(tty)) {
 		if (c == START_CHAR(tty)) {
 			start_tty(tty);
-			commit_echoes(tty);
+			process_echoes(tty);
 			return 0;
 		}
 		if (c == STOP_CHAR(tty)) {
@@ -1820,8 +1820,10 @@
 	 * Fix tty hang when I_IXON(tty) is cleared, but the tty
 	 * been stopped by STOP_CHAR(tty) before it.
 	 */
-	if (!I_IXON(tty) && old && (old->c_iflag & IXON) && !tty->flow_stopped)
+	if (!I_IXON(tty) && old && (old->c_iflag & IXON) && !tty->flow_stopped) {
 		start_tty(tty);
+		process_echoes(tty);
+	}
 
 	/* The termios change make the tty ready for I/O */
 	if (waitqueue_active(&tty->write_wait))
@@ -1896,7 +1898,7 @@
 static inline int input_available_p(struct tty_struct *tty, int poll)
 {
 	struct n_tty_data *ldata = tty->disc_data;
-	int amt = poll && !TIME_CHAR(tty) ? MIN_CHAR(tty) : 1;
+	int amt = poll && !TIME_CHAR(tty) && MIN_CHAR(tty) ? MIN_CHAR(tty) : 1;
 
 	if (ldata->icanon && !L_EXTPROC(tty)) {
 		if (ldata->canon_head != ldata->read_tail)
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 61ecd70..69932b7 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -2433,6 +2433,24 @@
 	serial_dl_write(up, quot);
 
 	/*
+	 * XR17V35x UARTs have an extra fractional divisor register (DLD)
+	 *
+	 * We need to recalculate all of the registers, because DLM and DLL
+	 * are already rounded to a whole integer.
+	 *
+	 * When recalculating we use a 32x clock instead of a 16x clock to
+	 * allow 1-bit for rounding in the fractional part.
+	 */
+	if (up->port.type == PORT_XR17V35X) {
+		unsigned int baud_x32 = (port->uartclk * 2) / baud;
+		u16 quot = baud_x32 / 32;
+		u8 quot_frac = DIV_ROUND_CLOSEST(baud_x32 % 32, 2);
+
+		serial_dl_write(up, quot);
+		serial_port_out(port, 0x2, quot_frac & 0xf);
+	}
+
+	/*
 	 * LCR DLAB must be set to enable 64-byte FIFO mode. If the FCR
 	 * is written without DLAB set, this mode will be disabled.
 	 */
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index faa64e6..ed31135 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -391,7 +391,7 @@
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int dw8250_suspend(struct device *dev)
 {
 	struct dw8250_data *data = dev_get_drvdata(dev);
@@ -409,7 +409,7 @@
 
 	return 0;
 }
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_RUNTIME
 static int dw8250_runtime_suspend(struct device *dev)
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 50228ee..0ff3e36 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -783,7 +783,8 @@
 {
 	unsigned int bar;
 
-	if ((priv->dev->subsystem_device & 0xff00) == 0x3000) {
+	if ((priv->dev->device != PCI_DEVICE_ID_NETMOS_9865) &&
+	    (priv->dev->subsystem_device & 0xff00) == 0x3000) {
 		/* netmos apparently orders BARs by datasheet layout, so serial
 		 * ports get BARs 0 and 3 (or 1 and 4 for memmapped)
 		 */
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index fa511eb..77f0351 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -738,9 +738,6 @@
 			return retval;
 		}
 		disable_irq(up->wakeirq);
-	} else {
-		dev_info(up->port.dev, "no wakeirq for uart%d\n",
-			 up->port.line);
 	}
 
 	dev_dbg(up->port.dev, "serial_omap_startup+%d\n", up->port.line);
@@ -1604,8 +1601,11 @@
 					    flags & SER_RS485_RTS_AFTER_SEND);
 		if (ret < 0)
 			return ret;
-	} else
+	} else if (up->rts_gpio == -EPROBE_DEFER) {
+		return -EPROBE_DEFER;
+	} else {
 		up->rts_gpio = -EINVAL;
+	}
 
 	if (of_property_read_u32_array(np, "rs485-rts-delay",
 				    rs485_delay, 2) == 0) {
@@ -1687,6 +1687,9 @@
 	up->port.iotype = UPIO_MEM;
 	up->port.irq = uartirq;
 	up->wakeirq = wakeirq;
+	if (!up->wakeirq)
+		dev_info(up->port.dev, "no wakeirq for uart%d\n",
+			 up->port.line);
 
 	up->port.regshift = 2;
 	up->port.fifosize = 64;
diff --git a/drivers/tty/serial/sirfsoc_uart.c b/drivers/tty/serial/sirfsoc_uart.c
index 49a2ffd..b7bfe24 100644
--- a/drivers/tty/serial/sirfsoc_uart.c
+++ b/drivers/tty/serial/sirfsoc_uart.c
@@ -542,8 +542,10 @@
 	wr_regl(port, ureg->sirfsoc_rx_dma_io_ctrl,
 			rd_regl(port, ureg->sirfsoc_rx_dma_io_ctrl) |
 			SIRFUART_IO_MODE);
-	sirfsoc_uart_pio_rx_chars(port, 4 - sirfport->rx_io_count);
 	spin_unlock_irqrestore(&sirfport->rx_lock, flags);
+	spin_lock(&port->lock);
+	sirfsoc_uart_pio_rx_chars(port, 4 - sirfport->rx_io_count);
+	spin_unlock(&port->lock);
 	if (sirfport->rx_io_count == 4) {
 		spin_lock_irqsave(&sirfport->rx_lock, flags);
 		sirfport->rx_io_count = 0;
diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index cf86e72..dc697ce 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -433,13 +433,10 @@
 	unsigned long flags;
 	int locked = 1;
 
-	local_irq_save(flags);
-	if (port->sysrq) {
-		locked = 0;
-	} else if (oops_in_progress) {
-		locked = spin_trylock(&port->lock);
-	} else
-		spin_lock(&port->lock);
+	if (port->sysrq || oops_in_progress)
+		locked = spin_trylock_irqsave(&port->lock, flags);
+	else
+		spin_lock_irqsave(&port->lock, flags);
 
 	while (n > 0) {
 		unsigned long ra = __pa(con_write_page);
@@ -470,8 +467,7 @@
 	}
 
 	if (locked)
-		spin_unlock(&port->lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&port->lock, flags);
 }
 
 static inline void sunhv_console_putchar(struct uart_port *port, char c)
@@ -492,7 +488,10 @@
 	unsigned long flags;
 	int i, locked = 1;
 
-	local_irq_save(flags);
+	if (port->sysrq || oops_in_progress)
+		locked = spin_trylock_irqsave(&port->lock, flags);
+	else
+		spin_lock_irqsave(&port->lock, flags);
 	if (port->sysrq) {
 		locked = 0;
 	} else if (oops_in_progress) {
@@ -507,8 +506,7 @@
 	}
 
 	if (locked)
-		spin_unlock(&port->lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&port->lock, flags);
 }
 
 static struct console sunhv_console = {
diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index 380fb53..5faa8e9 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -844,20 +844,16 @@
 	unsigned long flags;
 	int locked = 1;
 
-	local_irq_save(flags);
-	if (up->port.sysrq) {
-		locked = 0;
-	} else if (oops_in_progress) {
-		locked = spin_trylock(&up->port.lock);
-	} else
-		spin_lock(&up->port.lock);
+	if (up->port.sysrq || oops_in_progress)
+		locked = spin_trylock_irqsave(&up->port.lock, flags);
+	else
+		spin_lock_irqsave(&up->port.lock, flags);
 
 	uart_console_write(&up->port, s, n, sunsab_console_putchar);
 	sunsab_tec_wait(up);
 
 	if (locked)
-		spin_unlock(&up->port.lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&up->port.lock, flags);
 }
 
 static int sunsab_console_setup(struct console *con, char *options)
diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c
index db79b76..9a0f24f 100644
--- a/drivers/tty/serial/sunsu.c
+++ b/drivers/tty/serial/sunsu.c
@@ -1295,13 +1295,10 @@
 	unsigned int ier;
 	int locked = 1;
 
-	local_irq_save(flags);
-	if (up->port.sysrq) {
-		locked = 0;
-	} else if (oops_in_progress) {
-		locked = spin_trylock(&up->port.lock);
-	} else
-		spin_lock(&up->port.lock);
+	if (up->port.sysrq || oops_in_progress)
+		locked = spin_trylock_irqsave(&up->port.lock, flags);
+	else
+		spin_lock_irqsave(&up->port.lock, flags);
 
 	/*
 	 *	First save the UER then disable the interrupts
@@ -1319,8 +1316,7 @@
 	serial_out(up, UART_IER, ier);
 
 	if (locked)
-		spin_unlock(&up->port.lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&up->port.lock, flags);
 }
 
 /*
diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c
index 45a8c6a..a2c40ed 100644
--- a/drivers/tty/serial/sunzilog.c
+++ b/drivers/tty/serial/sunzilog.c
@@ -1195,20 +1195,16 @@
 	unsigned long flags;
 	int locked = 1;
 
-	local_irq_save(flags);
-	if (up->port.sysrq) {
-		locked = 0;
-	} else if (oops_in_progress) {
-		locked = spin_trylock(&up->port.lock);
-	} else
-		spin_lock(&up->port.lock);
+	if (up->port.sysrq || oops_in_progress)
+		locked = spin_trylock_irqsave(&up->port.lock, flags);
+	else
+		spin_lock_irqsave(&up->port.lock, flags);
 
 	uart_console_write(&up->port, s, count, sunzilog_putchar);
 	udelay(2);
 
 	if (locked)
-		spin_unlock(&up->port.lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&up->port.lock, flags);
 }
 
 static int __init sunzilog_console_setup(struct console *con, char *options)
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 61b1137..23b5d32 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1164,6 +1164,8 @@
 			scr_memsetw(vc->vc_screenbuf, vc->vc_video_erase_char,
 				    vc->vc_screenbuf_size >> 1);
 			set_origin(vc);
+			if (CON_IS_VISIBLE(vc))
+				update_screen(vc);
 			/* fall through */
 		case 2: /* erase whole display */
 			count = vc->vc_cols * vc->vc_rows;
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 80de2f8..4ab2cb6 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -105,7 +105,7 @@
 
 	do {
 		/* flush any pending transfer */
-		hw_write(ci, OP_ENDPTFLUSH, BIT(n), BIT(n));
+		hw_write(ci, OP_ENDPTFLUSH, ~0, BIT(n));
 		while (hw_read(ci, OP_ENDPTFLUSH, BIT(n)))
 			cpu_relax();
 	} while (hw_read(ci, OP_ENDPTSTAT, BIT(n)));
@@ -205,7 +205,7 @@
 	if (is_ctrl && dir == RX && hw_read(ci, OP_ENDPTSETUPSTAT, BIT(num)))
 		return -EAGAIN;
 
-	hw_write(ci, OP_ENDPTPRIME, BIT(n), BIT(n));
+	hw_write(ci, OP_ENDPTPRIME, ~0, BIT(n));
 
 	while (hw_read(ci, OP_ENDPTPRIME, BIT(n)))
 		cpu_relax();
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 8d72f0c..062967c 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -717,6 +717,10 @@
 			result = -ENOMEM;
 			goto err;
 		}
+
+		if (dev->quirks & USB_QUIRK_DELAY_INIT)
+			msleep(100);
+
 		result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno,
 		    bigbuffer, length);
 		if (result < 0) {
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 5d01558..ab90a01 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -63,8 +63,10 @@
 	dynid->id.idProduct = idProduct;
 	dynid->id.match_flags = USB_DEVICE_ID_MATCH_DEVICE;
 	if (fields > 2 && bInterfaceClass) {
-		if (bInterfaceClass > 255)
-			return -EINVAL;
+		if (bInterfaceClass > 255) {
+			retval = -EINVAL;
+			goto fail;
+		}
 
 		dynid->id.bInterfaceClass = (u8)bInterfaceClass;
 		dynid->id.match_flags |= USB_DEVICE_ID_MATCH_INT_CLASS;
@@ -73,17 +75,21 @@
 	if (fields > 4) {
 		const struct usb_device_id *id = id_table;
 
-		if (!id)
-			return -ENODEV;
+		if (!id) {
+			retval = -ENODEV;
+			goto fail;
+		}
 
 		for (; id->match_flags; id++)
 			if (id->idVendor == refVendor && id->idProduct == refProduct)
 				break;
 
-		if (id->match_flags)
+		if (id->match_flags) {
 			dynid->id.driver_info = id->driver_info;
-		else
-			return -ENODEV;
+		} else {
+			retval = -ENODEV;
+			goto fail;
+		}
 	}
 
 	spin_lock(&dynids->lock);
@@ -95,6 +101,10 @@
 	if (retval)
 		return retval;
 	return count;
+
+fail:
+	kfree(dynid);
+	return retval;
 }
 EXPORT_SYMBOL_GPL(usb_store_new_id);
 
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 199aaea..2518c32 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1032,7 +1032,6 @@
 					dev_name(&usb_dev->dev), retval);
 			return retval;
 		}
-		usb_dev->lpm_capable = usb_device_supports_lpm(usb_dev);
 	}
 
 	retval = usb_new_device (usb_dev);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index babba88..5cbf78d 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -128,7 +128,7 @@
 	return usb_get_intfdata(hdev->actconfig->interface[0]);
 }
 
-int usb_device_supports_lpm(struct usb_device *udev)
+static int usb_device_supports_lpm(struct usb_device *udev)
 {
 	/* USB 2.1 (and greater) devices indicate LPM support through
 	 * their USB 2.0 Extended Capabilities BOS descriptor.
@@ -149,11 +149,6 @@
 				"Power management will be impacted.\n");
 		return 0;
 	}
-
-	/* udev is root hub */
-	if (!udev->parent)
-		return 1;
-
 	if (udev->parent->lpm_capable)
 		return 1;
 
@@ -1045,7 +1040,7 @@
 		 */
 		if (type == HUB_INIT) {
 			delay = hub_power_on(hub, false);
-			PREPARE_DELAYED_WORK(&hub->init_work, hub_init_func2);
+			INIT_DELAYED_WORK(&hub->init_work, hub_init_func2);
 			schedule_delayed_work(&hub->init_work,
 					msecs_to_jiffies(delay));
 
@@ -1199,7 +1194,7 @@
 
 		/* Don't do a long sleep inside a workqueue routine */
 		if (type == HUB_INIT2) {
-			PREPARE_DELAYED_WORK(&hub->init_work, hub_init_func3);
+			INIT_DELAYED_WORK(&hub->init_work, hub_init_func3);
 			schedule_delayed_work(&hub->init_work,
 					msecs_to_jiffies(delay));
 			return;		/* Continues at init3: below */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 8f37063..739ee8e 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -47,6 +47,10 @@
 	/* Microsoft LifeCam-VX700 v2.0 */
 	{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Logitech HD Pro Webcams C920 and C930e */
+	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
+	{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
+
 	/* Logitech Quickcam Fusion */
 	{ USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME },
 
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index c493836..8238577 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -35,7 +35,6 @@
 		unsigned int size);
 extern int usb_get_bos_descriptor(struct usb_device *dev);
 extern void usb_release_bos_descriptor(struct usb_device *dev);
-extern int usb_device_supports_lpm(struct usb_device *udev);
 extern char *usb_cache_string(struct usb_device *udev, int index);
 extern int usb_set_configuration(struct usb_device *dev, int configuration);
 extern int usb_choose_configuration(struct usb_device *udev);
diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c
index 8565d87..1d12988 100644
--- a/drivers/usb/dwc2/core.c
+++ b/drivers/usb/dwc2/core.c
@@ -216,7 +216,7 @@
 	int retval = 0;
 
 	if (!select_phy)
-		return -ENODEV;
+		return 0;
 
 	usbcfg = readl(hsotg->regs + GUSBCFG);
 
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index f59484d..4d918ed 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -2565,25 +2565,14 @@
 				     struct usb_host_endpoint *ep)
 {
 	struct dwc2_hsotg *hsotg = dwc2_hcd_to_hsotg(hcd);
-	int is_control = usb_endpoint_xfer_control(&ep->desc);
-	int is_out = usb_endpoint_dir_out(&ep->desc);
-	int epnum = usb_endpoint_num(&ep->desc);
-	struct usb_device *udev;
 	unsigned long flags;
 
 	dev_dbg(hsotg->dev,
 		"DWC OTG HCD EP RESET: bEndpointAddress=0x%02x\n",
 		ep->desc.bEndpointAddress);
 
-	udev = to_usb_device(hsotg->dev);
-
 	spin_lock_irqsave(&hsotg->lock, flags);
-
-	usb_settoggle(udev, epnum, is_out, 0);
-	if (is_control)
-		usb_settoggle(udev, epnum, !is_out, 0);
 	dwc2_hcd_endpoint_reset(hsotg, ep);
-
 	spin_unlock_irqrestore(&hsotg->lock, flags);
 }
 
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index d01d0d3..eaba547 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -124,6 +124,9 @@
 	int retval;
 	int irq;
 
+	if (usb_disabled())
+		return -ENODEV;
+
 	match = of_match_device(dwc2_of_match_table, &dev->dev);
 	if (match && match->data) {
 		params = match->data;
diff --git a/drivers/usb/gadget/bcm63xx_udc.c b/drivers/usb/gadget/bcm63xx_udc.c
index 888fbb4..e969eb8 100644
--- a/drivers/usb/gadget/bcm63xx_udc.c
+++ b/drivers/usb/gadget/bcm63xx_udc.c
@@ -360,24 +360,30 @@
 	bcm_writel(val, udc->iudma_regs + off);
 }
 
-static inline u32 usb_dmac_readl(struct bcm63xx_udc *udc, u32 off)
+static inline u32 usb_dmac_readl(struct bcm63xx_udc *udc, u32 off, int chan)
 {
-	return bcm_readl(udc->iudma_regs + IUDMA_DMAC_OFFSET + off);
+	return bcm_readl(udc->iudma_regs + IUDMA_DMAC_OFFSET + off +
+			(ENETDMA_CHAN_WIDTH * chan));
 }
 
-static inline void usb_dmac_writel(struct bcm63xx_udc *udc, u32 val, u32 off)
+static inline void usb_dmac_writel(struct bcm63xx_udc *udc, u32 val, u32 off,
+					int chan)
 {
-	bcm_writel(val, udc->iudma_regs + IUDMA_DMAC_OFFSET + off);
+	bcm_writel(val, udc->iudma_regs + IUDMA_DMAC_OFFSET + off +
+			(ENETDMA_CHAN_WIDTH * chan));
 }
 
-static inline u32 usb_dmas_readl(struct bcm63xx_udc *udc, u32 off)
+static inline u32 usb_dmas_readl(struct bcm63xx_udc *udc, u32 off, int chan)
 {
-	return bcm_readl(udc->iudma_regs + IUDMA_DMAS_OFFSET + off);
+	return bcm_readl(udc->iudma_regs + IUDMA_DMAS_OFFSET + off +
+			(ENETDMA_CHAN_WIDTH * chan));
 }
 
-static inline void usb_dmas_writel(struct bcm63xx_udc *udc, u32 val, u32 off)
+static inline void usb_dmas_writel(struct bcm63xx_udc *udc, u32 val, u32 off,
+					int chan)
 {
-	bcm_writel(val, udc->iudma_regs + IUDMA_DMAS_OFFSET + off);
+	bcm_writel(val, udc->iudma_regs + IUDMA_DMAS_OFFSET + off +
+			(ENETDMA_CHAN_WIDTH * chan));
 }
 
 static inline void set_clocks(struct bcm63xx_udc *udc, bool is_enabled)
@@ -638,7 +644,7 @@
 	} while (!last_bd);
 
 	usb_dmac_writel(udc, ENETDMAC_CHANCFG_EN_MASK,
-			ENETDMAC_CHANCFG_REG(iudma->ch_idx));
+			ENETDMAC_CHANCFG_REG, iudma->ch_idx);
 }
 
 /**
@@ -694,9 +700,9 @@
 		bcm63xx_fifo_reset_ep(udc, max(0, iudma->ep_num));
 
 	/* stop DMA, then wait for the hardware to wrap up */
-	usb_dmac_writel(udc, 0, ENETDMAC_CHANCFG_REG(ch_idx));
+	usb_dmac_writel(udc, 0, ENETDMAC_CHANCFG_REG, ch_idx);
 
-	while (usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG(ch_idx)) &
+	while (usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG, ch_idx) &
 				   ENETDMAC_CHANCFG_EN_MASK) {
 		udelay(1);
 
@@ -713,10 +719,10 @@
 			dev_warn(udc->dev, "forcibly halting IUDMA channel %d\n",
 				 ch_idx);
 			usb_dmac_writel(udc, ENETDMAC_CHANCFG_BUFHALT_MASK,
-					ENETDMAC_CHANCFG_REG(ch_idx));
+					ENETDMAC_CHANCFG_REG, ch_idx);
 		}
 	}
-	usb_dmac_writel(udc, ~0, ENETDMAC_IR_REG(ch_idx));
+	usb_dmac_writel(udc, ~0, ENETDMAC_IR_REG, ch_idx);
 
 	/* don't leave "live" HW-owned entries for the next guy to step on */
 	for (d = iudma->bd_ring; d <= iudma->end_bd; d++)
@@ -728,11 +734,11 @@
 
 	/* set up IRQs, UBUS burst size, and BD base for this channel */
 	usb_dmac_writel(udc, ENETDMAC_IR_BUFDONE_MASK,
-			ENETDMAC_IRMASK_REG(ch_idx));
-	usb_dmac_writel(udc, 8, ENETDMAC_MAXBURST_REG(ch_idx));
+			ENETDMAC_IRMASK_REG, ch_idx);
+	usb_dmac_writel(udc, 8, ENETDMAC_MAXBURST_REG, ch_idx);
 
-	usb_dmas_writel(udc, iudma->bd_ring_dma, ENETDMAS_RSTART_REG(ch_idx));
-	usb_dmas_writel(udc, 0, ENETDMAS_SRAM2_REG(ch_idx));
+	usb_dmas_writel(udc, iudma->bd_ring_dma, ENETDMAS_RSTART_REG, ch_idx);
+	usb_dmas_writel(udc, 0, ENETDMAS_SRAM2_REG, ch_idx);
 }
 
 /**
@@ -2035,7 +2041,7 @@
 	spin_lock(&udc->lock);
 
 	usb_dmac_writel(udc, ENETDMAC_IR_BUFDONE_MASK,
-			ENETDMAC_IR_REG(iudma->ch_idx));
+			ENETDMAC_IR_REG, iudma->ch_idx);
 	bep = iudma->bep;
 	rc = iudma_read(udc, iudma);
 
@@ -2175,18 +2181,18 @@
 		seq_printf(s, " [ep%d]:\n",
 			   max_t(int, iudma_defaults[ch_idx].ep_num, 0));
 		seq_printf(s, "  cfg: %08x; irqstat: %08x; irqmask: %08x; maxburst: %08x\n",
-			   usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG(ch_idx)),
-			   usb_dmac_readl(udc, ENETDMAC_IR_REG(ch_idx)),
-			   usb_dmac_readl(udc, ENETDMAC_IRMASK_REG(ch_idx)),
-			   usb_dmac_readl(udc, ENETDMAC_MAXBURST_REG(ch_idx)));
+			   usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG, ch_idx),
+			   usb_dmac_readl(udc, ENETDMAC_IR_REG, ch_idx),
+			   usb_dmac_readl(udc, ENETDMAC_IRMASK_REG, ch_idx),
+			   usb_dmac_readl(udc, ENETDMAC_MAXBURST_REG, ch_idx));
 
-		sram2 = usb_dmas_readl(udc, ENETDMAS_SRAM2_REG(ch_idx));
-		sram3 = usb_dmas_readl(udc, ENETDMAS_SRAM3_REG(ch_idx));
+		sram2 = usb_dmas_readl(udc, ENETDMAS_SRAM2_REG, ch_idx);
+		sram3 = usb_dmas_readl(udc, ENETDMAS_SRAM3_REG, ch_idx);
 		seq_printf(s, "  base: %08x; index: %04x_%04x; desc: %04x_%04x %08x\n",
-			   usb_dmas_readl(udc, ENETDMAS_RSTART_REG(ch_idx)),
+			   usb_dmas_readl(udc, ENETDMAS_RSTART_REG, ch_idx),
 			   sram2 >> 16, sram2 & 0xffff,
 			   sram3 >> 16, sram3 & 0xffff,
-			   usb_dmas_readl(udc, ENETDMAS_SRAM4_REG(ch_idx)));
+			   usb_dmas_readl(udc, ENETDMAS_SRAM4_REG, ch_idx));
 		seq_printf(s, "  desc: %d/%d used", iudma->n_bds_used,
 			   iudma->n_bds);
 
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index 306a2b5..2b43343 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -585,7 +585,6 @@
 			     char __user *buf, size_t len, int read)
 {
 	struct ffs_epfile *epfile = file->private_data;
-	struct usb_gadget *gadget = epfile->ffs->gadget;
 	struct ffs_ep *ep;
 	char *data = NULL;
 	ssize_t ret, data_len;
@@ -622,6 +621,12 @@
 	/* Allocate & copy */
 	if (!halt) {
 		/*
+		 * if we _do_ wait above, the epfile->ffs->gadget might be NULL
+		 * before the waiting completes, so do not assign to 'gadget' earlier
+		 */
+		struct usb_gadget *gadget = epfile->ffs->gadget;
+
+		/*
 		 * Controller may require buffer size to be aligned to
 		 * maxpacketsize of an out endpoint.
 		 */
diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c
index bf7a56b..69b76ef 100644
--- a/drivers/usb/gadget/printer.c
+++ b/drivers/usb/gadget/printer.c
@@ -1157,7 +1157,7 @@
 
 	usb_gadget_set_selfpowered(gadget);
 
-	if (gadget->is_otg) {
+	if (gadget_is_otg(gadget)) {
 		otg_descriptor.bmAttributes |= USB_OTG_HNP;
 		printer_cfg_driver.descriptors = otg_desc;
 		printer_cfg_driver.bmAttributes |= USB_CONFIG_ATT_WAKEUP;
diff --git a/drivers/usb/gadget/s3c2410_udc.c b/drivers/usb/gadget/s3c2410_udc.c
index f04b2c3..dd9678f 100644
--- a/drivers/usb/gadget/s3c2410_udc.c
+++ b/drivers/usb/gadget/s3c2410_udc.c
@@ -1629,7 +1629,7 @@
 		ep->ep.desc = NULL;
 		ep->halted = 0;
 		INIT_LIST_HEAD(&ep->queue);
-		usb_ep_set_maxpacket_limit(&ep->ep, &ep->ep.maxpacket);
+		usb_ep_set_maxpacket_limit(&ep->ep, ep->ep.maxpacket);
 	}
 }
 
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 4711427..81cda09 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -685,8 +685,15 @@
 	struct ehci_hcd		*ehci = hcd_to_ehci (hcd);
 	u32			status, masked_status, pcd_status = 0, cmd;
 	int			bh;
+	unsigned long		flags;
 
-	spin_lock (&ehci->lock);
+	/*
+	 * For threadirqs option we use spin_lock_irqsave() variant to prevent
+	 * deadlock with ehci hrtimer callback, because hrtimer callbacks run
+	 * in interrupt context even when threadirqs is specified. We can go
+	 * back to spin_lock() variant when hrtimer callbacks become threaded.
+	 */
+	spin_lock_irqsave(&ehci->lock, flags);
 
 	status = ehci_readl(ehci, &ehci->regs->status);
 
@@ -704,7 +711,7 @@
 
 	/* Shared IRQ? */
 	if (!masked_status || unlikely(ehci->rh_state == EHCI_RH_HALTED)) {
-		spin_unlock(&ehci->lock);
+		spin_unlock_irqrestore(&ehci->lock, flags);
 		return IRQ_NONE;
 	}
 
@@ -815,7 +822,7 @@
 
 	if (bh)
 		ehci_work (ehci);
-	spin_unlock (&ehci->lock);
+	spin_unlock_irqrestore(&ehci->lock, flags);
 	if (pcd_status)
 		usb_hcd_poll_rh_status(hcd);
 	return IRQ_HANDLED;
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index 47b858f..7ae0c4d 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -238,6 +238,7 @@
 	int			port;
 	int			mask;
 	int			changed;
+	bool			fs_idle_delay;
 
 	ehci_dbg(ehci, "suspend root hub\n");
 
@@ -272,6 +273,7 @@
 	ehci->bus_suspended = 0;
 	ehci->owned_ports = 0;
 	changed = 0;
+	fs_idle_delay = false;
 	port = HCS_N_PORTS(ehci->hcs_params);
 	while (port--) {
 		u32 __iomem	*reg = &ehci->regs->port_status [port];
@@ -300,16 +302,32 @@
 		}
 
 		if (t1 != t2) {
+			/*
+			 * On some controllers, Wake-On-Disconnect will
+			 * generate false wakeup signals until the bus
+			 * switches over to full-speed idle.  For their
+			 * sake, add a delay if we need one.
+			 */
+			if ((t2 & PORT_WKDISC_E) &&
+					ehci_port_speed(ehci, t2) ==
+						USB_PORT_STAT_HIGH_SPEED)
+				fs_idle_delay = true;
 			ehci_writel(ehci, t2, reg);
 			changed = 1;
 		}
 	}
+	spin_unlock_irq(&ehci->lock);
+
+	if ((changed && ehci->has_tdi_phy_lpm) || fs_idle_delay) {
+		/*
+		 * Wait for HCD to enter low-power mode or for the bus
+		 * to switch to full-speed idle.
+		 */
+		usleep_range(5000, 5500);
+	}
 
 	if (changed && ehci->has_tdi_phy_lpm) {
-		spin_unlock_irq(&ehci->lock);
-		msleep(5);	/* 5 ms for HCD to enter low-power mode */
 		spin_lock_irq(&ehci->lock);
-
 		port = HCS_N_PORTS(ehci->hcs_params);
 		while (port--) {
 			u32 __iomem	*hostpc_reg = &ehci->regs->hostpc[port];
@@ -322,8 +340,8 @@
 					port, (t3 & HOSTPC_PHCD) ?
 					"succeeded" : "failed");
 		}
+		spin_unlock_irq(&ehci->lock);
 	}
-	spin_unlock_irq(&ehci->lock);
 
 	/* Apparently some devices need a >= 1-uframe delay here */
 	if (ehci->bus_suspended)
diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c
index b016d38..eb009a4 100644
--- a/drivers/usb/host/xhci-dbg.c
+++ b/drivers/usb/host/xhci-dbg.c
@@ -203,12 +203,12 @@
 				addr, (unsigned int)temp);
 
 	addr = &ir_set->erst_base;
-	temp_64 = readq(addr);
+	temp_64 = xhci_read_64(xhci, addr);
 	xhci_dbg(xhci, "  %p: ir_set.erst_base = @%08llx\n",
 			addr, temp_64);
 
 	addr = &ir_set->erst_dequeue;
-	temp_64 = readq(addr);
+	temp_64 = xhci_read_64(xhci, addr);
 	xhci_dbg(xhci, "  %p: ir_set.erst_dequeue = @%08llx\n",
 			addr, temp_64);
 }
@@ -412,7 +412,7 @@
 {
 	u64 val;
 
-	val = readq(&xhci->op_regs->cmd_ring);
+	val = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	xhci_dbg(xhci, "// xHC command ring deq ptr low bits + flags = @%08x\n",
 			lower_32_bits(val));
 	xhci_dbg(xhci, "// xHC command ring deq ptr high bits = @%08x\n",
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 873c272..bce4391 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1958,7 +1958,7 @@
 		xhci_warn(xhci, "WARN something wrong with SW event ring "
 				"dequeue ptr.\n");
 	/* Update HC event ring dequeue pointer */
-	temp = readq(&xhci->ir_set->erst_dequeue);
+	temp = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
 	temp &= ERST_PTR_MASK;
 	/* Don't clear the EHB bit (which is RW1C) because
 	 * there might be more events to service.
@@ -1967,7 +1967,7 @@
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"// Write event ring dequeue pointer, "
 			"preserving EHB bit");
-	writeq(((u64) deq & (u64) ~ERST_PTR_MASK) | temp,
+	xhci_write_64(xhci, ((u64) deq & (u64) ~ERST_PTR_MASK) | temp,
 			&xhci->ir_set->erst_dequeue);
 }
 
@@ -2269,7 +2269,7 @@
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"// Device context base array address = 0x%llx (DMA), %p (virt)",
 			(unsigned long long)xhci->dcbaa->dma, xhci->dcbaa);
-	writeq(dma, &xhci->op_regs->dcbaa_ptr);
+	xhci_write_64(xhci, dma, &xhci->op_regs->dcbaa_ptr);
 
 	/*
 	 * Initialize the ring segment pool.  The ring must be a contiguous
@@ -2312,13 +2312,13 @@
 			(unsigned long long)xhci->cmd_ring->first_seg->dma);
 
 	/* Set the address in the Command Ring Control register */
-	val_64 = readq(&xhci->op_regs->cmd_ring);
+	val_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	val_64 = (val_64 & (u64) CMD_RING_RSVD_BITS) |
 		(xhci->cmd_ring->first_seg->dma & (u64) ~CMD_RING_RSVD_BITS) |
 		xhci->cmd_ring->cycle_state;
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"// Setting command ring address to 0x%x", val);
-	writeq(val_64, &xhci->op_regs->cmd_ring);
+	xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring);
 	xhci_dbg_cmd_ptrs(xhci);
 
 	xhci->lpm_command = xhci_alloc_command(xhci, true, true, flags);
@@ -2396,10 +2396,10 @@
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"// Set ERST base address for ir_set 0 = 0x%llx",
 			(unsigned long long)xhci->erst.erst_dma_addr);
-	val_64 = readq(&xhci->ir_set->erst_base);
+	val_64 = xhci_read_64(xhci, &xhci->ir_set->erst_base);
 	val_64 &= ERST_PTR_MASK;
 	val_64 |= (xhci->erst.erst_dma_addr & (u64) ~ERST_PTR_MASK);
-	writeq(val_64, &xhci->ir_set->erst_base);
+	xhci_write_64(xhci, val_64, &xhci->ir_set->erst_base);
 
 	/* Set the event ring dequeue address */
 	xhci_set_hc_event_deq(xhci);
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 3c898c1..04f986d 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -142,6 +142,11 @@
 				"QUIRK: Resetting on resume");
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 	}
+	if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
+			pdev->device == 0x0015 &&
+			pdev->subsystem_vendor == PCI_VENDOR_ID_SAMSUNG &&
+			pdev->subsystem_device == 0xc0cd)
+		xhci->quirks |= XHCI_RESET_ON_RESUME;
 	if (pdev->vendor == PCI_VENDOR_ID_VIA)
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
 }
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index a0b248c..0ed64eb 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -307,13 +307,14 @@
 		return 0;
 	}
 
-	temp_64 = readq(&xhci->op_regs->cmd_ring);
+	temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	if (!(temp_64 & CMD_RING_RUNNING)) {
 		xhci_dbg(xhci, "Command ring had been stopped\n");
 		return 0;
 	}
 	xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
-	writeq(temp_64 | CMD_RING_ABORT, &xhci->op_regs->cmd_ring);
+	xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
+			&xhci->op_regs->cmd_ring);
 
 	/* Section 4.6.1.2 of xHCI 1.0 spec says software should
 	 * time the completion od all xHCI commands, including
@@ -2864,8 +2865,9 @@
 		/* Clear the event handler busy flag (RW1C);
 		 * the event ring should be empty.
 		 */
-		temp_64 = readq(&xhci->ir_set->erst_dequeue);
-		writeq(temp_64 | ERST_EHB, &xhci->ir_set->erst_dequeue);
+		temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
+		xhci_write_64(xhci, temp_64 | ERST_EHB,
+				&xhci->ir_set->erst_dequeue);
 		spin_unlock(&xhci->lock);
 
 		return IRQ_HANDLED;
@@ -2877,7 +2879,7 @@
 	 */
 	while (xhci_handle_event(xhci) > 0) {}
 
-	temp_64 = readq(&xhci->ir_set->erst_dequeue);
+	temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
 	/* If necessary, update the HW's version of the event ring deq ptr. */
 	if (event_ring_deq != xhci->event_ring->dequeue) {
 		deq = xhci_trb_virt_to_dma(xhci->event_ring->deq_seg,
@@ -2892,7 +2894,7 @@
 
 	/* Clear the event handler busy flag (RW1C); event ring is empty. */
 	temp_64 |= ERST_EHB;
-	writeq(temp_64, &xhci->ir_set->erst_dequeue);
+	xhci_write_64(xhci, temp_64, &xhci->ir_set->erst_dequeue);
 
 	spin_unlock(&xhci->lock);
 
@@ -2965,58 +2967,8 @@
 	}
 
 	while (1) {
-		if (room_on_ring(xhci, ep_ring, num_trbs)) {
-			union xhci_trb *trb = ep_ring->enqueue;
-			unsigned int usable = ep_ring->enq_seg->trbs +
-					TRBS_PER_SEGMENT - 1 - trb;
-			u32 nop_cmd;
-
-			/*
-			 * Section 4.11.7.1 TD Fragments states that a link
-			 * TRB must only occur at the boundary between
-			 * data bursts (eg 512 bytes for 480M).
-			 * While it is possible to split a large fragment
-			 * we don't know the size yet.
-			 * Simplest solution is to fill the trb before the
-			 * LINK with nop commands.
-			 */
-			if (num_trbs == 1 || num_trbs <= usable || usable == 0)
-				break;
-
-			if (ep_ring->type != TYPE_BULK)
-				/*
-				 * While isoc transfers might have a buffer that
-				 * crosses a 64k boundary it is unlikely.
-				 * Since we can't add NOPs without generating
-				 * gaps in the traffic just hope it never
-				 * happens at the end of the ring.
-				 * This could be fixed by writing a LINK TRB
-				 * instead of the first NOP - however the
-				 * TRB_TYPE_LINK_LE32() calls would all need
-				 * changing to check the ring length.
-				 */
-				break;
-
-			if (num_trbs >= TRBS_PER_SEGMENT) {
-				xhci_err(xhci, "Too many fragments %d, max %d\n",
-						num_trbs, TRBS_PER_SEGMENT - 1);
-				return -EINVAL;
-			}
-
-			nop_cmd = cpu_to_le32(TRB_TYPE(TRB_TR_NOOP) |
-					ep_ring->cycle_state);
-			ep_ring->num_trbs_free -= usable;
-			do {
-				trb->generic.field[0] = 0;
-				trb->generic.field[1] = 0;
-				trb->generic.field[2] = 0;
-				trb->generic.field[3] = nop_cmd;
-				trb++;
-			} while (--usable);
-			ep_ring->enqueue = trb;
-			if (room_on_ring(xhci, ep_ring, num_trbs))
-				break;
-		}
+		if (room_on_ring(xhci, ep_ring, num_trbs))
+			break;
 
 		if (ep_ring == xhci->cmd_ring) {
 			xhci_err(xhci, "Do not support expand command ring\n");
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index ad36439..924a6cc 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -611,7 +611,7 @@
 	xhci_dbg(xhci, "Event ring:\n");
 	xhci_debug_ring(xhci, xhci->event_ring);
 	xhci_dbg_ring_ptrs(xhci, xhci->event_ring);
-	temp_64 = readq(&xhci->ir_set->erst_dequeue);
+	temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
 	temp_64 &= ~ERST_PTR_MASK;
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"ERST deq = 64'h%0lx", (long unsigned int) temp_64);
@@ -756,11 +756,11 @@
 {
 	xhci->s3.command = readl(&xhci->op_regs->command);
 	xhci->s3.dev_nt = readl(&xhci->op_regs->dev_notification);
-	xhci->s3.dcbaa_ptr = readq(&xhci->op_regs->dcbaa_ptr);
+	xhci->s3.dcbaa_ptr = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr);
 	xhci->s3.config_reg = readl(&xhci->op_regs->config_reg);
 	xhci->s3.erst_size = readl(&xhci->ir_set->erst_size);
-	xhci->s3.erst_base = readq(&xhci->ir_set->erst_base);
-	xhci->s3.erst_dequeue = readq(&xhci->ir_set->erst_dequeue);
+	xhci->s3.erst_base = xhci_read_64(xhci, &xhci->ir_set->erst_base);
+	xhci->s3.erst_dequeue = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
 	xhci->s3.irq_pending = readl(&xhci->ir_set->irq_pending);
 	xhci->s3.irq_control = readl(&xhci->ir_set->irq_control);
 }
@@ -769,11 +769,11 @@
 {
 	writel(xhci->s3.command, &xhci->op_regs->command);
 	writel(xhci->s3.dev_nt, &xhci->op_regs->dev_notification);
-	writeq(xhci->s3.dcbaa_ptr, &xhci->op_regs->dcbaa_ptr);
+	xhci_write_64(xhci, xhci->s3.dcbaa_ptr, &xhci->op_regs->dcbaa_ptr);
 	writel(xhci->s3.config_reg, &xhci->op_regs->config_reg);
 	writel(xhci->s3.erst_size, &xhci->ir_set->erst_size);
-	writeq(xhci->s3.erst_base, &xhci->ir_set->erst_base);
-	writeq(xhci->s3.erst_dequeue, &xhci->ir_set->erst_dequeue);
+	xhci_write_64(xhci, xhci->s3.erst_base, &xhci->ir_set->erst_base);
+	xhci_write_64(xhci, xhci->s3.erst_dequeue, &xhci->ir_set->erst_dequeue);
 	writel(xhci->s3.irq_pending, &xhci->ir_set->irq_pending);
 	writel(xhci->s3.irq_control, &xhci->ir_set->irq_control);
 }
@@ -783,7 +783,7 @@
 	u64	val_64;
 
 	/* step 2: initialize command ring buffer */
-	val_64 = readq(&xhci->op_regs->cmd_ring);
+	val_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	val_64 = (val_64 & (u64) CMD_RING_RSVD_BITS) |
 		(xhci_trb_virt_to_dma(xhci->cmd_ring->deq_seg,
 				      xhci->cmd_ring->dequeue) &
@@ -792,7 +792,7 @@
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"// Setting command ring address to 0x%llx",
 			(long unsigned long) val_64);
-	writeq(val_64, &xhci->op_regs->cmd_ring);
+	xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring);
 }
 
 /*
@@ -3842,7 +3842,7 @@
 	if (ret) {
 		return ret;
 	}
-	temp_64 = readq(&xhci->op_regs->dcbaa_ptr);
+	temp_64 = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_address,
 			"Op regs DCBAA ptr = %#016llx", temp_64);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_address,
@@ -4730,8 +4730,8 @@
 	struct device		*dev = hcd->self.controller;
 	int			retval;
 
-	/* Limit the block layer scatter-gather lists to half a segment. */
-	hcd->self.sg_tablesize = TRBS_PER_SEGMENT / 2;
+	/* Accept arbitrarily long scatter-gather lists */
+	hcd->self.sg_tablesize = ~0;
 
 	/* support to build packet from discontinuous buffers */
 	hcd->self.no_sg_constraint = 1;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index f8416639..58ed9d0 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -28,17 +28,6 @@
 #include <linux/kernel.h>
 #include <linux/usb/hcd.h>
 
-/*
- * Registers should always be accessed with double word or quad word accesses.
- *
- * Some xHCI implementations may support 64-bit address pointers.  Registers
- * with 64-bit address pointers should be written to with dword accesses by
- * writing the low dword first (ptr[0]), then the high dword (ptr[1]) second.
- * xHCI implementations that do not support 64-bit address pointers will ignore
- * the high dword, and write order is irrelevant.
- */
-#include <asm-generic/io-64-nonatomic-lo-hi.h>
-
 /* Code sharing between pci-quirks and xhci hcd */
 #include	"xhci-ext-caps.h"
 #include "pci-quirks.h"
@@ -1279,7 +1268,7 @@
  * since the command ring is 64-byte aligned.
  * It must also be greater than 16.
  */
-#define TRBS_PER_SEGMENT	256
+#define TRBS_PER_SEGMENT	64
 /* Allow two commands + a link TRB, along with any reserved command TRBs */
 #define MAX_RSVD_CMD_TRBS	(TRBS_PER_SEGMENT - 3)
 #define TRB_SEGMENT_SIZE	(TRBS_PER_SEGMENT*16)
@@ -1614,6 +1603,34 @@
 #define xhci_warn_ratelimited(xhci, fmt, args...) \
 	dev_warn_ratelimited(xhci_to_hcd(xhci)->self.controller , fmt , ## args)
 
+/*
+ * Registers should always be accessed with double word or quad word accesses.
+ *
+ * Some xHCI implementations may support 64-bit address pointers.  Registers
+ * with 64-bit address pointers should be written to with dword accesses by
+ * writing the low dword first (ptr[0]), then the high dword (ptr[1]) second.
+ * xHCI implementations that do not support 64-bit address pointers will ignore
+ * the high dword, and write order is irrelevant.
+ */
+static inline u64 xhci_read_64(const struct xhci_hcd *xhci,
+		__le64 __iomem *regs)
+{
+	__u32 __iomem *ptr = (__u32 __iomem *) regs;
+	u64 val_lo = readl(ptr);
+	u64 val_hi = readl(ptr + 1);
+	return val_lo + (val_hi << 32);
+}
+static inline void xhci_write_64(struct xhci_hcd *xhci,
+				 const u64 val, __le64 __iomem *regs)
+{
+	__u32 __iomem *ptr = (__u32 __iomem *) regs;
+	u32 val_lo = lower_32_bits(val);
+	u32 val_hi = upper_32_bits(val);
+
+	writel(val_lo, ptr);
+	writel(val_hi, ptr + 1);
+}
+
 static inline int xhci_link_trb_quirk(struct xhci_hcd *xhci)
 {
 	return xhci->quirks & XHCI_LINK_TRB_QUIRK;
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index fc192ad..239ad0b 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -477,8 +477,11 @@
 				musb->port1_status |=
 						(USB_PORT_STAT_C_SUSPEND << 16)
 						| MUSB_PORT_STAT_RESUME;
+				musb->rh_timer = jiffies
+						 + msecs_to_jiffies(20);
 				schedule_delayed_work(
-					&musb->finish_resume_work, 20);
+					&musb->finish_resume_work,
+					msecs_to_jiffies(20));
 
 				musb->xceiv->state = OTG_STATE_A_HOST;
 				musb->is_active = 1;
@@ -2157,11 +2160,19 @@
 	void __iomem *musb_base = musb->mregs;
 	void __iomem *ep_target_regs;
 	void __iomem *epio;
+	u8 power;
 
 	musb_writew(musb_base, MUSB_FRAME, musb->context.frame);
 	musb_writeb(musb_base, MUSB_TESTMODE, musb->context.testmode);
 	musb_write_ulpi_buscontrol(musb->mregs, musb->context.busctl);
-	musb_writeb(musb_base, MUSB_POWER, musb->context.power);
+
+	/* Don't affect SUSPENDM/RESUME bits in POWER reg */
+	power = musb_readb(musb_base, MUSB_POWER);
+	power &= MUSB_POWER_SUSPENDM | MUSB_POWER_RESUME;
+	musb->context.power &= ~(MUSB_POWER_SUSPENDM | MUSB_POWER_RESUME);
+	power |= musb->context.power;
+	musb_writeb(musb_base, MUSB_POWER, power);
+
 	musb_writew(musb_base, MUSB_INTRTXE, musb->intrtxe);
 	musb_writew(musb_base, MUSB_INTRRXE, musb->intrrxe);
 	musb_writeb(musb_base, MUSB_INTRUSBE, musb->context.intrusbe);
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index ed45572..abb38c3 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -1183,6 +1183,9 @@
 				csr = MUSB_CSR0_H_STATUSPKT
 					| MUSB_CSR0_TXPKTRDY;
 
+			/* disable ping token in status phase */
+			csr |= MUSB_CSR0_H_DIS_PING;
+
 			/* flag status stage */
 			musb->ep0_stage = MUSB_EP0_STATUS;
 
diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c
index eb63443..e2d2d8c 100644
--- a/drivers/usb/musb/musb_virthub.c
+++ b/drivers/usb/musb/musb_virthub.c
@@ -135,7 +135,8 @@
 
 		/* later, GetPortStatus will stop RESUME signaling */
 		musb->port1_status |= MUSB_PORT_STAT_RESUME;
-		schedule_delayed_work(&musb->finish_resume_work, 20);
+		schedule_delayed_work(&musb->finish_resume_work,
+				      msecs_to_jiffies(20));
 	}
 }
 
@@ -158,7 +159,6 @@
 	 */
 	power = musb_readb(mbase, MUSB_POWER);
 	if (do_reset) {
-
 		/*
 		 * If RESUME is set, we must make sure it stays minimum 20 ms.
 		 * Then we must clear RESUME and wait a bit to let musb start
@@ -167,11 +167,22 @@
 		 * detected".
 		 */
 		if (power &  MUSB_POWER_RESUME) {
-			while (time_before(jiffies, musb->rh_timer))
-				msleep(1);
+			long remain = (unsigned long) musb->rh_timer - jiffies;
+
+			if (musb->rh_timer > 0 && remain > 0) {
+				/* take into account the minimum delay after resume */
+				schedule_delayed_work(
+					&musb->deassert_reset_work, remain);
+				return;
+			}
+
 			musb_writeb(mbase, MUSB_POWER,
-				power & ~MUSB_POWER_RESUME);
-			msleep(1);
+				    power & ~MUSB_POWER_RESUME);
+
+			/* Give the core 1 ms to clear MUSB_POWER_RESUME */
+			schedule_delayed_work(&musb->deassert_reset_work,
+					      msecs_to_jiffies(1));
+			return;
 		}
 
 		power &= 0xf0;
@@ -180,7 +191,8 @@
 
 		musb->port1_status |= USB_PORT_STAT_RESET;
 		musb->port1_status &= ~USB_PORT_STAT_ENABLE;
-		schedule_delayed_work(&musb->deassert_reset_work, 50);
+		schedule_delayed_work(&musb->deassert_reset_work,
+				      msecs_to_jiffies(50));
 	} else {
 		dev_dbg(musb->controller, "root port reset stopped\n");
 		musb_writeb(mbase, MUSB_POWER,
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 2a408cd..8aa59a2 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -659,7 +659,6 @@
 				OTG_INTERFSEL);
 
 		omap2430_low_level_exit(musb);
-		phy_power_off(musb->phy);
 	}
 
 	return 0;
@@ -674,7 +673,6 @@
 		omap2430_low_level_init(musb);
 		musb_writel(musb->mregs, OTG_INTERFSEL,
 				musb->context.otg_interfsel);
-		phy_power_on(musb->phy);
 	}
 
 	return 0;
diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c
index 8546c8d..d204f74 100644
--- a/drivers/usb/phy/phy-msm-usb.c
+++ b/drivers/usb/phy/phy-msm-usb.c
@@ -159,32 +159,6 @@
 	return rc;
 }
 
-#ifdef CONFIG_PM_SLEEP
-#define USB_PHY_SUSP_DIG_VOL  500000
-static int msm_hsusb_config_vddcx(int high)
-{
-	int max_vol = USB_PHY_VDD_DIG_VOL_MAX;
-	int min_vol;
-	int ret;
-
-	if (high)
-		min_vol = USB_PHY_VDD_DIG_VOL_MIN;
-	else
-		min_vol = USB_PHY_SUSP_DIG_VOL;
-
-	ret = regulator_set_voltage(hsusb_vddcx, min_vol, max_vol);
-	if (ret) {
-		pr_err("%s: unable to set the voltage for regulator "
-			"HSUSB_VDDCX\n", __func__);
-		return ret;
-	}
-
-	pr_debug("%s: min_vol:%d max_vol:%d\n", __func__, min_vol, max_vol);
-
-	return ret;
-}
-#endif
-
 static int msm_hsusb_ldo_set_mode(int on)
 {
 	int ret = 0;
@@ -440,7 +414,32 @@
 #define PHY_SUSPEND_TIMEOUT_USEC	(500 * 1000)
 #define PHY_RESUME_TIMEOUT_USEC	(100 * 1000)
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
+
+#define USB_PHY_SUSP_DIG_VOL  500000
+static int msm_hsusb_config_vddcx(int high)
+{
+	int max_vol = USB_PHY_VDD_DIG_VOL_MAX;
+	int min_vol;
+	int ret;
+
+	if (high)
+		min_vol = USB_PHY_VDD_DIG_VOL_MIN;
+	else
+		min_vol = USB_PHY_SUSP_DIG_VOL;
+
+	ret = regulator_set_voltage(hsusb_vddcx, min_vol, max_vol);
+	if (ret) {
+		pr_err("%s: unable to set the voltage for regulator "
+			"HSUSB_VDDCX\n", __func__);
+		return ret;
+	}
+
+	pr_debug("%s: min_vol:%d max_vol:%d\n", __func__, min_vol, max_vol);
+
+	return ret;
+}
+
 static int msm_otg_suspend(struct msm_otg *motg)
 {
 	struct usb_phy *phy = &motg->phy;
@@ -1733,22 +1732,18 @@
 }
 #endif
 
-#ifdef CONFIG_PM
 static const struct dev_pm_ops msm_otg_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(msm_otg_pm_suspend, msm_otg_pm_resume)
 	SET_RUNTIME_PM_OPS(msm_otg_runtime_suspend, msm_otg_runtime_resume,
 				msm_otg_runtime_idle)
 };
-#endif
 
 static struct platform_driver msm_otg_driver = {
 	.remove = msm_otg_remove,
 	.driver = {
 		.name = DRIVER_NAME,
 		.owner = THIS_MODULE,
-#ifdef CONFIG_PM
 		.pm = &msm_otg_dev_pm_ops,
-#endif
 	},
 };
 
diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c
index e6f61e4..8afa813 100644
--- a/drivers/usb/phy/phy.c
+++ b/drivers/usb/phy/phy.c
@@ -130,7 +130,7 @@
 
 	phy = __usb_find_phy(&phy_list, type);
 	if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) {
-		pr_err("unable to find transceiver of type %s\n",
+		pr_debug("PHY: unable to find transceiver of type %s\n",
 			usb_phy_type_string(type));
 		goto err0;
 	}
@@ -228,7 +228,7 @@
 
 	phy = __usb_find_phy_dev(dev, &phy_bind_list, index);
 	if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) {
-		pr_err("unable to find transceiver\n");
+		dev_dbg(dev, "unable to find transceiver\n");
 		goto err0;
 	}
 
@@ -424,10 +424,8 @@
 	unsigned long flags;
 
 	phy_bind = kzalloc(sizeof(*phy_bind), GFP_KERNEL);
-	if (!phy_bind) {
-		pr_err("phy_bind(): No memory for phy_bind");
+	if (!phy_bind)
 		return -ENOMEM;
-	}
 
 	phy_bind->dev_name = dev_name;
 	phy_bind->phy_dev_name = phy_dev_name;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index ce0d7b0..44ab129 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -152,6 +152,7 @@
 	{ USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_NXTCAM_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_EV3CON_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_0_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_1_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_2_PID) },
@@ -191,6 +192,8 @@
 	{ USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_IOBOARD_PID) },
 	{ USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_MINI_IOBOARD_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SPROG_II) },
+	{ USB_DEVICE(FTDI_VID, FTDI_TAGSYS_LP101_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_TAGSYS_P200X_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_LENZ_LIUSB_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_XF_632_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_XF_634_PID) },
@@ -904,6 +907,8 @@
 	/* Crucible Devices */
 	{ USB_DEVICE(FTDI_VID, FTDI_CT_COMET_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_Z3X_PID) },
+	/* Cressi Devices */
+	{ USB_DEVICE(FTDI_VID, FTDI_CRESSI_PID) },
 	{ }					/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index a7019d1..e599fbf 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -50,6 +50,7 @@
 #define TI_XDS100V2_PID		0xa6d0
 
 #define FTDI_NXTCAM_PID		0xABB8 /* NXTCam for Mindstorms NXT */
+#define FTDI_EV3CON_PID		0xABB9 /* Mindstorms EV3 Console Adapter */
 
 /* US Interface Navigator (http://www.usinterface.com/) */
 #define FTDI_USINT_CAT_PID	0xb810	/* Navigator CAT and 2nd PTT lines */
@@ -363,6 +364,12 @@
 /* Sprog II (Andrew Crosland's SprogII DCC interface) */
 #define FTDI_SPROG_II		0xF0C8
 
+/*
+ * Two of the Tagsys RFID Readers
+ */
+#define FTDI_TAGSYS_LP101_PID	0xF0E9	/* Tagsys L-P101 RFID*/
+#define FTDI_TAGSYS_P200X_PID	0xF0EE	/* Tagsys Medio P200x RFID*/
+
 /* an infrared receiver for user access control with IR tags */
 #define FTDI_PIEGROUP_PID	0xF208	/* Product Id */
 
@@ -1313,3 +1320,9 @@
  * Manufacturer: Smart GSM Team
  */
 #define FTDI_Z3X_PID		0x0011
+
+/*
+ * Product: Cressi PC Interface
+ * Manufacturer: Cressi
+ */
+#define FTDI_CRESSI_PID		0x87d0
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 5c86f57..68fc9fe 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1362,7 +1362,8 @@
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1267, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1268, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1269, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1270, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1270, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&net_intf5_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1271, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1272, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1273, 0xff, 0xff, 0xff) },
@@ -1525,7 +1526,8 @@
 	/* Cinterion */
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_E) },
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) },
-	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8) },
+	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX) },
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX),
 		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index c65437c..968a402 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -139,6 +139,9 @@
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 0)},	/* Sierra Wireless EM7700 Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 2)},	/* Sierra Wireless EM7700 NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 3)},	/* Sierra Wireless EM7700 Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)},	/* Netgear AirCard 340U Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)},	/* Netgear AirCard 340U NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)},	/* Netgear AirCard 340U Modem */
 
 	{ }				/* Terminating entry */
 };
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index f112b07..fb79775 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -71,7 +71,8 @@
 
 /* Suunto ANT+ USB Driver */
 #define SUUNTO_IDS()			\
-	{ USB_DEVICE(0x0fcf, 0x1008) }
+	{ USB_DEVICE(0x0fcf, 0x1008) },	\
+	{ USB_DEVICE(0x0fcf, 0x1009) } /* Dynastream ANT USB-m Stick */
 DEVICE(suunto, SUUNTO_IDS);
 
 /* Siemens USB/MPI adapter */
diff --git a/drivers/usb/storage/Kconfig b/drivers/usb/storage/Kconfig
index 8470e1b..1dd0604 100644
--- a/drivers/usb/storage/Kconfig
+++ b/drivers/usb/storage/Kconfig
@@ -18,7 +18,9 @@
 
 	  This option depends on 'SCSI' support being enabled, but you
 	  probably also need 'SCSI device support: SCSI disk support'
-	  (BLK_DEV_SD) for most USB storage devices.
+	  (BLK_DEV_SD) for most USB storage devices.  Some devices also
+	  will require 'Probe all LUNs on each SCSI device'
+	  (SCSI_MULTI_LUN).
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called usb-storage.
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 18509e6..9d38ddc 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -78,6 +78,8 @@
 
 static int slave_alloc (struct scsi_device *sdev)
 {
+	struct us_data *us = host_to_us(sdev->host);
+
 	/*
 	 * Set the INQUIRY transfer length to 36.  We don't use any of
 	 * the extra data and many devices choke if asked for more or
@@ -102,6 +104,10 @@
 	 */
 	blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1));
 
+	/* Tell the SCSI layer if we know there is more than one LUN */
+	if (us->protocol == USB_PR_BULK && us->max_lun > 0)
+		sdev->sdev_bflags |= BLIST_FORCELUN;
+
 	return 0;
 }
 
diff --git a/drivers/usb/storage/unusual_cypress.h b/drivers/usb/storage/unusual_cypress.h
index 65a6a75..82e8ed0 100644
--- a/drivers/usb/storage/unusual_cypress.h
+++ b/drivers/usb/storage/unusual_cypress.h
@@ -31,7 +31,7 @@
 		"Cypress ISD-300LP",
 		USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0),
 
-UNUSUAL_DEV( 0x14cd, 0x6116, 0x0000, 0x0219,
+UNUSUAL_DEV( 0x14cd, 0x6116, 0x0160, 0x0160,
 		"Super Top",
 		"USB 2.0  SATA BRIDGE",
 		USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0),
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index ad06255..adbeb25 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1455,6 +1455,13 @@
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_FIX_CAPACITY ),
 
+/* Reported by Moritz Moeller-Herrmann <moritz-kernel@moeller-herrmann.de> */
+UNUSUAL_DEV(  0x0fca, 0x8004, 0x0201, 0x0201,
+		"Research In Motion",
+		"BlackBerry Bold 9000",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_MAX_SECTORS_64 ),
+
 /* Reported by Michael Stattmann <michael@stattmann.com> */
 UNUSUAL_DEV(  0x0fce, 0xd008, 0x0000, 0x0000,
 		"Sony Ericsson",
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 4fb7a8f..54af4e9 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -186,12 +186,12 @@
 	if (pfn_valid(pfn)) {
 		bool reserved;
 		struct page *tail = pfn_to_page(pfn);
-		struct page *head = compound_trans_head(tail);
+		struct page *head = compound_head(tail);
 		reserved = !!(PageReserved(head));
 		if (head != tail) {
 			/*
 			 * "head" is not a dangling pointer
-			 * (compound_trans_head takes care of that)
+			 * (compound_head takes care of that)
 			 * but the hugepage may have been split
 			 * from under us (and we may not hold a
 			 * reference count on the head page so it can
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 9a68409..e1e22e0 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -70,7 +70,12 @@
 };
 
 struct vhost_net_ubuf_ref {
-	struct kref kref;
+	/* refcount follows semantics similar to kref:
+	 *  0: object is released
+	 *  1: no outstanding ubufs
+	 * >1: outstanding ubufs
+	 */
+	atomic_t refcount;
 	wait_queue_head_t wait;
 	struct vhost_virtqueue *vq;
 };
@@ -116,14 +121,6 @@
 	vhost_net_zcopy_mask |= 0x1 << vq;
 }
 
-static void vhost_net_zerocopy_done_signal(struct kref *kref)
-{
-	struct vhost_net_ubuf_ref *ubufs;
-
-	ubufs = container_of(kref, struct vhost_net_ubuf_ref, kref);
-	wake_up(&ubufs->wait);
-}
-
 static struct vhost_net_ubuf_ref *
 vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy)
 {
@@ -134,21 +131,24 @@
 	ubufs = kmalloc(sizeof(*ubufs), GFP_KERNEL);
 	if (!ubufs)
 		return ERR_PTR(-ENOMEM);
-	kref_init(&ubufs->kref);
+	atomic_set(&ubufs->refcount, 1);
 	init_waitqueue_head(&ubufs->wait);
 	ubufs->vq = vq;
 	return ubufs;
 }
 
-static void vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs)
+static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs)
 {
-	kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal);
+	int r = atomic_sub_return(1, &ubufs->refcount);
+	if (unlikely(!r))
+		wake_up(&ubufs->wait);
+	return r;
 }
 
 static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs)
 {
-	kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal);
-	wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount));
+	vhost_net_ubuf_put(ubufs);
+	wait_event(ubufs->wait, !atomic_read(&ubufs->refcount));
 }
 
 static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs)
@@ -306,23 +306,26 @@
 {
 	struct vhost_net_ubuf_ref *ubufs = ubuf->ctx;
 	struct vhost_virtqueue *vq = ubufs->vq;
-	int cnt = atomic_read(&ubufs->kref.refcount);
+	int cnt;
+
+	rcu_read_lock_bh();
 
 	/* set len to mark this desc buffers done DMA */
 	vq->heads[ubuf->desc].len = success ?
 		VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
-	vhost_net_ubuf_put(ubufs);
+	cnt = vhost_net_ubuf_put(ubufs);
 
 	/*
 	 * Trigger polling thread if guest stopped submitting new buffers:
-	 * in this case, the refcount after decrement will eventually reach 1
-	 * so here it is 2.
+	 * in this case, the refcount after decrement will eventually reach 1.
 	 * We also trigger polling periodically after each 16 packets
 	 * (the value 16 here is more or less arbitrary, it's tuned to trigger
 	 * less than 10% of times).
 	 */
-	if (cnt <= 2 || !(cnt % 16))
+	if (cnt <= 1 || !(cnt % 16))
 		vhost_poll_queue(&vq->poll);
+
+	rcu_read_unlock_bh();
 }
 
 /* Expects to be always run from workqueue - which acts as
@@ -420,7 +423,7 @@
 			msg.msg_control = ubuf;
 			msg.msg_controllen = sizeof(ubuf);
 			ubufs = nvq->ubufs;
-			kref_get(&ubufs->kref);
+			atomic_inc(&ubufs->refcount);
 			nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
 		} else {
 			msg.msg_control = NULL;
@@ -502,9 +505,13 @@
 			r = -ENOBUFS;
 			goto err;
 		}
-		d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+		r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
 				      ARRAY_SIZE(vq->iov) - seg, &out,
 				      &in, log, log_num);
+		if (unlikely(r < 0))
+			goto err;
+
+		d = r;
 		if (d == vq->num) {
 			r = 0;
 			goto err;
@@ -529,6 +536,12 @@
 	*iovcount = seg;
 	if (unlikely(log))
 		*log_num = nlogs;
+
+	/* Detect overrun */
+	if (unlikely(datalen > 0)) {
+		r = UIO_MAXIOV + 1;
+		goto err;
+	}
 	return headcount;
 err:
 	vhost_discard_vq_desc(vq, headcount);
@@ -584,6 +597,14 @@
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
 			break;
+		/* On overrun, truncate and discard */
+		if (unlikely(headcount > UIO_MAXIOV)) {
+			msg.msg_iovlen = 1;
+			err = sock->ops->recvmsg(NULL, sock, &msg,
+						 1, MSG_DONTWAIT | MSG_TRUNC);
+			pr_debug("Discarded rx packet: len %zd\n", sock_len);
+			continue;
+		}
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
@@ -780,7 +801,7 @@
 		vhost_net_ubuf_put_and_wait(n->vqs[VHOST_NET_VQ_TX].ubufs);
 		mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex);
 		n->tx_flush = false;
-		kref_init(&n->vqs[VHOST_NET_VQ_TX].ubufs->kref);
+		atomic_set(&n->vqs[VHOST_NET_VQ_TX].ubufs->refcount, 1);
 		mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex);
 	}
 }
@@ -800,6 +821,8 @@
 		fput(tx_sock->file);
 	if (rx_sock)
 		fput(rx_sock->file);
+	/* Make sure no callbacks are outstanding */
+	synchronize_rcu_bh();
 	/* We do an extra flush before freeing memory,
 	 * since jobs can re-queue themselves. */
 	vhost_net_flush(n);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 0a025b8..e48d4a6 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1001,6 +1001,12 @@
 			break;
 		}
 
+		/* virtio-scsi spec requires byte 0 of the lun to be 1 */
+		if (unlikely(v_req.lun[0] != 1)) {
+			vhost_scsi_send_bad_target(vs, vq, head, out);
+			continue;
+		}
+
 		/* Extract the tpgt */
 		target = v_req.lun[1];
 		tpg = ACCESS_ONCE(vs_tpg[target]);
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 22262a3..dade5b7 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -364,7 +364,7 @@
 
 config FB_IMX
 	tristate "Freescale i.MX1/21/25/27 LCD support"
-	depends on FB && IMX_HAVE_PLATFORM_IMX_FB
+	depends on FB && ARCH_MXC
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
diff --git a/drivers/video/console/sticore.c b/drivers/video/console/sticore.c
index 4ad24f2..cecd3de 100644
--- a/drivers/video/console/sticore.c
+++ b/drivers/video/console/sticore.c
@@ -488,7 +488,7 @@
 	return 0;
 }
 
-#ifdef CONFIG_FONTS
+#ifdef CONFIG_FONT_SUPPORT
 static struct sti_cooked_font *
 sti_select_fbfont(struct sti_cooked_rom *cooked_rom, const char *fbfont_name)
 {
diff --git a/drivers/video/exynos/Kconfig b/drivers/video/exynos/Kconfig
index 1129d0e..75c8a8e 100644
--- a/drivers/video/exynos/Kconfig
+++ b/drivers/video/exynos/Kconfig
@@ -22,7 +22,8 @@
 
 config EXYNOS_LCD_S6E8AX0
 	bool "S6E8AX0 MIPI AMOLED LCD Driver"
-	depends on (EXYNOS_MIPI_DSI && BACKLIGHT_CLASS_DEVICE && LCD_CLASS_DEVICE)
+	depends on EXYNOS_MIPI_DSI && BACKLIGHT_CLASS_DEVICE
+	depends on (LCD_CLASS_DEVICE = y)
 	default n
 	help
 	  If you have an S6E8AX0 MIPI AMOLED LCD Panel, say Y to enable its
diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c
index bbeb8dd..77d6221 100644
--- a/drivers/video/omap2/dss/dispc.c
+++ b/drivers/video/omap2/dss/dispc.c
@@ -2160,8 +2160,8 @@
 	*five_taps = false;
 
 	do {
-		in_height = DIV_ROUND_UP(height, *decim_y);
-		in_width = DIV_ROUND_UP(width, *decim_x);
+		in_height = height / *decim_y;
+		in_width = width / *decim_x;
 		*core_clk = dispc.feat->calc_core_clk(pclk, in_width,
 				in_height, out_width, out_height, mem_to_mem);
 		error = (in_width > maxsinglelinewidth || !*core_clk ||
@@ -2199,8 +2199,8 @@
 			dss_feat_get_param_max(FEAT_PARAM_LINEWIDTH);
 
 	do {
-		in_height = DIV_ROUND_UP(height, *decim_y);
-		in_width = DIV_ROUND_UP(width, *decim_x);
+		in_height = height / *decim_y;
+		in_width = width / *decim_x;
 		*five_taps = in_height > out_height;
 
 		if (in_width > maxsinglelinewidth)
@@ -2268,7 +2268,7 @@
 {
 	u16 in_width, in_width_max;
 	int decim_x_min = *decim_x;
-	u16 in_height = DIV_ROUND_UP(height, *decim_y);
+	u16 in_height = height / *decim_y;
 	const int maxsinglelinewidth =
 				dss_feat_get_param_max(FEAT_PARAM_LINEWIDTH);
 	const int maxdownscale = dss_feat_get_param_max(FEAT_PARAM_DOWNSCALE);
@@ -2287,7 +2287,7 @@
 		return -EINVAL;
 
 	do {
-		in_width = DIV_ROUND_UP(width, *decim_x);
+		in_width = width / *decim_x;
 	} while (*decim_x <= *x_predecim &&
 			in_width > maxsinglelinewidth && ++*decim_x);
 
@@ -2466,8 +2466,8 @@
 	if (r)
 		return r;
 
-	in_width = DIV_ROUND_UP(in_width, x_predecim);
-	in_height = DIV_ROUND_UP(in_height, y_predecim);
+	in_width = in_width / x_predecim;
+	in_height = in_height / y_predecim;
 
 	if (color_mode == OMAP_DSS_COLOR_YUV2 ||
 			color_mode == OMAP_DSS_COLOR_UYVY ||
diff --git a/drivers/video/omap2/dss/dpi.c b/drivers/video/omap2/dss/dpi.c
index 7411f26..23ef21f 100644
--- a/drivers/video/omap2/dss/dpi.c
+++ b/drivers/video/omap2/dss/dpi.c
@@ -117,7 +117,7 @@
 	/* outputs */
 
 	struct dsi_clock_info dsi_cinfo;
-	unsigned long long fck;
+	unsigned long fck;
 	struct dispc_clock_info dispc_cinfo;
 };
 
diff --git a/drivers/video/omap2/dss/sdi.c b/drivers/video/omap2/dss/sdi.c
index efb9ee9..ba806c9 100644
--- a/drivers/video/omap2/dss/sdi.c
+++ b/drivers/video/omap2/dss/sdi.c
@@ -46,7 +46,7 @@
 struct sdi_clk_calc_ctx {
 	unsigned long pck_min, pck_max;
 
-	unsigned long long fck;
+	unsigned long fck;
 	struct dispc_clock_info dispc_cinfo;
 };
 
diff --git a/drivers/vme/bridges/vme_ca91cx42.c b/drivers/vme/bridges/vme_ca91cx42.c
index a06edbf..1b5d48c 100644
--- a/drivers/vme/bridges/vme_ca91cx42.c
+++ b/drivers/vme/bridges/vme_ca91cx42.c
@@ -884,7 +884,7 @@
 		if (done == count)
 			goto out;
 	}
-	if ((uintptr_t)addr & 0x2) {
+	if ((uintptr_t)(addr + done) & 0x2) {
 		if ((count - done) < 2) {
 			*(u8 *)(buf + done) = ioread8(addr + done);
 			done += 1;
@@ -938,7 +938,7 @@
 		if (done == count)
 			goto out;
 	}
-	if ((uintptr_t)addr & 0x2) {
+	if ((uintptr_t)(addr + done) & 0x2) {
 		if ((count - done) < 2) {
 			iowrite8(*(u8 *)(buf + done), addr + done);
 			done += 1;
diff --git a/drivers/vme/bridges/vme_tsi148.c b/drivers/vme/bridges/vme_tsi148.c
index 16830d8..9911cd5 100644
--- a/drivers/vme/bridges/vme_tsi148.c
+++ b/drivers/vme/bridges/vme_tsi148.c
@@ -1289,7 +1289,7 @@
 		if (done == count)
 			goto out;
 	}
-	if ((uintptr_t)addr & 0x2) {
+	if ((uintptr_t)(addr + done) & 0x2) {
 		if ((count - done) < 2) {
 			*(u8 *)(buf + done) = ioread8(addr + done);
 			done += 1;
@@ -1371,7 +1371,7 @@
 		if (done == count)
 			goto out;
 	}
-	if ((uintptr_t)addr & 0x2) {
+	if ((uintptr_t)(addr + done) & 0x2) {
 		if ((count - done) < 2) {
 			iowrite8(*(u8 *)(buf + done), addr + done);
 			done += 1;
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 4c4c566..79d2589 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -223,6 +223,7 @@
 
 config DW_WATCHDOG
 	tristate "Synopsys DesignWare watchdog"
+	depends on HAS_IOMEM
 	help
 	  Say Y here if to include support for the Synopsys DesignWare
 	  watchdog timer found in many chips.
diff --git a/drivers/watchdog/w83697hf_wdt.c b/drivers/watchdog/w83697hf_wdt.c
index aaf2995..68b45fc 100644
--- a/drivers/watchdog/w83697hf_wdt.c
+++ b/drivers/watchdog/w83697hf_wdt.c
@@ -402,7 +402,7 @@
 
 	if (!found) {
 		pr_err("No W83697HF/HG could be found\n");
-		ret = -EIO;
+		ret = -ENODEV;
 		goto out;
 	}
 
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index d75c811..45e00af 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -16,7 +16,6 @@
 dom0-$(CONFIG_X86) += pcpu.o
 obj-$(CONFIG_XEN_DOM0)			+= $(dom0-y)
 obj-$(CONFIG_BLOCK)			+= biomerge.o
-obj-$(CONFIG_XEN_XENCOMM)		+= xencomm.o
 obj-$(CONFIG_XEN_BALLOON)		+= xen-balloon.o
 obj-$(CONFIG_XEN_SELFBALLOONING)	+= xen-selfballoon.o
 obj-$(CONFIG_XEN_DEV_EVTCHN)		+= xen-evtchn.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 37d06ea..61a6ac8 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -399,12 +399,26 @@
 			state = BP_EAGAIN;
 			break;
 		}
-
-		pfn = page_to_pfn(page);
-		frame_list[i] = pfn_to_mfn(pfn);
-
 		scrub_page(page);
 
+		frame_list[i] = page_to_pfn(page);
+	}
+
+	/*
+	 * Ensure that ballooned highmem pages don't have kmaps.
+	 *
+	 * Do this before changing the p2m as kmap_flush_unused()
+	 * reads PTEs to obtain pages (and hence needs the original
+	 * p2m entry).
+	 */
+	kmap_flush_unused();
+
+	/* Update direct mapping, invalidate P2M, and add to balloon. */
+	for (i = 0; i < nr_pages; i++) {
+		pfn = frame_list[i];
+		frame_list[i] = pfn_to_mfn(pfn);
+		page = pfn_to_page(pfn);
+
 #ifdef CONFIG_XEN_HAVE_PVMMU
 		/*
 		 * Ballooned out frames are effectively replaced with
@@ -429,11 +443,9 @@
 		}
 #endif
 
-		balloon_append(pfn_to_page(pfn));
+		balloon_append(page);
 	}
 
-	/* Ensure that ballooned highmem pages don't have kmaps. */
-	kmap_flush_unused();
 	flush_tlb_all();
 
 	set_xen_guest_handle(reservation.extent_start, frame_list);
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 4672e00..f4a9e33 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -862,6 +862,8 @@
 			irq = ret;
 			goto out;
 		}
+		/* New interdomain events are bound to VCPU 0. */
+		bind_evtchn_to_cpu(evtchn, 0);
 	} else {
 		struct irq_info *info = info_for_irq(irq);
 		WARN_ON(info == NULL || info->type != IRQT_EVTCHN);
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 34a2704..073b4a1 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -284,10 +284,8 @@
 	}
 
 	pr_debug("map %d+%d\n", map->index, map->count);
-	err = gnttab_map_refs_userspace(map->map_ops,
-					use_ptemod ? map->kmap_ops : NULL,
-					map->pages,
-					map->count);
+	err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL,
+			map->pages, map->count);
 	if (err)
 		return err;
 
@@ -317,10 +315,9 @@
 		}
 	}
 
-	err = gnttab_unmap_refs_userspace(map->unmap_ops + offset,
-					  use_ptemod ? map->kmap_ops + offset : NULL,
-					  map->pages + offset,
-					  pages);
+	err = gnttab_unmap_refs(map->unmap_ops + offset,
+			use_ptemod ? map->kmap_ops + offset : NULL, map->pages + offset,
+			pages);
 	if (err)
 		return err;
 
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 8ee13e2..b84e3ab 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -928,17 +928,15 @@
 }
 EXPORT_SYMBOL_GPL(gnttab_batch_copy);
 
-int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
+int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		    struct gnttab_map_grant_ref *kmap_ops,
-		    struct page **pages, unsigned int count,
-		    bool m2p_override)
+		    struct page **pages, unsigned int count)
 {
 	int i, ret;
 	bool lazy = false;
 	pte_t *pte;
-	unsigned long mfn, pfn;
+	unsigned long mfn;
 
-	BUG_ON(kmap_ops && !m2p_override);
 	ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count);
 	if (ret)
 		return ret;
@@ -957,12 +955,10 @@
 			set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT,
 					map_ops[i].dev_bus_addr >> PAGE_SHIFT);
 		}
-		return 0;
+		return ret;
 	}
 
-	if (m2p_override &&
-	    !in_interrupt() &&
-	    paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
+	if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
 		arch_enter_lazy_mmu_mode();
 		lazy = true;
 	}
@@ -979,20 +975,8 @@
 		} else {
 			mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
 		}
-		pfn = page_to_pfn(pages[i]);
-
-		WARN_ON(PagePrivate(pages[i]));
-		SetPagePrivate(pages[i]);
-		set_page_private(pages[i], mfn);
-
-		pages[i]->index = pfn_to_mfn(pfn);
-		if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		if (m2p_override)
-			ret = m2p_add_override(mfn, pages[i], kmap_ops ?
-					       &kmap_ops[i] : NULL);
+		ret = m2p_add_override(mfn, pages[i], kmap_ops ?
+				       &kmap_ops[i] : NULL);
 		if (ret)
 			goto out;
 	}
@@ -1003,32 +987,15 @@
 
 	return ret;
 }
-
-int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
-		    struct page **pages, unsigned int count)
-{
-	return __gnttab_map_refs(map_ops, NULL, pages, count, false);
-}
 EXPORT_SYMBOL_GPL(gnttab_map_refs);
 
-int gnttab_map_refs_userspace(struct gnttab_map_grant_ref *map_ops,
-			      struct gnttab_map_grant_ref *kmap_ops,
-			      struct page **pages, unsigned int count)
-{
-	return __gnttab_map_refs(map_ops, kmap_ops, pages, count, true);
-}
-EXPORT_SYMBOL_GPL(gnttab_map_refs_userspace);
-
-int __gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
+int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 		      struct gnttab_map_grant_ref *kmap_ops,
-		      struct page **pages, unsigned int count,
-		      bool m2p_override)
+		      struct page **pages, unsigned int count)
 {
 	int i, ret;
 	bool lazy = false;
-	unsigned long pfn, mfn;
 
-	BUG_ON(kmap_ops && !m2p_override);
 	ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count);
 	if (ret)
 		return ret;
@@ -1039,33 +1006,17 @@
 			set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT,
 					INVALID_P2M_ENTRY);
 		}
-		return 0;
+		return ret;
 	}
 
-	if (m2p_override &&
-	    !in_interrupt() &&
-	    paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
+	if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
 		arch_enter_lazy_mmu_mode();
 		lazy = true;
 	}
 
 	for (i = 0; i < count; i++) {
-		pfn = page_to_pfn(pages[i]);
-		mfn = get_phys_to_machine(pfn);
-		if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		set_page_private(pages[i], INVALID_P2M_ENTRY);
-		WARN_ON(!PagePrivate(pages[i]));
-		ClearPagePrivate(pages[i]);
-		set_phys_to_machine(pfn, pages[i]->index);
-		if (m2p_override)
-			ret = m2p_remove_override(pages[i],
-						  kmap_ops ?
-						   &kmap_ops[i] : NULL,
-						  mfn);
+		ret = m2p_remove_override(pages[i], kmap_ops ?
+				       &kmap_ops[i] : NULL);
 		if (ret)
 			goto out;
 	}
@@ -1076,22 +1027,8 @@
 
 	return ret;
 }
-
-int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *map_ops,
-		    struct page **pages, unsigned int count)
-{
-	return __gnttab_unmap_refs(map_ops, NULL, pages, count, false);
-}
 EXPORT_SYMBOL_GPL(gnttab_unmap_refs);
 
-int gnttab_unmap_refs_userspace(struct gnttab_unmap_grant_ref *map_ops,
-				struct gnttab_map_grant_ref *kmap_ops,
-				struct page **pages, unsigned int count)
-{
-	return __gnttab_unmap_refs(map_ops, kmap_ops, pages, count, true);
-}
-EXPORT_SYMBOL_GPL(gnttab_unmap_refs_userspace);
-
 static unsigned nr_status_frames(unsigned nr_grant_frames)
 {
 	BUG_ON(grefs_per_grant_frame == 0);
diff --git a/drivers/xen/xencomm.c b/drivers/xen/xencomm.c
deleted file mode 100644
index 4793fc5..0000000
--- a/drivers/xen/xencomm.c
+++ /dev/null
@@ -1,219 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
- * Copyright (C) IBM Corp. 2006
- *
- * Authors: Hollis Blanchard <hollisb@us.ibm.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include <asm/page.h>
-#include <xen/xencomm.h>
-#include <xen/interface/xen.h>
-#include <asm/xen/xencomm.h>	/* for xencomm_is_phys_contiguous() */
-
-static int xencomm_init(struct xencomm_desc *desc,
-			void *buffer, unsigned long bytes)
-{
-	unsigned long recorded = 0;
-	int i = 0;
-
-	while ((recorded < bytes) && (i < desc->nr_addrs)) {
-		unsigned long vaddr = (unsigned long)buffer + recorded;
-		unsigned long paddr;
-		int offset;
-		int chunksz;
-
-		offset = vaddr % PAGE_SIZE; /* handle partial pages */
-		chunksz = min(PAGE_SIZE - offset, bytes - recorded);
-
-		paddr = xencomm_vtop(vaddr);
-		if (paddr == ~0UL) {
-			printk(KERN_DEBUG "%s: couldn't translate vaddr %lx\n",
-			       __func__, vaddr);
-			return -EINVAL;
-		}
-
-		desc->address[i++] = paddr;
-		recorded += chunksz;
-	}
-
-	if (recorded < bytes) {
-		printk(KERN_DEBUG
-		       "%s: could only translate %ld of %ld bytes\n",
-		       __func__, recorded, bytes);
-		return -ENOSPC;
-	}
-
-	/* mark remaining addresses invalid (just for safety) */
-	while (i < desc->nr_addrs)
-		desc->address[i++] = XENCOMM_INVALID;
-
-	desc->magic = XENCOMM_MAGIC;
-
-	return 0;
-}
-
-static struct xencomm_desc *xencomm_alloc(gfp_t gfp_mask,
-					  void *buffer, unsigned long bytes)
-{
-	struct xencomm_desc *desc;
-	unsigned long buffer_ulong = (unsigned long)buffer;
-	unsigned long start = buffer_ulong & PAGE_MASK;
-	unsigned long end = (buffer_ulong + bytes) | ~PAGE_MASK;
-	unsigned long nr_addrs = (end - start + 1) >> PAGE_SHIFT;
-	unsigned long size = sizeof(*desc) +
-		sizeof(desc->address[0]) * nr_addrs;
-
-	/*
-	 * slab allocator returns at least sizeof(void*) aligned pointer.
-	 * When sizeof(*desc) > sizeof(void*), struct xencomm_desc might
-	 * cross page boundary.
-	 */
-	if (sizeof(*desc) > sizeof(void *)) {
-		unsigned long order = get_order(size);
-		desc = (struct xencomm_desc *)__get_free_pages(gfp_mask,
-							       order);
-		if (desc == NULL)
-			return NULL;
-
-		desc->nr_addrs =
-			((PAGE_SIZE << order) - sizeof(struct xencomm_desc)) /
-			sizeof(*desc->address);
-	} else {
-		desc = kmalloc(size, gfp_mask);
-		if (desc == NULL)
-			return NULL;
-
-		desc->nr_addrs = nr_addrs;
-	}
-	return desc;
-}
-
-void xencomm_free(struct xencomm_handle *desc)
-{
-	if (desc && !((ulong)desc & XENCOMM_INLINE_FLAG)) {
-		struct xencomm_desc *desc__ = (struct xencomm_desc *)desc;
-		if (sizeof(*desc__) > sizeof(void *)) {
-			unsigned long size = sizeof(*desc__) +
-				sizeof(desc__->address[0]) * desc__->nr_addrs;
-			unsigned long order = get_order(size);
-			free_pages((unsigned long)__va(desc), order);
-		} else
-			kfree(__va(desc));
-	}
-}
-
-static int xencomm_create(void *buffer, unsigned long bytes,
-			  struct xencomm_desc **ret, gfp_t gfp_mask)
-{
-	struct xencomm_desc *desc;
-	int rc;
-
-	pr_debug("%s: %p[%ld]\n", __func__, buffer, bytes);
-
-	if (bytes == 0) {
-		/* don't create a descriptor; Xen recognizes NULL. */
-		BUG_ON(buffer != NULL);
-		*ret = NULL;
-		return 0;
-	}
-
-	BUG_ON(buffer == NULL); /* 'bytes' is non-zero */
-
-	desc = xencomm_alloc(gfp_mask, buffer, bytes);
-	if (!desc) {
-		printk(KERN_DEBUG "%s failure\n", "xencomm_alloc");
-		return -ENOMEM;
-	}
-
-	rc = xencomm_init(desc, buffer, bytes);
-	if (rc) {
-		printk(KERN_DEBUG "%s failure: %d\n", "xencomm_init", rc);
-		xencomm_free((struct xencomm_handle *)__pa(desc));
-		return rc;
-	}
-
-	*ret = desc;
-	return 0;
-}
-
-static struct xencomm_handle *xencomm_create_inline(void *ptr)
-{
-	unsigned long paddr;
-
-	BUG_ON(!xencomm_is_phys_contiguous((unsigned long)ptr));
-
-	paddr = (unsigned long)xencomm_pa(ptr);
-	BUG_ON(paddr & XENCOMM_INLINE_FLAG);
-	return (struct xencomm_handle *)(paddr | XENCOMM_INLINE_FLAG);
-}
-
-/* "mini" routine, for stack-based communications: */
-static int xencomm_create_mini(void *buffer,
-	unsigned long bytes, struct xencomm_mini *xc_desc,
-	struct xencomm_desc **ret)
-{
-	int rc = 0;
-	struct xencomm_desc *desc;
-	BUG_ON(((unsigned long)xc_desc) % sizeof(*xc_desc) != 0);
-
-	desc = (void *)xc_desc;
-
-	desc->nr_addrs = XENCOMM_MINI_ADDRS;
-
-	rc = xencomm_init(desc, buffer, bytes);
-	if (!rc)
-		*ret = desc;
-
-	return rc;
-}
-
-struct xencomm_handle *xencomm_map(void *ptr, unsigned long bytes)
-{
-	int rc;
-	struct xencomm_desc *desc;
-
-	if (xencomm_is_phys_contiguous((unsigned long)ptr))
-		return xencomm_create_inline(ptr);
-
-	rc = xencomm_create(ptr, bytes, &desc, GFP_KERNEL);
-
-	if (rc || desc == NULL)
-		return NULL;
-
-	return xencomm_pa(desc);
-}
-
-struct xencomm_handle *__xencomm_map_no_alloc(void *ptr, unsigned long bytes,
-			struct xencomm_mini *xc_desc)
-{
-	int rc;
-	struct xencomm_desc *desc = NULL;
-
-	if (xencomm_is_phys_contiguous((unsigned long)ptr))
-		return xencomm_create_inline(ptr);
-
-	rc = xencomm_create_mini(ptr, bytes, xc_desc,
-				&desc);
-
-	if (rc)
-		return NULL;
-
-	return xencomm_pa(desc);
-}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 6621f80..be75b50 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -75,6 +75,7 @@
 	const struct afs_call_type *type;	/* type of call */
 	const struct afs_wait_mode *wait_mode;	/* completion wait mode */
 	wait_queue_head_t	waitq;		/* processes awaiting completion */
+	work_func_t		async_workfn;
 	struct work_struct	async_work;	/* asynchronous work processor */
 	struct work_struct	work;		/* actual work processor */
 	struct sk_buff_head	rx_queue;	/* received packets */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 8ad8c2a..ef943df 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -644,7 +644,7 @@
 
 		/* we can't just delete the call because the work item may be
 		 * queued */
-		PREPARE_WORK(&call->async_work, afs_delete_async_call);
+		call->async_workfn = afs_delete_async_call;
 		queue_work(afs_async_calls, &call->async_work);
 	}
 
@@ -663,6 +663,13 @@
 	call->reply_size += len;
 }
 
+static void afs_async_workfn(struct work_struct *work)
+{
+	struct afs_call *call = container_of(work, struct afs_call, async_work);
+
+	call->async_workfn(work);
+}
+
 /*
  * accept the backlog of incoming calls
  */
@@ -685,7 +692,8 @@
 				return;
 			}
 
-			INIT_WORK(&call->async_work, afs_process_async_call);
+			call->async_workfn = afs_process_async_call;
+			INIT_WORK(&call->async_work, afs_async_workfn);
 			call->wait_mode = &afs_async_incoming_call;
 			call->type = &afs_RXCMxxxx;
 			init_waitqueue_head(&call->waitq);
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 2408473..80ef38c 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -41,19 +41,8 @@
 static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
 				int flags, const char *dev_name, void *data)
 {
-	struct dentry *root;
-	root = mount_pseudo(fs_type, "anon_inode:", NULL,
+	return mount_pseudo(fs_type, "anon_inode:", NULL,
 			&anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC);
-	if (!IS_ERR(root)) {
-		struct super_block *s = root->d_sb;
-		anon_inode_inode = alloc_anon_inode(s);
-		if (IS_ERR(anon_inode_inode)) {
-			dput(root);
-			deactivate_locked_super(s);
-			root = ERR_CAST(anon_inode_inode);
-		}
-	}
-	return root;
 }
 
 static struct file_system_type anon_inode_fs_type = {
@@ -175,22 +164,15 @@
 
 static int __init anon_inode_init(void)
 {
-	int error;
-
-	error = register_filesystem(&anon_inode_fs_type);
-	if (error)
-		goto err_exit;
 	anon_inode_mnt = kern_mount(&anon_inode_fs_type);
-	if (IS_ERR(anon_inode_mnt)) {
-		error = PTR_ERR(anon_inode_mnt);
-		goto err_unregister_filesystem;
-	}
-	return 0;
+	if (IS_ERR(anon_inode_mnt))
+		panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt));
 
-err_unregister_filesystem:
-	unregister_filesystem(&anon_inode_fs_type);
-err_exit:
-	panic(KERN_ERR "anon_inode_init() failed (%d)\n", error);
+	anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb);
+	if (IS_ERR(anon_inode_inode))
+		panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode));
+
+	return 0;
 }
 
 fs_initcall(anon_inode_init);
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 0bad24d..4f70f38 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -114,6 +114,14 @@
 }
 EXPORT_SYMBOL(bio_integrity_free);
 
+static inline unsigned int bip_integrity_vecs(struct bio_integrity_payload *bip)
+{
+	if (bip->bip_slab == BIO_POOL_NONE)
+		return BIP_INLINE_VECS;
+
+	return bvec_nr_vecs(bip->bip_slab);
+}
+
 /**
  * bio_integrity_add_page - Attach integrity metadata
  * @bio:	bio to update
@@ -129,7 +137,7 @@
 	struct bio_integrity_payload *bip = bio->bi_integrity;
 	struct bio_vec *iv;
 
-	if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) {
+	if (bip->bip_vcnt >= bip_integrity_vecs(bip)) {
 		printk(KERN_ERR "%s: bip_vec full\n", __func__);
 		return 0;
 	}
@@ -226,7 +234,8 @@
 }
 EXPORT_SYMBOL(bio_integrity_tag_size);
 
-int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len, int set)
+static int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len,
+			     int set)
 {
 	struct bio_integrity_payload *bip = bio->bi_integrity;
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
@@ -449,11 +458,10 @@
 	struct blk_integrity_exchg bix;
 	struct bio_vec *bv;
 	sector_t sector = bio->bi_integrity->bip_iter.bi_sector;
-	unsigned int sectors, total, ret;
+	unsigned int sectors, ret = 0;
 	void *prot_buf = bio->bi_integrity->bip_buf;
 	int i;
 
-	ret = total = 0;
 	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
 	bix.sector_size = bi->sector_size;
 
@@ -475,8 +483,6 @@
 		sectors = bv->bv_len / bi->sector_size;
 		sector += sectors;
 		prot_buf += sectors * bi->tuple_size;
-		total += sectors * bi->tuple_size;
-		BUG_ON(total > bio->bi_integrity->bip_iter.bi_size);
 
 		kunmap_atomic(kaddr);
 	}
diff --git a/fs/bio.c b/fs/bio.c
index 75c49a3..8754e7b 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -611,7 +611,6 @@
 struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 			     struct bio_set *bs)
 {
-	unsigned nr_iovecs = 0;
 	struct bvec_iter iter;
 	struct bio_vec bv;
 	struct bio *bio;
@@ -638,10 +637,7 @@
 	 *    __bio_clone_fast() anyways.
 	 */
 
-	bio_for_each_segment(bv, bio_src, iter)
-		nr_iovecs++;
-
-	bio = bio_alloc_bioset(gfp_mask, nr_iovecs, bs);
+	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
 	if (!bio)
 		return NULL;
 
@@ -650,9 +646,18 @@
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
+	if (bio->bi_rw & REQ_DISCARD)
+		goto integrity_clone;
+
+	if (bio->bi_rw & REQ_WRITE_SAME) {
+		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
+		goto integrity_clone;
+	}
+
 	bio_for_each_segment(bv, bio_src, iter)
 		bio->bi_io_vec[bio->bi_vcnt++] = bv;
 
+integrity_clone:
 	if (bio_integrity(bio_src)) {
 		int ret;
 
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 49a62b4..0e8388e 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -92,11 +92,11 @@
 #include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include <linux/mutex.h>
-#include <linux/crc32c.h>
 #include <linux/genhd.h>
 #include <linux/blkdev.h>
 #include "ctree.h"
 #include "disk-io.h"
+#include "hash.h"
 #include "transaction.h"
 #include "extent_io.h"
 #include "volumes.h"
@@ -1823,7 +1823,7 @@
 		size_t sublen = i ? PAGE_CACHE_SIZE :
 				    (PAGE_CACHE_SIZE - BTRFS_CSUM_SIZE);
 
-		crc = crc32c(crc, data, sublen);
+		crc = btrfs_crc32c(crc, data, sublen);
 	}
 	btrfs_csum_final(crc, csum);
 	if (memcmp(csum, h->csum, state->csum_size))
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index e2600cd..b01fb6c 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1010,6 +1010,8 @@
 		bytes = min(bytes, working_bytes);
 		kaddr = kmap_atomic(page_out);
 		memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
+		if (*pg_index == (vcnt - 1) && *pg_offset == 0)
+			memset(kaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
 		kunmap_atomic(kaddr);
 		flush_dcache_page(page_out);
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 0e69295..81ea553 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -26,7 +26,6 @@
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
-#include <linux/crc32c.h>
 #include <linux/slab.h>
 #include <linux/migrate.h>
 #include <linux/ratelimit.h>
@@ -35,6 +34,7 @@
 #include <asm/unaligned.h>
 #include "ctree.h"
 #include "disk-io.h"
+#include "hash.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
 #include "volumes.h"
@@ -244,7 +244,7 @@
 
 u32 btrfs_csum_data(char *data, u32 seed, size_t len)
 {
-	return crc32c(seed, data, len);
+	return btrfs_crc32c(seed, data, len);
 }
 
 void btrfs_csum_final(u32 crc, char *result)
@@ -3839,7 +3839,6 @@
 			rb_erase(&ref->rb_node, &head->ref_root);
 			atomic_dec(&delayed_refs->num_entries);
 			btrfs_put_delayed_ref(ref);
-			cond_resched_lock(&head->lock);
 		}
 		if (head->must_insert_reserved)
 			pin_bytes = true;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9c9ecc9..32312e0 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2385,6 +2385,7 @@
 			spin_unlock(&delayed_refs->lock);
 			locked_ref = NULL;
 			cond_resched();
+			count++;
 			continue;
 		}
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5c4ab9c..d3d4448 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2629,7 +2629,7 @@
 			EXTENT_DEFRAG, 1, cached_state);
 	if (ret) {
 		u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
-		if (last_snapshot >= BTRFS_I(inode)->generation)
+		if (0 && last_snapshot >= BTRFS_I(inode)->generation)
 			/* the inode is shared */
 			new = record_old_file_extents(inode, ordered_extent);
 
@@ -5154,7 +5154,7 @@
 			return ERR_CAST(inode);
 	}
 
-	return d_splice_alias(inode, dentry);
+	return d_materialise_unique(dentry, inode);
 }
 
 unsigned char btrfs_filetype_table[] = {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index b013489..a6d8efa 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3537,20 +3537,6 @@
 	return ret;
 }
 
-static long btrfs_ioctl_global_rsv(struct btrfs_root *root, void __user *arg)
-{
-	struct btrfs_block_rsv *block_rsv = &root->fs_info->global_block_rsv;
-	u64 reserved;
-
-	spin_lock(&block_rsv->lock);
-	reserved = block_rsv->reserved;
-	spin_unlock(&block_rsv->lock);
-
-	if (arg && copy_to_user(arg, &reserved, sizeof(reserved)))
-		return -EFAULT;
-	return 0;
-}
-
 /*
  * there are many ways the trans_start and trans_end ioctls can lead
  * to deadlocks.  They should only be used by applications that
@@ -4525,7 +4511,7 @@
 	spin_lock(&root->fs_info->super_lock);
 	strcpy(super_block->label, label);
 	spin_unlock(&root->fs_info->super_lock);
-	ret = btrfs_end_transaction(trans, root);
+	ret = btrfs_commit_transaction(trans, root);
 
 out_unlock:
 	mnt_drop_write_file(file);
@@ -4668,7 +4654,7 @@
 	if (ret)
 		return ret;
 
-	trans = btrfs_start_transaction(root, 1);
+	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
@@ -4689,7 +4675,7 @@
 	btrfs_set_super_incompat_flags(super_block, newflags);
 	spin_unlock(&root->fs_info->super_lock);
 
-	return btrfs_end_transaction(trans, root);
+	return btrfs_commit_transaction(trans, root);
 }
 
 long btrfs_ioctl(struct file *file, unsigned int
@@ -4757,8 +4743,6 @@
 		return btrfs_ioctl_logical_to_ino(root, argp);
 	case BTRFS_IOC_SPACE_INFO:
 		return btrfs_ioctl_space_info(root, argp);
-	case BTRFS_IOC_GLOBAL_RSV:
-		return btrfs_ioctl_global_rsv(root, argp);
 	case BTRFS_IOC_SYNC: {
 		int ret;
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 730dce3..9dde971 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -24,12 +24,12 @@
 #include <linux/xattr.h>
 #include <linux/posix_acl_xattr.h>
 #include <linux/radix-tree.h>
-#include <linux/crc32c.h>
 #include <linux/vmalloc.h>
 #include <linux/string.h>
 
 #include "send.h"
 #include "backref.h"
+#include "hash.h"
 #include "locking.h"
 #include "disk-io.h"
 #include "btrfs_inode.h"
@@ -620,7 +620,7 @@
 	hdr->len = cpu_to_le32(sctx->send_size - sizeof(*hdr));
 	hdr->crc = 0;
 
-	crc = crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size);
+	crc = btrfs_crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size);
 	hdr->crc = cpu_to_le32(crc);
 
 	ret = write_buf(sctx->send_filp, sctx->send_buf, sctx->send_size,
@@ -1332,6 +1332,16 @@
 	}
 
 	if (cur_clone_root) {
+		if (compressed != BTRFS_COMPRESS_NONE) {
+			/*
+			 * Offsets given by iterate_extent_inodes() are relative
+			 * to the start of the extent, we need to add logical
+			 * offset from the file extent item.
+			 * (See why at backref.c:check_extent_in_eb())
+			 */
+			cur_clone_root->offset += btrfs_file_extent_offset(eb,
+									   fi);
+		}
 		*found = cur_clone_root;
 		ret = 0;
 	} else {
@@ -2774,8 +2784,6 @@
 	return 0;
 }
 
-#ifdef CONFIG_BTRFS_ASSERT
-
 static int del_waiting_dir_move(struct send_ctx *sctx, u64 ino)
 {
 	struct rb_node *n = sctx->waiting_dir_moves.rb_node;
@@ -2796,8 +2804,6 @@
 	return -ENOENT;
 }
 
-#endif
-
 static int add_pending_dir_move(struct send_ctx *sctx, u64 parent_ino)
 {
 	struct rb_node **p = &sctx->pending_dir_moves.rb_node;
@@ -2902,7 +2908,9 @@
 	}
 
 	sctx->send_progress = sctx->cur_ino + 1;
-	ASSERT(del_waiting_dir_move(sctx, pm->ino) == 0);
+	ret = del_waiting_dir_move(sctx, pm->ino);
+	ASSERT(ret == 0);
+
 	ret = get_cur_path(sctx, pm->ino, pm->gen, to_path);
 	if (ret < 0)
 		goto out;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index c02f633..d04db81 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -566,7 +566,7 @@
 				kfree(num);
 
 				if (info->max_inline) {
-					info->max_inline = max_t(u64,
+					info->max_inline = min_t(u64,
 						info->max_inline,
 						root->sectorsize);
 				}
@@ -855,6 +855,7 @@
 	struct btrfs_path *path;
 	struct btrfs_key location;
 	struct inode *inode;
+	struct dentry *dentry;
 	u64 dir_id;
 	int new = 0;
 
@@ -925,7 +926,13 @@
 		return dget(sb->s_root);
 	}
 
-	return d_obtain_alias(inode);
+	dentry = d_obtain_alias(inode);
+	if (!IS_ERR(dentry)) {
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags &= ~DCACHE_DISCONNECTED;
+		spin_unlock(&dentry->d_lock);
+	}
+	return dentry;
 }
 
 static int btrfs_fill_super(struct super_block *sb,
@@ -1996,7 +2003,7 @@
 	btrfs_hash_exit();
 }
 
-module_init(init_btrfs_fs)
+late_initcall(init_btrfs_fs);
 module_exit(exit_btrfs_fs)
 
 MODULE_LICENSE("GPL");
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 782374d..865f4cf 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -578,8 +578,14 @@
 		return -ENOMEM;
 
 	list_for_each_entry(dev, &fs_devices->devices, dev_list) {
-		struct hd_struct *disk = dev->bdev->bd_part;
-		struct kobject *disk_kobj = &part_to_dev(disk)->kobj;
+		struct hd_struct *disk;
+		struct kobject *disk_kobj;
+
+		if (!dev->bdev)
+			continue;
+
+		disk = dev->bdev->bd_part;
+		disk_kobj = &part_to_dev(disk)->kobj;
 
 		error = sysfs_create_link(fs_info->device_dir_kobj,
 					  disk_kobj, disk_kobj->name);
diff --git a/fs/buffer.c b/fs/buffer.c
index 651dba1..27265a8 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -654,14 +654,16 @@
 static void __set_page_dirty(struct page *page,
 		struct address_space *mapping, int warn)
 {
-	spin_lock_irq(&mapping->tree_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
 		account_page_dirtied(page, mapping);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
-	spin_unlock_irq(&mapping->tree_lock);
+	spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 }
 
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 4c2d452..21887d6 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -54,11 +54,6 @@
 	return acl;
 }
 
-void ceph_forget_all_cached_acls(struct inode *inode)
-{
-	forget_all_cached_acls(inode);
-}
-
 struct posix_acl *ceph_get_acl(struct inode *inode, int type)
 {
 	int size;
@@ -160,11 +155,7 @@
 			goto out_dput;
 	}
 
-	if (value)
-		ret = __ceph_setxattr(dentry, name, value, size, 0);
-	else
-		ret = __ceph_removexattr(dentry, name);
-
+	ret = __ceph_setxattr(dentry, name, value, size, 0);
 	if (ret) {
 		if (new_mode != old_mode) {
 			newattrs.ia_mode = old_mode;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 6da4df8..45eda6d 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -100,6 +100,14 @@
 	return p & 0xffffffff;
 }
 
+static int fpos_cmp(loff_t l, loff_t r)
+{
+	int v = ceph_frag_compare(fpos_frag(l), fpos_frag(r));
+	if (v)
+		return v;
+	return (int)(fpos_off(l) - fpos_off(r));
+}
+
 /*
  * When possible, we try to satisfy a readdir by peeking at the
  * dcache.  We make this work by carefully ordering dentries on
@@ -156,7 +164,7 @@
 		if (!d_unhashed(dentry) && dentry->d_inode &&
 		    ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
 		    ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
-		    ctx->pos <= di->offset)
+		    fpos_cmp(ctx->pos, di->offset) <= 0)
 			break;
 		dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry,
 		     dentry->d_name.len, dentry->d_name.name, di->offset,
@@ -695,9 +703,8 @@
 	ceph_mdsc_put_request(req);
 
 	if (!err)
-		err = ceph_init_acl(dentry, dentry->d_inode, dir);
-
-	if (err)
+		ceph_init_acl(dentry, dentry->d_inode, dir);
+	else
 		d_drop(dentry);
 	return err;
 }
@@ -735,7 +742,9 @@
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
 	ceph_mdsc_put_request(req);
-	if (err)
+	if (!err)
+		ceph_init_acl(dentry, dentry->d_inode, dir);
+	else
 		d_drop(dentry);
 	return err;
 }
@@ -776,7 +785,9 @@
 		err = ceph_handle_notrace_create(dir, dentry);
 	ceph_mdsc_put_request(req);
 out:
-	if (err < 0)
+	if (!err)
+		ceph_init_acl(dentry, dentry->d_inode, dir);
+	else
 		d_drop(dentry);
 	return err;
 }
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index dfd2ce3..09c7afe 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -286,6 +286,7 @@
 	} else {
 		dout("atomic_open finish_open on dn %p\n", dn);
 		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
+			ceph_init_acl(dentry, dentry->d_inode, dir);
 			*opened |= FILE_CREATED;
 		}
 		err = finish_open(file, dentry, ceph_open, opened);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 2df963f..10a4ccb 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -144,7 +144,11 @@
 	Opt_ino32,
 	Opt_noino32,
 	Opt_fscache,
-	Opt_nofscache
+	Opt_nofscache,
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	Opt_acl,
+#endif
+	Opt_noacl
 };
 
 static match_table_t fsopt_tokens = {
@@ -172,6 +176,10 @@
 	{Opt_noino32, "noino32"},
 	{Opt_fscache, "fsc"},
 	{Opt_nofscache, "nofsc"},
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	{Opt_acl, "acl"},
+#endif
+	{Opt_noacl, "noacl"},
 	{-1, NULL}
 };
 
@@ -271,6 +279,14 @@
 	case Opt_nofscache:
 		fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
 		break;
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	case Opt_acl:
+		fsopt->sb_flags |= MS_POSIXACL;
+		break;
+#endif
+	case Opt_noacl:
+		fsopt->sb_flags &= ~MS_POSIXACL;
+		break;
 	default:
 		BUG_ON(token);
 	}
@@ -438,6 +454,13 @@
 	else
 		seq_puts(m, ",nofsc");
 
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	if (fsopt->sb_flags & MS_POSIXACL)
+		seq_puts(m, ",acl");
+	else
+		seq_puts(m, ",noacl");
+#endif
+
 	if (fsopt->wsize)
 		seq_printf(m, ",wsize=%d", fsopt->wsize);
 	if (fsopt->rsize != CEPH_RSIZE_DEFAULT)
@@ -819,9 +842,6 @@
 
 	s->s_flags = fsc->mount_options->sb_flags;
 	s->s_maxbytes = 1ULL << 40;  /* temp value until we get mdsmap */
-#ifdef CONFIG_CEPH_FS_POSIX_ACL
-	s->s_flags |= MS_POSIXACL;
-#endif
 
 	s->s_xattr = ceph_xattr_handlers;
 	s->s_fs_info = fsc;
@@ -911,6 +931,10 @@
 	struct ceph_options *opt = NULL;
 
 	dout("ceph_mount\n");
+
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	flags |= MS_POSIXACL;
+#endif
 	err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path);
 	if (err < 0) {
 		res = ERR_PTR(err);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 19793b5..d8801a9 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -13,6 +13,7 @@
 #include <linux/wait.h>
 #include <linux/writeback.h>
 #include <linux/slab.h>
+#include <linux/posix_acl.h>
 
 #include <linux/ceph/libceph.h>
 
@@ -743,7 +744,11 @@
 struct posix_acl *ceph_get_acl(struct inode *, int);
 int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 int ceph_init_acl(struct dentry *, struct inode *, struct inode *);
-void ceph_forget_all_cached_acls(struct inode *inode);
+
+static inline void ceph_forget_all_cached_acls(struct inode *inode)
+{
+       forget_all_cached_acls(inode);
+}
 
 #else
 
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 898b656..a55ec37 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -12,6 +12,9 @@
 #define XATTR_CEPH_PREFIX "ceph."
 #define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1)
 
+static int __remove_xattr(struct ceph_inode_info *ci,
+			  struct ceph_inode_xattr *xattr);
+
 /*
  * List of handlers for synthetic system.* attributes. Other
  * attributes are handled directly.
@@ -319,8 +322,7 @@
 static int __set_xattr(struct ceph_inode_info *ci,
 			   const char *name, int name_len,
 			   const char *val, int val_len,
-			   int dirty,
-			   int should_free_name, int should_free_val,
+			   int flags, int update_xattr,
 			   struct ceph_inode_xattr **newxattr)
 {
 	struct rb_node **p;
@@ -349,12 +351,31 @@
 		xattr = NULL;
 	}
 
+	if (update_xattr) {
+		int err = 0;
+		if (xattr && (flags & XATTR_CREATE))
+			err = -EEXIST;
+		else if (!xattr && (flags & XATTR_REPLACE))
+			err = -ENODATA;
+		if (err) {
+			kfree(name);
+			kfree(val);
+			return err;
+		}
+		if (update_xattr < 0) {
+			if (xattr)
+				__remove_xattr(ci, xattr);
+			kfree(name);
+			return 0;
+		}
+	}
+
 	if (!xattr) {
 		new = 1;
 		xattr = *newxattr;
 		xattr->name = name;
 		xattr->name_len = name_len;
-		xattr->should_free_name = should_free_name;
+		xattr->should_free_name = update_xattr;
 
 		ci->i_xattrs.count++;
 		dout("__set_xattr count=%d\n", ci->i_xattrs.count);
@@ -364,7 +385,7 @@
 		if (xattr->should_free_val)
 			kfree((void *)xattr->val);
 
-		if (should_free_name) {
+		if (update_xattr) {
 			kfree((void *)name);
 			name = xattr->name;
 		}
@@ -379,8 +400,8 @@
 		xattr->val = "";
 
 	xattr->val_len = val_len;
-	xattr->dirty = dirty;
-	xattr->should_free_val = (val && should_free_val);
+	xattr->dirty = update_xattr;
+	xattr->should_free_val = (val && update_xattr);
 
 	if (new) {
 		rb_link_node(&xattr->node, parent, p);
@@ -442,7 +463,7 @@
 			  struct ceph_inode_xattr *xattr)
 {
 	if (!xattr)
-		return -EOPNOTSUPP;
+		return -ENODATA;
 
 	rb_erase(&xattr->node, &ci->i_xattrs.index);
 
@@ -588,7 +609,7 @@
 			p += len;
 
 			err = __set_xattr(ci, name, namelen, val, len,
-					  0, 0, 0, &xattrs[numattr]);
+					  0, 0, &xattrs[numattr]);
 
 			if (err < 0)
 				goto bad;
@@ -850,6 +871,9 @@
 
 	dout("setxattr value=%.*s\n", (int)size, value);
 
+	if (!value)
+		flags |= CEPH_XATTR_REMOVE;
+
 	/* do request */
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR,
 				       USE_AUTH_MDS);
@@ -892,7 +916,7 @@
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int issued;
 	int err;
-	int dirty;
+	int dirty = 0;
 	int name_len = strlen(name);
 	int val_len = size;
 	char *newname = NULL;
@@ -953,12 +977,14 @@
 		goto retry;
 	}
 
-	err = __set_xattr(ci, newname, name_len, newval,
-			  val_len, 1, 1, 1, &xattr);
+	err = __set_xattr(ci, newname, name_len, newval, val_len,
+			  flags, value ? 1 : -1, &xattr);
 
-	dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
-	ci->i_xattrs.dirty = true;
-	inode->i_ctime = CURRENT_TIME;
+	if (!err) {
+		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
+		ci->i_xattrs.dirty = true;
+		inode->i_ctime = CURRENT_TIME;
+	}
 
 	spin_unlock(&ci->i_ceph_lock);
 	if (dirty)
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 8f9b4f7..7ff866d 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -865,8 +865,8 @@
 	return rc;
 }
 
-static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
-		__u16 fid, u32 *pacllen)
+struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
+		const struct cifs_fid *cifsfid, u32 *pacllen)
 {
 	struct cifs_ntsd *pntsd = NULL;
 	unsigned int xid;
@@ -877,7 +877,8 @@
 		return ERR_CAST(tlink);
 
 	xid = get_xid();
-	rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), fid, &pntsd, pacllen);
+	rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), cifsfid->netfid, &pntsd,
+				pacllen);
 	free_xid(xid);
 
 	cifs_put_tlink(tlink);
@@ -946,7 +947,7 @@
 	if (!open_file)
 		return get_cifs_acl_by_path(cifs_sb, path, pacllen);
 
-	pntsd = get_cifs_acl_by_fid(cifs_sb, open_file->fid.netfid, pacllen);
+	pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen);
 	cifsFileInfo_put(open_file);
 	return pntsd;
 }
@@ -1006,19 +1007,31 @@
 /* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */
 int
 cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
-		  struct inode *inode, const char *path, const __u16 *pfid)
+		  struct inode *inode, const char *path,
+		  const struct cifs_fid *pfid)
 {
 	struct cifs_ntsd *pntsd = NULL;
 	u32 acllen = 0;
 	int rc = 0;
+	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+	struct cifs_tcon *tcon;
 
 	cifs_dbg(NOISY, "converting ACL to mode for %s\n", path);
 
-	if (pfid)
-		pntsd = get_cifs_acl_by_fid(cifs_sb, *pfid, &acllen);
-	else
-		pntsd = get_cifs_acl(cifs_sb, inode, path, &acllen);
+	if (IS_ERR(tlink))
+		return PTR_ERR(tlink);
+	tcon = tlink_tcon(tlink);
 
+	if (pfid && (tcon->ses->server->ops->get_acl_by_fid))
+		pntsd = tcon->ses->server->ops->get_acl_by_fid(cifs_sb, pfid,
+							  &acllen);
+	else if (tcon->ses->server->ops->get_acl)
+		pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
+							&acllen);
+	else {
+		cifs_put_tlink(tlink);
+		return -EOPNOTSUPP;
+	}
 	/* if we can retrieve the ACL, now parse Access Control Entries, ACEs */
 	if (IS_ERR(pntsd)) {
 		rc = PTR_ERR(pntsd);
@@ -1030,6 +1043,8 @@
 			cifs_dbg(VFS, "parse sec desc failed rc = %d\n", rc);
 	}
 
+	cifs_put_tlink(tlink);
+
 	return rc;
 }
 
@@ -1043,15 +1058,30 @@
 	__u32 secdesclen = 0;
 	struct cifs_ntsd *pntsd = NULL; /* acl obtained from server */
 	struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+	struct cifs_tcon *tcon;
+
+	if (IS_ERR(tlink))
+		return PTR_ERR(tlink);
+	tcon = tlink_tcon(tlink);
 
 	cifs_dbg(NOISY, "set ACL from mode for %s\n", path);
 
 	/* Get the security descriptor */
-	pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen);
+
+	if (tcon->ses->server->ops->get_acl == NULL) {
+		cifs_put_tlink(tlink);
+		return -EOPNOTSUPP;
+	}
+
+	pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
+						&secdesclen);
 	if (IS_ERR(pntsd)) {
 		rc = PTR_ERR(pntsd);
 		cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc);
-		goto out;
+		cifs_put_tlink(tlink);
+		return rc;
 	}
 
 	/*
@@ -1064,6 +1094,7 @@
 	pnntsd = kmalloc(secdesclen, GFP_KERNEL);
 	if (!pnntsd) {
 		kfree(pntsd);
+		cifs_put_tlink(tlink);
 		return -ENOMEM;
 	}
 
@@ -1072,14 +1103,18 @@
 
 	cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc);
 
+	if (tcon->ses->server->ops->set_acl == NULL)
+		rc = -EOPNOTSUPP;
+
 	if (!rc) {
 		/* Set the security descriptor */
-		rc = set_cifs_acl(pnntsd, secdesclen, inode, path, aclflag);
+		rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode,
+						     path, aclflag);
 		cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc);
 	}
+	cifs_put_tlink(tlink);
 
 	kfree(pnntsd);
 	kfree(pntsd);
-out:
 	return rc;
 }
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index a245d18..c0f3718 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -323,7 +323,8 @@
 	/* async read from the server */
 	int (*async_readv)(struct cifs_readdata *);
 	/* async write to the server */
-	int (*async_writev)(struct cifs_writedata *);
+	int (*async_writev)(struct cifs_writedata *,
+			    void (*release)(struct kref *));
 	/* sync read from the server */
 	int (*sync_read)(const unsigned int, struct cifsFileInfo *,
 			 struct cifs_io_parms *, unsigned int *, char **,
@@ -395,6 +396,12 @@
 	int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *,
 			const char *, const void *, const __u16,
 			const struct nls_table *, int);
+	struct cifs_ntsd * (*get_acl)(struct cifs_sb_info *, struct inode *,
+			const char *, u32 *);
+	struct cifs_ntsd * (*get_acl_by_fid)(struct cifs_sb_info *,
+			const struct cifs_fid *, u32 *);
+	int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *,
+			int);
 };
 
 struct smb_version_values {
@@ -506,7 +513,7 @@
 static inline unsigned int
 get_rfc1002_length(void *buf)
 {
-	return be32_to_cpu(*((__be32 *)buf));
+	return be32_to_cpu(*((__be32 *)buf)) & 0xffffff;
 }
 
 static inline void
@@ -1064,7 +1071,7 @@
 	unsigned int			pagesz;
 	unsigned int			tailsz;
 	unsigned int			nr_pages;
-	struct page			*pages[1];
+	struct page			*pages[];
 };
 
 /*
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 79e6e9a..acc4ee8 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -151,7 +151,7 @@
 
 extern int cifs_get_inode_info(struct inode **inode, const char *full_path,
 			       FILE_ALL_INFO *data, struct super_block *sb,
-			       int xid, const __u16 *fid);
+			       int xid, const struct cifs_fid *fid);
 extern int cifs_get_inode_info_unix(struct inode **pinode,
 			const unsigned char *search_path,
 			struct super_block *sb, unsigned int xid);
@@ -162,11 +162,13 @@
 				      const unsigned int xid);
 extern int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb,
 			      struct cifs_fattr *fattr, struct inode *inode,
-			      const char *path, const __u16 *pfid);
+			      const char *path, const struct cifs_fid *pfid);
 extern int id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64,
 					kuid_t, kgid_t);
 extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *,
 					const char *, u32 *);
+extern struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *,
+						const struct cifs_fid *, u32 *);
 extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *,
 				const char *, int);
 
@@ -488,7 +490,8 @@
 int cifs_async_readv(struct cifs_readdata *rdata);
 int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid);
 
-int cifs_async_writev(struct cifs_writedata *wdata);
+int cifs_async_writev(struct cifs_writedata *wdata,
+		      void (*release)(struct kref *kref));
 void cifs_writev_complete(struct work_struct *work);
 struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages,
 						work_func_t complete);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 4d881c3..f3264bd 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1910,7 +1910,7 @@
 
 	do {
 		server = tlink_tcon(wdata->cfile->tlink)->ses->server;
-		rc = server->ops->async_writev(wdata);
+		rc = server->ops->async_writev(wdata, cifs_writedata_release);
 	} while (rc == -EAGAIN);
 
 	for (i = 0; i < wdata->nr_pages; i++) {
@@ -1962,15 +1962,9 @@
 {
 	struct cifs_writedata *wdata;
 
-	/* this would overflow */
-	if (nr_pages == 0) {
-		cifs_dbg(VFS, "%s: called with nr_pages == 0!\n", __func__);
-		return NULL;
-	}
-
 	/* writedata + number of page pointers */
 	wdata = kzalloc(sizeof(*wdata) +
-			sizeof(struct page *) * (nr_pages - 1), GFP_NOFS);
+			sizeof(struct page *) * nr_pages, GFP_NOFS);
 	if (wdata != NULL) {
 		kref_init(&wdata->refcount);
 		INIT_LIST_HEAD(&wdata->list);
@@ -2031,7 +2025,8 @@
 
 /* cifs_async_writev - send an async write, and set up mid to handle result */
 int
-cifs_async_writev(struct cifs_writedata *wdata)
+cifs_async_writev(struct cifs_writedata *wdata,
+		  void (*release)(struct kref *kref))
 {
 	int rc = -EACCES;
 	WRITE_REQ *smb = NULL;
@@ -2105,7 +2100,7 @@
 	if (rc == 0)
 		cifs_stats_inc(&tcon->stats.cifs_stats.num_writes);
 	else
-		kref_put(&wdata->refcount, cifs_writedata_release);
+		kref_put(&wdata->refcount, release);
 
 async_writev_out:
 	cifs_small_buf_release(smb);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index d3a6796..3db0c5f 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -378,7 +378,7 @@
 					      xid);
 	else {
 		rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb,
-					 xid, &fid->netfid);
+					 xid, fid);
 		if (newinode) {
 			if (server->ops->set_lease_key)
 				server->ops->set_lease_key(newinode, fid);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 853d6d1..834fce7 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -244,7 +244,7 @@
 					      xid);
 	else
 		rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb,
-					 xid, &fid->netfid);
+					 xid, fid);
 
 out:
 	kfree(buf);
@@ -2043,7 +2043,8 @@
 			}
 			wdata->pid = wdata->cfile->pid;
 			server = tlink_tcon(wdata->cfile->tlink)->ses->server;
-			rc = server->ops->async_writev(wdata);
+			rc = server->ops->async_writev(wdata,
+							cifs_writedata_release);
 		} while (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN);
 
 		for (i = 0; i < nr_pages; ++i)
@@ -2331,9 +2332,20 @@
 }
 
 static void
-cifs_uncached_writev_complete(struct work_struct *work)
+cifs_uncached_writedata_release(struct kref *refcount)
 {
 	int i;
+	struct cifs_writedata *wdata = container_of(refcount,
+					struct cifs_writedata, refcount);
+
+	for (i = 0; i < wdata->nr_pages; i++)
+		put_page(wdata->pages[i]);
+	cifs_writedata_release(refcount);
+}
+
+static void
+cifs_uncached_writev_complete(struct work_struct *work)
+{
 	struct cifs_writedata *wdata = container_of(work,
 					struct cifs_writedata, work);
 	struct inode *inode = wdata->cfile->dentry->d_inode;
@@ -2347,12 +2359,7 @@
 
 	complete(&wdata->done);
 
-	if (wdata->result != -EAGAIN) {
-		for (i = 0; i < wdata->nr_pages; i++)
-			put_page(wdata->pages[i]);
-	}
-
-	kref_put(&wdata->refcount, cifs_writedata_release);
+	kref_put(&wdata->refcount, cifs_uncached_writedata_release);
 }
 
 /* attempt to send write to server, retry on any -EAGAIN errors */
@@ -2370,7 +2377,8 @@
 			if (rc != 0)
 				continue;
 		}
-		rc = server->ops->async_writev(wdata);
+		rc = server->ops->async_writev(wdata,
+					       cifs_uncached_writedata_release);
 	} while (rc == -EAGAIN);
 
 	return rc;
@@ -2381,7 +2389,7 @@
 		 unsigned long nr_segs, loff_t *poffset)
 {
 	unsigned long nr_pages, i;
-	size_t copied, len, cur_len;
+	size_t bytes, copied, len, cur_len;
 	ssize_t total_written = 0;
 	loff_t offset;
 	struct iov_iter it;
@@ -2436,14 +2444,45 @@
 
 		save_len = cur_len;
 		for (i = 0; i < nr_pages; i++) {
-			copied = min_t(const size_t, cur_len, PAGE_SIZE);
+			bytes = min_t(const size_t, cur_len, PAGE_SIZE);
 			copied = iov_iter_copy_from_user(wdata->pages[i], &it,
-							 0, copied);
+							 0, bytes);
 			cur_len -= copied;
 			iov_iter_advance(&it, copied);
+			/*
+			 * If we didn't copy as much as we expected, then that
+			 * may mean we trod into an unmapped area. Stop copying
+			 * at that point. On the next pass through the big
+			 * loop, we'll likely end up getting a zero-length
+			 * write and bailing out of it.
+			 */
+			if (copied < bytes)
+				break;
 		}
 		cur_len = save_len - cur_len;
 
+		/*
+		 * If we have no data to send, then that probably means that
+		 * the copy above failed altogether. That's most likely because
+		 * the address in the iovec was bogus. Set the rc to -EFAULT,
+		 * free anything we allocated and bail out.
+		 */
+		if (!cur_len) {
+			for (i = 0; i < nr_pages; i++)
+				put_page(wdata->pages[i]);
+			kfree(wdata);
+			rc = -EFAULT;
+			break;
+		}
+
+		/*
+		 * i + 1 now represents the number of pages we actually used in
+		 * the copy phase above. Bring nr_pages down to that, and free
+		 * any pages that we didn't use.
+		 */
+		for ( ; nr_pages > i + 1; nr_pages--)
+			put_page(wdata->pages[nr_pages - 1]);
+
 		wdata->sync_mode = WB_SYNC_ALL;
 		wdata->nr_pages = nr_pages;
 		wdata->offset = (__u64)offset;
@@ -2454,7 +2493,8 @@
 		wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE);
 		rc = cifs_uncached_retry_writev(wdata);
 		if (rc) {
-			kref_put(&wdata->refcount, cifs_writedata_release);
+			kref_put(&wdata->refcount,
+				 cifs_uncached_writedata_release);
 			break;
 		}
 
@@ -2496,7 +2536,7 @@
 			}
 		}
 		list_del_init(&wdata->list);
-		kref_put(&wdata->refcount, cifs_writedata_release);
+		kref_put(&wdata->refcount, cifs_uncached_writedata_release);
 	}
 
 	if (total_written > 0)
@@ -2539,31 +2579,19 @@
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
 	struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
 	ssize_t rc = -EACCES;
+	loff_t lock_pos = pos;
 
-	BUG_ON(iocb->ki_pos != pos);
-
+	if (file->f_flags & O_APPEND)
+		lock_pos = i_size_read(inode);
 	/*
 	 * We need to hold the sem to be sure nobody modifies lock list
 	 * with a brlock that prevents writing.
 	 */
 	down_read(&cinode->lock_sem);
-	if (!cifs_find_lock_conflict(cfile, pos, iov_length(iov, nr_segs),
+	if (!cifs_find_lock_conflict(cfile, lock_pos, iov_length(iov, nr_segs),
 				     server->vals->exclusive_lock_type, NULL,
-				     CIFS_WRITE_OP)) {
-		mutex_lock(&inode->i_mutex);
-		rc = __generic_file_aio_write(iocb, iov, nr_segs,
-					       &iocb->ki_pos);
-		mutex_unlock(&inode->i_mutex);
-	}
-
-	if (rc > 0) {
-		ssize_t err;
-
-		err = generic_write_sync(file, pos, rc);
-		if (err < 0 && rc > 0)
-			rc = err;
-	}
-
+				     CIFS_WRITE_OP))
+		rc = generic_file_aio_write(iocb, iov, nr_segs, pos);
 	up_read(&cinode->lock_sem);
 	return rc;
 }
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 9cb9679..aadc2b6 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -527,10 +527,15 @@
 		return PTR_ERR(tlink);
 	tcon = tlink_tcon(tlink);
 
-	rc = CIFSSMBQAllEAs(xid, tcon, path, "SETFILEBITS",
-			    ea_value, 4 /* size of buf */, cifs_sb->local_nls,
-			    cifs_sb->mnt_cifs_flags &
-				CIFS_MOUNT_MAP_SPECIAL_CHR);
+	if (tcon->ses->server->ops->query_all_EAs == NULL) {
+		cifs_put_tlink(tlink);
+		return -EOPNOTSUPP;
+	}
+
+	rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path,
+			"SETFILEBITS", ea_value, 4 /* size of buf */,
+			cifs_sb->local_nls,
+			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
 	cifs_put_tlink(tlink);
 	if (rc < 0)
 		return (int)rc;
@@ -672,7 +677,7 @@
 int
 cifs_get_inode_info(struct inode **inode, const char *full_path,
 		    FILE_ALL_INFO *data, struct super_block *sb, int xid,
-		    const __u16 *fid)
+		    const struct cifs_fid *fid)
 {
 	bool validinum = false;
 	__u16 srchflgs;
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 9ac5bfc..526fb89 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -1067,6 +1067,15 @@
 	.query_mf_symlink = cifs_query_mf_symlink,
 	.create_mf_symlink = cifs_create_mf_symlink,
 	.is_read_op = cifs_is_read_op,
+#ifdef CONFIG_CIFS_XATTR
+	.query_all_EAs = CIFSSMBQAllEAs,
+	.set_EA = CIFSSMBSetEA,
+#endif /* CIFS_XATTR */
+#ifdef CONFIG_CIFS_ACL
+	.get_acl = get_cifs_acl,
+	.get_acl_by_fid = get_cifs_acl_by_fid,
+	.set_acl = set_cifs_acl,
+#endif /* CIFS_ACL */
 };
 
 struct smb_version_values smb1_values = {
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index c383508..bc0bb9c 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -57,4 +57,7 @@
 #define SMB2_CMACAES_SIZE (16)
 #define SMB3_SIGNKEY_SIZE (16)
 
+/* Maximum buffer size value we can send with 1 credit */
+#define SMB2_MAX_BUFFER_SIZE 65536
+
 #endif	/* _SMB2_GLOB_H */
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 757da3e..192f51a 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -182,11 +182,8 @@
 	/* start with specified wsize, or default */
 	wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE;
 	wsize = min_t(unsigned int, wsize, server->max_write);
-	/*
-	 * limit write size to 2 ** 16, because we don't support multicredit
-	 * requests now.
-	 */
-	wsize = min_t(unsigned int, wsize, 2 << 15);
+	/* set it to the maximum buffer size value we can send with 1 credit */
+	wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE);
 
 	return wsize;
 }
@@ -200,11 +197,8 @@
 	/* start with specified rsize, or default */
 	rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE;
 	rsize = min_t(unsigned int, rsize, server->max_read);
-	/*
-	 * limit write size to 2 ** 16, because we don't support multicredit
-	 * requests now.
-	 */
-	rsize = min_t(unsigned int, rsize, 2 << 15);
+	/* set it to the maximum buffer size value we can send with 1 credit */
+	rsize = min_t(unsigned int, rsize, SMB2_MAX_BUFFER_SIZE);
 
 	return rsize;
 }
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2013234..8603447 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -413,7 +413,9 @@
 
 	/* SMB2 only has an extended negflavor */
 	server->negflavor = CIFS_NEGFLAVOR_EXTENDED;
-	server->maxBuf = le32_to_cpu(rsp->MaxTransactSize);
+	/* set it to the maximum buffer size value we can send with 1 credit */
+	server->maxBuf = min_t(unsigned int, le32_to_cpu(rsp->MaxTransactSize),
+			       SMB2_MAX_BUFFER_SIZE);
 	server->max_read = le32_to_cpu(rsp->MaxReadSize);
 	server->max_write = le32_to_cpu(rsp->MaxWriteSize);
 	/* BB Do we need to validate the SecurityMode? */
@@ -1890,7 +1892,8 @@
 
 /* smb2_async_writev - send an async write, and set up mid to handle result */
 int
-smb2_async_writev(struct cifs_writedata *wdata)
+smb2_async_writev(struct cifs_writedata *wdata,
+		  void (*release)(struct kref *kref))
 {
 	int rc = -EACCES;
 	struct smb2_write_req *req = NULL;
@@ -1938,7 +1941,7 @@
 				smb2_writev_callback, wdata, 0);
 
 	if (rc) {
-		kref_put(&wdata->refcount, cifs_writedata_release);
+		kref_put(&wdata->refcount, release);
 		cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
 	}
 
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 93adc64..0ce48db 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -123,7 +123,8 @@
 extern int smb2_async_readv(struct cifs_readdata *rdata);
 extern int SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 		     unsigned int *nbytes, char **buf, int *buf_type);
-extern int smb2_async_writev(struct cifs_writedata *wdata);
+extern int smb2_async_writev(struct cifs_writedata *wdata,
+			     void (*release)(struct kref *kref));
 extern int SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 		      unsigned int *nbytes, struct kvec *iov, int n_vec);
 extern int SMB2_echo(struct TCP_Server_Info *server);
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index b375709..18cd565 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -270,6 +270,26 @@
 		iov->iov_len = rqst->rq_pagesz;
 }
 
+static unsigned long
+rqst_len(struct smb_rqst *rqst)
+{
+	unsigned int i;
+	struct kvec *iov = rqst->rq_iov;
+	unsigned long buflen = 0;
+
+	/* total up iov array first */
+	for (i = 0; i < rqst->rq_nvec; i++)
+		buflen += iov[i].iov_len;
+
+	/* add in the page array if there is one */
+	if (rqst->rq_npages) {
+		buflen += rqst->rq_pagesz * (rqst->rq_npages - 1);
+		buflen += rqst->rq_tailsz;
+	}
+
+	return buflen;
+}
+
 static int
 smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 {
@@ -277,6 +297,7 @@
 	struct kvec *iov = rqst->rq_iov;
 	int n_vec = rqst->rq_nvec;
 	unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base);
+	unsigned long send_length;
 	unsigned int i;
 	size_t total_len = 0, sent;
 	struct socket *ssocket = server->ssocket;
@@ -285,6 +306,14 @@
 	if (ssocket == NULL)
 		return -ENOTSOCK;
 
+	/* sanity check send length */
+	send_length = rqst_len(rqst);
+	if (send_length != smb_buf_length + 4) {
+		WARN(1, "Send length mismatch(send_length=%lu smb_buf_length=%u)\n",
+			send_length, smb_buf_length);
+		return -EIO;
+	}
+
 	cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length);
 	dump_smb(iov[0].iov_base, iov[0].iov_len);
 
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 95c43bb..5ac836a 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -176,8 +176,12 @@
 			rc = -ENOMEM;
 		} else {
 			memcpy(pacl, ea_value, value_size);
-			rc = set_cifs_acl(pacl, value_size,
-				direntry->d_inode, full_path, CIFS_ACL_DACL);
+			if (pTcon->ses->server->ops->set_acl)
+				rc = pTcon->ses->server->ops->set_acl(pacl,
+						value_size, direntry->d_inode,
+						full_path, CIFS_ACL_DACL);
+			else
+				rc = -EOPNOTSUPP;
 			if (rc == 0) /* force revalidate of the inode */
 				CIFS_I(direntry->d_inode)->time = 0;
 			kfree(pacl);
@@ -323,8 +327,11 @@
 			u32 acllen;
 			struct cifs_ntsd *pacl;
 
-			pacl = get_cifs_acl(cifs_sb, direntry->d_inode,
-						full_path, &acllen);
+			if (pTcon->ses->server->ops->get_acl == NULL)
+				goto get_ea_exit; /* rc already EOPNOTSUPP */
+
+			pacl = pTcon->ses->server->ops->get_acl(cifs_sb,
+					direntry->d_inode, full_path, &acllen);
 			if (IS_ERR(pacl)) {
 				rc = PTR_ERR(pacl);
 				cifs_dbg(VFS, "%s: error %zd getting sec desc\n",
diff --git a/fs/compat.c b/fs/compat.c
index 6af20de..19252b9 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -72,8 +72,8 @@
  * Not all architectures have sys_utime, so implement this in terms
  * of sys_utimes.
  */
-asmlinkage long compat_sys_utime(const char __user *filename,
-				 struct compat_utimbuf __user *t)
+COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename,
+		       struct compat_utimbuf __user *, t)
 {
 	struct timespec tv[2];
 
@@ -87,7 +87,7 @@
 	return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0);
 }
 
-asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filename, struct compat_timespec __user *t, int flags)
+COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags)
 {
 	struct timespec tv[2];
 
@@ -102,7 +102,7 @@
 	return do_utimes(dfd, filename, t ? tv : NULL, flags);
 }
 
-asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, struct compat_timeval __user *t)
+COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t)
 {
 	struct timespec tv[2];
 
@@ -121,7 +121,7 @@
 	return do_utimes(dfd, filename, t ? tv : NULL, 0);
 }
 
-asmlinkage long compat_sys_utimes(const char __user *filename, struct compat_timeval __user *t)
+COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t)
 {
 	return compat_sys_futimesat(AT_FDCWD, filename, t);
 }
@@ -159,8 +159,8 @@
 	return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }
 
-asmlinkage long compat_sys_newstat(const char __user * filename,
-		struct compat_stat __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename,
+		       struct compat_stat __user *, statbuf)
 {
 	struct kstat stat;
 	int error;
@@ -171,8 +171,8 @@
 	return cp_compat_stat(&stat, statbuf);
 }
 
-asmlinkage long compat_sys_newlstat(const char __user * filename,
-		struct compat_stat __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename,
+		       struct compat_stat __user *, statbuf)
 {
 	struct kstat stat;
 	int error;
@@ -184,9 +184,9 @@
 }
 
 #ifndef __ARCH_WANT_STAT64
-asmlinkage long compat_sys_newfstatat(unsigned int dfd,
-		const char __user *filename,
-		struct compat_stat __user *statbuf, int flag)
+COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd,
+		       const char __user *, filename,
+		       struct compat_stat __user *, statbuf, int, flag)
 {
 	struct kstat stat;
 	int error;
@@ -198,8 +198,8 @@
 }
 #endif
 
-asmlinkage long compat_sys_newfstat(unsigned int fd,
-		struct compat_stat __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd,
+		       struct compat_stat __user *, statbuf)
 {
 	struct kstat stat;
 	int error = vfs_fstat(fd, &stat);
@@ -247,7 +247,7 @@
  * The following statfs calls are copies of code from fs/statfs.c and
  * should be checked against those from time to time
  */
-asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf)
+COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf)
 {
 	struct kstatfs tmp;
 	int error = user_statfs(pathname, &tmp);
@@ -256,7 +256,7 @@
 	return error;
 }
 
-asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf)
+COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf)
 {
 	struct kstatfs tmp;
 	int error = fd_statfs(fd, &tmp);
@@ -298,7 +298,7 @@
 	return 0;
 }
 
-asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf)
+COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
 {
 	struct kstatfs tmp;
 	int error;
@@ -312,7 +312,7 @@
 	return error;
 }
 
-asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf)
+COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
 {
 	struct kstatfs tmp;
 	int error;
@@ -331,7 +331,7 @@
  * Given how simple this syscall is that apporach is more maintainable
  * than the various conversion hacks.
  */
-asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u)
+COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u)
 {
 	struct compat_ustat tmp;
 	struct kstatfs sbuf;
@@ -399,8 +399,8 @@
 }
 #endif
 
-asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd,
-		unsigned long arg)
+COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
+		       compat_ulong_t, arg)
 {
 	mm_segment_t old_fs;
 	struct flock f;
@@ -468,16 +468,15 @@
 	return ret;
 }
 
-asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd,
-		unsigned long arg)
+COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
+		       compat_ulong_t, arg)
 {
 	if ((cmd == F_GETLK64) || (cmd == F_SETLK64) || (cmd == F_SETLKW64))
 		return -EINVAL;
 	return compat_sys_fcntl64(fd, cmd, arg);
 }
 
-asmlinkage long
-compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p)
+COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_reqs, u32 __user *, ctx32p)
 {
 	long ret;
 	aio_context_t ctx64;
@@ -496,32 +495,24 @@
 	return ret;
 }
 
-asmlinkage long
-compat_sys_io_getevents(aio_context_t ctx_id,
-				 unsigned long min_nr,
-				 unsigned long nr,
-				 struct io_event __user *events,
-				 struct compat_timespec __user *timeout)
+COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
+		       compat_long_t, min_nr,
+		       compat_long_t, nr,
+		       struct io_event __user *, events,
+		       struct compat_timespec __user *, timeout)
 {
-	long ret;
 	struct timespec t;
 	struct timespec __user *ut = NULL;
 
-	ret = -EFAULT;
-	if (unlikely(!access_ok(VERIFY_WRITE, events, 
-				nr * sizeof(struct io_event))))
-		goto out;
 	if (timeout) {
 		if (get_compat_timespec(&t, timeout))
-			goto out;
+			return -EFAULT;
 
 		ut = compat_alloc_user_space(sizeof(*ut));
 		if (copy_to_user(ut, &t, sizeof(t)) )
-			goto out;
+			return -EFAULT;
 	} 
-	ret = sys_io_getevents(ctx_id, min_nr, nr, events, ut);
-out:
-	return ret;
+	return sys_io_getevents(ctx_id, min_nr, nr, events, ut);
 }
 
 /* A write operation does a read from user space and vice versa */
@@ -617,8 +608,8 @@
 
 #define MAX_AIO_SUBMITS 	(PAGE_SIZE/sizeof(struct iocb *))
 
-asmlinkage long
-compat_sys_io_submit(aio_context_t ctx_id, int nr, u32 __user *iocb)
+COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
+		       int, nr, u32 __user *, iocb)
 {
 	struct iocb __user * __user *iocb64; 
 	long ret;
@@ -770,10 +761,10 @@
 #define NCPFS_NAME      "ncpfs"
 #define NFS4_NAME	"nfs4"
 
-asmlinkage long compat_sys_mount(const char __user * dev_name,
-				 const char __user * dir_name,
-				 const char __user * type, unsigned long flags,
-				 const void __user * data)
+COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
+		       const char __user *, dir_name,
+		       const char __user *, type, compat_ulong_t, flags,
+		       const void __user *, data)
 {
 	char *kernel_type;
 	unsigned long data_page;
@@ -869,8 +860,8 @@
 	return -EFAULT;
 }
 
-asmlinkage long compat_sys_old_readdir(unsigned int fd,
-	struct compat_old_linux_dirent __user *dirent, unsigned int count)
+COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
+		struct compat_old_linux_dirent __user *, dirent, unsigned int, count)
 {
 	int error;
 	struct fd f = fdget(fd);
@@ -948,8 +939,8 @@
 	return -EFAULT;
 }
 
-asmlinkage long compat_sys_getdents(unsigned int fd,
-		struct compat_linux_dirent __user *dirent, unsigned int count)
+COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
+		struct compat_linux_dirent __user *, dirent, unsigned int, count)
 {
 	struct fd f;
 	struct compat_linux_dirent __user * lastdirent;
@@ -981,7 +972,7 @@
 	return error;
 }
 
-#ifndef __ARCH_OMIT_COMPAT_SYS_GETDENTS64
+#ifdef __ARCH_WANT_COMPAT_SYS_GETDENTS64
 
 struct compat_getdents_callback64 {
 	struct dir_context ctx;
@@ -1033,8 +1024,8 @@
 	return -EFAULT;
 }
 
-asmlinkage long compat_sys_getdents64(unsigned int fd,
-		struct linux_dirent64 __user * dirent, unsigned int count)
+COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd,
+		struct linux_dirent64 __user *, dirent, unsigned int, count)
 {
 	struct fd f;
 	struct linux_dirent64 __user * lastdirent;
@@ -1066,7 +1057,7 @@
 	fdput(f);
 	return error;
 }
-#endif /* ! __ARCH_OMIT_COMPAT_SYS_GETDENTS64 */
+#endif /* __ARCH_WANT_COMPAT_SYS_GETDENTS64 */
 
 /*
  * Exactly like fs/open.c:sys_open(), except that it doesn't set the
@@ -1287,9 +1278,9 @@
 	return ret;
 }
 
-asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
-	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
-	struct compat_timeval __user *tvp)
+COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp,
+	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
+	struct compat_timeval __user *, tvp)
 {
 	struct timespec end_time, *to = NULL;
 	struct compat_timeval tv;
@@ -1320,7 +1311,7 @@
 	compat_uptr_t tvp;
 };
 
-asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg)
+COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg)
 {
 	struct compat_sel_arg_struct a;
 
@@ -1381,9 +1372,9 @@
 	return ret;
 }
 
-asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp,
-	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
-	struct compat_timespec __user *tsp, void __user *sig)
+COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp,
+	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
+	struct compat_timespec __user *, tsp, void __user *, sig)
 {
 	compat_size_t sigsetsize = 0;
 	compat_uptr_t up = 0;
@@ -1400,9 +1391,9 @@
 				 sigsetsize);
 }
 
-asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
-	unsigned int nfds, struct compat_timespec __user *tsp,
-	const compat_sigset_t __user *sigmask, compat_size_t sigsetsize)
+COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds,
+	unsigned int,  nfds, struct compat_timespec __user *, tsp,
+	const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize)
 {
 	compat_sigset_t ss32;
 	sigset_t ksigmask, sigsaved;
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index a81147e..4d24d17 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -88,6 +88,11 @@
 #define	ELF_HWCAP		COMPAT_ELF_HWCAP
 #endif
 
+#ifdef	COMPAT_ELF_HWCAP2
+#undef	ELF_HWCAP2
+#define	ELF_HWCAP2		COMPAT_ELF_HWCAP2
+#endif
+
 #ifdef	COMPAT_ARCH_DLINFO
 #undef	ARCH_DLINFO
 #define	ARCH_DLINFO		COMPAT_ARCH_DLINFO
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 3881610..e822890 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1538,9 +1538,10 @@
 	return ioctl_pointer[i] == xcmd;
 }
 
-asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
-				unsigned long arg)
+COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
+		       compat_ulong_t, arg32)
 {
+	unsigned long arg = arg32;
 	struct fd f = fdget(fd);
 	int error = -EBADF;
 	if (!f.file)
diff --git a/fs/dcache.c b/fs/dcache.c
index 265e0ce..ca02c13 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2833,9 +2833,9 @@
 	u32 dlen = ACCESS_ONCE(name->len);
 	char *p;
 
-	if (*buflen < dlen + 1)
-		return -ENAMETOOLONG;
 	*buflen -= dlen + 1;
+	if (*buflen < 0)
+		return -ENAMETOOLONG;
 	p = *buffer -= dlen + 1;
 	*p++ = '/';
 	while (dlen--) {
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index 8dd524f..cdb2971 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -21,7 +21,7 @@
 	u32 attributes;
 	struct inode *inode = file->f_mapping->host;
 	unsigned long datasize = count - sizeof(attributes);
-	ssize_t bytes = 0;
+	ssize_t bytes;
 	bool set = false;
 
 	if (count < sizeof(attributes))
@@ -33,14 +33,9 @@
 	if (attributes & ~(EFI_VARIABLE_MASK))
 		return -EINVAL;
 
-	data = kmalloc(datasize, GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	if (copy_from_user(data, userbuf + sizeof(attributes), datasize)) {
-		bytes = -EFAULT;
-		goto out;
-	}
+	data = memdup_user(userbuf + sizeof(attributes), datasize);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
 	bytes = efivar_entry_set_get_size(var, attributes, &datasize,
 					  data, &set);
diff --git a/fs/exec.c b/fs/exec.c
index e1529b4..4f59402 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -748,11 +748,10 @@
 
 #endif /* CONFIG_MMU */
 
-struct file *open_exec(const char *name)
+static struct file *do_open_exec(struct filename *name)
 {
 	struct file *file;
 	int err;
-	struct filename tmp = { .name = name };
 	static const struct open_flags open_exec_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
 		.acc_mode = MAY_EXEC | MAY_OPEN,
@@ -760,7 +759,7 @@
 		.lookup_flags = LOOKUP_FOLLOW,
 	};
 
-	file = do_filp_open(AT_FDCWD, &tmp, &open_exec_flags);
+	file = do_filp_open(AT_FDCWD, name, &open_exec_flags);
 	if (IS_ERR(file))
 		goto out;
 
@@ -784,6 +783,12 @@
 	fput(file);
 	return ERR_PTR(err);
 }
+
+struct file *open_exec(const char *name)
+{
+	struct filename tmp = { .name = name };
+	return do_open_exec(&tmp);
+}
 EXPORT_SYMBOL(open_exec);
 
 int kernel_read(struct file *file, loff_t offset,
@@ -1162,7 +1167,7 @@
 	return -ENOMEM;
 }
 
-void free_bprm(struct linux_binprm *bprm)
+static void free_bprm(struct linux_binprm *bprm)
 {
 	free_arg_pages(bprm);
 	if (bprm->cred) {
@@ -1432,7 +1437,7 @@
 /*
  * sys_execve() executes a new program.
  */
-static int do_execve_common(const char *filename,
+static int do_execve_common(struct filename *filename,
 				struct user_arg_ptr argv,
 				struct user_arg_ptr envp)
 {
@@ -1441,6 +1446,9 @@
 	struct files_struct *displaced;
 	int retval;
 
+	if (IS_ERR(filename))
+		return PTR_ERR(filename);
+
 	/*
 	 * We move the actual failure in case of RLIMIT_NPROC excess from
 	 * set*uid() to execve() because too many poorly written programs
@@ -1473,7 +1481,7 @@
 	check_unsafe_exec(bprm);
 	current->in_execve = 1;
 
-	file = open_exec(filename);
+	file = do_open_exec(filename);
 	retval = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out_unmark;
@@ -1481,8 +1489,7 @@
 	sched_exec();
 
 	bprm->file = file;
-	bprm->filename = filename;
-	bprm->interp = filename;
+	bprm->filename = bprm->interp = filename->name;
 
 	retval = bprm_mm_init(bprm);
 	if (retval)
@@ -1523,6 +1530,7 @@
 	acct_update_integrals(current);
 	task_numa_free(current);
 	free_bprm(bprm);
+	putname(filename);
 	if (displaced)
 		put_files_struct(displaced);
 	return retval;
@@ -1544,10 +1552,11 @@
 	if (displaced)
 		reset_files_struct(displaced);
 out_ret:
+	putname(filename);
 	return retval;
 }
 
-int do_execve(const char *filename,
+int do_execve(struct filename *filename,
 	const char __user *const __user *__argv,
 	const char __user *const __user *__envp)
 {
@@ -1557,7 +1566,7 @@
 }
 
 #ifdef CONFIG_COMPAT
-static int compat_do_execve(const char *filename,
+static int compat_do_execve(struct filename *filename,
 	const compat_uptr_t __user *__argv,
 	const compat_uptr_t __user *__envp)
 {
@@ -1607,25 +1616,13 @@
 		const char __user *const __user *, argv,
 		const char __user *const __user *, envp)
 {
-	struct filename *path = getname(filename);
-	int error = PTR_ERR(path);
-	if (!IS_ERR(path)) {
-		error = do_execve(path->name, argv, envp);
-		putname(path);
-	}
-	return error;
+	return do_execve(getname(filename), argv, envp);
 }
 #ifdef CONFIG_COMPAT
-asmlinkage long compat_sys_execve(const char __user * filename,
-	const compat_uptr_t __user * argv,
-	const compat_uptr_t __user * envp)
+COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
+	const compat_uptr_t __user *, argv,
+	const compat_uptr_t __user *, envp)
 {
-	struct filename *path = getname(filename);
-	int error = PTR_ERR(path);
-	if (!IS_ERR(path)) {
-		error = compat_do_execve(path->name, argv, envp);
-		putname(path);
-	}
-	return error;
+	return compat_do_execve(getname(filename), argv, envp);
 }
 #endif
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index ece5556..d3a534f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -771,6 +771,8 @@
 	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))		       \
 		(einode)->xtime.tv_sec = 				       \
 			(signed)le32_to_cpu((raw_inode)->xtime);	       \
+	else								       \
+		(einode)->xtime.tv_sec = 0;				       \
 	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
 		ext4_decode_extra_time(&(einode)->xtime,		       \
 				       raw_inode->xtime ## _extra);	       \
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 10cff47..74bc2d5 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3906,6 +3906,7 @@
 		} else
 			err = ret;
 		map->m_flags |= EXT4_MAP_MAPPED;
+		map->m_pblk = newblock;
 		if (allocated > map->m_len)
 			allocated = map->m_len;
 		map->m_len = allocated;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 43e64f6..1a50739 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -152,7 +152,7 @@
 	if (ret > 0) {
 		ssize_t err;
 
-		err = generic_write_sync(file, pos, ret);
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
 		if (err < 0 && ret > 0)
 			ret = err;
 	}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 6e39895..24bfd7f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -38,6 +38,7 @@
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
 #include <linux/aio.h>
+#include <linux/bitops.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -3921,18 +3922,20 @@
 void ext4_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = EXT4_I(inode)->i_flags;
+	unsigned int new_fl = 0;
 
-	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
 	if (flags & EXT4_SYNC_FL)
-		inode->i_flags |= S_SYNC;
+		new_fl |= S_SYNC;
 	if (flags & EXT4_APPEND_FL)
-		inode->i_flags |= S_APPEND;
+		new_fl |= S_APPEND;
 	if (flags & EXT4_IMMUTABLE_FL)
-		inode->i_flags |= S_IMMUTABLE;
+		new_fl |= S_IMMUTABLE;
 	if (flags & EXT4_NOATIME_FL)
-		inode->i_flags |= S_NOATIME;
+		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
-		inode->i_flags |= S_DIRSYNC;
+		new_fl |= S_DIRSYNC;
+	set_mask_bits(&inode->i_flags,
+		      S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 6bea806..a2a837f 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -140,7 +140,7 @@
 	handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
 	if (IS_ERR(handle)) {
 		err = -EINVAL;
-		goto swap_boot_out;
+		goto journal_err_out;
 	}
 
 	/* Protect extent tree against block allocations via delalloc */
@@ -198,6 +198,7 @@
 
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
+journal_err_out:
 	ext4_inode_resume_unlocked_dio(inode);
 	ext4_inode_resume_unlocked_dio(inode_bl);
 
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index c5adbb3..f3b84cd 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -243,6 +243,7 @@
 	ext4_group_t group;
 	ext4_group_t last_group;
 	unsigned overhead;
+	__u16 uninit_mask = (flexbg_size > 1) ? ~EXT4_BG_BLOCK_UNINIT : ~0;
 
 	BUG_ON(flex_gd->count == 0 || group_data == NULL);
 
@@ -266,7 +267,7 @@
 	src_group++;
 	for (; src_group <= last_group; src_group++) {
 		overhead = ext4_group_overhead_blocks(sb, src_group);
-		if (overhead != 0)
+		if (overhead == 0)
 			last_blk += group_data[src_group - group].blocks_count;
 		else
 			break;
@@ -280,8 +281,7 @@
 		group = ext4_get_group_number(sb, start_blk - 1);
 		group -= group_data[0].group;
 		group_data[group].free_blocks_count--;
-		if (flexbg_size > 1)
-			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+		flex_gd->bg_flags[group] &= uninit_mask;
 	}
 
 	/* Allocate inode bitmaps */
@@ -292,22 +292,30 @@
 		group = ext4_get_group_number(sb, start_blk - 1);
 		group -= group_data[0].group;
 		group_data[group].free_blocks_count--;
-		if (flexbg_size > 1)
-			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+		flex_gd->bg_flags[group] &= uninit_mask;
 	}
 
 	/* Allocate inode tables */
 	for (; it_index < flex_gd->count; it_index++) {
-		if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk)
+		unsigned int itb = EXT4_SB(sb)->s_itb_per_group;
+		ext4_fsblk_t next_group_start;
+
+		if (start_blk + itb > last_blk)
 			goto next_group;
 		group_data[it_index].inode_table = start_blk;
-		group = ext4_get_group_number(sb, start_blk - 1);
+		group = ext4_get_group_number(sb, start_blk);
+		next_group_start = ext4_group_first_block_no(sb, group + 1);
 		group -= group_data[0].group;
-		group_data[group].free_blocks_count -=
-					EXT4_SB(sb)->s_itb_per_group;
-		if (flexbg_size > 1)
-			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
 
+		if (start_blk + itb > next_group_start) {
+			flex_gd->bg_flags[group + 1] &= uninit_mask;
+			overhead = start_blk + itb - next_group_start;
+			group_data[group + 1].free_blocks_count -= overhead;
+			itb -= overhead;
+		}
+
+		group_data[group].free_blocks_count -= itb;
+		flex_gd->bg_flags[group] &= uninit_mask;
 		start_blk += EXT4_SB(sb)->s_itb_per_group;
 	}
 
@@ -401,7 +409,7 @@
 		start = ext4_group_first_block_no(sb, group);
 		group -= flex_gd->groups[0].group;
 
-		count2 = sb->s_blocksize * 8 - (block - start);
+		count2 = EXT4_BLOCKS_PER_GROUP(sb) - (block - start);
 		if (count2 > count)
 			count2 = count;
 
@@ -620,7 +628,7 @@
 			if (err)
 				goto out;
 			count = group_table_count[j];
-			start = group_data[i].block_bitmap;
+			start = (&group_data[i].block_bitmap)[j];
 			block = start;
 		}
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 1f7784d..710fed2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3695,16 +3695,22 @@
 	for (i = 0; i < 4; i++)
 		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
 	sbi->s_def_hash_version = es->s_def_hash_version;
-	i = le32_to_cpu(es->s_flags);
-	if (i & EXT2_FLAGS_UNSIGNED_HASH)
-		sbi->s_hash_unsigned = 3;
-	else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+	if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
+		i = le32_to_cpu(es->s_flags);
+		if (i & EXT2_FLAGS_UNSIGNED_HASH)
+			sbi->s_hash_unsigned = 3;
+		else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
 #ifdef __CHAR_UNSIGNED__
-		es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
-		sbi->s_hash_unsigned = 3;
+			if (!(sb->s_flags & MS_RDONLY))
+				es->s_flags |=
+					cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+			sbi->s_hash_unsigned = 3;
 #else
-		es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+			if (!(sb->s_flags & MS_RDONLY))
+				es->s_flags |=
+					cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
 #endif
+		}
 	}
 
 	/* Handle clustersize */
diff --git a/fs/file.c b/fs/file.c
index 771578b..b61293b 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -34,7 +34,7 @@
 	 * vmalloc() if the allocation size will be considered "large" by the VM.
 	 */
 	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
-		void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN);
+		void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY);
 		if (data != NULL)
 			return data;
 	}
@@ -497,7 +497,7 @@
 	error = fd;
 #if 1
 	/* Sanity check */
-	if (rcu_dereference_raw(fdt->fd[fd]) != NULL) {
+	if (rcu_access_pointer(fdt->fd[fd]) != NULL) {
 		printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd);
 		rcu_assign_pointer(fdt->fd[fd], NULL);
 	}
@@ -683,35 +683,54 @@
  * The fput_needed flag returned by fget_light should be passed to the
  * corresponding fput_light.
  */
-struct file *__fget_light(unsigned int fd, fmode_t mask, int *fput_needed)
+static unsigned long __fget_light(unsigned int fd, fmode_t mask)
 {
 	struct files_struct *files = current->files;
 	struct file *file;
 
-	*fput_needed = 0;
 	if (atomic_read(&files->count) == 1) {
 		file = __fcheck_files(files, fd);
-		if (file && (file->f_mode & mask))
-			file = NULL;
+		if (!file || unlikely(file->f_mode & mask))
+			return 0;
+		return (unsigned long)file;
 	} else {
 		file = __fget(fd, mask);
-		if (file)
-			*fput_needed = 1;
+		if (!file)
+			return 0;
+		return FDPUT_FPUT | (unsigned long)file;
 	}
-
-	return file;
 }
-struct file *fget_light(unsigned int fd, int *fput_needed)
+unsigned long __fdget(unsigned int fd)
 {
-	return __fget_light(fd, FMODE_PATH, fput_needed);
+	return __fget_light(fd, FMODE_PATH);
 }
-EXPORT_SYMBOL(fget_light);
+EXPORT_SYMBOL(__fdget);
 
-struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+unsigned long __fdget_raw(unsigned int fd)
 {
-	return __fget_light(fd, 0, fput_needed);
+	return __fget_light(fd, 0);
 }
 
+unsigned long __fdget_pos(unsigned int fd)
+{
+	unsigned long v = __fdget(fd);
+	struct file *file = (struct file *)(v & ~3);
+
+	if (file && (file->f_mode & FMODE_ATOMIC_POS)) {
+		if (file_count(file) > 1) {
+			v |= FDPUT_POS_UNLOCK;
+			mutex_lock(&file->f_pos_lock);
+		}
+	}
+	return v;
+}
+
+/*
+ * We only lock f_pos if we have threads or if the file might be
+ * shared with another process. In both cases we'll have an elevated
+ * file count (done either by fdget() or by fork()).
+ */
+
 void set_close_on_exec(unsigned int fd, int flag)
 {
 	struct files_struct *files = current->files;
diff --git a/fs/file_table.c b/fs/file_table.c
index 5fff903..5b24008 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -135,6 +135,7 @@
 	atomic_long_set(&f->f_count, 1);
 	rwlock_init(&f->f_owner.lock);
 	spin_lock_init(&f->f_lock);
+	mutex_init(&f->f_pos_lock);
 	eventpoll_init_file(f);
 	/* f->f_version: 0 */
 	return f;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e0259a1..d754e3c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -40,18 +40,13 @@
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
-	/*
-	 * Write only inodes dirtied before this time. Don't forget to set
-	 * older_than_this_is_set when you set this.
-	 */
-	unsigned long older_than_this;
+	unsigned long *older_than_this;
 	enum writeback_sync_modes sync_mode;
 	unsigned int tagged_writepages:1;
 	unsigned int for_kupdate:1;
 	unsigned int range_cyclic:1;
 	unsigned int for_background:1;
 	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
-	unsigned int older_than_this_is_set:1;
 	enum wb_reason reason;		/* why was writeback initiated? */
 
 	struct list_head list;		/* pending work list */
@@ -252,10 +247,10 @@
 	int do_sb_sort = 0;
 	int moved = 0;
 
-	WARN_ON_ONCE(!work->older_than_this_is_set);
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (inode_dirtied_after(inode, work->older_than_this))
+		if (work->older_than_this &&
+		    inode_dirtied_after(inode, *work->older_than_this))
 			break;
 		list_move(&inode->i_wb_list, &tmp);
 		moved++;
@@ -742,8 +737,6 @@
 		.sync_mode	= WB_SYNC_NONE,
 		.range_cyclic	= 1,
 		.reason		= reason,
-		.older_than_this = jiffies,
-		.older_than_this_is_set = 1,
 	};
 
 	spin_lock(&wb->list_lock);
@@ -802,13 +795,12 @@
 {
 	unsigned long wb_start = jiffies;
 	long nr_pages = work->nr_pages;
+	unsigned long oldest_jif;
 	struct inode *inode;
 	long progress;
 
-	if (!work->older_than_this_is_set) {
-		work->older_than_this = jiffies;
-		work->older_than_this_is_set = 1;
-	}
+	oldest_jif = jiffies;
+	work->older_than_this = &oldest_jif;
 
 	spin_lock(&wb->list_lock);
 	for (;;) {
@@ -842,10 +834,10 @@
 		 * safe.
 		 */
 		if (work->for_kupdate) {
-			work->older_than_this = jiffies -
+			oldest_jif = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
 		} else if (work->for_background)
-			work->older_than_this = jiffies;
+			oldest_jif = jiffies;
 
 		trace_writeback_start(wb->bdi, work);
 		if (list_empty(&wb->b_io))
@@ -1357,21 +1349,18 @@
 
 /**
  * sync_inodes_sb	-	sync sb inode pages
- * @sb:			the superblock
- * @older_than_this:	timestamp
+ * @sb: the superblock
  *
  * This function writes and waits on any dirty inode belonging to this
- * superblock that has been dirtied before given timestamp.
+ * super_block.
  */
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this)
+void sync_inodes_sb(struct super_block *sb)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct wb_writeback_work work = {
 		.sb		= sb,
 		.sync_mode	= WB_SYNC_ALL,
 		.nr_pages	= LONG_MAX,
-		.older_than_this = older_than_this,
-		.older_than_this_is_set = 1,
 		.range_cyclic	= 0,
 		.done		= &done,
 		.reason		= WB_REASON_SYNC,
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index e1959ef..b5ebc2d 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -50,6 +50,8 @@
 	struct fscache_object *xobj;
 	struct rb_node **p = &fscache_object_list.rb_node, *parent = NULL;
 
+	ASSERT(RB_EMPTY_NODE(&obj->objlist_link));
+
 	write_lock(&fscache_object_list_lock);
 
 	while (*p) {
@@ -75,6 +77,9 @@
  */
 void fscache_objlist_remove(struct fscache_object *obj)
 {
+	if (RB_EMPTY_NODE(&obj->objlist_link))
+		return;
+
 	write_lock(&fscache_object_list_lock);
 
 	BUG_ON(RB_EMPTY_ROOT(&fscache_object_list));
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 53d35c5..d3b4539 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -314,6 +314,9 @@
 	object->cache = cache;
 	object->cookie = cookie;
 	object->parent = NULL;
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+	RB_CLEAR_NODE(&object->objlist_link);
+#endif
 
 	object->oob_event_mask = 0;
 	for (t = object->oob_table; t->events; t++)
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 968ce41..32602c6 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -103,6 +103,8 @@
 		folder = &entry->folder;
 		memset(folder, 0, sizeof(*folder));
 		folder->type = cpu_to_be16(HFSPLUS_FOLDER);
+		if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags))
+			folder->flags |= cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT);
 		folder->id = cpu_to_be32(inode->i_ino);
 		HFSPLUS_I(inode)->create_date =
 			folder->create_date =
@@ -203,6 +205,36 @@
 	return hfs_brec_find(fd, hfs_find_rec_by_key);
 }
 
+static void hfsplus_subfolders_inc(struct inode *dir)
+{
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+
+	if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+		/*
+		 * Increment subfolder count. Note, the value is only meaningful
+		 * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set.
+		 */
+		HFSPLUS_I(dir)->subfolders++;
+	}
+}
+
+static void hfsplus_subfolders_dec(struct inode *dir)
+{
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+
+	if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+		/*
+		 * Decrement subfolder count. Note, the value is only meaningful
+		 * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set.
+		 *
+		 * Check for zero. Some subfolders may have been created
+		 * by an implementation ignorant of this counter.
+		 */
+		if (HFSPLUS_I(dir)->subfolders)
+			HFSPLUS_I(dir)->subfolders--;
+	}
+}
+
 int hfsplus_create_cat(u32 cnid, struct inode *dir,
 		struct qstr *str, struct inode *inode)
 {
@@ -247,6 +279,8 @@
 		goto err1;
 
 	dir->i_size++;
+	if (S_ISDIR(inode->i_mode))
+		hfsplus_subfolders_inc(dir);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
 	hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
 
@@ -336,6 +370,8 @@
 		goto out;
 
 	dir->i_size--;
+	if (type == HFSPLUS_FOLDER)
+		hfsplus_subfolders_dec(dir);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
 	hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
 
@@ -380,6 +416,7 @@
 
 	hfs_bnode_read(src_fd.bnode, &entry, src_fd.entryoffset,
 				src_fd.entrylength);
+	type = be16_to_cpu(entry.type);
 
 	/* create new dir entry with the data from the old entry */
 	hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name);
@@ -394,6 +431,8 @@
 	if (err)
 		goto out;
 	dst_dir->i_size++;
+	if (type == HFSPLUS_FOLDER)
+		hfsplus_subfolders_inc(dst_dir);
 	dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* finally remove the old entry */
@@ -405,6 +444,8 @@
 	if (err)
 		goto out;
 	src_dir->i_size--;
+	if (type == HFSPLUS_FOLDER)
+		hfsplus_subfolders_dec(src_dir);
 	src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* remove old thread entry */
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 08846425b..62d571e 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -242,6 +242,7 @@
 	 */
 	sector_t fs_blocks;
 	u8 userflags;		/* BSD user file flags */
+	u32 subfolders;		/* Subfolder count (HFSX only) */
 	struct list_head open_dir_list;
 	loff_t phys_size;
 
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index 8ffb3a8..5a12682 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -261,7 +261,7 @@
 	struct DInfo user_info;
 	struct DXInfo finder_info;
 	__be32 text_encoding;
-	u32 reserved;
+	__be32 subfolders;	/* Subfolder count in HFSX. Reserved in HFS+. */
 } __packed;
 
 /* HFS file info (stolen from hfs.h) */
@@ -301,11 +301,13 @@
 	struct hfsplus_fork_raw rsrc_fork;
 } __packed;
 
-/* File attribute bits */
+/* File and folder flag bits */
 #define HFSPLUS_FILE_LOCKED		0x0001
 #define HFSPLUS_FILE_THREAD_EXISTS	0x0002
 #define HFSPLUS_XATTR_EXISTS		0x0004
 #define HFSPLUS_ACL_EXISTS		0x0008
+#define HFSPLUS_HAS_FOLDER_COUNT	0x0010	/* Folder has subfolder count
+						 * (HFSX only) */
 
 /* HFS+ catalog thread (part of a cat_entry) */
 struct hfsplus_cat_thread {
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index fa929f3..a4f45bd 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -375,6 +375,7 @@
 	hip->extent_state = 0;
 	hip->flags = 0;
 	hip->userflags = 0;
+	hip->subfolders = 0;
 	memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec));
 	memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
 	hip->alloc_blocks = 0;
@@ -494,6 +495,10 @@
 		inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date);
 		HFSPLUS_I(inode)->create_date = folder->create_date;
 		HFSPLUS_I(inode)->fs_blocks = 0;
+		if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) {
+			HFSPLUS_I(inode)->subfolders =
+				be32_to_cpu(folder->subfolders);
+		}
 		inode->i_op = &hfsplus_dir_inode_operations;
 		inode->i_fop = &hfsplus_dir_operations;
 	} else if (type == HFSPLUS_FILE) {
@@ -566,6 +571,10 @@
 		folder->content_mod_date = hfsp_ut2mt(inode->i_mtime);
 		folder->attribute_mod_date = hfsp_ut2mt(inode->i_ctime);
 		folder->valence = cpu_to_be32(inode->i_size - 2);
+		if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) {
+			folder->subfolders =
+				cpu_to_be32(HFSPLUS_I(inode)->subfolders);
+		}
 		hfs_bnode_write(fd.bnode, &entry, fd.entryoffset,
 					 sizeof(struct hfsplus_cat_folder));
 	} else if (HFSPLUS_IS_RSRC(inode)) {
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 968eab5..68537e8 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -75,7 +75,7 @@
 	int token;
 
 	if (!input)
-		return 0;
+		return 1;
 
 	while ((p = strsep(&input, ",")) != NULL) {
 		if (!*p)
diff --git a/fs/hpfs/alloc.c b/fs/hpfs/alloc.c
index cdb84a8..58b5106 100644
--- a/fs/hpfs/alloc.c
+++ b/fs/hpfs/alloc.c
@@ -8,6 +8,58 @@
 
 #include "hpfs_fn.h"
 
+static void hpfs_claim_alloc(struct super_block *s, secno sec)
+{
+	struct hpfs_sb_info *sbi = hpfs_sb(s);
+	if (sbi->sb_n_free != (unsigned)-1) {
+		if (unlikely(!sbi->sb_n_free)) {
+			hpfs_error(s, "free count underflow, allocating sector %08x", sec);
+			sbi->sb_n_free = -1;
+			return;
+		}
+		sbi->sb_n_free--;
+	}
+}
+
+static void hpfs_claim_free(struct super_block *s, secno sec)
+{
+	struct hpfs_sb_info *sbi = hpfs_sb(s);
+	if (sbi->sb_n_free != (unsigned)-1) {
+		if (unlikely(sbi->sb_n_free >= sbi->sb_fs_size)) {
+			hpfs_error(s, "free count overflow, freeing sector %08x", sec);
+			sbi->sb_n_free = -1;
+			return;
+		}
+		sbi->sb_n_free++;
+	}
+}
+
+static void hpfs_claim_dirband_alloc(struct super_block *s, secno sec)
+{
+	struct hpfs_sb_info *sbi = hpfs_sb(s);
+	if (sbi->sb_n_free_dnodes != (unsigned)-1) {
+		if (unlikely(!sbi->sb_n_free_dnodes)) {
+			hpfs_error(s, "dirband free count underflow, allocating sector %08x", sec);
+			sbi->sb_n_free_dnodes = -1;
+			return;
+		}
+		sbi->sb_n_free_dnodes--;
+	}
+}
+
+static void hpfs_claim_dirband_free(struct super_block *s, secno sec)
+{
+	struct hpfs_sb_info *sbi = hpfs_sb(s);
+	if (sbi->sb_n_free_dnodes != (unsigned)-1) {
+		if (unlikely(sbi->sb_n_free_dnodes >= sbi->sb_dirband_size / 4)) {
+			hpfs_error(s, "dirband free count overflow, freeing sector %08x", sec);
+			sbi->sb_n_free_dnodes = -1;
+			return;
+		}
+		sbi->sb_n_free_dnodes++;
+	}
+}
+
 /*
  * Check if a sector is allocated in bitmap
  * This is really slow. Turned on only if chk==2
@@ -203,9 +255,15 @@
 	}
 	sec = 0;
 	ret:
+	if (sec) {
+		i = 0;
+		do
+			hpfs_claim_alloc(s, sec + i);
+		while (unlikely(++i < n));
+	}
 	if (sec && f_p) {
 		for (i = 0; i < forward; i++) {
-			if (!hpfs_alloc_if_possible(s, sec + i + 1)) {
+			if (!hpfs_alloc_if_possible(s, sec + n + i)) {
 				hpfs_error(s, "Prealloc doesn't work! Wanted %d, allocated at %08x, can't allocate %d", forward, sec, i);
 				sec = 0;
 				break;
@@ -228,6 +286,7 @@
 	nr >>= 2;
 	sec = alloc_in_bmp(s, (~0x3fff) | nr, 1, 0);
 	if (!sec) return 0;
+	hpfs_claim_dirband_alloc(s, sec);
 	return ((sec & 0x3fff) << 2) + sbi->sb_dirband_start;
 }
 
@@ -242,6 +301,7 @@
 		bmp[(sec & 0x3fff) >> 5] &= cpu_to_le32(~(1 << (sec & 0x1f)));
 		hpfs_mark_4buffers_dirty(&qbh);
 		hpfs_brelse4(&qbh);
+		hpfs_claim_alloc(s, sec);
 		return 1;
 	}
 	hpfs_brelse4(&qbh);
@@ -275,6 +335,7 @@
 		return;
 	}
 	bmp[(sec & 0x3fff) >> 5] |= cpu_to_le32(1 << (sec & 0x1f));
+	hpfs_claim_free(s, sec);
 	if (!--n) {
 		hpfs_mark_4buffers_dirty(&qbh);
 		hpfs_brelse4(&qbh);
@@ -359,6 +420,7 @@
 		bmp[ssec >> 5] |= cpu_to_le32(1 << (ssec & 0x1f));
 		hpfs_mark_4buffers_dirty(&qbh);
 		hpfs_brelse4(&qbh);
+		hpfs_claim_dirband_free(s, dno);
 	}
 }
 
@@ -366,7 +428,7 @@
 			 dnode_secno *dno, struct quad_buffer_head *qbh)
 {
 	struct dnode *d;
-	if (hpfs_count_one_bitmap(s, hpfs_sb(s)->sb_dmap) > FREE_DNODES_ADD) {
+	if (hpfs_get_free_dnodes(s) > FREE_DNODES_ADD) {
 		if (!(*dno = alloc_in_dirband(s, near)))
 			if (!(*dno = hpfs_alloc_sector(s, near, 4, 0))) return NULL;
 	} else {
diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c
index 4d0a1af..139ef16 100644
--- a/fs/hpfs/buffer.c
+++ b/fs/hpfs/buffer.c
@@ -86,7 +86,6 @@
 void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffer_head *qbh,
 		   int ahead)
 {
-	struct buffer_head *bh;
 	char *data;
 
 	hpfs_lock_assert(s);
@@ -100,34 +99,32 @@
 
 	hpfs_prefetch_sectors(s, secno, 4 + ahead);
 
+	if (!(qbh->bh[0] = sb_bread(s, secno + 0))) goto bail0;
+	if (!(qbh->bh[1] = sb_bread(s, secno + 1))) goto bail1;
+	if (!(qbh->bh[2] = sb_bread(s, secno + 2))) goto bail2;
+	if (!(qbh->bh[3] = sb_bread(s, secno + 3))) goto bail3;
+
+	if (likely(qbh->bh[1]->b_data == qbh->bh[0]->b_data + 1 * 512) &&
+	    likely(qbh->bh[2]->b_data == qbh->bh[0]->b_data + 2 * 512) &&
+	    likely(qbh->bh[3]->b_data == qbh->bh[0]->b_data + 3 * 512)) {
+		return qbh->data = qbh->bh[0]->b_data;
+	}
+
 	qbh->data = data = kmalloc(2048, GFP_NOFS);
 	if (!data) {
 		printk("HPFS: hpfs_map_4sectors: out of memory\n");
-		goto bail;
+		goto bail4;
 	}
 
-	qbh->bh[0] = bh = sb_bread(s, secno);
-	if (!bh)
-		goto bail0;
-	memcpy(data, bh->b_data, 512);
-
-	qbh->bh[1] = bh = sb_bread(s, secno + 1);
-	if (!bh)
-		goto bail1;
-	memcpy(data + 512, bh->b_data, 512);
-
-	qbh->bh[2] = bh = sb_bread(s, secno + 2);
-	if (!bh)
-		goto bail2;
-	memcpy(data + 2 * 512, bh->b_data, 512);
-
-	qbh->bh[3] = bh = sb_bread(s, secno + 3);
-	if (!bh)
-		goto bail3;
-	memcpy(data + 3 * 512, bh->b_data, 512);
+	memcpy(data + 0 * 512, qbh->bh[0]->b_data, 512);
+	memcpy(data + 1 * 512, qbh->bh[1]->b_data, 512);
+	memcpy(data + 2 * 512, qbh->bh[2]->b_data, 512);
+	memcpy(data + 3 * 512, qbh->bh[3]->b_data, 512);
 
 	return data;
 
+ bail4:
+	brelse(qbh->bh[3]);
  bail3:
 	brelse(qbh->bh[2]);
  bail2:
@@ -135,9 +132,6 @@
  bail1:
 	brelse(qbh->bh[0]);
  bail0:
-	kfree(data);
-	printk("HPFS: hpfs_map_4sectors: read error\n");
- bail:
 	return NULL;
 }
 
@@ -155,44 +149,54 @@
 		return NULL;
 	}
 
-	/*return hpfs_map_4sectors(s, secno, qbh, 0);*/
+	if (!hpfs_get_sector(s, secno + 0, &qbh->bh[0])) goto bail0;
+	if (!hpfs_get_sector(s, secno + 1, &qbh->bh[1])) goto bail1;
+	if (!hpfs_get_sector(s, secno + 2, &qbh->bh[2])) goto bail2;
+	if (!hpfs_get_sector(s, secno + 3, &qbh->bh[3])) goto bail3;
+
+	if (likely(qbh->bh[1]->b_data == qbh->bh[0]->b_data + 1 * 512) &&
+	    likely(qbh->bh[2]->b_data == qbh->bh[0]->b_data + 2 * 512) &&
+	    likely(qbh->bh[3]->b_data == qbh->bh[0]->b_data + 3 * 512)) {
+		return qbh->data = qbh->bh[0]->b_data;
+	}
+
 	if (!(qbh->data = kmalloc(2048, GFP_NOFS))) {
 		printk("HPFS: hpfs_get_4sectors: out of memory\n");
-		return NULL;
+		goto bail4;
 	}
-	if (!(hpfs_get_sector(s, secno, &qbh->bh[0]))) goto bail0;
-	if (!(hpfs_get_sector(s, secno + 1, &qbh->bh[1]))) goto bail1;
-	if (!(hpfs_get_sector(s, secno + 2, &qbh->bh[2]))) goto bail2;
-	if (!(hpfs_get_sector(s, secno + 3, &qbh->bh[3]))) goto bail3;
-	memcpy(qbh->data, qbh->bh[0]->b_data, 512);
-	memcpy(qbh->data + 512, qbh->bh[1]->b_data, 512);
-	memcpy(qbh->data + 2*512, qbh->bh[2]->b_data, 512);
-	memcpy(qbh->data + 3*512, qbh->bh[3]->b_data, 512);
 	return qbh->data;
 
-	bail3:	brelse(qbh->bh[2]);
-	bail2:	brelse(qbh->bh[1]);
-	bail1:	brelse(qbh->bh[0]);
-	bail0:
+bail4:
+	brelse(qbh->bh[3]);
+bail3:
+	brelse(qbh->bh[2]);
+bail2:
+	brelse(qbh->bh[1]);
+bail1:
+	brelse(qbh->bh[0]);
+bail0:
 	return NULL;
 }
 	
 
 void hpfs_brelse4(struct quad_buffer_head *qbh)
 {
-	brelse(qbh->bh[3]);
-	brelse(qbh->bh[2]);
-	brelse(qbh->bh[1]);
+	if (unlikely(qbh->data != qbh->bh[0]->b_data))
+		kfree(qbh->data);
 	brelse(qbh->bh[0]);
-	kfree(qbh->data);
+	brelse(qbh->bh[1]);
+	brelse(qbh->bh[2]);
+	brelse(qbh->bh[3]);
 }	
 
 void hpfs_mark_4buffers_dirty(struct quad_buffer_head *qbh)
 {
-	memcpy(qbh->bh[0]->b_data, qbh->data, 512);
-	memcpy(qbh->bh[1]->b_data, qbh->data + 512, 512);
-	memcpy(qbh->bh[2]->b_data, qbh->data + 2 * 512, 512);
-	memcpy(qbh->bh[3]->b_data, qbh->data + 3 * 512, 512);
+	if (unlikely(qbh->data != qbh->bh[0]->b_data)) {
+		memcpy(qbh->bh[0]->b_data, qbh->data + 0 * 512, 512);
+		memcpy(qbh->bh[1]->b_data, qbh->data + 1 * 512, 512);
+		memcpy(qbh->bh[2]->b_data, qbh->data + 2 * 512, 512);
+		memcpy(qbh->bh[3]->b_data, qbh->data + 3 * 512, 512);
+	}
 	mark_buffer_dirty(qbh->bh[0]);
 	mark_buffer_dirty(qbh->bh[1]);
 	mark_buffer_dirty(qbh->bh[2]);
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index 6797bf8..3ba49c0 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -312,7 +312,7 @@
 __printf(2, 3)
 void hpfs_error(struct super_block *, const char *, ...);
 int hpfs_stop_cycles(struct super_block *, int, int *, int *, char *);
-unsigned hpfs_count_one_bitmap(struct super_block *, secno);
+unsigned hpfs_get_free_dnodes(struct super_block *);
 
 /*
  * local time (HPFS) to GMT (Unix)
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index b8d01ef..4534ff6 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -121,7 +121,7 @@
 	call_rcu(&hpfs_sb(s)->rcu, lazy_free_sbi);
 }
 
-unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno)
+static unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno)
 {
 	struct quad_buffer_head qbh;
 	unsigned long *bits;
@@ -129,7 +129,7 @@
 
 	bits = hpfs_map_4sectors(s, secno, &qbh, 0);
 	if (!bits)
-		return 0;
+		return (unsigned)-1;
 	count = bitmap_weight(bits, 2048 * BITS_PER_BYTE);
 	hpfs_brelse4(&qbh);
 	return count;
@@ -144,30 +144,45 @@
 		hpfs_prefetch_bitmap(s, n);
 	}
 	for (n = 0; n < n_bands; n++) {
+		unsigned c;
 		hpfs_prefetch_bitmap(s, n + COUNT_RD_AHEAD);
-		count += hpfs_count_one_bitmap(s, le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[n]));
+		c = hpfs_count_one_bitmap(s, le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[n]));
+		if (c != (unsigned)-1)
+			count += c;
 	}
 	return count;
 }
 
+unsigned hpfs_get_free_dnodes(struct super_block *s)
+{
+	struct hpfs_sb_info *sbi = hpfs_sb(s);
+	if (sbi->sb_n_free_dnodes == (unsigned)-1) {
+		unsigned c = hpfs_count_one_bitmap(s, sbi->sb_dmap);
+		if (c == (unsigned)-1)
+			return 0;
+		sbi->sb_n_free_dnodes = c;
+	}
+	return sbi->sb_n_free_dnodes;
+}
+
 static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *s = dentry->d_sb;
 	struct hpfs_sb_info *sbi = hpfs_sb(s);
 	u64 id = huge_encode_dev(s->s_bdev->bd_dev);
+
 	hpfs_lock(s);
 
-	/*if (sbi->sb_n_free == -1) {*/
+	if (sbi->sb_n_free == (unsigned)-1)
 		sbi->sb_n_free = count_bitmaps(s);
-		sbi->sb_n_free_dnodes = hpfs_count_one_bitmap(s, sbi->sb_dmap);
-	/*}*/
+
 	buf->f_type = s->s_magic;
 	buf->f_bsize = 512;
 	buf->f_blocks = sbi->sb_fs_size;
 	buf->f_bfree = sbi->sb_n_free;
 	buf->f_bavail = sbi->sb_n_free;
 	buf->f_files = sbi->sb_dirband_size / 4;
-	buf->f_ffree = sbi->sb_n_free_dnodes;
+	buf->f_ffree = hpfs_get_free_dnodes(s);
 	buf->f_fsid.val[0] = (u32)id;
 	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = 254;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 8360674..60bb365 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -514,11 +514,13 @@
 	 * similarly constrained call sites
 	 */
 	ret = start_this_handle(journal, handle, GFP_NOFS);
-	if (ret < 0)
+	if (ret < 0) {
 		jbd2_journal_free_reserved(handle);
+		return ret;
+	}
 	handle->h_type = type;
 	handle->h_line_no = line_no;
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(jbd2_journal_start_reserved);
 
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index e973b85..5a8ea16 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -86,6 +86,8 @@
 		rc = posix_acl_equiv_mode(acl, &inode->i_mode);
 		if (rc < 0)
 			return rc;
+		inode->i_ctime = CURRENT_TIME;
+		mark_inode_dirty(inode);
 		if (rc == 0)
 			acl = NULL;
 		break;
diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c
index 3bd5ee4..46325d5 100644
--- a/fs/jfs/xattr.c
+++ b/fs/jfs/xattr.c
@@ -854,9 +854,6 @@
 	int rc;
 	tid_t tid;
 
-	if ((rc = can_set_xattr(inode, name, value, value_len)))
-		return rc;
-
 	/*
 	 * If this is a request for a synthetic attribute in the system.*
 	 * namespace use the generic infrastructure to resolve a handler
@@ -865,6 +862,9 @@
 	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
 		return generic_setxattr(dentry, name, value, value_len, flags);
 
+	if ((rc = can_set_xattr(inode, name, value, value_len)))
+		return rc;
+
 	if (value == NULL) {	/* empty EA, do not remove */
 		value = "";
 		value_len = 0;
@@ -1034,9 +1034,6 @@
 	int rc;
 	tid_t tid;
 
-	if ((rc = can_set_xattr(inode, name, NULL, 0)))
-		return rc;
-
 	/*
 	 * If this is a request for a synthetic attribute in the system.*
 	 * namespace use the generic infrastructure to resolve a handler
@@ -1045,6 +1042,9 @@
 	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
 		return generic_removexattr(dentry, name);
 
+	if ((rc = can_set_xattr(inode, name, NULL, 0)))
+		return rc;
+
 	tid = txBegin(inode->i_sb, 0);
 	mutex_lock(&ji->commit_mutex);
 	rc = __jfs_setxattr(tid, dentry->d_inode, name, NULL, 0, XATTR_REPLACE);
@@ -1061,7 +1061,7 @@
  * attributes are handled directly.
  */
 const struct xattr_handler *jfs_xattr_handlers[] = {
-#ifdef JFS_POSIX_ACL
+#ifdef CONFIG_JFS_POSIX_ACL
 	&posix_acl_access_xattr_handler,
 	&posix_acl_default_xattr_handler,
 #endif
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 5104cf5..bd6e18b 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -187,19 +187,23 @@
 
 	kn->u.completion = (void *)&wait;
 
-	rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
+	if (kn->flags & KERNFS_LOCKDEP)
+		rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
 	/* atomic_add_return() is a mb(), put_active() will always see
 	 * the updated kn->u.completion.
 	 */
 	v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active);
 
 	if (v != KN_DEACTIVATED_BIAS) {
-		lock_contended(&kn->dep_map, _RET_IP_);
+		if (kn->flags & KERNFS_LOCKDEP)
+			lock_contended(&kn->dep_map, _RET_IP_);
 		wait_for_completion(&wait);
 	}
 
-	lock_acquired(&kn->dep_map, _RET_IP_);
-	rwsem_release(&kn->dep_map, 1, _RET_IP_);
+	if (kn->flags & KERNFS_LOCKDEP) {
+		lock_acquired(&kn->dep_map, _RET_IP_);
+		rwsem_release(&kn->dep_map, 1, _RET_IP_);
+	}
 }
 
 /**
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 0d6ce89..0f4152d 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -94,6 +94,7 @@
  * @fs_type: file_system_type of the fs being mounted
  * @flags: mount flags specified for the mount
  * @root: kernfs_root of the hierarchy being mounted
+ * @new_sb_created: tell the caller if we allocated a new superblock
  * @ns: optional namespace tag of the mount
  *
  * This is to be called from each kernfs user's file_system_type->mount()
@@ -104,7 +105,8 @@
  * The return value can be passed to the vfs layer verbatim.
  */
 struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-			       struct kernfs_root *root, const void *ns)
+			       struct kernfs_root *root, bool *new_sb_created,
+			       const void *ns)
 {
 	struct super_block *sb;
 	struct kernfs_super_info *info;
@@ -122,6 +124,10 @@
 		kfree(info);
 	if (IS_ERR(sb))
 		return ERR_CAST(sb);
+
+	if (new_sb_created)
+		*new_sb_created = !sb->s_root;
+
 	if (!sb->s_root) {
 		error = kernfs_fill_super(sb);
 		if (error) {
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index e066a39..ab798a8 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -779,6 +779,7 @@
 	struct nlm_file		*file = block->b_file;
 	struct nlm_lock		*lock = &block->b_call->a_args.lock;
 	int			error;
+	loff_t			fl_start, fl_end;
 
 	dprintk("lockd: grant blocked lock %p\n", block);
 
@@ -796,9 +797,16 @@
 	}
 
 	/* Try the lock operation again */
+	/* vfs_lock_file() can mangle fl_start and fl_end, but we need
+	 * them unchanged for the GRANT_MSG
+	 */
 	lock->fl.fl_flags |= FL_SLEEP;
+	fl_start = lock->fl.fl_start;
+	fl_end = lock->fl.fl_end;
 	error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
 	lock->fl.fl_flags &= ~FL_SLEEP;
+	lock->fl.fl_start = fl_start;
+	lock->fl.fl_end = fl_end;
 
 	switch (error) {
 	case 0:
diff --git a/fs/mount.h b/fs/mount.h
index a17458c..b29e42f 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -19,13 +19,13 @@
 };
 
 struct mountpoint {
-	struct list_head m_hash;
+	struct hlist_node m_hash;
 	struct dentry *m_dentry;
 	int m_count;
 };
 
 struct mount {
-	struct list_head mnt_hash;
+	struct hlist_node mnt_hash;
 	struct mount *mnt_parent;
 	struct dentry *mnt_mountpoint;
 	struct vfsmount mnt;
diff --git a/fs/namei.c b/fs/namei.c
index d580df2..4b491b4 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -196,6 +196,7 @@
 		goto error;
 
 	result->uptr = filename;
+	result->aname = NULL;
 	audit_getname(result);
 	return result;
 
@@ -210,6 +211,35 @@
 	return getname_flags(filename, 0, NULL);
 }
 
+/*
+ * The "getname_kernel()" interface doesn't do pathnames longer
+ * than EMBEDDED_NAME_MAX. Deal with it - you're a kernel user.
+ */
+struct filename *
+getname_kernel(const char * filename)
+{
+	struct filename *result;
+	char *kname;
+	int len;
+
+	len = strlen(filename);
+	if (len >= EMBEDDED_NAME_MAX)
+		return ERR_PTR(-ENAMETOOLONG);
+
+	result = __getname();
+	if (unlikely(!result))
+		return ERR_PTR(-ENOMEM);
+
+	kname = (char *)result + sizeof(*result);
+	result->name = kname;
+	result->uptr = NULL;
+	result->aname = NULL;
+	result->separate = false;
+
+	strlcpy(kname, filename, EMBEDDED_NAME_MAX);
+	return result;
+}
+
 #ifdef CONFIG_AUDITSYSCALL
 void putname(struct filename *name)
 {
@@ -1079,7 +1109,7 @@
 			return false;
 
 		if (!d_mountpoint(path->dentry))
-			break;
+			return true;
 
 		mounted = __lookup_mnt(path->mnt, path->dentry);
 		if (!mounted)
@@ -1095,20 +1125,7 @@
 		 */
 		*inode = path->dentry->d_inode;
 	}
-	return true;
-}
-
-static void follow_mount_rcu(struct nameidata *nd)
-{
-	while (d_mountpoint(nd->path.dentry)) {
-		struct mount *mounted;
-		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
-		if (!mounted)
-			break;
-		nd->path.mnt = &mounted->mnt;
-		nd->path.dentry = mounted->mnt.mnt_root;
-		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
-	}
+	return read_seqretry(&mount_lock, nd->m_seq);
 }
 
 static int follow_dotdot_rcu(struct nameidata *nd)
@@ -1136,7 +1153,17 @@
 			break;
 		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
 	}
-	follow_mount_rcu(nd);
+	while (d_mountpoint(nd->path.dentry)) {
+		struct mount *mounted;
+		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
+		if (!mounted)
+			break;
+		nd->path.mnt = &mounted->mnt;
+		nd->path.dentry = mounted->mnt.mnt_root;
+		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
+		if (!read_seqretry(&mount_lock, nd->m_seq))
+			goto failed;
+	}
 	nd->inode = nd->path.dentry->d_inode;
 	return 0;
 
@@ -1854,7 +1881,7 @@
 
 		nd->path = f.file->f_path;
 		if (flags & LOOKUP_RCU) {
-			if (f.need_put)
+			if (f.flags & FDPUT_FPUT)
 				*fp = f.file;
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			rcu_read_lock();
diff --git a/fs/namespace.c b/fs/namespace.c
index 22e5367..2ffc5a2 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -23,11 +23,34 @@
 #include <linux/uaccess.h>
 #include <linux/proc_ns.h>
 #include <linux/magic.h>
+#include <linux/bootmem.h>
 #include "pnode.h"
 #include "internal.h"
 
-#define HASH_SHIFT ilog2(PAGE_SIZE / sizeof(struct list_head))
-#define HASH_SIZE (1UL << HASH_SHIFT)
+static unsigned int m_hash_mask __read_mostly;
+static unsigned int m_hash_shift __read_mostly;
+static unsigned int mp_hash_mask __read_mostly;
+static unsigned int mp_hash_shift __read_mostly;
+
+static __initdata unsigned long mhash_entries;
+static int __init set_mhash_entries(char *str)
+{
+	if (!str)
+		return 0;
+	mhash_entries = simple_strtoul(str, &str, 0);
+	return 1;
+}
+__setup("mhash_entries=", set_mhash_entries);
+
+static __initdata unsigned long mphash_entries;
+static int __init set_mphash_entries(char *str)
+{
+	if (!str)
+		return 0;
+	mphash_entries = simple_strtoul(str, &str, 0);
+	return 1;
+}
+__setup("mphash_entries=", set_mphash_entries);
 
 static int event;
 static DEFINE_IDA(mnt_id_ida);
@@ -36,8 +59,8 @@
 static int mnt_id_start = 0;
 static int mnt_group_start = 1;
 
-static struct list_head *mount_hashtable __read_mostly;
-static struct list_head *mountpoint_hashtable __read_mostly;
+static struct hlist_head *mount_hashtable __read_mostly;
+static struct hlist_head *mountpoint_hashtable __read_mostly;
 static struct kmem_cache *mnt_cache __read_mostly;
 static DECLARE_RWSEM(namespace_sem);
 
@@ -55,12 +78,19 @@
  */
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
 
-static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
+static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry)
 {
 	unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
 	tmp += ((unsigned long)dentry / L1_CACHE_BYTES);
-	tmp = tmp + (tmp >> HASH_SHIFT);
-	return tmp & (HASH_SIZE - 1);
+	tmp = tmp + (tmp >> m_hash_shift);
+	return &mount_hashtable[tmp & m_hash_mask];
+}
+
+static inline struct hlist_head *mp_hash(struct dentry *dentry)
+{
+	unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES);
+	tmp = tmp + (tmp >> mp_hash_shift);
+	return &mountpoint_hashtable[tmp & mp_hash_mask];
 }
 
 /*
@@ -187,7 +217,7 @@
 		mnt->mnt_writers = 0;
 #endif
 
-		INIT_LIST_HEAD(&mnt->mnt_hash);
+		INIT_HLIST_NODE(&mnt->mnt_hash);
 		INIT_LIST_HEAD(&mnt->mnt_child);
 		INIT_LIST_HEAD(&mnt->mnt_mounts);
 		INIT_LIST_HEAD(&mnt->mnt_list);
@@ -575,10 +605,10 @@
  */
 struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 {
-	struct list_head *head = mount_hashtable + hash(mnt, dentry);
+	struct hlist_head *head = m_hash(mnt, dentry);
 	struct mount *p;
 
-	list_for_each_entry_rcu(p, head, mnt_hash)
+	hlist_for_each_entry_rcu(p, head, mnt_hash)
 		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
 			return p;
 	return NULL;
@@ -590,13 +620,17 @@
  */
 struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
 {
-	struct list_head *head = mount_hashtable + hash(mnt, dentry);
-	struct mount *p;
-
-	list_for_each_entry_reverse(p, head, mnt_hash)
-		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
-			return p;
-	return NULL;
+	struct mount *p, *res;
+	res = p = __lookup_mnt(mnt, dentry);
+	if (!p)
+		goto out;
+	hlist_for_each_entry_continue(p, mnt_hash) {
+		if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
+			break;
+		res = p;
+	}
+out:
+	return res;
 }
 
 /*
@@ -633,11 +667,11 @@
 
 static struct mountpoint *new_mountpoint(struct dentry *dentry)
 {
-	struct list_head *chain = mountpoint_hashtable + hash(NULL, dentry);
+	struct hlist_head *chain = mp_hash(dentry);
 	struct mountpoint *mp;
 	int ret;
 
-	list_for_each_entry(mp, chain, m_hash) {
+	hlist_for_each_entry(mp, chain, m_hash) {
 		if (mp->m_dentry == dentry) {
 			/* might be worth a WARN_ON() */
 			if (d_unlinked(dentry))
@@ -659,7 +693,7 @@
 
 	mp->m_dentry = dentry;
 	mp->m_count = 1;
-	list_add(&mp->m_hash, chain);
+	hlist_add_head(&mp->m_hash, chain);
 	return mp;
 }
 
@@ -670,7 +704,7 @@
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags &= ~DCACHE_MOUNTED;
 		spin_unlock(&dentry->d_lock);
-		list_del(&mp->m_hash);
+		hlist_del(&mp->m_hash);
 		kfree(mp);
 	}
 }
@@ -712,7 +746,7 @@
 	mnt->mnt_parent = mnt;
 	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
 	list_del_init(&mnt->mnt_child);
-	list_del_init(&mnt->mnt_hash);
+	hlist_del_init_rcu(&mnt->mnt_hash);
 	put_mountpoint(mnt->mnt_mp);
 	mnt->mnt_mp = NULL;
 }
@@ -739,15 +773,14 @@
 			struct mountpoint *mp)
 {
 	mnt_set_mountpoint(parent, mp, mnt);
-	list_add_tail(&mnt->mnt_hash, mount_hashtable +
-			hash(&parent->mnt, mp->m_dentry));
+	hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
 	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
 }
 
 /*
  * vfsmount lock must be held for write
  */
-static void commit_tree(struct mount *mnt)
+static void commit_tree(struct mount *mnt, struct mount *shadows)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;
@@ -762,8 +795,11 @@
 
 	list_splice(&head, n->list.prev);
 
-	list_add_tail(&mnt->mnt_hash, mount_hashtable +
-				hash(&parent->mnt, mnt->mnt_mountpoint));
+	if (shadows)
+		hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash);
+	else
+		hlist_add_head_rcu(&mnt->mnt_hash,
+				m_hash(&parent->mnt, mnt->mnt_mountpoint));
 	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
 	touch_mnt_namespace(n);
 }
@@ -1153,26 +1189,28 @@
 
 EXPORT_SYMBOL(may_umount);
 
-static LIST_HEAD(unmounted);	/* protected by namespace_sem */
+static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
 
 static void namespace_unlock(void)
 {
 	struct mount *mnt;
-	LIST_HEAD(head);
+	struct hlist_head head = unmounted;
 
-	if (likely(list_empty(&unmounted))) {
+	if (likely(hlist_empty(&head))) {
 		up_write(&namespace_sem);
 		return;
 	}
 
-	list_splice_init(&unmounted, &head);
+	head.first->pprev = &head.first;
+	INIT_HLIST_HEAD(&unmounted);
+
 	up_write(&namespace_sem);
 
 	synchronize_rcu();
 
-	while (!list_empty(&head)) {
-		mnt = list_first_entry(&head, struct mount, mnt_hash);
-		list_del_init(&mnt->mnt_hash);
+	while (!hlist_empty(&head)) {
+		mnt = hlist_entry(head.first, struct mount, mnt_hash);
+		hlist_del_init(&mnt->mnt_hash);
 		if (mnt->mnt_ex_mountpoint.mnt)
 			path_put(&mnt->mnt_ex_mountpoint);
 		mntput(&mnt->mnt);
@@ -1193,16 +1231,19 @@
  */
 void umount_tree(struct mount *mnt, int how)
 {
-	LIST_HEAD(tmp_list);
+	HLIST_HEAD(tmp_list);
 	struct mount *p;
+	struct mount *last = NULL;
 
-	for (p = mnt; p; p = next_mnt(p, mnt))
-		list_move(&p->mnt_hash, &tmp_list);
+	for (p = mnt; p; p = next_mnt(p, mnt)) {
+		hlist_del_init_rcu(&p->mnt_hash);
+		hlist_add_head(&p->mnt_hash, &tmp_list);
+	}
 
 	if (how)
 		propagate_umount(&tmp_list);
 
-	list_for_each_entry(p, &tmp_list, mnt_hash) {
+	hlist_for_each_entry(p, &tmp_list, mnt_hash) {
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
@@ -1220,8 +1261,13 @@
 			p->mnt_mp = NULL;
 		}
 		change_mnt_propagation(p, MS_PRIVATE);
+		last = p;
 	}
-	list_splice(&tmp_list, &unmounted);
+	if (last) {
+		last->mnt_hash.next = unmounted.first;
+		unmounted.first = tmp_list.first;
+		unmounted.first->pprev = &unmounted.first;
+	}
 }
 
 static void shrink_submounts(struct mount *mnt);
@@ -1605,24 +1651,23 @@
 			struct mountpoint *dest_mp,
 			struct path *parent_path)
 {
-	LIST_HEAD(tree_list);
+	HLIST_HEAD(tree_list);
 	struct mount *child, *p;
+	struct hlist_node *n;
 	int err;
 
 	if (IS_MNT_SHARED(dest_mnt)) {
 		err = invent_group_ids(source_mnt, true);
 		if (err)
 			goto out;
-	}
-	err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
-	if (err)
-		goto out_cleanup_ids;
-
-	lock_mount_hash();
-
-	if (IS_MNT_SHARED(dest_mnt)) {
+		err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
+		if (err)
+			goto out_cleanup_ids;
+		lock_mount_hash();
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
 			set_mnt_shared(p);
+	} else {
+		lock_mount_hash();
 	}
 	if (parent_path) {
 		detach_mnt(source_mnt, parent_path);
@@ -1630,20 +1675,22 @@
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-		commit_tree(source_mnt);
+		commit_tree(source_mnt, NULL);
 	}
 
-	list_for_each_entry_safe(child, p, &tree_list, mnt_hash) {
-		list_del_init(&child->mnt_hash);
-		commit_tree(child);
+	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
+		struct mount *q;
+		hlist_del_init(&child->mnt_hash);
+		q = __lookup_mnt_last(&child->mnt_parent->mnt,
+				      child->mnt_mountpoint);
+		commit_tree(child, q);
 	}
 	unlock_mount_hash();
 
 	return 0;
 
  out_cleanup_ids:
-	if (IS_MNT_SHARED(dest_mnt))
-		cleanup_group_ids(source_mnt, NULL);
+	cleanup_group_ids(source_mnt, NULL);
  out:
 	return err;
 }
@@ -2777,18 +2824,24 @@
 	mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
 			0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
 
-	mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);
-	mountpoint_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);
+	mount_hashtable = alloc_large_system_hash("Mount-cache",
+				sizeof(struct hlist_head),
+				mhash_entries, 19,
+				0,
+				&m_hash_shift, &m_hash_mask, 0, 0);
+	mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache",
+				sizeof(struct hlist_head),
+				mphash_entries, 19,
+				0,
+				&mp_hash_shift, &mp_hash_mask, 0, 0);
 
 	if (!mount_hashtable || !mountpoint_hashtable)
 		panic("Failed to allocate mount hash table\n");
 
-	printk(KERN_INFO "Mount-cache hash table entries: %lu\n", HASH_SIZE);
-
-	for (u = 0; u < HASH_SIZE; u++)
-		INIT_LIST_HEAD(&mount_hashtable[u]);
-	for (u = 0; u < HASH_SIZE; u++)
-		INIT_LIST_HEAD(&mountpoint_hashtable[u]);
+	for (u = 0; u <= m_hash_mask; u++)
+		INIT_HLIST_HEAD(&mount_hashtable[u]);
+	for (u = 0; u <= mp_hash_mask; u++)
+		INIT_HLIST_HEAD(&mountpoint_hashtable[u]);
 
 	kernfs_init();
 
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index ef792f2..5d8ccec 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -659,16 +659,19 @@
 
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (delegation == NULL)
+		goto out_enoent;
 
-	if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
-		rcu_read_unlock();
-		return -ENOENT;
-	}
+	if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
+		goto out_enoent;
 	nfs_mark_return_delegation(server, delegation);
 	rcu_read_unlock();
 
 	nfs_delegation_run_state_manager(clp);
 	return 0;
+out_enoent:
+	rcu_read_unlock();
+	return -ENOENT;
 }
 
 static struct inode *
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index be38b57..4a48fe4 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1846,6 +1846,11 @@
 							GFP_KERNEL)) {
 		SetPageUptodate(page);
 		unlock_page(page);
+		/*
+		 * add_to_page_cache_lru() grabs an extra page refcount.
+		 * Drop it here to avoid leaking this page later.
+		 */
+		page_cache_release(page);
 	} else
 		__free_page(page);
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 28a0a3c..360114a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -164,17 +164,16 @@
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
 		nfs_fscache_invalidate(inode);
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-					| NFS_INO_INVALID_LABEL
 					| NFS_INO_INVALID_DATA
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
 					| NFS_INO_REVAL_PAGECACHE;
 	} else
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-					| NFS_INO_INVALID_LABEL
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
 					| NFS_INO_REVAL_PAGECACHE;
+	nfs_zap_label_cache_locked(nfsi);
 }
 
 void nfs_zap_caches(struct inode *inode)
@@ -266,6 +265,13 @@
 }
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
+static void nfs_clear_label_invalid(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL;
+	spin_unlock(&inode->i_lock);
+}
+
 void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 					struct nfs4_label *label)
 {
@@ -283,6 +289,7 @@
 					__func__,
 					(char *)label->label,
 					label->len, error);
+		nfs_clear_label_invalid(inode);
 	}
 }
 
@@ -1648,7 +1655,7 @@
 		inode->i_blocks = fattr->du.nfs2.blocks;
 
 	/* Update attrtimeo value if we're out of the unstable period */
-	if (invalid & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) {
+	if (invalid & NFS_INO_INVALID_ATTR) {
 		nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 		nfsi->attrtimeo_timestamp = now;
@@ -1661,7 +1668,6 @@
 		}
 	}
 	invalid &= ~NFS_INO_INVALID_ATTR;
-	invalid &= ~NFS_INO_INVALID_LABEL;
 	/* Don't invalidate the data if we were to blame */
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
 				|| S_ISLNK(inode->i_mode)))
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 8b5cc04..b46cf5a 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -176,7 +176,8 @@
 extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
 						      struct nfs_fh *);
 extern int nfs4_update_server(struct nfs_server *server, const char *hostname,
-					struct sockaddr *sap, size_t salen);
+					struct sockaddr *sap, size_t salen,
+					struct net *net);
 extern void nfs_free_server(struct nfs_server *server);
 extern struct nfs_server *nfs_clone_server(struct nfs_server *,
 					   struct nfs_fh *,
@@ -279,9 +280,18 @@
 	}
 	return;
 }
+
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+	if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL))
+		nfsi->cache_validity |= NFS_INO_INVALID_LABEL;
+}
 #else
 static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; }
 static inline void nfs4_label_free(void *label) {}
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+}
 #endif /* CONFIG_NFS_V4_SECURITY_LABEL */
 
 /* proc.c */
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 9a5ca03..871d6ed 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -80,7 +80,7 @@
 	}
 
 	if (res.acl_access != NULL) {
-		if (posix_acl_equiv_mode(res.acl_access, NULL) ||
+		if ((posix_acl_equiv_mode(res.acl_access, NULL) == 0) ||
 		    res.acl_access->a_count == 0) {
 			posix_acl_release(res.acl_access);
 			res.acl_access = NULL;
@@ -113,7 +113,7 @@
 	return ERR_PTR(status);
 }
 
-int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 		struct posix_acl *dfacl)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
@@ -198,6 +198,15 @@
 	return status;
 }
 
+int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+		struct posix_acl *dfacl)
+{
+	int ret;
+	ret = __nfs3_proc_setacls(inode, acl, dfacl);
+	return (ret == -EOPNOTSUPP) ? 0 : ret;
+
+}
+
 int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	struct posix_acl *alloc = NULL, *dfacl = NULL;
@@ -225,7 +234,7 @@
 		if (IS_ERR(alloc))
 			goto fail;
 	}
-	status = nfs3_proc_setacls(inode, acl, dfacl);
+	status = __nfs3_proc_setacls(inode, acl, dfacl);
 	posix_acl_release(alloc);
 	return status;
 
@@ -233,25 +242,6 @@
 	return PTR_ERR(alloc);
 }
 
-int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode,
-		umode_t mode)
-{
-	struct posix_acl *default_acl, *acl;
-	int error;
-
-	error = posix_acl_create(dir, &mode, &default_acl, &acl);
-	if (error)
-		return (error == -EOPNOTSUPP) ? 0 : error;
-
-	error = nfs3_proc_setacls(inode, acl, default_acl);
-
-	if (acl)
-		posix_acl_release(acl);
-	if (default_acl)
-		posix_acl_release(default_acl);
-	return error;
-}
-
 const struct xattr_handler *nfs3_xattr_handlers[] = {
 	&posix_acl_access_xattr_handler,
 	&posix_acl_default_xattr_handler,
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index aa9bc97..a462ef0 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -18,6 +18,7 @@
 #include <linux/lockd/bind.h>
 #include <linux/nfs_mount.h>
 #include <linux/freezer.h>
+#include <linux/xattr.h>
 
 #include "iostat.h"
 #include "internal.h"
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index dbb3e1f..0e46d3d 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -170,7 +170,7 @@
 void nfs40_shutdown_client(struct nfs_client *clp)
 {
 	if (clp->cl_slot_tbl) {
-		nfs4_release_slot_table(clp->cl_slot_tbl);
+		nfs4_shutdown_slot_table(clp->cl_slot_tbl);
 		kfree(clp->cl_slot_tbl);
 	}
 }
@@ -1135,6 +1135,7 @@
  * @hostname: new end-point's hostname
  * @sap: new end-point's socket address
  * @salen: size of "sap"
+ * @net: net namespace
  *
  * The nfs_server must be quiescent before this function is invoked.
  * Either its session is drained (NFSv4.1+), or its transport is
@@ -1143,13 +1144,13 @@
  * Returns zero on success, or a negative errno value.
  */
 int nfs4_update_server(struct nfs_server *server, const char *hostname,
-		       struct sockaddr *sap, size_t salen)
+		       struct sockaddr *sap, size_t salen, struct net *net)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct rpc_clnt *clnt = server->client;
 	struct xprt_create xargs = {
 		.ident		= clp->cl_proto,
-		.net		= &init_net,
+		.net		= net,
 		.dstaddr	= sap,
 		.addrlen	= salen,
 		.servername	= hostname,
@@ -1189,7 +1190,7 @@
 	error = nfs4_set_client(server, hostname, sap, salen, buf,
 				clp->cl_rpcclient->cl_auth->au_flavor,
 				clp->cl_proto, clnt->cl_timeout,
-				clp->cl_minorversion, clp->cl_net);
+				clp->cl_minorversion, net);
 	nfs_put_client(clp);
 	if (error != 0) {
 		nfs_server_insert_lists(server);
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 12c8132..b9a35c0 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -324,8 +324,9 @@
 			&rdata->res.seq_res,
 			task))
 		return;
-	nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
-			rdata->args.lock_context, FMODE_READ);
+	if (nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
+			rdata->args.lock_context, FMODE_READ) == -EIO)
+		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
 }
 
 static void filelayout_read_call_done(struct rpc_task *task, void *data)
@@ -435,8 +436,9 @@
 			&wdata->res.seq_res,
 			task))
 		return;
-	nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
-			wdata->args.lock_context, FMODE_WRITE);
+	if (nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
+			wdata->args.lock_context, FMODE_WRITE) == -EIO)
+		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
 }
 
 static void filelayout_write_call_done(struct rpc_task *task, void *data)
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 4e7f05d..3d5dbf8 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -121,9 +121,8 @@
 }
 
 static size_t nfs_parse_server_name(char *string, size_t len,
-		struct sockaddr *sa, size_t salen, struct nfs_server *server)
+		struct sockaddr *sa, size_t salen, struct net *net)
 {
-	struct net *net = rpc_net_ns(server->client);
 	ssize_t ret;
 
 	ret = rpc_pton(net, string, len, sa, salen);
@@ -223,6 +222,7 @@
 				     const struct nfs4_fs_location *location)
 {
 	const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+	struct net *net = rpc_net_ns(NFS_SB(mountdata->sb)->client);
 	struct vfsmount *mnt = ERR_PTR(-ENOENT);
 	char *mnt_path;
 	unsigned int maxbuflen;
@@ -248,8 +248,7 @@
 			continue;
 
 		mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len,
-				mountdata->addr, addr_bufsize,
-				NFS_SB(mountdata->sb));
+				mountdata->addr, addr_bufsize, net);
 		if (mountdata->addrlen == 0)
 			continue;
 
@@ -419,6 +418,7 @@
 		const struct nfs4_fs_location *location)
 {
 	const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+	struct net *net = rpc_net_ns(server->client);
 	struct sockaddr *sap;
 	unsigned int s;
 	size_t salen;
@@ -440,7 +440,7 @@
 			continue;
 
 		salen = nfs_parse_server_name(buf->data, buf->len,
-						sap, addr_bufsize, server);
+						sap, addr_bufsize, net);
 		if (salen == 0)
 			continue;
 		rpc_set_port(sap, NFS_PORT);
@@ -450,7 +450,7 @@
 		if (hostname == NULL)
 			break;
 
-		error = nfs4_update_server(server, hostname, sap, salen);
+		error = nfs4_update_server(server, hostname, sap, salen, net);
 		kfree(hostname);
 		if (error == 0)
 			break;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 42da6af..450bfed 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1620,15 +1620,15 @@
 {
 	struct nfs4_opendata *data = calldata;
 
-	nfs40_setup_sequence(data->o_arg.server, &data->o_arg.seq_args,
-				&data->o_res.seq_res, task);
+	nfs40_setup_sequence(data->o_arg.server, &data->c_arg.seq_args,
+				&data->c_res.seq_res, task);
 }
 
 static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_opendata *data = calldata;
 
-	nfs40_sequence_done(task, &data->o_res.seq_res);
+	nfs40_sequence_done(task, &data->c_res.seq_res);
 
 	data->rpc_status = task->tk_status;
 	if (data->rpc_status == 0) {
@@ -1686,7 +1686,7 @@
 	};
 	int status;
 
-	nfs4_init_sequence(&data->o_arg.seq_args, &data->o_res.seq_res, 1);
+	nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1);
 	kref_get(&data->kref);
 	data->rpc_done = 0;
 	data->rpc_status = 0;
@@ -2398,13 +2398,16 @@
 
 	if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) {
 		/* Use that stateid */
-	} else if (truncate && state != NULL && nfs4_valid_open_stateid(state)) {
+	} else if (truncate && state != NULL) {
 		struct nfs_lockowner lockowner = {
 			.l_owner = current->files,
 			.l_pid = current->tgid,
 		};
-		nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
-				&lockowner);
+		if (!nfs4_valid_open_stateid(state))
+			return -EBADF;
+		if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
+				&lockowner) == -EIO)
+			return -EBADF;
 	} else
 		nfs4_stateid_copy(&arg.stateid, &zero_stateid);
 
@@ -4011,8 +4014,9 @@
 {
 	nfs4_stateid current_stateid;
 
-	if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode))
-		return false;
+	/* If the current stateid represents a lost lock, then exit */
+	if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode) == -EIO)
+		return true;
 	return nfs4_stateid_match(stateid, &current_stateid);
 }
 
@@ -5828,8 +5832,7 @@
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server;
 	struct nfs_release_lockowner_args args;
-	struct nfs4_sequence_args seq_args;
-	struct nfs4_sequence_res seq_res;
+	struct nfs_release_lockowner_res res;
 	unsigned long timestamp;
 };
 
@@ -5837,7 +5840,7 @@
 {
 	struct nfs_release_lockowner_data *data = calldata;
 	nfs40_setup_sequence(data->server,
-				&data->seq_args, &data->seq_res, task);
+				&data->args.seq_args, &data->res.seq_res, task);
 	data->timestamp = jiffies;
 }
 
@@ -5846,7 +5849,7 @@
 	struct nfs_release_lockowner_data *data = calldata;
 	struct nfs_server *server = data->server;
 
-	nfs40_sequence_done(task, &data->seq_res);
+	nfs40_sequence_done(task, &data->res.seq_res);
 
 	switch (task->tk_status) {
 	case 0:
@@ -5887,7 +5890,6 @@
 	data = kmalloc(sizeof(*data), GFP_NOFS);
 	if (!data)
 		return -ENOMEM;
-	nfs4_init_sequence(&data->seq_args, &data->seq_res, 0);
 	data->lsp = lsp;
 	data->server = server;
 	data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
@@ -5895,6 +5897,8 @@
 	data->args.lock_owner.s_dev = server->s_dev;
 
 	msg.rpc_argp = &data->args;
+	msg.rpc_resp = &data->res;
+	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
 	rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data);
 	return 0;
 }
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index cf883c7..e799dc3 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -231,14 +231,23 @@
 	return ret;
 }
 
+/*
+ * nfs4_release_slot_table - release all slot table entries
+ */
+static void nfs4_release_slot_table(struct nfs4_slot_table *tbl)
+{
+	nfs4_shrink_slot_table(tbl, 0);
+}
+
 /**
- * nfs4_release_slot_table - release resources attached to a slot table
+ * nfs4_shutdown_slot_table - release resources attached to a slot table
  * @tbl: slot table to shut down
  *
  */
-void nfs4_release_slot_table(struct nfs4_slot_table *tbl)
+void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl)
 {
-	nfs4_shrink_slot_table(tbl, 0);
+	nfs4_release_slot_table(tbl);
+	rpc_destroy_wait_queue(&tbl->slot_tbl_waitq);
 }
 
 /**
@@ -422,7 +431,7 @@
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 
-static void nfs4_destroy_session_slot_tables(struct nfs4_session *session)
+static void nfs4_release_session_slot_tables(struct nfs4_session *session)
 {
 	nfs4_release_slot_table(&session->fc_slot_table);
 	nfs4_release_slot_table(&session->bc_slot_table);
@@ -450,7 +459,7 @@
 	if (status && tbl->slots == NULL)
 		/* Fore and back channel share a connection so get
 		 * both slot tables or neither */
-		nfs4_destroy_session_slot_tables(ses);
+		nfs4_release_session_slot_tables(ses);
 	return status;
 }
 
@@ -470,6 +479,12 @@
 	return session;
 }
 
+static void nfs4_destroy_session_slot_tables(struct nfs4_session *session)
+{
+	nfs4_shutdown_slot_table(&session->fc_slot_table);
+	nfs4_shutdown_slot_table(&session->bc_slot_table);
+}
+
 void nfs4_destroy_session(struct nfs4_session *session)
 {
 	struct rpc_xprt *xprt;
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 2323061..b34ada9 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -74,7 +74,7 @@
 
 extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
 		unsigned int max_reqs, const char *queue);
-extern void nfs4_release_slot_table(struct nfs4_slot_table *tbl);
+extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl);
 extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
 extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
 extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e5be725..0deb321 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -974,9 +974,6 @@
 	else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
 		nfs4_stateid_copy(dst, &lsp->ls_stateid);
 		ret = 0;
-		smp_rmb();
-		if (!list_empty(&lsp->ls_seqid.list))
-			ret = -EWOULDBLOCK;
 	}
 	spin_unlock(&state->state_lock);
 	nfs4_put_lock_state(lsp);
@@ -984,10 +981,9 @@
 	return ret;
 }
 
-static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
 {
 	const nfs4_stateid *src;
-	int ret;
 	int seq;
 
 	do {
@@ -996,12 +992,7 @@
 		if (test_bit(NFS_OPEN_STATE, &state->flags))
 			src = &state->open_stateid;
 		nfs4_stateid_copy(dst, src);
-		ret = 0;
-		smp_rmb();
-		if (!list_empty(&state->owner->so_seqid.list))
-			ret = -EWOULDBLOCK;
 	} while (read_seqretry(&state->seqlock, seq));
-	return ret;
 }
 
 /*
@@ -1015,15 +1006,19 @@
 	if (ret == -EIO)
 		/* A lost lock - don't even consider delegations */
 		goto out;
-	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
+	/* returns true if delegation stateid found and copied */
+	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) {
+		ret = 0;
 		goto out;
+	}
 	if (ret != -ENOENT)
 		/* nfs4_copy_delegation_stateid() didn't over-write
 		 * dst, so it still has the lock stateid which we now
 		 * choose to use.
 		 */
 		goto out;
-	ret = nfs4_copy_open_stateid(dst, state);
+	nfs4_copy_open_stateid(dst, state);
+	ret = 0;
 out:
 	if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41))
 		dst->seqid = 0;
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index d3a5871..d190e33 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -151,17 +151,15 @@
 		pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
 		if (IS_ERR(pacl))
 			return PTR_ERR(pacl);
-		/* allocate for worst case: one (deny, allow) pair each: */
-		size += 2 * pacl->a_count;
 	}
+	/* allocate for worst case: one (deny, allow) pair each: */
+	size += 2 * pacl->a_count;
 
 	if (S_ISDIR(inode->i_mode)) {
 		flags = NFS4_ACL_DIR;
 		dpacl = get_acl(inode, ACL_TYPE_DEFAULT);
 		if (dpacl)
 			size += 2 * dpacl->a_count;
-	} else {
-		dpacl = NULL;
 	}
 
 	*acl = nfs4_acl_new(size);
@@ -170,8 +168,7 @@
 		goto out;
 	}
 
-	if (pacl)
-		_posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT);
+	_posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT);
 
 	if (dpacl)
 		_posix_to_nfsv4_one(dpacl, *acl, flags | NFS4_ACL_TYPE_DEFAULT);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 017d3cb..6d7be3f 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -449,6 +449,7 @@
 	fh_lock(fhp);
 	host_err = notify_change(dentry, iap, NULL);
 	fh_unlock(fhp);
+	err = nfserrno(host_err);
 
 out_put_write_access:
 	if (size_change)
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 0b9ff43..abc8cbc 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -86,7 +86,7 @@
 				struct fsnotify_mark *inode_mark,
 				struct fsnotify_mark *vfsmount_mark,
 				u32 mask, void *data, int data_type,
-				const unsigned char *file_name)
+				const unsigned char *file_name, u32 cookie)
 {
 	struct dnotify_mark *dn_mark;
 	struct dnotify_struct *dn;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 0e792f5..dc638f7 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -147,7 +147,7 @@
 				 struct fsnotify_mark *inode_mark,
 				 struct fsnotify_mark *fanotify_mark,
 				 u32 mask, void *data, int data_type,
-				 const unsigned char *file_name)
+				 const unsigned char *file_name, u32 cookie)
 {
 	int ret = 0;
 	struct fanotify_event_info *event;
@@ -192,10 +192,12 @@
 
 	ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge);
 	if (ret) {
-		BUG_ON(mask & FAN_ALL_PERM_EVENTS);
+		/* Permission events shouldn't be merged */
+		BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS);
 		/* Our event wasn't used in the end. Free it. */
 		fsnotify_destroy_event(group, fsn_event);
-		ret = 0;
+
+		return 0;
 	}
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index b6175fa..287a22c 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -698,6 +698,7 @@
 	struct fsnotify_group *group;
 	int f_flags, fd;
 	struct user_struct *user;
+	struct fanotify_event_info *oevent;
 
 	pr_debug("%s: flags=%d event_f_flags=%d\n",
 		__func__, flags, event_f_flags);
@@ -730,8 +731,20 @@
 	group->fanotify_data.user = user;
 	atomic_inc(&user->fanotify_listeners);
 
+	oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+	if (unlikely(!oevent)) {
+		fd = -ENOMEM;
+		goto out_destroy_group;
+	}
+	group->overflow_event = &oevent->fse;
+	fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+	oevent->tgid = get_pid(task_tgid(current));
+	oevent->path.mnt = NULL;
+	oevent->path.dentry = NULL;
+
 	group->fanotify_data.f_flags = event_f_flags;
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	oevent->response = 0;
 	mutex_init(&group->fanotify_data.access_mutex);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 1d4e1ea..9d3e9c5 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -179,7 +179,7 @@
 
 	return group->ops->handle_event(group, to_tell, inode_mark,
 					vfsmount_mark, mask, data, data_is,
-					file_name);
+					file_name, cookie);
 }
 
 /*
diff --git a/fs/notify/group.c b/fs/notify/group.c
index ee674fe..ad19959 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -55,6 +55,13 @@
 	/* clear the notification queue of all events */
 	fsnotify_flush_notify(group);
 
+	/*
+	 * Destroy overflow event (we cannot use fsnotify_destroy_event() as
+	 * that deliberately ignores overflow events.
+	 */
+	if (group->overflow_event)
+		group->ops->free_event(group->overflow_event);
+
 	fsnotify_put_group(group);
 }
 
@@ -99,7 +106,6 @@
 	INIT_LIST_HEAD(&group->marks_list);
 
 	group->ops = ops;
-	fsnotify_init_event(&group->overflow_event, NULL, FS_Q_OVERFLOW);
 
 	return group;
 }
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index 485eef3..ed855ef 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -27,6 +27,6 @@
 				struct fsnotify_mark *inode_mark,
 				struct fsnotify_mark *vfsmount_mark,
 				u32 mask, void *data, int data_type,
-				const unsigned char *file_name);
+				const unsigned char *file_name, u32 cookie);
 
 extern const struct fsnotify_ops inotify_fsnotify_ops;
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index d5ee563..43ab1e1 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -67,7 +67,7 @@
 			 struct fsnotify_mark *inode_mark,
 			 struct fsnotify_mark *vfsmount_mark,
 			 u32 mask, void *data, int data_type,
-			 const unsigned char *file_name)
+			 const unsigned char *file_name, u32 cookie)
 {
 	struct inotify_inode_mark *i_mark;
 	struct inotify_event_info *event;
@@ -103,6 +103,7 @@
 	fsn_event = &event->fse;
 	fsnotify_init_event(fsn_event, inode, mask);
 	event->wd = i_mark->wd;
+	event->sync_cookie = cookie;
 	event->name_len = len;
 	if (len)
 		strcpy(event->name, file_name);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 497395c..78a2ca3 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -495,7 +495,7 @@
 
 	/* Queue ignore event for the watch */
 	inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
-			     NULL, FSNOTIFY_EVENT_NONE, NULL);
+			     NULL, FSNOTIFY_EVENT_NONE, NULL, 0);
 
 	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
 	/* remove this mark from the idr */
@@ -633,11 +633,23 @@
 static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 {
 	struct fsnotify_group *group;
+	struct inotify_event_info *oevent;
 
 	group = fsnotify_alloc_group(&inotify_fsnotify_ops);
 	if (IS_ERR(group))
 		return group;
 
+	oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL);
+	if (unlikely(!oevent)) {
+		fsnotify_destroy_group(group);
+		return ERR_PTR(-ENOMEM);
+	}
+	group->overflow_event = &oevent->fse;
+	fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+	oevent->wd = -1;
+	oevent->sync_cookie = 0;
+	oevent->name_len = 0;
+
 	group->max_events = max_events;
 
 	spin_lock_init(&group->inotify_data.idr_lock);
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 18b3c44..1e58402 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -80,7 +80,8 @@
 /*
  * Add an event to the group notification queue.  The group can later pull this
  * event off the queue to deal with.  The function returns 0 if the event was
- * added to the queue, 1 if the event was merged with some other queued event.
+ * added to the queue, 1 if the event was merged with some other queued event,
+ * 2 if the queue of events has overflown.
  */
 int fsnotify_add_notify_event(struct fsnotify_group *group,
 			      struct fsnotify_event *event,
@@ -95,10 +96,14 @@
 	mutex_lock(&group->notification_mutex);
 
 	if (group->q_len >= group->max_events) {
+		ret = 2;
 		/* Queue overflow event only if it isn't already queued */
-		if (list_empty(&group->overflow_event.list))
-			event = &group->overflow_event;
-		ret = 1;
+		if (!list_empty(&group->overflow_event->list)) {
+			mutex_unlock(&group->notification_mutex);
+			return ret;
+		}
+		event = group->overflow_event;
+		goto queue;
 	}
 
 	if (!list_empty(list) && merge) {
@@ -109,6 +114,7 @@
 		}
 	}
 
+queue:
 	group->q_len++;
 	list_add_tail(&event->list, list);
 	mutex_unlock(&group->notification_mutex);
@@ -132,7 +138,11 @@
 
 	event = list_first_entry(&group->notification_list,
 				 struct fsnotify_event, list);
-	list_del(&event->list);
+	/*
+	 * We need to init list head for the case of overflow event so that
+	 * check in fsnotify_add_notify_events() works
+	 */
+	list_del_init(&event->list);
 	group->q_len--;
 
 	return event;
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index ea4ba9d..db9bd8a 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -2134,7 +2134,7 @@
 	ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
 	if (ret > 0) {
-		int err = generic_write_sync(file, pos, ret);
+		int err = generic_write_sync(file, iocb->ki_pos - ret, ret);
 		if (err < 0)
 			ret = err;
 	}
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 8750ae1..e2edff3 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -4742,6 +4742,7 @@
 				enum ocfs2_alloc_restarted *reason_ret)
 {
 	int status = 0, err = 0;
+	int need_free = 0;
 	int free_extents;
 	enum ocfs2_alloc_restarted reason = RESTART_NONE;
 	u32 bit_off, num_bits;
@@ -4796,7 +4797,8 @@
 					      OCFS2_JOURNAL_ACCESS_WRITE);
 	if (status < 0) {
 		mlog_errno(status);
-		goto leave;
+		need_free = 1;
+		goto bail;
 	}
 
 	block = ocfs2_clusters_to_blocks(osb->sb, bit_off);
@@ -4807,7 +4809,8 @@
 				     num_bits, flags, meta_ac);
 	if (status < 0) {
 		mlog_errno(status);
-		goto leave;
+		need_free = 1;
+		goto bail;
 	}
 
 	ocfs2_journal_dirty(handle, et->et_root_bh);
@@ -4821,6 +4824,19 @@
 		reason = RESTART_TRANS;
 	}
 
+bail:
+	if (need_free) {
+		if (data_ac->ac_which == OCFS2_AC_USE_LOCAL)
+			ocfs2_free_local_alloc_bits(osb, handle, data_ac,
+					bit_off, num_bits);
+		else
+			ocfs2_free_clusters(handle,
+					data_ac->ac_inode,
+					data_ac->ac_bh,
+					ocfs2_clusters_to_blocks(osb->sb, bit_off),
+					num_bits);
+	}
+
 leave:
 	if (reason_ret)
 		*reason_ret = reason;
@@ -6805,6 +6821,8 @@
 					 struct buffer_head *di_bh)
 {
 	int ret, i, has_data, num_pages = 0;
+	int need_free = 0;
+	u32 bit_off, num;
 	handle_t *handle;
 	u64 uninitialized_var(block);
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
@@ -6850,7 +6868,6 @@
 	}
 
 	if (has_data) {
-		u32 bit_off, num;
 		unsigned int page_end;
 		u64 phys;
 
@@ -6886,6 +6903,7 @@
 		ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages);
 		if (ret) {
 			mlog_errno(ret);
+			need_free = 1;
 			goto out_commit;
 		}
 
@@ -6896,6 +6914,7 @@
 		ret = ocfs2_read_inline_data(inode, pages[0], di_bh);
 		if (ret) {
 			mlog_errno(ret);
+			need_free = 1;
 			goto out_commit;
 		}
 
@@ -6927,6 +6946,7 @@
 		ret = ocfs2_insert_extent(handle, &et, 0, block, 1, 0, NULL);
 		if (ret) {
 			mlog_errno(ret);
+			need_free = 1;
 			goto out_commit;
 		}
 
@@ -6938,6 +6958,18 @@
 		dquot_free_space_nodirty(inode,
 					  ocfs2_clusters_to_bytes(osb->sb, 1));
 
+	if (need_free) {
+		if (data_ac->ac_which == OCFS2_AC_USE_LOCAL)
+			ocfs2_free_local_alloc_bits(osb, handle, data_ac,
+					bit_off, num);
+		else
+			ocfs2_free_clusters(handle,
+					data_ac->ac_inode,
+					data_ac->ac_bh,
+					ocfs2_clusters_to_blocks(osb->sb, bit_off),
+					num);
+	}
+
 	ocfs2_commit_trans(osb, handle);
 
 out_unlock:
@@ -7126,7 +7158,7 @@
 	if (end > i_size_read(inode))
 		end = i_size_read(inode);
 
-	BUG_ON(start >= end);
+	BUG_ON(start > end);
 
 	if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) ||
 	    !(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) ||
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index d77d71e..51632c4 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -185,6 +185,9 @@
 			      file->f_path.dentry->d_name.name,
 			      (unsigned long long)datasync);
 
+	if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
+		return -EROFS;
+
 	err = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (err)
 		return err;
@@ -474,11 +477,6 @@
 		goto bail;
 	}
 
-	/* lets handle the simple truncate cases before doing any more
-	 * cluster locking. */
-	if (new_i_size == le64_to_cpu(fe->i_size))
-		goto bail;
-
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
 	ocfs2_resv_discard(&osb->osb_la_resmap,
@@ -718,7 +716,8 @@
  * While a write will already be ordering the data, a truncate will not.
  * Thus, we need to explicitly order the zeroed pages.
  */
-static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode)
+static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode,
+						struct buffer_head *di_bh)
 {
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	handle_t *handle = NULL;
@@ -735,7 +734,14 @@
 	}
 
 	ret = ocfs2_jbd2_file_inode(handle, inode);
-	if (ret < 0)
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret)
 		mlog_errno(ret);
 
 out:
@@ -751,7 +757,7 @@
  * to be too fragile to do exactly what we need without us having to
  * worry about recursive locking in ->write_begin() and ->write_end(). */
 static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
-				 u64 abs_to)
+				 u64 abs_to, struct buffer_head *di_bh)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
@@ -759,6 +765,7 @@
 	handle_t *handle = NULL;
 	int ret = 0;
 	unsigned zero_from, zero_to, block_start, block_end;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 
 	BUG_ON(abs_from >= abs_to);
 	BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT));
@@ -801,7 +808,8 @@
 		}
 
 		if (!handle) {
-			handle = ocfs2_zero_start_ordered_transaction(inode);
+			handle = ocfs2_zero_start_ordered_transaction(inode,
+								      di_bh);
 			if (IS_ERR(handle)) {
 				ret = PTR_ERR(handle);
 				handle = NULL;
@@ -818,8 +826,22 @@
 			ret = 0;
 	}
 
-	if (handle)
+	if (handle) {
+		/*
+		 * fs-writeback will release the dirty pages without page lock
+		 * whose offset are over inode size, the release happens at
+		 * block_write_full_page_endio().
+		 */
+		i_size_write(inode, abs_to);
+		inode->i_blocks = ocfs2_inode_sector_count(inode);
+		di->i_size = cpu_to_le64((u64)i_size_read(inode));
+		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+		di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+		di->i_mtime_nsec = di->i_ctime_nsec;
+		ocfs2_journal_dirty(handle, di_bh);
 		ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+	}
 
 out_unlock:
 	unlock_page(page);
@@ -915,7 +937,7 @@
  * has made sure that the entire range needs zeroing.
  */
 static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
-				   u64 range_end)
+				   u64 range_end, struct buffer_head *di_bh)
 {
 	int rc = 0;
 	u64 next_pos;
@@ -931,7 +953,7 @@
 		next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE;
 		if (next_pos > range_end)
 			next_pos = range_end;
-		rc = ocfs2_write_zero_page(inode, zero_pos, next_pos);
+		rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh);
 		if (rc < 0) {
 			mlog_errno(rc);
 			break;
@@ -977,7 +999,7 @@
 			range_end = zero_to_size;
 
 		ret = ocfs2_zero_extend_range(inode, range_start,
-					      range_end);
+					      range_end, di_bh);
 		if (ret) {
 			mlog_errno(ret);
 			break;
@@ -1145,14 +1167,14 @@
 		goto bail_unlock_rw;
 	}
 
-	if (size_change && attr->ia_size != i_size_read(inode)) {
+	if (size_change) {
 		status = inode_newsize_ok(inode, attr->ia_size);
 		if (status)
 			goto bail_unlock;
 
 		inode_dio_wait(inode);
 
-		if (i_size_read(inode) > attr->ia_size) {
+		if (i_size_read(inode) >= attr->ia_size) {
 			if (ocfs2_should_order_data(inode)) {
 				status = ocfs2_begin_ordered_truncate(inode,
 								      attr->ia_size);
@@ -2371,8 +2393,8 @@
 
 	if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) ||
 	    ((file->f_flags & O_DIRECT) && !direct_io)) {
-		ret = filemap_fdatawrite_range(file->f_mapping, pos,
-					       pos + count - 1);
+		ret = filemap_fdatawrite_range(file->f_mapping, *ppos,
+					       *ppos + count - 1);
 		if (ret < 0)
 			written = ret;
 
@@ -2385,8 +2407,8 @@
 		}
 
 		if (!ret)
-			ret = filemap_fdatawait_range(file->f_mapping, pos,
-						      pos + count - 1);
+			ret = filemap_fdatawait_range(file->f_mapping, *ppos,
+						      *ppos + count - 1);
 	}
 
 	/*
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index cd5496b..0440134 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -781,6 +781,48 @@
 	return status;
 }
 
+int ocfs2_free_local_alloc_bits(struct ocfs2_super *osb,
+				handle_t *handle,
+				struct ocfs2_alloc_context *ac,
+				u32 bit_off,
+				u32 num_bits)
+{
+	int status, start;
+	u32 clear_bits;
+	struct inode *local_alloc_inode;
+	void *bitmap;
+	struct ocfs2_dinode *alloc;
+	struct ocfs2_local_alloc *la;
+
+	BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL);
+
+	local_alloc_inode = ac->ac_inode;
+	alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
+	la = OCFS2_LOCAL_ALLOC(alloc);
+
+	bitmap = la->la_bitmap;
+	start = bit_off - le32_to_cpu(la->la_bm_off);
+	clear_bits = num_bits;
+
+	status = ocfs2_journal_access_di(handle,
+			INODE_CACHE(local_alloc_inode),
+			osb->local_alloc_bh,
+			OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	while (clear_bits--)
+		ocfs2_clear_bit(start++, bitmap);
+
+	le32_add_cpu(&alloc->id1.bitmap1.i_used, -num_bits);
+	ocfs2_journal_dirty(handle, osb->local_alloc_bh);
+
+bail:
+	return status;
+}
+
 static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc)
 {
 	u32 count;
diff --git a/fs/ocfs2/localalloc.h b/fs/ocfs2/localalloc.h
index 1be9b58..44a7d1f 100644
--- a/fs/ocfs2/localalloc.h
+++ b/fs/ocfs2/localalloc.h
@@ -55,6 +55,12 @@
 				 u32 *bit_off,
 				 u32 *num_bits);
 
+int ocfs2_free_local_alloc_bits(struct ocfs2_super *osb,
+				handle_t *handle,
+				struct ocfs2_alloc_context *ac,
+				u32 bit_off,
+				u32 num_bits);
+
 void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb,
 				      unsigned int num_clusters);
 void ocfs2_la_enable_worker(struct work_struct *work);
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index f4d609b..3683643 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -664,6 +664,7 @@
 	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
 	struct ocfs2_dir_lookup_result lookup = { NULL, };
 	sigset_t oldset;
+	u64 old_de_ino;
 
 	trace_ocfs2_link((unsigned long long)OCFS2_I(inode)->ip_blkno,
 			 old_dentry->d_name.len, old_dentry->d_name.name,
@@ -686,6 +687,22 @@
 		goto out;
 	}
 
+	err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name,
+			old_dentry->d_name.len, &old_de_ino);
+	if (err) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	/*
+	 * Check whether another node removed the source inode while we
+	 * were in the vfs.
+	 */
+	if (old_de_ino != OCFS2_I(inode)->ip_blkno) {
+		err = -ENOENT;
+		goto out;
+	}
+
 	err = ocfs2_check_dir_for_entry(dir, dentry->d_name.name,
 					dentry->d_name.len);
 	if (err)
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index aaa5061..d7b5108 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -717,6 +717,12 @@
 	 */
 	if (status < 0)
 		mlog_errno(status);
+	/*
+	 * Clear dq_off so that we search for the structure in quota file next
+	 * time we acquire it. The structure might be deleted and reallocated
+	 * elsewhere by another node while our dquot structure is on freelist.
+	 */
+	dquot->dq_off = 0;
 	clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
 out_trans:
 	ocfs2_commit_trans(osb, handle);
@@ -756,16 +762,17 @@
 	status = ocfs2_lock_global_qf(info, 1);
 	if (status < 0)
 		goto out;
-	if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
-		status = ocfs2_qinfo_lock(info, 0);
-		if (status < 0)
-			goto out_dq;
-		status = qtree_read_dquot(&info->dqi_gi, dquot);
-		ocfs2_qinfo_unlock(info, 0);
-		if (status < 0)
-			goto out_dq;
-	}
-	set_bit(DQ_READ_B, &dquot->dq_flags);
+	status = ocfs2_qinfo_lock(info, 0);
+	if (status < 0)
+		goto out_dq;
+	/*
+	 * We always want to read dquot structure from disk because we don't
+	 * know what happened with it while it was on freelist.
+	 */
+	status = qtree_read_dquot(&info->dqi_gi, dquot);
+	ocfs2_qinfo_unlock(info, 0);
+	if (status < 0)
+		goto out_dq;
 
 	OCFS2_DQUOT(dquot)->dq_use_count++;
 	OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2e4344b..2001862 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -1303,10 +1303,6 @@
 	ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
 
 out:
-	/* Clear the read bit so that next time someone uses this
-	 * dquot he reads fresh info from disk and allocates local
-	 * dquot structure */
-	clear_bit(DQ_READ_B, &dquot->dq_flags);
 	return status;
 }
 
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 1324e66..ca5ce14 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -346,7 +346,9 @@
 
 	strlcpy(new_conn->cc_name, group, GROUP_NAME_MAX + 1);
 	new_conn->cc_namelen = grouplen;
-	strlcpy(new_conn->cc_cluster_name, cluster_name, CLUSTER_NAME_MAX + 1);
+	if (cluster_name_len)
+		strlcpy(new_conn->cc_cluster_name, cluster_name,
+			CLUSTER_NAME_MAX + 1);
 	new_conn->cc_cluster_name_len = cluster_name_len;
 	new_conn->cc_recovery_handler = recovery_handler;
 	new_conn->cc_recovery_data = recovery_data;
diff --git a/fs/open.c b/fs/open.c
index 4b3e1ed..b9ed8b2 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -705,6 +705,10 @@
 		return 0;
 	}
 
+	/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
+	if (S_ISREG(inode->i_mode))
+		f->f_mode |= FMODE_ATOMIC_POS;
+
 	f->f_op = fops_get(inode->i_fop);
 	if (unlikely(WARN_ON(!f->f_op))) {
 		error = -ENODEV;
diff --git a/fs/pnode.c b/fs/pnode.c
index c7221bb..88396df 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -220,14 +220,14 @@
  * @tree_list : list of heads of trees to be attached.
  */
 int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
-		    struct mount *source_mnt, struct list_head *tree_list)
+		    struct mount *source_mnt, struct hlist_head *tree_list)
 {
 	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
 	struct mount *m, *child;
 	int ret = 0;
 	struct mount *prev_dest_mnt = dest_mnt;
 	struct mount *prev_src_mnt  = source_mnt;
-	LIST_HEAD(tmp_list);
+	HLIST_HEAD(tmp_list);
 
 	for (m = propagation_next(dest_mnt, dest_mnt); m;
 			m = propagation_next(m, dest_mnt)) {
@@ -246,27 +246,29 @@
 		child = copy_tree(source, source->mnt.mnt_root, type);
 		if (IS_ERR(child)) {
 			ret = PTR_ERR(child);
-			list_splice(tree_list, tmp_list.prev);
+			tmp_list = *tree_list;
+			tmp_list.first->pprev = &tmp_list.first;
+			INIT_HLIST_HEAD(tree_list);
 			goto out;
 		}
 
 		if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) {
 			mnt_set_mountpoint(m, dest_mp, child);
-			list_add_tail(&child->mnt_hash, tree_list);
+			hlist_add_head(&child->mnt_hash, tree_list);
 		} else {
 			/*
 			 * This can happen if the parent mount was bind mounted
 			 * on some subdirectory of a shared/slave mount.
 			 */
-			list_add_tail(&child->mnt_hash, &tmp_list);
+			hlist_add_head(&child->mnt_hash, &tmp_list);
 		}
 		prev_dest_mnt = m;
 		prev_src_mnt  = child;
 	}
 out:
 	lock_mount_hash();
-	while (!list_empty(&tmp_list)) {
-		child = list_first_entry(&tmp_list, struct mount, mnt_hash);
+	while (!hlist_empty(&tmp_list)) {
+		child = hlist_entry(tmp_list.first, struct mount, mnt_hash);
 		umount_tree(child, 0);
 	}
 	unlock_mount_hash();
@@ -338,8 +340,10 @@
 		 * umount the child only if the child has no
 		 * other children
 		 */
-		if (child && list_empty(&child->mnt_mounts))
-			list_move_tail(&child->mnt_hash, &mnt->mnt_hash);
+		if (child && list_empty(&child->mnt_mounts)) {
+			hlist_del_init_rcu(&child->mnt_hash);
+			hlist_add_before_rcu(&child->mnt_hash, &mnt->mnt_hash);
+		}
 	}
 }
 
@@ -350,11 +354,11 @@
  *
  * vfsmount lock must be held for write
  */
-int propagate_umount(struct list_head *list)
+int propagate_umount(struct hlist_head *list)
 {
 	struct mount *mnt;
 
-	list_for_each_entry(mnt, list, mnt_hash)
+	hlist_for_each_entry(mnt, list, mnt_hash)
 		__propagate_umount(mnt);
 	return 0;
 }
diff --git a/fs/pnode.h b/fs/pnode.h
index 59e7eda..fc28a27 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -36,8 +36,8 @@
 
 void change_mnt_propagation(struct mount *, int);
 int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
-		struct list_head *);
-int propagate_umount(struct list_head *);
+		struct hlist_head *);
+int propagate_umount(struct hlist_head *);
 int propagate_mount_busy(struct mount *, int);
 void mnt_release_group_id(struct mount *);
 int get_dominating_id(struct mount *mnt, const struct path *root);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 38bae5a..11c54fd 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -521,8 +521,11 @@
 		return -EOPNOTSUPP;
 
 	acl = get_acl(inode, ACL_TYPE_ACCESS);
-	if (IS_ERR_OR_NULL(acl))
+	if (IS_ERR_OR_NULL(acl)) {
+		if (acl == ERR_PTR(-EOPNOTSUPP))
+			return 0;
 		return PTR_ERR(acl);
+	}
 
 	ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode);
 	if (ret)
@@ -544,14 +547,15 @@
 		goto no_acl;
 
 	p = get_acl(dir, ACL_TYPE_DEFAULT);
-	if (IS_ERR(p))
+	if (IS_ERR(p)) {
+		if (p == ERR_PTR(-EOPNOTSUPP))
+			goto apply_umask;
 		return PTR_ERR(p);
-
-	if (!p) {
-		*mode &= ~current_umask();
-		goto no_acl;
 	}
 
+	if (!p)
+		goto apply_umask;
+
 	*acl = posix_acl_clone(p, GFP_NOFS);
 	if (!*acl)
 		return -ENOMEM;
@@ -575,6 +579,8 @@
 	}
 	return 0;
 
+apply_umask:
+	*mode &= ~current_umask();
 no_acl:
 	*default_acl = NULL;
 	*acl = NULL;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5150706..b976062 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1824,6 +1824,7 @@
 	if (rc)
 		goto out_mmput;
 
+	rc = -ENOENT;
 	down_read(&mm->mmap_sem);
 	vma = find_exact_vma(mm, vm_start, vm_end);
 	if (vma && vma->vm_file) {
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 02174a6..e647c55 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -121,9 +121,8 @@
 	 * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
 	 * to make sure a given page is a thp, not a non-huge compound page.
 	 */
-	else if (PageTransCompound(page) &&
-		 (PageLRU(compound_trans_head(page)) ||
-		  PageAnon(compound_trans_head(page))))
+	else if (PageTransCompound(page) && (PageLRU(compound_head(page)) ||
+					     PageAnon(compound_head(page))))
 		u |= 1 << KPF_THP;
 
 	/*
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 2ca7ba0..88d4585 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -468,17 +468,24 @@
 			return rc;
 		}
 		nhdr_ptr = notes_section;
-		while (real_sz < max_sz) {
-			if (nhdr_ptr->n_namesz == 0)
-				break;
+		while (nhdr_ptr->n_namesz != 0) {
 			sz = sizeof(Elf64_Nhdr) +
 				((nhdr_ptr->n_namesz + 3) & ~3) +
 				((nhdr_ptr->n_descsz + 3) & ~3);
+			if ((real_sz + sz) > max_sz) {
+				pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
+					nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
+				break;
+			}
 			real_sz += sz;
 			nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz);
 		}
 		kfree(notes_section);
 		phdr_ptr->p_memsz = real_sz;
+		if (real_sz == 0) {
+			pr_warn("Warning: Zero PT_NOTE entries found\n");
+			return -EINVAL;
+		}
 	}
 
 	return 0;
@@ -648,17 +655,24 @@
 			return rc;
 		}
 		nhdr_ptr = notes_section;
-		while (real_sz < max_sz) {
-			if (nhdr_ptr->n_namesz == 0)
-				break;
+		while (nhdr_ptr->n_namesz != 0) {
 			sz = sizeof(Elf32_Nhdr) +
 				((nhdr_ptr->n_namesz + 3) & ~3) +
 				((nhdr_ptr->n_descsz + 3) & ~3);
+			if ((real_sz + sz) > max_sz) {
+				pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
+					nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
+				break;
+			}
 			real_sz += sz;
 			nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz);
 		}
 		kfree(notes_section);
 		phdr_ptr->p_memsz = real_sz;
+		if (real_sz == 0) {
+			pr_warn("Warning: Zero PT_NOTE entries found\n");
+			return -EINVAL;
+		}
 	}
 
 	return 0;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 831d49a..cfc8dcc 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -581,9 +581,17 @@
 		dqstats_inc(DQST_LOOKUPS);
 		dqput(old_dquot);
 		old_dquot = dquot;
-		ret = fn(dquot, priv);
-		if (ret < 0)
-			goto out;
+		/*
+		 * ->release_dquot() can be racing with us. Our reference
+		 * protects us from new calls to it so just wait for any
+		 * outstanding call and recheck the DQ_ACTIVE_B after that.
+		 */
+		wait_on_dquot(dquot);
+		if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+			ret = fn(dquot, priv);
+			if (ret < 0)
+				goto out;
+		}
 		spin_lock(&dq_list_lock);
 		/* We are safe to continue now because our dquot could not
 		 * be moved out of the inuse list while we hold the reference */
diff --git a/fs/read_write.c b/fs/read_write.c
index edc5746..31c6efa 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -264,10 +264,22 @@
 }
 EXPORT_SYMBOL(vfs_llseek);
 
+static inline struct fd fdget_pos(int fd)
+{
+	return __to_fd(__fdget_pos(fd));
+}
+
+static inline void fdput_pos(struct fd f)
+{
+	if (f.flags & FDPUT_POS_UNLOCK)
+		mutex_unlock(&f.file->f_pos_lock);
+	fdput(f);
+}
+
 SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
 {
 	off_t retval;
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	if (!f.file)
 		return -EBADF;
 
@@ -278,7 +290,7 @@
 		if (res != (loff_t)retval)
 			retval = -EOVERFLOW;	/* LFS: should only happen on 32 bit platforms */
 	}
-	fdput(f);
+	fdput_pos(f);
 	return retval;
 }
 
@@ -295,7 +307,7 @@
 		unsigned int, whence)
 {
 	int retval;
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	loff_t offset;
 
 	if (!f.file)
@@ -315,7 +327,7 @@
 			retval = 0;
 	}
 out_putf:
-	fdput(f);
+	fdput_pos(f);
 	return retval;
 }
 #endif
@@ -498,7 +510,7 @@
 
 SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -506,7 +518,7 @@
 		ret = vfs_read(f.file, buf, count, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 	return ret;
 }
@@ -514,7 +526,7 @@
 SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
 		size_t, count)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -522,7 +534,7 @@
 		ret = vfs_write(f.file, buf, count, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 
 	return ret;
@@ -797,7 +809,7 @@
 SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -805,7 +817,7 @@
 		ret = vfs_readv(f.file, vec, vlen, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 
 	if (ret > 0)
@@ -817,7 +829,7 @@
 SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -825,7 +837,7 @@
 		ret = vfs_writev(f.file, vec, vlen, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 
 	if (ret > 0)
@@ -968,7 +980,7 @@
 		const struct compat_iovec __user *,vec,
 		compat_ulong_t, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret;
 	loff_t pos;
 
@@ -978,13 +990,13 @@
 	ret = compat_readv(f.file, vec, vlen, &pos);
 	if (ret >= 0)
 		f.file->f_pos = pos;
-	fdput(f);
+	fdput_pos(f);
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
-		unsigned long, vlen, loff_t, pos)
+static long __compat_sys_preadv64(unsigned long fd,
+				  const struct compat_iovec __user *vec,
+				  unsigned long vlen, loff_t pos)
 {
 	struct fd f;
 	ssize_t ret;
@@ -1001,12 +1013,22 @@
 	return ret;
 }
 
+#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
+COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
+		const struct compat_iovec __user *,vec,
+		unsigned long, vlen, loff_t, pos)
+{
+	return __compat_sys_preadv64(fd, vec, vlen, pos);
+}
+#endif
+
 COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
 		const struct compat_iovec __user *,vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
-	return compat_sys_preadv64(fd, vec, vlen, pos);
+
+	return __compat_sys_preadv64(fd, vec, vlen, pos);
 }
 
 static size_t compat_writev(struct file *file,
@@ -1035,7 +1057,7 @@
 		const struct compat_iovec __user *, vec,
 		compat_ulong_t, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret;
 	loff_t pos;
 
@@ -1045,13 +1067,13 @@
 	ret = compat_writev(f.file, vec, vlen, &pos);
 	if (ret >= 0)
 		f.file->f_pos = pos;
-	fdput(f);
+	fdput_pos(f);
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
-		unsigned long, vlen, loff_t, pos)
+static long __compat_sys_pwritev64(unsigned long fd,
+				   const struct compat_iovec __user *vec,
+				   unsigned long vlen, loff_t pos)
 {
 	struct fd f;
 	ssize_t ret;
@@ -1068,12 +1090,22 @@
 	return ret;
 }
 
+#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
+COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
+		const struct compat_iovec __user *,vec,
+		unsigned long, vlen, loff_t, pos)
+{
+	return __compat_sys_pwritev64(fd, vec, vlen, pos);
+}
+#endif
+
 COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
 		const struct compat_iovec __user *,vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
-	return compat_sys_pwritev64(fd, vec, vlen, pos);
+
+	return __compat_sys_pwritev64(fd, vec, vlen, pos);
 }
 #endif
 
diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c
index 2b7882b..9a3c68c 100644
--- a/fs/reiserfs/do_balan.c
+++ b/fs/reiserfs/do_balan.c
@@ -324,23 +324,17 @@
 			switch (flag) {
 			case M_INSERT:	/* insert item into L[0] */
 
-				if (item_pos == tb->lnum[0] - 1
-				    && tb->lbytes != -1) {
+				if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) {
 					/* part of new item falls into L[0] */
 					int new_item_len;
 					int version;
 
-					ret_val =
-					    leaf_shift_left(tb, tb->lnum[0] - 1,
-							    -1);
+					ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, -1);
 
 					/* Calculate item length to insert to S[0] */
-					new_item_len =
-					    ih_item_len(ih) - tb->lbytes;
+					new_item_len = ih_item_len(ih) - tb->lbytes;
 					/* Calculate and check item length to insert to L[0] */
-					put_ih_item_len(ih,
-							ih_item_len(ih) -
-							new_item_len);
+					put_ih_item_len(ih, ih_item_len(ih) - new_item_len);
 
 					RFALSE(ih_item_len(ih) <= 0,
 					       "PAP-12080: there is nothing to insert into L[0]: ih_item_len=%d",
@@ -349,30 +343,18 @@
 					/* Insert new item into L[0] */
 					buffer_info_init_left(tb, &bi);
 					leaf_insert_into_buf(&bi,
-							     n + item_pos -
-							     ret_val, ih, body,
-							     zeros_num >
-							     ih_item_len(ih) ?
-							     ih_item_len(ih) :
-							     zeros_num);
+							n + item_pos - ret_val, ih, body,
+							zeros_num > ih_item_len(ih) ? ih_item_len(ih) : zeros_num);
 
 					version = ih_version(ih);
 
 					/* Calculate key component, item length and body to insert into S[0] */
-					set_le_ih_k_offset(ih,
-							   le_ih_k_offset(ih) +
-							   (tb->
-							    lbytes <<
-							    (is_indirect_le_ih
-							     (ih) ? tb->tb_sb->
-							     s_blocksize_bits -
-							     UNFM_P_SHIFT :
-							     0)));
+					set_le_ih_k_offset(ih, le_ih_k_offset(ih) +
+							(tb-> lbytes << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0)));
 
 					put_ih_item_len(ih, new_item_len);
 					if (tb->lbytes > zeros_num) {
-						body +=
-						    (tb->lbytes - zeros_num);
+						body += (tb->lbytes - zeros_num);
 						zeros_num = 0;
 					} else
 						zeros_num -= tb->lbytes;
@@ -383,15 +365,10 @@
 				} else {
 					/* new item in whole falls into L[0] */
 					/* Shift lnum[0]-1 items to L[0] */
-					ret_val =
-					    leaf_shift_left(tb, tb->lnum[0] - 1,
-							    tb->lbytes);
+					ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, tb->lbytes);
 					/* Insert new item into L[0] */
 					buffer_info_init_left(tb, &bi);
-					leaf_insert_into_buf(&bi,
-							     n + item_pos -
-							     ret_val, ih, body,
-							     zeros_num);
+					leaf_insert_into_buf(&bi, n + item_pos - ret_val, ih, body, zeros_num);
 					tb->insert_size[0] = 0;
 					zeros_num = 0;
 				}
@@ -399,264 +376,117 @@
 
 			case M_PASTE:	/* append item in L[0] */
 
-				if (item_pos == tb->lnum[0] - 1
-				    && tb->lbytes != -1) {
+				if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) {
 					/* we must shift the part of the appended item */
-					if (is_direntry_le_ih
-					    (B_N_PITEM_HEAD(tbS0, item_pos))) {
+					if (is_direntry_le_ih(B_N_PITEM_HEAD(tbS0, item_pos))) {
 
 						RFALSE(zeros_num,
 						       "PAP-12090: invalid parameter in case of a directory");
 						/* directory item */
 						if (tb->lbytes > pos_in_item) {
 							/* new directory entry falls into L[0] */
-							struct item_head
-							    *pasted;
-							int l_pos_in_item =
-							    pos_in_item;
+							struct item_head *pasted;
+							int l_pos_in_item = pos_in_item;
 
 							/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 entries from given directory item */
-							ret_val =
-							    leaf_shift_left(tb,
-									    tb->
-									    lnum
-									    [0],
-									    tb->
-									    lbytes
-									    -
-									    1);
-							if (ret_val
-							    && !item_pos) {
-								pasted =
-								    B_N_PITEM_HEAD
-								    (tb->L[0],
-								     B_NR_ITEMS
-								     (tb->
-								      L[0]) -
-								     1);
-								l_pos_in_item +=
-								    I_ENTRY_COUNT
-								    (pasted) -
-								    (tb->
-								     lbytes -
-								     1);
+							ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes-1);
+							if (ret_val && !item_pos) {
+								pasted = B_N_PITEM_HEAD(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1);
+								l_pos_in_item += I_ENTRY_COUNT(pasted) - (tb->lbytes -1);
 							}
 
 							/* Append given directory entry to directory item */
 							buffer_info_init_left(tb, &bi);
-							leaf_paste_in_buffer
-							    (&bi,
-							     n + item_pos -
-							     ret_val,
-							     l_pos_in_item,
-							     tb->insert_size[0],
-							     body, zeros_num);
+							leaf_paste_in_buffer(&bi, n + item_pos - ret_val, l_pos_in_item, tb->insert_size[0], body, zeros_num);
 
 							/* previous string prepared space for pasting new entry, following string pastes this entry */
 
 							/* when we have merge directory item, pos_in_item has been changed too */
 
 							/* paste new directory entry. 1 is entry number */
-							leaf_paste_entries(&bi,
-									   n +
-									   item_pos
-									   -
-									   ret_val,
-									   l_pos_in_item,
-									   1,
-									   (struct
-									    reiserfs_de_head
-									    *)
-									   body,
-									   body
-									   +
-									   DEH_SIZE,
-									   tb->
-									   insert_size
-									   [0]
-							    );
+							leaf_paste_entries(&bi, n + item_pos - ret_val, l_pos_in_item,
+									   1, (struct reiserfs_de_head *) body,
+									   body + DEH_SIZE, tb->insert_size[0]);
 							tb->insert_size[0] = 0;
 						} else {
 							/* new directory item doesn't fall into L[0] */
 							/* Shift lnum[0]-1 items in whole. Shift lbytes directory entries from directory item number lnum[0] */
-							leaf_shift_left(tb,
-									tb->
-									lnum[0],
-									tb->
-									lbytes);
+							leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
 						}
 						/* Calculate new position to append in item body */
 						pos_in_item -= tb->lbytes;
 					} else {
 						/* regular object */
-						RFALSE(tb->lbytes <= 0,
-						       "PAP-12095: there is nothing to shift to L[0]. lbytes=%d",
-						       tb->lbytes);
-						RFALSE(pos_in_item !=
-						       ih_item_len
-						       (B_N_PITEM_HEAD
-							(tbS0, item_pos)),
+						RFALSE(tb->lbytes <= 0, "PAP-12095: there is nothing to shift to L[0]. lbytes=%d", tb->lbytes);
+						RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)),
 						       "PAP-12100: incorrect position to paste: item_len=%d, pos_in_item=%d",
-						       ih_item_len
-						       (B_N_PITEM_HEAD
-							(tbS0, item_pos)),
-						       pos_in_item);
+						       ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)),pos_in_item);
 
 						if (tb->lbytes >= pos_in_item) {
 							/* appended item will be in L[0] in whole */
 							int l_n;
 
 							/* this bytes number must be appended to the last item of L[h] */
-							l_n =
-							    tb->lbytes -
-							    pos_in_item;
+							l_n = tb->lbytes - pos_in_item;
 
 							/* Calculate new insert_size[0] */
-							tb->insert_size[0] -=
-							    l_n;
+							tb->insert_size[0] -= l_n;
 
-							RFALSE(tb->
-							       insert_size[0] <=
-							       0,
+							RFALSE(tb->insert_size[0] <= 0,
 							       "PAP-12105: there is nothing to paste into L[0]. insert_size=%d",
-							       tb->
-							       insert_size[0]);
-							ret_val =
-							    leaf_shift_left(tb,
-									    tb->
-									    lnum
-									    [0],
-									    ih_item_len
-									    (B_N_PITEM_HEAD
-									     (tbS0,
-									      item_pos)));
+							       tb->insert_size[0]);
+							ret_val = leaf_shift_left(tb, tb->lnum[0], ih_item_len
+									    (B_N_PITEM_HEAD(tbS0, item_pos)));
 							/* Append to body of item in L[0] */
 							buffer_info_init_left(tb, &bi);
 							leaf_paste_in_buffer
-							    (&bi,
-							     n + item_pos -
-							     ret_val,
-							     ih_item_len
-							     (B_N_PITEM_HEAD
-							      (tb->L[0],
-							       n + item_pos -
-							       ret_val)), l_n,
-							     body,
-							     zeros_num >
-							     l_n ? l_n :
-							     zeros_num);
+							    (&bi, n + item_pos - ret_val, ih_item_len
+							     (B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val)),
+							     l_n, body,
+							     zeros_num > l_n ? l_n : zeros_num);
 							/* 0-th item in S0 can be only of DIRECT type when l_n != 0 */
 							{
 								int version;
-								int temp_l =
-								    l_n;
+								int temp_l = l_n;
 
-								RFALSE
-								    (ih_item_len
-								     (B_N_PITEM_HEAD
-								      (tbS0,
-								       0)),
+								RFALSE(ih_item_len(B_N_PITEM_HEAD(tbS0, 0)),
 								     "PAP-12106: item length must be 0");
-								RFALSE
-								    (comp_short_le_keys
-								     (B_N_PKEY
-								      (tbS0, 0),
-								      B_N_PKEY
-								      (tb->L[0],
-								       n +
-								       item_pos
-								       -
-								       ret_val)),
+								RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY
+								      (tb->L[0], n + item_pos - ret_val)),
 								     "PAP-12107: items must be of the same file");
 								if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val))) {
-									temp_l =
-									    l_n
-									    <<
-									    (tb->
-									     tb_sb->
-									     s_blocksize_bits
-									     -
-									     UNFM_P_SHIFT);
+									temp_l = l_n << (tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT);
 								}
 								/* update key of first item in S0 */
-								version =
-								    ih_version
-								    (B_N_PITEM_HEAD
-								     (tbS0, 0));
-								set_le_key_k_offset
-								    (version,
-								     B_N_PKEY
-								     (tbS0, 0),
-								     le_key_k_offset
-								     (version,
-								      B_N_PKEY
-								      (tbS0,
-								       0)) +
-								     temp_l);
+								version = ih_version(B_N_PITEM_HEAD(tbS0, 0));
+								set_le_key_k_offset(version, B_N_PKEY(tbS0, 0),
+								     le_key_k_offset(version,B_N_PKEY(tbS0, 0)) + temp_l);
 								/* update left delimiting key */
-								set_le_key_k_offset
-								    (version,
-								     B_N_PDELIM_KEY
-								     (tb->
-								      CFL[0],
-								      tb->
-								      lkey[0]),
-								     le_key_k_offset
-								     (version,
-								      B_N_PDELIM_KEY
-								      (tb->
-								       CFL[0],
-								       tb->
-								       lkey[0]))
-								     + temp_l);
+								set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]),
+								     le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0])) + temp_l);
 							}
 
 							/* Calculate new body, position in item and insert_size[0] */
 							if (l_n > zeros_num) {
-								body +=
-								    (l_n -
-								     zeros_num);
+								body += (l_n - zeros_num);
 								zeros_num = 0;
 							} else
-								zeros_num -=
-								    l_n;
+								zeros_num -= l_n;
 							pos_in_item = 0;
 
-							RFALSE
-							    (comp_short_le_keys
-							     (B_N_PKEY(tbS0, 0),
-							      B_N_PKEY(tb->L[0],
-								       B_NR_ITEMS
-								       (tb->
-									L[0]) -
-								       1))
-							     ||
-							     !op_is_left_mergeable
-							     (B_N_PKEY(tbS0, 0),
-							      tbS0->b_size)
-							     ||
-							     !op_is_left_mergeable
-							     (B_N_PDELIM_KEY
-							      (tb->CFL[0],
-							       tb->lkey[0]),
-							      tbS0->b_size),
+							RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1))
+							     || !op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size)
+							     || !op_is_left_mergeable(B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]), tbS0->b_size),
 							     "PAP-12120: item must be merge-able with left neighboring item");
 						} else {	/* only part of the appended item will be in L[0] */
 
 							/* Calculate position in item for append in S[0] */
-							pos_in_item -=
-							    tb->lbytes;
+							pos_in_item -= tb->lbytes;
 
-							RFALSE(pos_in_item <= 0,
-							       "PAP-12125: no place for paste. pos_in_item=%d",
-							       pos_in_item);
+							RFALSE(pos_in_item <= 0, "PAP-12125: no place for paste. pos_in_item=%d", pos_in_item);
 
 							/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */
-							leaf_shift_left(tb,
-									tb->
-									lnum[0],
-									tb->
-									lbytes);
+							leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
 						}
 					}
 				} else {	/* appended item will be in L[0] in whole */
@@ -665,52 +495,30 @@
 
 					if (!item_pos && op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size)) {	/* if we paste into first item of S[0] and it is left mergable */
 						/* then increment pos_in_item by the size of the last item in L[0] */
-						pasted =
-						    B_N_PITEM_HEAD(tb->L[0],
-								   n - 1);
+						pasted = B_N_PITEM_HEAD(tb->L[0], n - 1);
 						if (is_direntry_le_ih(pasted))
-							pos_in_item +=
-							    ih_entry_count
-							    (pasted);
+							pos_in_item += ih_entry_count(pasted);
 						else
-							pos_in_item +=
-							    ih_item_len(pasted);
+							pos_in_item += ih_item_len(pasted);
 					}
 
 					/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */
-					ret_val =
-					    leaf_shift_left(tb, tb->lnum[0],
-							    tb->lbytes);
+					ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
 					/* Append to body of item in L[0] */
 					buffer_info_init_left(tb, &bi);
-					leaf_paste_in_buffer(&bi,
-							     n + item_pos -
-							     ret_val,
+					leaf_paste_in_buffer(&bi, n + item_pos - ret_val,
 							     pos_in_item,
 							     tb->insert_size[0],
 							     body, zeros_num);
 
 					/* if appended item is directory, paste entry */
-					pasted =
-					    B_N_PITEM_HEAD(tb->L[0],
-							   n + item_pos -
-							   ret_val);
+					pasted = B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val);
 					if (is_direntry_le_ih(pasted))
-						leaf_paste_entries(&bi,
-								   n +
-								   item_pos -
-								   ret_val,
-								   pos_in_item,
-								   1,
-								   (struct
-								    reiserfs_de_head
-								    *)body,
-								   body +
-								   DEH_SIZE,
-								   tb->
-								   insert_size
-								   [0]
-						    );
+						leaf_paste_entries(&bi, n + item_pos - ret_val,
+								   pos_in_item, 1,
+								   (struct reiserfs_de_head *) body,
+								   body + DEH_SIZE,
+								   tb->insert_size[0]);
 					/* if appended item is indirect item, put unformatted node into un list */
 					if (is_indirect_le_ih(pasted))
 						set_ih_free_space(pasted, 0);
@@ -722,13 +530,7 @@
 				reiserfs_panic(tb->tb_sb, "PAP-12130",
 					       "lnum > 0: unexpected mode: "
 					       " %s(%d)",
-					       (flag ==
-						M_DELETE) ? "DELETE" : ((flag ==
-									 M_CUT)
-									? "CUT"
-									:
-									"UNKNOWN"),
-					       flag);
+					       (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
 			}
 		} else {
 			/* new item doesn't fall into L[0] */
@@ -748,14 +550,12 @@
 		case M_INSERT:	/* insert item */
 			if (n - tb->rnum[0] < item_pos) {	/* new item or its part falls to R[0] */
 				if (item_pos == n - tb->rnum[0] + 1 && tb->rbytes != -1) {	/* part of new item falls into R[0] */
-					loff_t old_key_comp, old_len,
-					    r_zeros_number;
+					loff_t old_key_comp, old_len, r_zeros_number;
 					const char *r_body;
 					int version;
 					loff_t offset;
 
-					leaf_shift_right(tb, tb->rnum[0] - 1,
-							 -1);
+					leaf_shift_right(tb, tb->rnum[0] - 1, -1);
 
 					version = ih_version(ih);
 					/* Remember key component and item length */
@@ -763,29 +563,17 @@
 					old_len = ih_item_len(ih);
 
 					/* Calculate key component and item length to insert into R[0] */
-					offset =
-					    le_ih_k_offset(ih) +
-					    ((old_len -
-					      tb->
-					      rbytes) << (is_indirect_le_ih(ih)
-							  ? tb->tb_sb->
-							  s_blocksize_bits -
-							  UNFM_P_SHIFT : 0));
+					offset = le_ih_k_offset(ih) + ((old_len - tb->rbytes) << (is_indirect_le_ih(ih) ? tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT : 0));
 					set_le_ih_k_offset(ih, offset);
 					put_ih_item_len(ih, tb->rbytes);
 					/* Insert part of the item into R[0] */
 					buffer_info_init_right(tb, &bi);
 					if ((old_len - tb->rbytes) > zeros_num) {
 						r_zeros_number = 0;
-						r_body =
-						    body + (old_len -
-							    tb->rbytes) -
-						    zeros_num;
+						r_body = body + (old_len - tb->rbytes) - zeros_num;
 					} else {
 						r_body = body;
-						r_zeros_number =
-						    zeros_num - (old_len -
-								 tb->rbytes);
+						r_zeros_number = zeros_num - (old_len - tb->rbytes);
 						zeros_num -= r_zeros_number;
 					}
 
@@ -798,25 +586,18 @@
 
 					/* Calculate key component and item length to insert into S[0] */
 					set_le_ih_k_offset(ih, old_key_comp);
-					put_ih_item_len(ih,
-							old_len - tb->rbytes);
+					put_ih_item_len(ih, old_len - tb->rbytes);
 
 					tb->insert_size[0] -= tb->rbytes;
 
 				} else {	/* whole new item falls into R[0] */
 
 					/* Shift rnum[0]-1 items to R[0] */
-					ret_val =
-					    leaf_shift_right(tb,
-							     tb->rnum[0] - 1,
-							     tb->rbytes);
+					ret_val = leaf_shift_right(tb, tb->rnum[0] - 1, tb->rbytes);
 					/* Insert new item into R[0] */
 					buffer_info_init_right(tb, &bi);
-					leaf_insert_into_buf(&bi,
-							     item_pos - n +
-							     tb->rnum[0] - 1,
-							     ih, body,
-							     zeros_num);
+					leaf_insert_into_buf(&bi, item_pos - n + tb->rnum[0] - 1,
+							     ih, body, zeros_num);
 
 					if (item_pos - n + tb->rnum[0] - 1 == 0) {
 						replace_key(tb, tb->CFR[0],
@@ -841,200 +622,97 @@
 
 						RFALSE(zeros_num,
 						       "PAP-12145: invalid parameter in case of a directory");
-						entry_count =
-						    I_ENTRY_COUNT(B_N_PITEM_HEAD
-								  (tbS0,
-								   item_pos));
+						entry_count = I_ENTRY_COUNT(B_N_PITEM_HEAD
+								  (tbS0, item_pos));
 						if (entry_count - tb->rbytes <
 						    pos_in_item)
 							/* new directory entry falls into R[0] */
 						{
 							int paste_entry_position;
 
-							RFALSE(tb->rbytes - 1 >=
-							       entry_count
-							       || !tb->
-							       insert_size[0],
+							RFALSE(tb->rbytes - 1 >= entry_count || !tb-> insert_size[0],
 							       "PAP-12150: no enough of entries to shift to R[0]: rbytes=%d, entry_count=%d",
-							       tb->rbytes,
-							       entry_count);
+							       tb->rbytes, entry_count);
 							/* Shift rnum[0]-1 items in whole. Shift rbytes-1 directory entries from directory item number rnum[0] */
-							leaf_shift_right(tb,
-									 tb->
-									 rnum
-									 [0],
-									 tb->
-									 rbytes
-									 - 1);
+							leaf_shift_right(tb, tb->rnum[0], tb->rbytes - 1);
 							/* Paste given directory entry to directory item */
-							paste_entry_position =
-							    pos_in_item -
-							    entry_count +
-							    tb->rbytes - 1;
+							paste_entry_position = pos_in_item - entry_count + tb->rbytes - 1;
 							buffer_info_init_right(tb, &bi);
-							leaf_paste_in_buffer
-							    (&bi, 0,
-							     paste_entry_position,
-							     tb->insert_size[0],
-							     body, zeros_num);
+							leaf_paste_in_buffer(&bi, 0, paste_entry_position, tb->insert_size[0], body, zeros_num);
 							/* paste entry */
-							leaf_paste_entries(&bi,
-									   0,
-									   paste_entry_position,
-									   1,
-									   (struct
-									    reiserfs_de_head
-									    *)
-									   body,
-									   body
-									   +
-									   DEH_SIZE,
-									   tb->
-									   insert_size
-									   [0]
-							    );
+							leaf_paste_entries(&bi, 0, paste_entry_position, 1,
+									   (struct reiserfs_de_head *) body,
+									   body + DEH_SIZE, tb->insert_size[0]);
 
-							if (paste_entry_position
-							    == 0) {
+							if (paste_entry_position == 0) {
 								/* change delimiting keys */
-								replace_key(tb,
-									    tb->
-									    CFR
-									    [0],
-									    tb->
-									    rkey
-									    [0],
-									    tb->
-									    R
-									    [0],
-									    0);
+								replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0],0);
 							}
 
 							tb->insert_size[0] = 0;
 							pos_in_item++;
 						} else {	/* new directory entry doesn't fall into R[0] */
 
-							leaf_shift_right(tb,
-									 tb->
-									 rnum
-									 [0],
-									 tb->
-									 rbytes);
+							leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
 						}
 					} else {	/* regular object */
 
-						int n_shift, n_rem,
-						    r_zeros_number;
+						int n_shift, n_rem, r_zeros_number;
 						const char *r_body;
 
 						/* Calculate number of bytes which must be shifted from appended item */
-						if ((n_shift =
-						     tb->rbytes -
-						     tb->insert_size[0]) < 0)
+						if ((n_shift = tb->rbytes - tb->insert_size[0]) < 0)
 							n_shift = 0;
 
-						RFALSE(pos_in_item !=
-						       ih_item_len
-						       (B_N_PITEM_HEAD
-							(tbS0, item_pos)),
+						RFALSE(pos_in_item != ih_item_len
+						       (B_N_PITEM_HEAD(tbS0, item_pos)),
 						       "PAP-12155: invalid position to paste. ih_item_len=%d, pos_in_item=%d",
-						       pos_in_item,
-						       ih_item_len
-						       (B_N_PITEM_HEAD
-							(tbS0, item_pos)));
+						       pos_in_item, ih_item_len
+						       (B_N_PITEM_HEAD(tbS0, item_pos)));
 
-						leaf_shift_right(tb,
-								 tb->rnum[0],
-								 n_shift);
+						leaf_shift_right(tb, tb->rnum[0], n_shift);
 						/* Calculate number of bytes which must remain in body after appending to R[0] */
-						if ((n_rem =
-						     tb->insert_size[0] -
-						     tb->rbytes) < 0)
+						if ((n_rem = tb->insert_size[0] - tb->rbytes) < 0)
 							n_rem = 0;
 
 						{
 							int version;
-							unsigned long temp_rem =
-							    n_rem;
+							unsigned long temp_rem = n_rem;
 
-							version =
-							    ih_version
-							    (B_N_PITEM_HEAD
-							     (tb->R[0], 0));
-							if (is_indirect_le_key
-							    (version,
-							     B_N_PKEY(tb->R[0],
-								      0))) {
-								temp_rem =
-								    n_rem <<
-								    (tb->tb_sb->
-								     s_blocksize_bits
-								     -
-								     UNFM_P_SHIFT);
+							version = ih_version(B_N_PITEM_HEAD(tb->R[0], 0));
+							if (is_indirect_le_key(version, B_N_PKEY(tb->R[0], 0))) {
+								temp_rem = n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT);
 							}
-							set_le_key_k_offset
-							    (version,
-							     B_N_PKEY(tb->R[0],
-								      0),
-							     le_key_k_offset
-							     (version,
-							      B_N_PKEY(tb->R[0],
-								       0)) +
-							     temp_rem);
-							set_le_key_k_offset
-							    (version,
-							     B_N_PDELIM_KEY(tb->
-									    CFR
-									    [0],
-									    tb->
-									    rkey
-									    [0]),
-							     le_key_k_offset
-							     (version,
-							      B_N_PDELIM_KEY
-							      (tb->CFR[0],
-							       tb->rkey[0])) +
-							     temp_rem);
+							set_le_key_k_offset(version, B_N_PKEY(tb->R[0], 0),
+							     le_key_k_offset(version, B_N_PKEY(tb->R[0], 0)) + temp_rem);
+							set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0]),
+							     le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0])) + temp_rem);
 						}
 /*		  k_offset (B_N_PKEY(tb->R[0],0)) += n_rem;
 		  k_offset (B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0])) += n_rem;*/
-						do_balance_mark_internal_dirty
-						    (tb, tb->CFR[0], 0);
+						do_balance_mark_internal_dirty(tb, tb->CFR[0], 0);
 
 						/* Append part of body into R[0] */
 						buffer_info_init_right(tb, &bi);
 						if (n_rem > zeros_num) {
 							r_zeros_number = 0;
-							r_body =
-							    body + n_rem -
-							    zeros_num;
+							r_body = body + n_rem - zeros_num;
 						} else {
 							r_body = body;
-							r_zeros_number =
-							    zeros_num - n_rem;
-							zeros_num -=
-							    r_zeros_number;
+							r_zeros_number = zeros_num - n_rem;
+							zeros_num -= r_zeros_number;
 						}
 
-						leaf_paste_in_buffer(&bi, 0,
-								     n_shift,
-								     tb->
-								     insert_size
-								     [0] -
-								     n_rem,
-								     r_body,
-								     r_zeros_number);
+						leaf_paste_in_buffer(&bi, 0, n_shift,
+								     tb->insert_size[0] - n_rem,
+								     r_body, r_zeros_number);
 
-						if (is_indirect_le_ih
-						    (B_N_PITEM_HEAD
-						     (tb->R[0], 0))) {
+						if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->R[0], 0))) {
 #if 0
 							RFALSE(n_rem,
 							       "PAP-12160: paste more than one unformatted node pointer");
 #endif
-							set_ih_free_space
-							    (B_N_PITEM_HEAD
-							     (tb->R[0], 0), 0);
+							set_ih_free_space(B_N_PITEM_HEAD(tb->R[0], 0), 0);
 						}
 						tb->insert_size[0] = n_rem;
 						if (!n_rem)
@@ -1044,58 +722,28 @@
 
 					struct item_head *pasted;
 
-					ret_val =
-					    leaf_shift_right(tb, tb->rnum[0],
-							     tb->rbytes);
+					ret_val = leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
 					/* append item in R[0] */
 					if (pos_in_item >= 0) {
 						buffer_info_init_right(tb, &bi);
-						leaf_paste_in_buffer(&bi,
-								     item_pos -
-								     n +
-								     tb->
-								     rnum[0],
-								     pos_in_item,
-								     tb->
-								     insert_size
-								     [0], body,
-								     zeros_num);
+						leaf_paste_in_buffer(&bi, item_pos - n + tb->rnum[0], pos_in_item,
+								     tb->insert_size[0], body, zeros_num);
 					}
 
 					/* paste new entry, if item is directory item */
-					pasted =
-					    B_N_PITEM_HEAD(tb->R[0],
-							   item_pos - n +
-							   tb->rnum[0]);
-					if (is_direntry_le_ih(pasted)
-					    && pos_in_item >= 0) {
-						leaf_paste_entries(&bi,
-								   item_pos -
-								   n +
-								   tb->rnum[0],
-								   pos_in_item,
-								   1,
-								   (struct
-								    reiserfs_de_head
-								    *)body,
-								   body +
-								   DEH_SIZE,
-								   tb->
-								   insert_size
-								   [0]
-						    );
+					pasted = B_N_PITEM_HEAD(tb->R[0], item_pos - n + tb->rnum[0]);
+					if (is_direntry_le_ih(pasted) && pos_in_item >= 0) {
+						leaf_paste_entries(&bi, item_pos - n + tb->rnum[0],
+								   pos_in_item, 1,
+								   (struct reiserfs_de_head *) body,
+								   body + DEH_SIZE, tb->insert_size[0]);
 						if (!pos_in_item) {
 
-							RFALSE(item_pos - n +
-							       tb->rnum[0],
+							RFALSE(item_pos - n + tb->rnum[0],
 							       "PAP-12165: directory item must be first item of node when pasting is in 0th position");
 
 							/* update delimiting keys */
-							replace_key(tb,
-								    tb->CFR[0],
-								    tb->rkey[0],
-								    tb->R[0],
-								    0);
+							replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0);
 						}
 					}
 
@@ -1111,22 +759,16 @@
 		default:	/* cases d and t */
 			reiserfs_panic(tb->tb_sb, "PAP-12175",
 				       "rnum > 0: unexpected mode: %s(%d)",
-				       (flag ==
-					M_DELETE) ? "DELETE" : ((flag ==
-								 M_CUT) ? "CUT"
-								: "UNKNOWN"),
-				       flag);
+				       (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
 		}
 
 	}
 
 	/* tb->rnum[0] > 0 */
 	RFALSE(tb->blknum[0] > 3,
-	       "PAP-12180: blknum can not be %d. It must be <= 3",
-	       tb->blknum[0]);
+	       "PAP-12180: blknum can not be %d. It must be <= 3", tb->blknum[0]);
 	RFALSE(tb->blknum[0] < 0,
-	       "PAP-12185: blknum can not be %d. It must be >= 0",
-	       tb->blknum[0]);
+	       "PAP-12185: blknum can not be %d. It must be >= 0", tb->blknum[0]);
 
 	/* if while adding to a node we discover that it is possible to split
 	   it in two, and merge the left part into the left neighbor and the
@@ -1177,8 +819,7 @@
 
 			if (n - snum[i] < item_pos) {	/* new item or it's part falls to first new node S_new[i] */
 				if (item_pos == n - snum[i] + 1 && sbytes[i] != -1) {	/* part of new item falls into S_new[i] */
-					int old_key_comp, old_len,
-					    r_zeros_number;
+					int old_key_comp, old_len, r_zeros_number;
 					const char *r_body;
 					int version;
 
@@ -1192,15 +833,8 @@
 					old_len = ih_item_len(ih);
 
 					/* Calculate key component and item length to insert into S_new[i] */
-					set_le_ih_k_offset(ih,
-							   le_ih_k_offset(ih) +
-							   ((old_len -
-							     sbytes[i]) <<
-							    (is_indirect_le_ih
-							     (ih) ? tb->tb_sb->
-							     s_blocksize_bits -
-							     UNFM_P_SHIFT :
-							     0)));
+					set_le_ih_k_offset(ih, le_ih_k_offset(ih) +
+							   ((old_len - sbytes[i]) << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0)));
 
 					put_ih_item_len(ih, sbytes[i]);
 
@@ -1209,39 +843,29 @@
 
 					if ((old_len - sbytes[i]) > zeros_num) {
 						r_zeros_number = 0;
-						r_body =
-						    body + (old_len -
-							    sbytes[i]) -
-						    zeros_num;
+						r_body = body + (old_len - sbytes[i]) - zeros_num;
 					} else {
 						r_body = body;
-						r_zeros_number =
-						    zeros_num - (old_len -
-								 sbytes[i]);
+						r_zeros_number = zeros_num - (old_len - sbytes[i]);
 						zeros_num -= r_zeros_number;
 					}
 
-					leaf_insert_into_buf(&bi, 0, ih, r_body,
-							     r_zeros_number);
+					leaf_insert_into_buf(&bi, 0, ih, r_body, r_zeros_number);
 
 					/* Calculate key component and item length to insert into S[i] */
 					set_le_ih_k_offset(ih, old_key_comp);
-					put_ih_item_len(ih,
-							old_len - sbytes[i]);
+					put_ih_item_len(ih, old_len - sbytes[i]);
 					tb->insert_size[0] -= sbytes[i];
 				} else {	/* whole new item falls into S_new[i] */
 
 					/* Shift snum[0] - 1 items to S_new[i] (sbytes[i] of split item) */
 					leaf_move_items(LEAF_FROM_S_TO_SNEW, tb,
-							snum[i] - 1, sbytes[i],
-							S_new[i]);
+							snum[i] - 1, sbytes[i], S_new[i]);
 
 					/* Insert new item into S_new[i] */
 					buffer_info_init_bh(tb, &bi, S_new[i]);
-					leaf_insert_into_buf(&bi,
-							     item_pos - n +
-							     snum[i] - 1, ih,
-							     body, zeros_num);
+					leaf_insert_into_buf(&bi, item_pos - n + snum[i] - 1,
+							     ih, body, zeros_num);
 
 					zeros_num = tb->insert_size[0] = 0;
 				}
@@ -1268,150 +892,73 @@
 
 						int entry_count;
 
-						entry_count =
-						    ih_entry_count(aux_ih);
+						entry_count = ih_entry_count(aux_ih);
 
-						if (entry_count - sbytes[i] <
-						    pos_in_item
-						    && pos_in_item <=
-						    entry_count) {
+						if (entry_count - sbytes[i] < pos_in_item && pos_in_item <= entry_count) {
 							/* new directory entry falls into S_new[i] */
 
-							RFALSE(!tb->
-							       insert_size[0],
-							       "PAP-12215: insert_size is already 0");
-							RFALSE(sbytes[i] - 1 >=
-							       entry_count,
+							RFALSE(!tb->insert_size[0], "PAP-12215: insert_size is already 0");
+							RFALSE(sbytes[i] - 1 >= entry_count,
 							       "PAP-12220: there are no so much entries (%d), only %d",
-							       sbytes[i] - 1,
-							       entry_count);
+							       sbytes[i] - 1, entry_count);
 
 							/* Shift snum[i]-1 items in whole. Shift sbytes[i] directory entries from directory item number snum[i] */
-							leaf_move_items
-							    (LEAF_FROM_S_TO_SNEW,
-							     tb, snum[i],
-							     sbytes[i] - 1,
-							     S_new[i]);
+							leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], sbytes[i] - 1, S_new[i]);
 							/* Paste given directory entry to directory item */
 							buffer_info_init_bh(tb, &bi, S_new[i]);
-							leaf_paste_in_buffer
-							    (&bi, 0,
-							     pos_in_item -
-							     entry_count +
-							     sbytes[i] - 1,
-							     tb->insert_size[0],
-							     body, zeros_num);
+							leaf_paste_in_buffer(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1,
+							     tb->insert_size[0], body, zeros_num);
 							/* paste new directory entry */
-							leaf_paste_entries(&bi,
-									   0,
-									   pos_in_item
-									   -
-									   entry_count
-									   +
-									   sbytes
-									   [i] -
-									   1, 1,
-									   (struct
-									    reiserfs_de_head
-									    *)
-									   body,
-									   body
-									   +
-									   DEH_SIZE,
-									   tb->
-									   insert_size
-									   [0]
-							    );
+							leaf_paste_entries(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1, 1,
+									   (struct reiserfs_de_head *) body,
+									   body + DEH_SIZE, tb->insert_size[0]);
 							tb->insert_size[0] = 0;
 							pos_in_item++;
 						} else {	/* new directory entry doesn't fall into S_new[i] */
-							leaf_move_items
-							    (LEAF_FROM_S_TO_SNEW,
-							     tb, snum[i],
-							     sbytes[i],
-							     S_new[i]);
+							leaf_move_items(LEAF_FROM_S_TO_SNEW,tb, snum[i], sbytes[i], S_new[i]);
 						}
 					} else {	/* regular object */
 
-						int n_shift, n_rem,
-						    r_zeros_number;
+						int n_shift, n_rem, r_zeros_number;
 						const char *r_body;
 
-						RFALSE(pos_in_item !=
-						       ih_item_len
-						       (B_N_PITEM_HEAD
-							(tbS0, item_pos))
-						       || tb->insert_size[0] <=
-						       0,
+						RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)) || tb->insert_size[0] <= 0,
 						       "PAP-12225: item too short or insert_size <= 0");
 
 						/* Calculate number of bytes which must be shifted from appended item */
-						n_shift =
-						    sbytes[i] -
-						    tb->insert_size[0];
+						n_shift = sbytes[i] - tb->insert_size[0];
 						if (n_shift < 0)
 							n_shift = 0;
-						leaf_move_items
-						    (LEAF_FROM_S_TO_SNEW, tb,
-						     snum[i], n_shift,
-						     S_new[i]);
+						leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], n_shift, S_new[i]);
 
 						/* Calculate number of bytes which must remain in body after append to S_new[i] */
-						n_rem =
-						    tb->insert_size[0] -
-						    sbytes[i];
+						n_rem = tb->insert_size[0] - sbytes[i];
 						if (n_rem < 0)
 							n_rem = 0;
 						/* Append part of body into S_new[0] */
 						buffer_info_init_bh(tb, &bi, S_new[i]);
 						if (n_rem > zeros_num) {
 							r_zeros_number = 0;
-							r_body =
-							    body + n_rem -
-							    zeros_num;
+							r_body = body + n_rem - zeros_num;
 						} else {
 							r_body = body;
-							r_zeros_number =
-							    zeros_num - n_rem;
-							zeros_num -=
-							    r_zeros_number;
+							r_zeros_number = zeros_num - n_rem;
+							zeros_num -= r_zeros_number;
 						}
 
-						leaf_paste_in_buffer(&bi, 0,
-								     n_shift,
-								     tb->
-								     insert_size
-								     [0] -
-								     n_rem,
-								     r_body,
-								     r_zeros_number);
+						leaf_paste_in_buffer(&bi, 0, n_shift,
+								     tb->insert_size[0] - n_rem,
+								     r_body, r_zeros_number);
 						{
 							struct item_head *tmp;
 
-							tmp =
-							    B_N_PITEM_HEAD(S_new
-									   [i],
-									   0);
+							tmp = B_N_PITEM_HEAD(S_new[i], 0);
 							if (is_indirect_le_ih
 							    (tmp)) {
-								set_ih_free_space
-								    (tmp, 0);
-								set_le_ih_k_offset
-								    (tmp,
-								     le_ih_k_offset
-								     (tmp) +
-								     (n_rem <<
-								      (tb->
-								       tb_sb->
-								       s_blocksize_bits
-								       -
-								       UNFM_P_SHIFT)));
+								set_ih_free_space(tmp, 0);
+								set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + (n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT)));
 							} else {
-								set_le_ih_k_offset
-								    (tmp,
-								     le_ih_k_offset
-								     (tmp) +
-								     n_rem);
+								set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + n_rem);
 							}
 						}
 
@@ -1426,8 +973,7 @@
 					struct item_head *pasted;
 
 #ifdef CONFIG_REISERFS_CHECK
-					struct item_head *ih_check =
-					    B_N_PITEM_HEAD(tbS0, item_pos);
+					struct item_head *ih_check = B_N_PITEM_HEAD(tbS0, item_pos);
 
 					if (!is_direntry_le_ih(ih_check)
 					    && (pos_in_item != ih_item_len(ih_check)
@@ -1439,8 +985,7 @@
 							     "to ih_item_len");
 #endif				/* CONFIG_REISERFS_CHECK */
 
-					leaf_mi =
-					    leaf_move_items(LEAF_FROM_S_TO_SNEW,
+					leaf_mi = leaf_move_items(LEAF_FROM_S_TO_SNEW,
 							    tb, snum[i],
 							    sbytes[i],
 							    S_new[i]);
@@ -1452,30 +997,19 @@
 					/* paste into item */
 					buffer_info_init_bh(tb, &bi, S_new[i]);
 					leaf_paste_in_buffer(&bi,
-							     item_pos - n +
-							     snum[i],
+							     item_pos - n + snum[i],
 							     pos_in_item,
 							     tb->insert_size[0],
 							     body, zeros_num);
 
-					pasted =
-					    B_N_PITEM_HEAD(S_new[i],
-							   item_pos - n +
-							   snum[i]);
+					pasted = B_N_PITEM_HEAD(S_new[i], item_pos - n + snum[i]);
 					if (is_direntry_le_ih(pasted)) {
 						leaf_paste_entries(&bi,
-								   item_pos -
-								   n + snum[i],
-								   pos_in_item,
-								   1,
-								   (struct
-								    reiserfs_de_head
-								    *)body,
-								   body +
-								   DEH_SIZE,
-								   tb->
-								   insert_size
-								   [0]
+								   item_pos - n + snum[i],
+								   pos_in_item, 1,
+								   (struct reiserfs_de_head *)body,
+								   body + DEH_SIZE,
+								   tb->insert_size[0]
 						    );
 					}
 
@@ -1495,11 +1029,7 @@
 		default:	/* cases d and t */
 			reiserfs_panic(tb->tb_sb, "PAP-12245",
 				       "blknum > 2: unexpected mode: %s(%d)",
-				       (flag ==
-					M_DELETE) ? "DELETE" : ((flag ==
-								 M_CUT) ? "CUT"
-								: "UNKNOWN"),
-				       flag);
+				       (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
 		}
 
 		memcpy(insert_key + i, B_N_PKEY(S_new[i], 0), KEY_SIZE);
@@ -1524,9 +1054,7 @@
 			/* If we insert the first key change the delimiting key */
 			if (item_pos == 0) {
 				if (tb->CFL[0])	/* can be 0 in reiserfsck */
-					replace_key(tb, tb->CFL[0], tb->lkey[0],
-						    tbS0, 0);
-
+					replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
 			}
 			break;
 
@@ -1536,53 +1064,27 @@
 				pasted = B_N_PITEM_HEAD(tbS0, item_pos);
 				/* when directory, may be new entry already pasted */
 				if (is_direntry_le_ih(pasted)) {
-					if (pos_in_item >= 0 &&
-					    pos_in_item <=
-					    ih_entry_count(pasted)) {
+					if (pos_in_item >= 0 && pos_in_item <= ih_entry_count(pasted)) {
 
 						RFALSE(!tb->insert_size[0],
 						       "PAP-12260: insert_size is 0 already");
 
 						/* prepare space */
 						buffer_info_init_tbS0(tb, &bi);
-						leaf_paste_in_buffer(&bi,
-								     item_pos,
-								     pos_in_item,
-								     tb->
-								     insert_size
-								     [0], body,
+						leaf_paste_in_buffer(&bi, item_pos, pos_in_item,
+								     tb->insert_size[0], body,
 								     zeros_num);
 
 						/* paste entry */
-						leaf_paste_entries(&bi,
-								   item_pos,
-								   pos_in_item,
-								   1,
-								   (struct
-								    reiserfs_de_head
-								    *)body,
-								   body +
-								   DEH_SIZE,
-								   tb->
-								   insert_size
-								   [0]
-						    );
+						leaf_paste_entries(&bi, item_pos, pos_in_item, 1,
+								   (struct reiserfs_de_head *)body,
+								   body + DEH_SIZE,
+								   tb->insert_size[0]);
 						if (!item_pos && !pos_in_item) {
-							RFALSE(!tb->CFL[0]
-							       || !tb->L[0],
+							RFALSE(!tb->CFL[0] || !tb->L[0],
 							       "PAP-12270: CFL[0]/L[0] must be specified");
-							if (tb->CFL[0]) {
-								replace_key(tb,
-									    tb->
-									    CFL
-									    [0],
-									    tb->
-									    lkey
-									    [0],
-									    tbS0,
-									    0);
-
-							}
+							if (tb->CFL[0])
+								replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
 						}
 						tb->insert_size[0] = 0;
 					}
@@ -1593,13 +1095,8 @@
 						       "PAP-12275: insert size must not be %d",
 						       tb->insert_size[0]);
 						buffer_info_init_tbS0(tb, &bi);
-						leaf_paste_in_buffer(&bi,
-								     item_pos,
-								     pos_in_item,
-								     tb->
-								     insert_size
-								     [0], body,
-								     zeros_num);
+						leaf_paste_in_buffer(&bi, item_pos, pos_in_item,
+								     tb->insert_size[0], body, zeros_num);
 
 						if (is_indirect_le_ih(pasted)) {
 #if 0
@@ -1611,8 +1108,7 @@
 							       tb->
 							       insert_size[0]);
 #endif
-							set_ih_free_space
-							    (pasted, 0);
+							set_ih_free_space(pasted, 0);
 						}
 						tb->insert_size[0] = 0;
 					}
@@ -1620,8 +1116,7 @@
 					else {
 						if (tb->insert_size[0]) {
 							print_cur_tb("12285");
-							reiserfs_panic(tb->
-								       tb_sb,
+							reiserfs_panic(tb->tb_sb,
 							    "PAP-12285",
 							    "insert_size "
 							    "must be 0 "
diff --git a/fs/sync.c b/fs/sync.c
index f155374..b28d1dd 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -27,11 +27,10 @@
  * wait == 1 case since in that case write_inode() functions do
  * sync_dirty_buffer() and thus effectively write one block at a time.
  */
-static int __sync_filesystem(struct super_block *sb, int wait,
-			     unsigned long start)
+static int __sync_filesystem(struct super_block *sb, int wait)
 {
 	if (wait)
-		sync_inodes_sb(sb, start);
+		sync_inodes_sb(sb);
 	else
 		writeback_inodes_sb(sb, WB_REASON_SYNC);
 
@@ -48,7 +47,6 @@
 int sync_filesystem(struct super_block *sb)
 {
 	int ret;
-	unsigned long start = jiffies;
 
 	/*
 	 * We need to be protected against the filesystem going from
@@ -62,17 +60,17 @@
 	if (sb->s_flags & MS_RDONLY)
 		return 0;
 
-	ret = __sync_filesystem(sb, 0, start);
+	ret = __sync_filesystem(sb, 0);
 	if (ret < 0)
 		return ret;
-	return __sync_filesystem(sb, 1, start);
+	return __sync_filesystem(sb, 1);
 }
 EXPORT_SYMBOL_GPL(sync_filesystem);
 
 static void sync_inodes_one_sb(struct super_block *sb, void *arg)
 {
 	if (!(sb->s_flags & MS_RDONLY))
-		sync_inodes_sb(sb, *((unsigned long *)arg));
+		sync_inodes_sb(sb);
 }
 
 static void sync_fs_one_sb(struct super_block *sb, void *arg)
@@ -104,10 +102,9 @@
 SYSCALL_DEFINE0(sync)
 {
 	int nowait = 0, wait = 1;
-	unsigned long start = jiffies;
 
 	wakeup_flusher_threads(0, WB_REASON_SYNC);
-	iterate_supers(sync_inodes_one_sb, &start);
+	iterate_supers(sync_inodes_one_sb, NULL);
 	iterate_supers(sync_fs_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &wait);
 	iterate_bdevs(fdatawrite_one_bdev, NULL);
@@ -222,23 +219,6 @@
 	return do_fsync(fd, 1);
 }
 
-/**
- * generic_write_sync - perform syncing after a write if file / inode is sync
- * @file:	file to which the write happened
- * @pos:	offset where the write started
- * @count:	length of the write
- *
- * This is just a simple wrapper about our general syncing function.
- */
-int generic_write_sync(struct file *file, loff_t pos, loff_t count)
-{
-	if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host))
-		return 0;
-	return vfs_fsync_range(file, pos, pos + count - 1,
-			       (file->f_flags & __O_SYNC) ? 0 : 1);
-}
-EXPORT_SYMBOL(generic_write_sync);
-
 /*
  * sys_sync_file_range() permits finely controlled syncing over a segment of
  * a file in the range offset .. (offset+nbytes-1) inclusive.  If nbytes is
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 6211230..3eaf5c6 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -27,6 +27,7 @@
 {
 	struct dentry *root;
 	void *ns;
+	bool new_sb;
 
 	if (!(flags & MS_KERNMOUNT)) {
 		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
@@ -37,8 +38,8 @@
 	}
 
 	ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
-	root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns);
-	if (IS_ERR(root))
+	root = kernfs_mount_ns(fs_type, flags, sysfs_root, &new_sb, ns);
+	if (IS_ERR(root) || !new_sb)
 		kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
 	return root;
 }
diff --git a/fs/udf/file.c b/fs/udf/file.c
index c02a27a..1037637 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -144,6 +144,7 @@
 	size_t count = iocb->ki_nbytes;
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
+	mutex_lock(&inode->i_mutex);
 	down_write(&iinfo->i_data_sem);
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
 		if (file->f_flags & O_APPEND)
@@ -156,6 +157,7 @@
 						pos + count)) {
 			err = udf_expand_file_adinicb(inode);
 			if (err) {
+				mutex_unlock(&inode->i_mutex);
 				udf_debug("udf_expand_adinicb: err=%d\n", err);
 				return err;
 			}
@@ -169,9 +171,17 @@
 	} else
 		up_write(&iinfo->i_data_sem);
 
-	retval = generic_file_aio_write(iocb, iov, nr_segs, ppos);
-	if (retval > 0)
+	retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	mutex_unlock(&inode->i_mutex);
+
+	if (retval > 0) {
+		ssize_t err;
+
 		mark_inode_dirty(inode);
+		err = generic_write_sync(file, iocb->ki_pos - retval, retval);
+		if (err < 0)
+			retval = err;
+	}
 
 	return retval;
 }
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 062b792..982ce05 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -265,6 +265,7 @@
 		.nr_to_write = 1,
 	};
 
+	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
 	if (!iinfo->i_lenAlloc) {
 		if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
 			iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 2e7989e..64b48ea 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -799,7 +799,7 @@
 		XFS_STATS_ADD(xs_write_bytes, ret);
 
 		/* Handle various SYNC-type writes */
-		err = generic_write_sync(file, pos, ret);
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
 		if (err < 0)
 			ret = err;
 	}
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index f35d5c9..9ddfb81 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -705,7 +705,6 @@
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct inode		*inode = VFS_I(ip);
-	int			mask = iattr->ia_valid;
 	xfs_off_t		oldsize, newsize;
 	struct xfs_trans	*tp;
 	int			error;
@@ -726,8 +725,8 @@
 
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(S_ISREG(ip->i_d.di_mode));
-	ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
-			ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
+	ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
+		ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
 
 	oldsize = inode->i_size;
 	newsize = iattr->ia_size;
@@ -736,7 +735,7 @@
 	 * Short circuit the truncate case for zero length files.
 	 */
 	if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
-		if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
+		if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
 			return 0;
 
 		/*
@@ -824,10 +823,11 @@
 	 * these flags set.  For all other operations the VFS set these flags
 	 * explicitly if it wants a timestamp update.
 	 */
-	if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
+	if (newsize != oldsize &&
+	    !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
 		iattr->ia_ctime = iattr->ia_mtime =
 			current_fs_time(inode->i_sb);
-		mask |= ATTR_CTIME | ATTR_MTIME;
+		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
 	}
 
 	/*
@@ -863,9 +863,9 @@
 		xfs_inode_clear_eofblocks_tag(ip);
 	}
 
-	if (mask & ATTR_MODE)
+	if (iattr->ia_valid & ATTR_MODE)
 		xfs_setattr_mode(ip, iattr);
-	if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
+	if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
 		xfs_setattr_time(ip, iattr);
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index cdebd83..4ef6fdb 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -205,16 +205,25 @@
 		/*
 		 * We 64-bit align the length of each iovec so that the start
 		 * of the next one is naturally aligned.  We'll need to
-		 * account for that slack space here.
+		 * account for that slack space here. Then round nbytes up
+		 * to 64-bit alignment so that the initial buffer alignment is
+		 * easy to calculate and verify.
 		 */
 		nbytes += niovecs * sizeof(uint64_t);
+		nbytes = round_up(nbytes, sizeof(uint64_t));
 
 		/* grab the old item if it exists for reservation accounting */
 		old_lv = lip->li_lv;
 
-		/* calc buffer size */
-		buf_size = sizeof(struct xfs_log_vec) + nbytes +
-				niovecs * sizeof(struct xfs_log_iovec);
+		/*
+		 * The data buffer needs to start 64-bit aligned, so round up
+		 * that space to ensure we can align it appropriately and not
+		 * overrun the buffer.
+		 */
+		buf_size = nbytes +
+			   round_up((sizeof(struct xfs_log_vec) +
+				     niovecs * sizeof(struct xfs_log_iovec)),
+				    sizeof(uint64_t));
 
 		/* compare to existing item size */
 		if (lip->li_lv && buf_size <= lip->li_lv->lv_size) {
@@ -251,6 +260,8 @@
 		/* The allocated data region lies beyond the iovec region */
 		lv->lv_buf_len = 0;
 		lv->lv_buf = (char *)lv + buf_size - nbytes;
+		ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
+
 		lip->li_ops->iop_format(lip, lv);
 insert:
 		ASSERT(lv->lv_buf_len <= nbytes);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 02df7b4..f96c056 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -282,22 +282,29 @@
 	struct xfs_sb	*sbp = &mp->m_sb;
 	int		error;
 	int		loud = !(flags & XFS_MFSI_QUIET);
+	const struct xfs_buf_ops *buf_ops;
 
 	ASSERT(mp->m_sb_bp == NULL);
 	ASSERT(mp->m_ddev_targp != NULL);
 
 	/*
+	 * For the initial read, we must guess at the sector
+	 * size based on the block device.  It's enough to
+	 * get the sb_sectsize out of the superblock and
+	 * then reread with the proper length.
+	 * We don't verify it yet, because it may not be complete.
+	 */
+	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
+	buf_ops = NULL;
+
+	/*
 	 * Allocate a (locked) buffer to hold the superblock.
 	 * This will be kept around at all times to optimize
 	 * access to the superblock.
 	 */
-	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
-
 reread:
 	bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
-				   BTOBB(sector_size), 0,
-				   loud ? &xfs_sb_buf_ops
-				        : &xfs_sb_quiet_buf_ops);
+				   BTOBB(sector_size), 0, buf_ops);
 	if (!bp) {
 		if (loud)
 			xfs_warn(mp, "SB buffer read failed");
@@ -328,12 +335,13 @@
 	}
 
 	/*
-	 * If device sector size is smaller than the superblock size,
-	 * re-read the superblock so the buffer is correctly sized.
+	 * Re-read the superblock so the buffer is correctly sized,
+	 * and properly verified.
 	 */
-	if (sector_size < sbp->sb_sectsize) {
+	if (buf_ops == NULL) {
 		xfs_buf_relse(bp);
 		sector_size = sbp->sb_sectsize;
+		buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
 		goto reread;
 	}
 
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index b7c9aea..1e11679 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -295,8 +295,7 @@
 	    sbp->sb_dblocks == 0					||
 	    sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp)			||
 	    sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) {
-		XFS_CORRUPTION_ERROR("SB sanity check failed",
-				XFS_ERRLEVEL_LOW, mp, sbp);
+		xfs_notice(mp, "SB sanity check failed");
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 
@@ -611,10 +610,10 @@
 						XFS_SB_VERSION_5) ||
 	     dsb->sb_crc != 0)) {
 
-		if (!xfs_verify_cksum(bp->b_addr, be16_to_cpu(dsb->sb_sectsize),
+		if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
 				      offsetof(struct xfs_sb, sb_crc))) {
 			/* Only fail bad secondaries on a known V5 filesystem */
-			if (bp->b_bn != XFS_SB_DADDR &&
+			if (bp->b_bn == XFS_SB_DADDR ||
 			    xfs_sb_version_hascrc(&mp->m_sb)) {
 				error = EFSCORRUPTED;
 				goto out_error;
@@ -625,7 +624,7 @@
 
 out_error:
 	if (error) {
-		if (error != EWRONGFS)
+		if (error == EFSCORRUPTED)
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
 					     mp, bp->b_addr);
 		xfs_buf_ioerror(bp, error);
@@ -644,7 +643,6 @@
 {
 	struct xfs_dsb	*dsb = XFS_BUF_TO_SBP(bp);
 
-
 	if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) {
 		/* XFS filesystem, verify noisily! */
 		xfs_sb_read_verify(bp);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index f317488..d971f49 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -913,7 +913,7 @@
 	struct super_block	*sb = mp->m_super;
 
 	if (down_read_trylock(&sb->s_umount)) {
-		sync_inodes_sb(sb, jiffies);
+		sync_inodes_sb(sb);
 		up_read(&sb->s_umount);
 	}
 }
diff --git a/include/asm-generic/bitops/const_hweight.h b/include/asm-generic/bitops/const_hweight.h
index fa2a50b..0a7e066 100644
--- a/include/asm-generic/bitops/const_hweight.h
+++ b/include/asm-generic/bitops/const_hweight.h
@@ -5,14 +5,15 @@
  * Compile time versions of __arch_hweightN()
  */
 #define __const_hweight8(w)		\
-      (	(!!((w) & (1ULL << 0))) +	\
-	(!!((w) & (1ULL << 1))) +	\
-	(!!((w) & (1ULL << 2))) +	\
-	(!!((w) & (1ULL << 3))) +	\
-	(!!((w) & (1ULL << 4))) +	\
-	(!!((w) & (1ULL << 5))) +	\
-	(!!((w) & (1ULL << 6))) +	\
-	(!!((w) & (1ULL << 7)))	)
+	((unsigned int)			\
+	 ((!!((w) & (1ULL << 0))) +	\
+	  (!!((w) & (1ULL << 1))) +	\
+	  (!!((w) & (1ULL << 2))) +	\
+	  (!!((w) & (1ULL << 3))) +	\
+	  (!!((w) & (1ULL << 4))) +	\
+	  (!!((w) & (1ULL << 5))) +	\
+	  (!!((w) & (1ULL << 6))) +	\
+	  (!!((w) & (1ULL << 7)))))
 
 #define __const_hweight16(w) (__const_hweight8(w)  + __const_hweight8((w)  >> 8 ))
 #define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16))
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 8e4f41d..1ec08c1 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -193,6 +193,19 @@
 }
 #endif
 
+#ifndef __HAVE_ARCH_PTE_UNUSED
+/*
+ * Some architectures provide facilities to virtualization guests
+ * so that they can flag allocated pages as unused. This allows the
+ * host to transparently reclaim unused pages. This function returns
+ * whether the pte's page is unused.
+ */
+static inline int pte_unused(pte_t pte)
+{
+	return 0;
+}
+#endif
+
 #ifndef __HAVE_ARCH_PMD_SAME
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
@@ -701,6 +714,18 @@
 }
 #endif
 
+#ifndef ptep_set_numa
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pte_t *ptep)
+{
+	pte_t ptent = *ptep;
+
+	ptent = pte_mknuma(ptent);
+	set_pte_at(mm, addr, ptep, ptent);
+	return;
+}
+#endif
+
 #ifndef pmd_mknuma
 static inline pmd_t pmd_mknuma(pmd_t pmd)
 {
@@ -708,6 +733,18 @@
 	return pmd_clear_flags(pmd, _PAGE_PRESENT);
 }
 #endif
+
+#ifndef pmdp_set_numa
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pmd_t *pmdp)
+{
+	pmd_t pmd = *pmdp;
+
+	pmd = pmd_mknuma(pmd);
+	set_pmd_at(mm, addr, pmdp, pmd);
+	return;
+}
+#endif
 #else
 extern int pte_numa(pte_t pte);
 extern int pmd_numa(pmd_t pmd);
@@ -715,6 +752,8 @@
 extern pmd_t pmd_mknonnuma(pmd_t pmd);
 extern pte_t pte_mknuma(pte_t pte);
 extern pmd_t pmd_mknuma(pmd_t pmd);
+extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp);
 #endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
 #else
 static inline int pmd_numa(pmd_t pmd)
@@ -742,10 +781,23 @@
 	return pte;
 }
 
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pte_t *ptep)
+{
+	return;
+}
+
+
 static inline pmd_t pmd_mknuma(pmd_t pmd)
 {
 	return pmd;
 }
+
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pmd_t *pmdp)
+{
+	return ;
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #endif /* CONFIG_MMU */
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index bb1e2cd..d48bf5a 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_RWSEM_H
-#define _ASM_POWERPC_RWSEM_H
+#ifndef _ASM_GENERIC_RWSEM_H
+#define _ASM_GENERIC_RWSEM_H
 
 #ifndef _LINUX_RWSEM_H
 #error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
@@ -8,7 +8,7 @@
 #ifdef __KERNEL__
 
 /*
- * R/W semaphores for PPC using the stuff in lib/rwsem.c.
+ * R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
  * Adapted largely from include/asm-i386/rwsem.h
  * by Paul Mackerras <paulus@samba.org>.
  */
@@ -16,7 +16,7 @@
 /*
  * the semaphore definition
  */
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_64BIT
 # define RWSEM_ACTIVE_MASK		0xffffffffL
 #else
 # define RWSEM_ACTIVE_MASK		0x0000ffffL
@@ -129,4 +129,4 @@
 }
 
 #endif	/* __KERNEL__ */
-#endif	/* _ASM_POWERPC_RWSEM_H */
+#endif	/* _ASM_GENERIC_RWSEM_H */
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 04086c5..04a7f31 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -199,6 +199,9 @@
 #define DRM_INFO(fmt, ...)				\
 	printk(KERN_INFO "[" DRM_NAME "] " fmt, ##__VA_ARGS__)
 
+#define DRM_INFO_ONCE(fmt, ...)				\
+	printk_once(KERN_INFO "[" DRM_NAME "] " fmt, ##__VA_ARGS__)
+
 /**
  * Debug output.
  *
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 71727b6..8f3dee0 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -907,6 +907,9 @@
 
 	/* whether async page flip is supported or not */
 	bool async_page_flip;
+
+	/* cursor size */
+	uint32_t cursor_width, cursor_height;
 };
 
 #define obj_to_crtc(x) container_of(x, struct drm_crtc, base)
diff --git a/include/drm/ttm/ttm_page_alloc.h b/include/drm/ttm/ttm_page_alloc.h
index d1f61bf..49a8284 100644
--- a/include/drm/ttm/ttm_page_alloc.h
+++ b/include/drm/ttm/ttm_page_alloc.h
@@ -29,6 +29,8 @@
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_memory.h>
 
+struct device;
+
 /**
  * Initialize pool allocator.
  */
diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h
index a1116a3..8c1603b 100644
--- a/include/dt-bindings/clock/tegra124-car.h
+++ b/include/dt-bindings/clock/tegra124-car.h
@@ -36,10 +36,10 @@
 #define TEGRA124_CLK_PWM 17
 #define TEGRA124_CLK_I2S2 18
 /* 20 (register bit affects vi and vi_sensor) */
-#define TEGRA124_CLK_GR_2D 21
+/* 21 */
 #define TEGRA124_CLK_USBD 22
 #define TEGRA124_CLK_ISP 23
-#define TEGRA124_CLK_GR_3D 24
+/* 26 */
 /* 25 */
 #define TEGRA124_CLK_DISP2 26
 #define TEGRA124_CLK_DISP1 27
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index be85127..f27000f 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -171,6 +171,11 @@
 	return 0;
 }
 
+static inline int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
+{
+	return -ENXIO;
+}
+
 static inline int kvm_vgic_init(struct kvm *kvm)
 {
 	return 0;
diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h
index 73a2500..1f16d50 100644
--- a/include/linux/ahci_platform.h
+++ b/include/linux/ahci_platform.h
@@ -19,15 +19,37 @@
 
 struct device;
 struct ata_port_info;
+struct ahci_host_priv;
+struct platform_device;
 
+/*
+ * Note ahci_platform_data is deprecated, it is only kept around for use
+ * by the old da850 and spear13xx ahci code.
+ * New drivers should instead declare their own platform_driver struct, and
+ * use ahci_platform* functions in their own probe, suspend and resume methods.
+ */
 struct ahci_platform_data {
 	int (*init)(struct device *dev, void __iomem *addr);
 	void (*exit)(struct device *dev);
 	int (*suspend)(struct device *dev);
 	int (*resume)(struct device *dev);
-	const struct ata_port_info *ata_port_info;
-	unsigned int force_port_map;
-	unsigned int mask_port_map;
 };
 
+int ahci_platform_enable_clks(struct ahci_host_priv *hpriv);
+void ahci_platform_disable_clks(struct ahci_host_priv *hpriv);
+int ahci_platform_enable_resources(struct ahci_host_priv *hpriv);
+void ahci_platform_disable_resources(struct ahci_host_priv *hpriv);
+struct ahci_host_priv *ahci_platform_get_resources(
+	struct platform_device *pdev);
+int ahci_platform_init_host(struct platform_device *pdev,
+			    struct ahci_host_priv *hpriv,
+			    const struct ata_port_info *pi_template,
+			    unsigned int force_port_map,
+			    unsigned int mask_port_map);
+
+int ahci_platform_suspend_host(struct device *dev);
+int ahci_platform_resume_host(struct device *dev);
+int ahci_platform_suspend(struct device *dev);
+int ahci_platform_resume(struct device *dev);
+
 #endif /* _AHCI_PLATFORM_H */
diff --git a/include/linux/audit.h b/include/linux/audit.h
index aa865a9..ec1464d 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -43,6 +43,7 @@
 struct mqstat;
 struct audit_watch;
 struct audit_tree;
+struct sk_buff;
 
 struct audit_krule {
 	int			vers_ops;
@@ -463,7 +464,7 @@
 extern int audit_filter_type(int type);
 extern int audit_rule_change(int type, __u32 portid, int seq,
 				void *data, size_t datasz);
-extern int audit_list_rules_send(__u32 portid, int seq);
+extern int audit_list_rules_send(struct sk_buff *request_skb, int seq);
 
 extern u32 audit_enabled;
 #else /* CONFIG_AUDIT */
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index fd8bf32..b4a745d 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -115,7 +115,6 @@
 extern int prepare_bprm_creds(struct linux_binprm *bprm);
 extern void install_exec_creds(struct linux_binprm *bprm);
 extern void set_binfmt(struct linux_binfmt *new);
-extern void free_bprm(struct linux_binprm *);
 extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t);
 
 #endif /* _LINUX_BINFMTS_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 7065452..5a4d39b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -250,6 +250,17 @@
 	struct bio_vec bv;
 	struct bvec_iter iter;
 
+	/*
+	 * We special case discard/write same, because they interpret bi_size
+	 * differently:
+	 */
+
+	if (bio->bi_rw & REQ_DISCARD)
+		return 1;
+
+	if (bio->bi_rw & REQ_WRITE_SAME)
+		return 1;
+
 	bio_for_each_segment(bv, bio, iter)
 		segs++;
 
@@ -332,6 +343,7 @@
 extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
 
 extern struct bio_set *fs_bio_set;
+unsigned int bio_integrity_tag_size(struct bio *bio);
 
 static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 {
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index abc9ca7..be5fd38 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -196,6 +196,21 @@
 
 #ifdef __KERNEL__
 
+#ifndef set_mask_bits
+#define set_mask_bits(ptr, _mask, _bits)	\
+({								\
+	const typeof(*ptr) mask = (_mask), bits = (_bits);	\
+	typeof(*ptr) old, new;					\
+								\
+	do {							\
+		old = ACCESS_ONCE(*ptr);			\
+		new = (old & ~mask) | bits;			\
+	} while (cmpxchg(ptr, old, new) != old);		\
+								\
+	new;							\
+})
+#endif
+
 #ifndef find_last_bit
 /**
  * find_last_bit - find the last set bit in a memory region
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 161b231..2ff2e8d 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -83,6 +83,8 @@
 	 */
 	rq_timed_out_fn		*timeout;
 
+	softirq_done_fn		*complete;
+
 	/*
 	 * Override for hctx allocations (should probably go)
 	 */
@@ -119,11 +121,11 @@
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
-void blk_mq_insert_request(struct request_queue *, struct request *, bool);
+void blk_mq_insert_request(struct request *, bool, bool, bool);
 void blk_mq_run_queues(struct request_queue *q, bool async);
 void blk_mq_free_request(struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, bool reserved);
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp);
 struct request *blk_mq_alloc_reserved_request(struct request_queue *q, int rw, gfp_t gfp);
 struct request *blk_mq_rq_from_tag(struct request_queue *q, unsigned int tag);
 
@@ -131,7 +133,15 @@
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_reg *, unsigned int);
 void blk_mq_free_single_hw_queue(struct blk_mq_hw_ctx *, unsigned int);
 
-void blk_mq_end_io(struct request *rq, int error);
+bool blk_mq_end_io_partial(struct request *rq, int error,
+		unsigned int nr_bytes);
+static inline void blk_mq_end_io(struct request *rq, int error)
+{
+	bool done = !blk_mq_end_io_partial(rq, error, blk_rq_bytes(rq));
+	BUG_ON(!done);
+}
+
+void blk_mq_complete_request(struct request *rq);
 
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8678c43..4afa4f8 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -98,7 +98,7 @@
 	struct list_head queuelist;
 	union {
 		struct call_single_data csd;
-		struct work_struct mq_flush_data;
+		struct work_struct mq_flush_work;
 	};
 
 	struct request_queue *q;
@@ -448,13 +448,8 @@
 	unsigned long		flush_pending_since;
 	struct list_head	flush_queue[2];
 	struct list_head	flush_data_in_flight;
-	union {
-		struct request	flush_rq;
-		struct {
-			spinlock_t mq_flush_lock;
-			struct work_struct mq_flush_work;
-		};
-	};
+	struct request		*flush_rq;
+	spinlock_t		mq_flush_lock;
 
 	struct mutex		sysfs_lock;
 
diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index 2f0543f..f9bbbb4 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -11,7 +11,9 @@
 #define CAN_SKB_H
 
 #include <linux/types.h>
+#include <linux/skbuff.h>
 #include <linux/can.h>
+#include <net/sock.h>
 
 /*
  * The struct can_skb_priv is used to transport additional information along
@@ -42,4 +44,40 @@
 	skb_reserve(skb, sizeof(struct can_skb_priv));
 }
 
+static inline void can_skb_destructor(struct sk_buff *skb)
+{
+	sock_put(skb->sk);
+}
+
+static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk)
+{
+	if (sk) {
+		sock_hold(sk);
+		skb->destructor = can_skb_destructor;
+		skb->sk = sk;
+	}
+}
+
+/*
+ * returns an unshared skb owned by the original sock to be echo'ed back
+ */
+static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
+{
+	if (skb_shared(skb)) {
+		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+		if (likely(nskb)) {
+			can_skb_set_owner(nskb, skb->sk);
+			consume_skb(skb);
+			return nskb;
+		} else {
+			kfree_skb(skb);
+			return NULL;
+		}
+	}
+
+	/* we can assume to have an unshared skb with proper owner */
+	return skb;
+}
+
 #endif /* CAN_SKB_H */
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 2623cff..25bfb0e 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -373,8 +373,9 @@
 /*
  * Ceph setxattr request flags.
  */
-#define CEPH_XATTR_CREATE  1
-#define CEPH_XATTR_REPLACE 2
+#define CEPH_XATTR_CREATE  (1 << 0)
+#define CEPH_XATTR_REPLACE (1 << 1)
+#define CEPH_XATTR_REMOVE  (1 << 31)
 
 union ceph_mds_request_args {
 	struct {
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 5c09759..9450f02 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -166,6 +166,8 @@
 	 *
 	 * The ID of the root cgroup is always 0, and a new cgroup
 	 * will be assigned with a smallest available ID.
+	 *
+	 * Allocating/Removing ID must be protected by cgroup_mutex.
 	 */
 	int id;
 
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index 092b641..4a21a87 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -245,6 +245,10 @@
 void omap2_init_clk_clkdm(struct clk_hw *clk);
 unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
 				    unsigned long parent_rate);
+int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long parent_rate);
+long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *prate);
 int omap2_clkops_enable_clkdm(struct clk_hw *hw);
 void omap2_clkops_disable_clkdm(struct clk_hw *hw);
 int omap2_clk_disable_autoidle_all(void);
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 3f448c6..01c0aa5 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -14,6 +14,7 @@
 #include <linux/if.h>
 #include <linux/fs.h>
 #include <linux/aio_abi.h>	/* for aio_context_t */
+#include <linux/unistd.h>
 
 #include <asm/compat.h>
 #include <asm/siginfo.h>
@@ -27,6 +28,9 @@
 #define __SC_DELOUSE(t,v) ((t)(unsigned long)(v))
 #endif
 
+#define COMPAT_SYSCALL_DEFINE0(name) \
+	asmlinkage long compat_sys_##name(void)
+
 #define COMPAT_SYSCALL_DEFINE1(name, ...) \
         COMPAT_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
 #define COMPAT_SYSCALL_DEFINE2(name, ...) \
@@ -68,6 +72,8 @@
 typedef __compat_uid32_t	compat_uid_t;
 typedef __compat_gid32_t	compat_gid_t;
 
+typedef	compat_ulong_t		compat_aio_context_t;
+
 struct compat_sel_arg_struct;
 struct rusage;
 
@@ -318,7 +324,7 @@
 asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp,
 		compat_ssize_t msgsz, int msgflg);
 asmlinkage long compat_sys_msgrcv(int msqid, compat_uptr_t msgp,
-		compat_ssize_t msgsz, long msgtyp, int msgflg);
+		compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg);
 long compat_sys_msgctl(int first, int second, void __user *uptr);
 long compat_sys_shmctl(int first, int second, void __user *uptr);
 long compat_sys_semtimedop(int semid, struct sembuf __user *tsems,
@@ -337,6 +343,19 @@
 asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd,
 		const struct compat_iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high);
+
+#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
+asmlinkage long compat_sys_preadv64(unsigned long fd,
+		const struct compat_iovec __user *vec,
+		unsigned long vlen, loff_t pos);
+#endif
+
+#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
+asmlinkage long compat_sys_pwritev64(unsigned long fd,
+		const struct compat_iovec __user *vec,
+		unsigned long vlen, loff_t pos);
+#endif
+
 asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int);
 
 asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv,
@@ -451,7 +470,7 @@
 asmlinkage long compat_sys_timerfd_gettime(int ufd,
 				   struct compat_itimerspec __user *otmr);
 
-asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_page,
+asmlinkage long compat_sys_move_pages(pid_t pid, compat_ulong_t nr_pages,
 				      __u32 __user *pages,
 				      const int __user *nodes,
 				      int __user *status,
@@ -481,20 +500,20 @@
 asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz,
 				     struct compat_statfs64 __user *buf);
 asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd,
-				   unsigned long arg);
+				   compat_ulong_t arg);
 asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd,
-				 unsigned long arg);
+				 compat_ulong_t arg);
 asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p);
-asmlinkage long compat_sys_io_getevents(aio_context_t ctx_id,
-					unsigned long min_nr,
-					unsigned long nr,
+asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id,
+					compat_long_t min_nr,
+					compat_long_t nr,
 					struct io_event __user *events,
 					struct compat_timespec __user *timeout);
-asmlinkage long compat_sys_io_submit(aio_context_t ctx_id, int nr,
+asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr,
 				     u32 __user *iocb);
 asmlinkage long compat_sys_mount(const char __user *dev_name,
 				 const char __user *dir_name,
-				 const char __user *type, unsigned long flags,
+				 const char __user *type, compat_ulong_t flags,
 				 const void __user *data);
 asmlinkage long compat_sys_old_readdir(unsigned int fd,
 				       struct compat_old_linux_dirent __user *,
@@ -502,9 +521,11 @@
 asmlinkage long compat_sys_getdents(unsigned int fd,
 				    struct compat_linux_dirent __user *dirent,
 				    unsigned int count);
+#ifdef __ARCH_WANT_COMPAT_SYS_GETDENTS64
 asmlinkage long compat_sys_getdents64(unsigned int fd,
 				      struct linux_dirent64 __user *dirent,
 				      unsigned int count);
+#endif
 asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *,
 				    unsigned int nr_segs, unsigned int flags);
 asmlinkage long compat_sys_open(const char __user *filename, int flags,
@@ -549,9 +570,9 @@
 				    unsigned vlen, unsigned int flags);
 asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg,
 				   unsigned int flags);
-asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len,
+asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len,
 				unsigned flags);
-asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, size_t len,
+asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len,
 			    unsigned flags, struct sockaddr __user *addr,
 			    int __user *addrlen);
 asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg,
@@ -615,16 +636,16 @@
 				struct compat_siginfo __user *uinfo);
 asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info);
 asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
-				 unsigned long arg);
+				 compat_ulong_t arg);
 asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val,
 		struct compat_timespec __user *utime, u32 __user *uaddr2,
 		u32 val3);
 asmlinkage long compat_sys_getsockopt(int fd, int level, int optname,
 				      char __user *optval, int __user *optlen);
-asmlinkage long compat_sys_kexec_load(unsigned long entry,
-				      unsigned long nr_segments,
+asmlinkage long compat_sys_kexec_load(compat_ulong_t entry,
+				      compat_ulong_t nr_segments,
 				      struct compat_kexec_segment __user *,
-				      unsigned long flags);
+				      compat_ulong_t flags);
 asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes,
 			const struct compat_mq_attr __user *u_mqstat,
 			struct compat_mq_attr __user *u_omqstat);
@@ -635,11 +656,11 @@
 			struct compat_mq_attr __user *u_attr);
 asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes,
 			const char __user *u_msg_ptr,
-			size_t msg_len, unsigned int msg_prio,
+			compat_size_t msg_len, unsigned int msg_prio,
 			const struct compat_timespec __user *u_abs_timeout);
 asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes,
 			char __user *u_msg_ptr,
-			size_t msg_len, unsigned int __user *u_msg_prio,
+			compat_size_t msg_len, unsigned int __user *u_msg_prio,
 			const struct compat_timespec __user *u_abs_timeout);
 asmlinkage long compat_sys_socketcall(int call, u32 __user *args);
 asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args);
@@ -654,12 +675,12 @@
 
 asmlinkage ssize_t compat_sys_process_vm_readv(compat_pid_t pid,
 		const struct compat_iovec __user *lvec,
-		unsigned long liovcnt, const struct compat_iovec __user *rvec,
-		unsigned long riovcnt, unsigned long flags);
+		compat_ulong_t liovcnt, const struct compat_iovec __user *rvec,
+		compat_ulong_t riovcnt, compat_ulong_t flags);
 asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid,
 		const struct compat_iovec __user *lvec,
-		unsigned long liovcnt, const struct compat_iovec __user *rvec,
-		unsigned long riovcnt, unsigned long flags);
+		compat_ulong_t liovcnt, const struct compat_iovec __user *rvec,
+		compat_ulong_t riovcnt, compat_ulong_t flags);
 
 asmlinkage long compat_sys_sendfile(int out_fd, int in_fd,
 				    compat_off_t __user *offset, compat_size_t count);
diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index ded4299..2507fd2 100644
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -75,11 +75,7 @@
  *
  * (asm goto is automatically volatile - the naming reflects this.)
  */
-#if GCC_VERSION <= 40801
-# define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
-#else
-# define asm_volatile_goto(x...)	do { asm goto(x); } while (0)
-#endif
+#define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
 
 #ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
 #if GCC_VERSION >= 40400
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index dfac5ed..f886985 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -171,7 +171,7 @@
 			       size_t size, int flags, const char *);
 
 #define dma_buf_export(priv, ops, size, flags)	\
-	dma_buf_export_named(priv, ops, size, flags, __FILE__)
+	dma_buf_export_named(priv, ops, size, flags, KBUILD_MODNAME)
 
 int dma_buf_fd(struct dma_buf *dmabuf, int flags);
 struct dma_buf *dma_buf_get(int fd);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 0a819e7..6c100ff 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -153,6 +153,102 @@
 	u8 sets_to_zero;
 } efi_time_cap_t;
 
+typedef struct {
+	efi_table_hdr_t hdr;
+	u32 raise_tpl;
+	u32 restore_tpl;
+	u32 allocate_pages;
+	u32 free_pages;
+	u32 get_memory_map;
+	u32 allocate_pool;
+	u32 free_pool;
+	u32 create_event;
+	u32 set_timer;
+	u32 wait_for_event;
+	u32 signal_event;
+	u32 close_event;
+	u32 check_event;
+	u32 install_protocol_interface;
+	u32 reinstall_protocol_interface;
+	u32 uninstall_protocol_interface;
+	u32 handle_protocol;
+	u32 __reserved;
+	u32 register_protocol_notify;
+	u32 locate_handle;
+	u32 locate_device_path;
+	u32 install_configuration_table;
+	u32 load_image;
+	u32 start_image;
+	u32 exit;
+	u32 unload_image;
+	u32 exit_boot_services;
+	u32 get_next_monotonic_count;
+	u32 stall;
+	u32 set_watchdog_timer;
+	u32 connect_controller;
+	u32 disconnect_controller;
+	u32 open_protocol;
+	u32 close_protocol;
+	u32 open_protocol_information;
+	u32 protocols_per_handle;
+	u32 locate_handle_buffer;
+	u32 locate_protocol;
+	u32 install_multiple_protocol_interfaces;
+	u32 uninstall_multiple_protocol_interfaces;
+	u32 calculate_crc32;
+	u32 copy_mem;
+	u32 set_mem;
+	u32 create_event_ex;
+} __packed efi_boot_services_32_t;
+
+typedef struct {
+	efi_table_hdr_t hdr;
+	u64 raise_tpl;
+	u64 restore_tpl;
+	u64 allocate_pages;
+	u64 free_pages;
+	u64 get_memory_map;
+	u64 allocate_pool;
+	u64 free_pool;
+	u64 create_event;
+	u64 set_timer;
+	u64 wait_for_event;
+	u64 signal_event;
+	u64 close_event;
+	u64 check_event;
+	u64 install_protocol_interface;
+	u64 reinstall_protocol_interface;
+	u64 uninstall_protocol_interface;
+	u64 handle_protocol;
+	u64 __reserved;
+	u64 register_protocol_notify;
+	u64 locate_handle;
+	u64 locate_device_path;
+	u64 install_configuration_table;
+	u64 load_image;
+	u64 start_image;
+	u64 exit;
+	u64 unload_image;
+	u64 exit_boot_services;
+	u64 get_next_monotonic_count;
+	u64 stall;
+	u64 set_watchdog_timer;
+	u64 connect_controller;
+	u64 disconnect_controller;
+	u64 open_protocol;
+	u64 close_protocol;
+	u64 open_protocol_information;
+	u64 protocols_per_handle;
+	u64 locate_handle_buffer;
+	u64 locate_protocol;
+	u64 install_multiple_protocol_interfaces;
+	u64 uninstall_multiple_protocol_interfaces;
+	u64 calculate_crc32;
+	u64 copy_mem;
+	u64 set_mem;
+	u64 create_event_ex;
+} __packed efi_boot_services_64_t;
+
 /*
  * EFI Boot Services table
  */
@@ -231,6 +327,15 @@
     EfiPciIoAttributeOperationMaximum
 } EFI_PCI_IO_PROTOCOL_ATTRIBUTE_OPERATION;
 
+typedef struct {
+	u32 read;
+	u32 write;
+} efi_pci_io_protocol_access_32_t;
+
+typedef struct {
+	u64 read;
+	u64 write;
+} efi_pci_io_protocol_access_64_t;
 
 typedef struct {
 	void *read;
@@ -238,6 +343,46 @@
 } efi_pci_io_protocol_access_t;
 
 typedef struct {
+	u32 poll_mem;
+	u32 poll_io;
+	efi_pci_io_protocol_access_32_t mem;
+	efi_pci_io_protocol_access_32_t io;
+	efi_pci_io_protocol_access_32_t pci;
+	u32 copy_mem;
+	u32 map;
+	u32 unmap;
+	u32 allocate_buffer;
+	u32 free_buffer;
+	u32 flush;
+	u32 get_location;
+	u32 attributes;
+	u32 get_bar_attributes;
+	u32 set_bar_attributes;
+	uint64_t romsize;
+	void *romimage;
+} efi_pci_io_protocol_32;
+
+typedef struct {
+	u64 poll_mem;
+	u64 poll_io;
+	efi_pci_io_protocol_access_64_t mem;
+	efi_pci_io_protocol_access_64_t io;
+	efi_pci_io_protocol_access_64_t pci;
+	u64 copy_mem;
+	u64 map;
+	u64 unmap;
+	u64 allocate_buffer;
+	u64 free_buffer;
+	u64 flush;
+	u64 get_location;
+	u64 attributes;
+	u64 get_bar_attributes;
+	u64 set_bar_attributes;
+	uint64_t romsize;
+	void *romimage;
+} efi_pci_io_protocol_64;
+
+typedef struct {
 	void *poll_mem;
 	void *poll_io;
 	efi_pci_io_protocol_access_t mem;
@@ -292,6 +437,42 @@
 
 typedef struct {
 	efi_table_hdr_t hdr;
+	u32 get_time;
+	u32 set_time;
+	u32 get_wakeup_time;
+	u32 set_wakeup_time;
+	u32 set_virtual_address_map;
+	u32 convert_pointer;
+	u32 get_variable;
+	u32 get_next_variable;
+	u32 set_variable;
+	u32 get_next_high_mono_count;
+	u32 reset_system;
+	u32 update_capsule;
+	u32 query_capsule_caps;
+	u32 query_variable_info;
+} efi_runtime_services_32_t;
+
+typedef struct {
+	efi_table_hdr_t hdr;
+	u64 get_time;
+	u64 set_time;
+	u64 get_wakeup_time;
+	u64 set_wakeup_time;
+	u64 set_virtual_address_map;
+	u64 convert_pointer;
+	u64 get_variable;
+	u64 get_next_variable;
+	u64 set_variable;
+	u64 get_next_high_mono_count;
+	u64 reset_system;
+	u64 update_capsule;
+	u64 query_capsule_caps;
+	u64 query_variable_info;
+} efi_runtime_services_64_t;
+
+typedef struct {
+	efi_table_hdr_t hdr;
 	void *get_time;
 	void *set_time;
 	void *get_wakeup_time;
@@ -485,6 +666,38 @@
 
 typedef struct {
 	u32 revision;
+	u32 parent_handle;
+	u32 system_table;
+	u32 device_handle;
+	u32 file_path;
+	u32 reserved;
+	u32 load_options_size;
+	u32 load_options;
+	u32 image_base;
+	__aligned_u64 image_size;
+	unsigned int image_code_type;
+	unsigned int image_data_type;
+	unsigned long unload;
+} efi_loaded_image_32_t;
+
+typedef struct {
+	u32 revision;
+	u64 parent_handle;
+	u64 system_table;
+	u64 device_handle;
+	u64 file_path;
+	u64 reserved;
+	u32 load_options_size;
+	u64 load_options;
+	u64 image_base;
+	__aligned_u64 image_size;
+	unsigned int image_code_type;
+	unsigned int image_data_type;
+	unsigned long unload;
+} efi_loaded_image_64_t;
+
+typedef struct {
+	u32 revision;
 	void *parent_handle;
 	efi_system_table_t *system_table;
 	void *device_handle;
@@ -511,6 +724,34 @@
 	efi_char16_t filename[1];
 } efi_file_info_t;
 
+typedef struct {
+	u64 revision;
+	u32 open;
+	u32 close;
+	u32 delete;
+	u32 read;
+	u32 write;
+	u32 get_position;
+	u32 set_position;
+	u32 get_info;
+	u32 set_info;
+	u32 flush;
+} efi_file_handle_32_t;
+
+typedef struct {
+	u64 revision;
+	u64 open;
+	u64 close;
+	u64 delete;
+	u64 read;
+	u64 write;
+	u64 get_position;
+	u64 set_position;
+	u64 get_info;
+	u64 set_info;
+	u64 flush;
+} efi_file_handle_64_t;
+
 typedef struct _efi_file_handle {
 	u64 revision;
 	efi_status_t (*open)(struct _efi_file_handle *,
@@ -573,6 +814,7 @@
 	efi_reset_system_t *reset_system;
 	efi_set_virtual_address_map_t *set_virtual_address_map;
 	struct efi_memory_map *memmap;
+	unsigned long flags;
 } efi;
 
 static inline int
@@ -659,18 +901,17 @@
 #define EFI_ARCH_1		6	/* First arch-specific bit */
 
 #ifdef CONFIG_EFI
-# ifdef CONFIG_X86
-extern int efi_enabled(int facility);
-# else
-static inline int efi_enabled(int facility)
+/*
+ * Test whether the above EFI_* bits are enabled.
+ */
+static inline bool efi_enabled(int feature)
 {
-	return 1;
+	return test_bit(feature, &efi.flags) != 0;
 }
-# endif
 #else
-static inline int efi_enabled(int facility)
+static inline bool efi_enabled(int feature)
 {
-	return 0;
+	return false;
 }
 #endif
 
@@ -809,6 +1050,17 @@
 	bool deleting;
 };
 
+struct efi_simple_text_output_protocol_32 {
+	u32 reset;
+	u32 output_string;
+	u32 test_string;
+};
+
+struct efi_simple_text_output_protocol_64 {
+	u64 reset;
+	u64 output_string;
+	u64 test_string;
+};
 
 struct efi_simple_text_output_protocol {
 	void *reset;
diff --git a/include/linux/file.h b/include/linux/file.h
index cbacf4f..4d69123 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -28,33 +28,36 @@
 
 struct fd {
 	struct file *file;
-	int need_put;
+	unsigned int flags;
 };
+#define FDPUT_FPUT       1
+#define FDPUT_POS_UNLOCK 2
 
 static inline void fdput(struct fd fd)
 {
-	if (fd.need_put)
+	if (fd.flags & FDPUT_FPUT)
 		fput(fd.file);
 }
 
 extern struct file *fget(unsigned int fd);
-extern struct file *fget_light(unsigned int fd, int *fput_needed);
+extern struct file *fget_raw(unsigned int fd);
+extern unsigned long __fdget(unsigned int fd);
+extern unsigned long __fdget_raw(unsigned int fd);
+extern unsigned long __fdget_pos(unsigned int fd);
+
+static inline struct fd __to_fd(unsigned long v)
+{
+	return (struct fd){(struct file *)(v & ~3),v & 3};
+}
 
 static inline struct fd fdget(unsigned int fd)
 {
-	int b;
-	struct file *f = fget_light(fd, &b);
-	return (struct fd){f,b};
+	return __to_fd(__fdget(fd));
 }
 
-extern struct file *fget_raw(unsigned int fd);
-extern struct file *fget_raw_light(unsigned int fd, int *fput_needed);
-
 static inline struct fd fdget_raw(unsigned int fd)
 {
-	int b;
-	struct file *f = fget_raw_light(fd, &b);
-	return (struct fd){f,b};
+	return __to_fd(__fdget_raw(fd));
 }
 
 extern int f_dupfd(unsigned int from, struct file *file, unsigned flags);
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 5d7782e..c3683bd 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -200,6 +200,7 @@
 	unsigned irmc:1;
 	unsigned bc_implemented:2;
 
+	work_func_t workfn;
 	struct delayed_work work;
 	struct fw_attribute_group attribute_group;
 };
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 09f553c..23b2a35 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -123,6 +123,9 @@
 /* File is opened with O_PATH; almost nothing can be done with it */
 #define FMODE_PATH		((__force fmode_t)0x4000)
 
+/* File needs atomic accesses to f_pos */
+#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
 
@@ -780,13 +783,14 @@
 	const struct file_operations	*f_op;
 
 	/*
-	 * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR.
+	 * Protects f_ep_links, f_flags.
 	 * Must not be taken from IRQ context.
 	 */
 	spinlock_t		f_lock;
 	atomic_long_t		f_count;
 	unsigned int 		f_flags;
 	fmode_t			f_mode;
+	struct mutex		f_pos_lock;
 	loff_t			f_pos;
 	struct fown_struct	f_owner;
 	const struct cred	*f_cred;
@@ -808,7 +812,7 @@
 #ifdef CONFIG_DEBUG_WRITECOUNT
 	unsigned long f_mnt_write_state;
 #endif
-};
+} __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
 
 struct file_handle {
 	__u32 handle_bytes;
@@ -2079,6 +2083,7 @@
 extern int filp_close(struct file *, fl_owner_t id);
 
 extern struct filename *getname(const char __user *);
+extern struct filename *getname_kernel(const char *);
 
 enum {
 	FILE_CREATED = 1,
@@ -2273,7 +2278,13 @@
 extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
 			   int datasync);
 extern int vfs_fsync(struct file *file, int datasync);
-extern int generic_write_sync(struct file *file, loff_t pos, loff_t count);
+static inline int generic_write_sync(struct file *file, loff_t pos, loff_t count)
+{
+	if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host))
+		return 0;
+	return vfs_fsync_range(file, pos, pos + count - 1,
+			       (file->f_flags & __O_SYNC) ? 0 : 1);
+}
 extern void emergency_sync(void);
 extern void emergency_remount(void);
 #ifdef CONFIG_BLOCK
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 3d286ff..64cf3ef 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -99,7 +99,7 @@
 			    struct fsnotify_mark *inode_mark,
 			    struct fsnotify_mark *vfsmount_mark,
 			    u32 mask, void *data, int data_type,
-			    const unsigned char *file_name);
+			    const unsigned char *file_name, u32 cookie);
 	void (*free_group_priv)(struct fsnotify_group *group);
 	void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
 	void (*free_event)(struct fsnotify_event *event);
@@ -160,7 +160,7 @@
 
 	struct fasync_struct *fsn_fa;    /* async notification */
 
-	struct fsnotify_event overflow_event;	/* Event we queue when the
+	struct fsnotify_event *overflow_event;	/* Event we queue when the
 						 * notification list is too
 						 * full */
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 4e4cc28..4cdb3a1 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -495,10 +495,6 @@
 	FILTER_TRACE_FN,
 };
 
-#define EVENT_STORAGE_SIZE 128
-extern struct mutex event_storage_mutex;
-extern char event_storage[EVENT_STORAGE_SIZE];
-
 extern int trace_event_raw_init(struct ftrace_event_call *call);
 extern int trace_define_field(struct ftrace_event_call *call, const char *type,
 			      const char *name, int offset, int size,
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 0437439..39b81dc 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -123,6 +123,10 @@
 			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
 			 __GFP_NO_KSWAPD)
 
+/*
+ * GFP_THISNODE does not perform any reclaim, you most likely want to
+ * use __GFP_THISNODE to allocate from a given node without fallback!
+ */
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE	(__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
 #else
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 4d34dbb..7a8144f 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -4,8 +4,6 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 
-#ifdef CONFIG_GPIOLIB
-
 struct device;
 struct gpio_chip;
 
@@ -18,6 +16,8 @@
  */
 struct gpio_desc;
 
+#ifdef CONFIG_GPIOLIB
+
 /* Acquire and dispose GPIOs */
 struct gpio_desc *__must_check gpiod_get(struct device *dev,
 					 const char *con_id);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index db51201..b826239 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -157,46 +157,6 @@
 		return HPAGE_PMD_NR;
 	return 1;
 }
-/*
- * compound_trans_head() should be used instead of compound_head(),
- * whenever the "page" passed as parameter could be the tail of a
- * transparent hugepage that could be undergoing a
- * __split_huge_page_refcount(). The page structure layout often
- * changes across releases and it makes extensive use of unions. So if
- * the page structure layout will change in a way that
- * page->first_page gets clobbered by __split_huge_page_refcount, the
- * implementation making use of smp_rmb() will be required.
- *
- * Currently we define compound_trans_head as compound_head, because
- * page->private is in the same union with page->first_page, and
- * page->private isn't clobbered. However this also means we're
- * currently leaving dirt into the page->private field of anonymous
- * pages resulting from a THP split, instead of setting page->private
- * to zero like for every other page that has PG_private not set. But
- * anonymous pages don't use page->private so this is not a problem.
- */
-#if 0
-/* This will be needed if page->private will be clobbered in split_huge_page */
-static inline struct page *compound_trans_head(struct page *page)
-{
-	if (PageTail(page)) {
-		struct page *head;
-		head = page->first_page;
-		smp_rmb();
-		/*
-		 * head may be a dangling pointer.
-		 * __split_huge_page_refcount clears PageTail before
-		 * overwriting first_page, so if PageTail is still
-		 * there it means the head pointer isn't dangling.
-		 */
-		if (PageTail(page))
-			return head;
-	}
-	return page;
-}
-#else
-#define compound_trans_head(page) compound_head(page)
-#endif
 
 extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp);
@@ -226,7 +186,6 @@
 	do { } while (0)
 #define split_huge_page_pmd_mm(__mm, __address, __pmd)	\
 	do { } while (0)
-#define compound_trans_head(page) compound_head(page)
 static inline int hugepage_madvise(struct vm_area_struct *vma,
 				   unsigned long *vm_flags, int advice)
 {
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 15da677..344883d 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -875,7 +875,7 @@
 struct vmbus_channel_initiate_contact {
 	struct vmbus_channel_message_header header;
 	u32 vmbus_version_requested;
-	u32 padding2;
+	u32 target_vcpu; /* The VCPU the host should respond to */
 	u64 interrupt_page;
 	u64 monitor_page1;
 	u64 monitor_page2;
diff --git a/include/linux/init.h b/include/linux/init.h
index e168880..a3ba270 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -163,6 +163,23 @@
 
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_LTO
+/* Work around a LTO gcc problem: when there is no reference to a variable
+ * in a module it will be moved to the end of the program. This causes
+ * reordering of initcalls which the kernel does not like.
+ * Add a dummy reference function to avoid this. The function is
+ * deleted by the linker.
+ */
+#define LTO_REFERENCE_INITCALL(x) \
+	; /* yes this is needed */			\
+	static __used __exit void *reference_##x(void)	\
+	{						\
+		return &x;				\
+	}
+#else
+#define LTO_REFERENCE_INITCALL(x)
+#endif
+
 /* initcalls are now grouped by functionality into separate 
  * subsections. Ordering inside the subsections is determined
  * by link order. 
@@ -175,7 +192,8 @@
 
 #define __define_initcall(fn, id) \
 	static initcall_t __initcall_##fn##id __used \
-	__attribute__((__section__(".initcall" #id ".init"))) = fn
+	__attribute__((__section__(".initcall" #id ".init"))) = fn; \
+	LTO_REFERENCE_INITCALL(__initcall_##fn##id)
 
 /*
  * Early initcalls run before initializing SMP.
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 0053add..a2678d3 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -158,6 +158,11 @@
 					 devname, dev_id);
 }
 
+extern int __must_check
+devm_request_any_context_irq(struct device *dev, unsigned int irq,
+		 irq_handler_t handler, unsigned long irqflags,
+		 const char *devname, void *dev_id);
+
 extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
 
 /*
diff --git a/include/linux/io.h b/include/linux/io.h
index f4f42fa..8a18e75 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -24,7 +24,7 @@
 
 struct device;
 
-void __iowrite32_copy(void __iomem *to, const void *from, size_t count);
+__visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count);
 void __iowrite64_copy(void __iomem *to, const void *from, size_t count);
 
 #ifdef CONFIG_MMU
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index e7831d2..35e7eca 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -118,9 +118,7 @@
  *     the new maximum will handle anyone else.  I may have to revisit this
  *     in the future.
  */
-#define MIN_QUEUESMAX			1
 #define DFLT_QUEUESMAX		      256
-#define HARD_QUEUESMAX		     1024
 #define MIN_MSGMAX			1
 #define DFLT_MSG		       10U
 #define DFLT_MSGMAX		       10
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 6601702..19ae05d 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -30,7 +30,9 @@
 	work->func = func;
 }
 
-void irq_work_queue(struct irq_work *work);
+#define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), }
+
+bool irq_work_queue(struct irq_work *work);
 void irq_work_run(void);
 void irq_work_sync(struct irq_work *work);
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 196d1ea..08fb024 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -458,7 +458,7 @@
 
 #define TAINT_PROPRIETARY_MODULE	0
 #define TAINT_FORCED_MODULE		1
-#define TAINT_UNSAFE_SMP		2
+#define TAINT_CPU_OUT_OF_SPEC		2
 #define TAINT_FORCED_RMMOD		3
 #define TAINT_MACHINE_CHECK		4
 #define TAINT_BAD_PAGE			5
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 5be9f02..d267623 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -249,7 +249,8 @@
 
 const void *kernfs_super_ns(struct super_block *sb);
 struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-			       struct kernfs_root *root, const void *ns);
+			       struct kernfs_root *root, bool *new_sb_created,
+			       const void *ns);
 void kernfs_kill_sb(struct super_block *sb);
 
 void kernfs_init(void);
@@ -317,7 +318,7 @@
 
 static inline struct dentry *
 kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-		struct kernfs_root *root, const void *ns)
+		struct kernfs_root *root, bool *new_sb_created, const void *ns)
 { return ERR_PTR(-ENOSYS); }
 
 static inline void kernfs_kill_sb(struct super_block *sb) { }
@@ -368,9 +369,9 @@
 
 static inline struct dentry *
 kernfs_mount(struct file_system_type *fs_type, int flags,
-	     struct kernfs_root *root)
+	     struct kernfs_root *root, bool *new_sb_created)
 {
-	return kernfs_mount_ns(fs_type, flags, root, NULL);
+	return kernfs_mount_ns(fs_type, flags, root, new_sb_created, NULL);
 }
 
 #endif	/* __LINUX_KERNFS_H */
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 6d4066c..a756419 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -127,12 +127,6 @@
 					struct kexec_segment __user *segments,
 					unsigned long flags);
 extern int kernel_kexec(void);
-#ifdef CONFIG_COMPAT
-extern asmlinkage long compat_sys_kexec_load(unsigned long entry,
-				unsigned long nr_segments,
-				struct compat_kexec_segment __user *segments,
-				unsigned long flags);
-#endif
 extern struct page *kimage_alloc_control_pages(struct kimage *image,
 						unsigned int order);
 extern void crash_kexec(struct pt_regs *);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index bec6dbe..1de36be 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -848,7 +848,6 @@
 	struct completion	park_req_pending;
 
 	pm_message_t		pm_mesg;
-	int			*pm_result;
 	enum ata_lpm_policy	target_lpm_policy;
 
 	struct timer_list	fastdrain_timer;
@@ -1140,16 +1139,14 @@
 #ifdef CONFIG_PM
 extern int ata_host_suspend(struct ata_host *host, pm_message_t mesg);
 extern void ata_host_resume(struct ata_host *host);
-extern int ata_sas_port_async_suspend(struct ata_port *ap, int *async);
-extern int ata_sas_port_async_resume(struct ata_port *ap, int *async);
+extern void ata_sas_port_suspend(struct ata_port *ap);
+extern void ata_sas_port_resume(struct ata_port *ap);
 #else
-static inline int ata_sas_port_async_suspend(struct ata_port *ap, int *async)
+static inline void ata_sas_port_suspend(struct ata_port *ap)
 {
-	return 0;
 }
-static inline int ata_sas_port_async_resume(struct ata_port *ap, int *async)
+static inline void ata_sas_port_resume(struct ata_port *ap)
 {
-	return 0;
 }
 #endif
 extern int ata_ratelimit(void);
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index a6a42dd..34a513a 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -12,9 +12,9 @@
 #endif
 
 #ifdef __cplusplus
-#define CPP_ASMLINKAGE extern "C"
+#define CPP_ASMLINKAGE extern "C" __visible
 #else
-#define CPP_ASMLINKAGE
+#define CPP_ASMLINKAGE __visible
 #endif
 
 #ifndef asmlinkage
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 060e513..008388f 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -265,7 +265,7 @@
 extern void lockdep_reset(void);
 extern void lockdep_reset_lock(struct lockdep_map *lock);
 extern void lockdep_free_key_range(void *start, unsigned long size);
-extern void lockdep_sys_exit(void);
+extern asmlinkage void lockdep_sys_exit(void);
 
 extern void lockdep_off(void);
 extern void lockdep_on(void);
diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h
index ad1ae7f..78c76cd 100644
--- a/include/linux/mfd/max8997-private.h
+++ b/include/linux/mfd/max8997-private.h
@@ -387,7 +387,7 @@
 	struct i2c_client *muic; /* slave addr 0x4a */
 	struct mutex iolock;
 
-	int type;
+	unsigned long type;
 	struct platform_device *battery; /* battery control (not fuel gauge) */
 
 	int irq;
diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h
index 4ecb24b..d68ada5 100644
--- a/include/linux/mfd/max8998-private.h
+++ b/include/linux/mfd/max8998-private.h
@@ -163,7 +163,7 @@
 	int ono;
 	u8 irq_masks_cur[MAX8998_NUM_IRQ_REGS];
 	u8 irq_masks_cache[MAX8998_NUM_IRQ_REGS];
-	int type;
+	unsigned long type;
 	bool wakeup;
 };
 
diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h
index a5a7f01..54b5458 100644
--- a/include/linux/mfd/tps65217.h
+++ b/include/linux/mfd/tps65217.h
@@ -252,7 +252,7 @@
 struct tps65217 {
 	struct device *dev;
 	struct tps65217_board *pdata;
-	unsigned int id;
+	unsigned long id;
 	struct regulator_desc desc[TPS65217_NUM_REGULATOR];
 	struct regulator_dev *rdev[TPS65217_NUM_REGULATOR];
 	struct regmap *regmap;
@@ -263,7 +263,7 @@
 	return dev_get_drvdata(dev);
 }
 
-static inline int tps65217_chip_id(struct tps65217 *tps65217)
+static inline unsigned long tps65217_chip_id(struct tps65217 *tps65217)
 {
 	return tps65217->id;
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 554548c..130bc8d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -38,8 +38,10 @@
 #include <linux/pci.h>
 #include <linux/spinlock_types.h>
 #include <linux/semaphore.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/radix-tree.h>
+
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/doorbell.h>
 
@@ -227,6 +229,7 @@
 	 * protect uuar allocation data structs
 	 */
 	struct mutex		lock;
+	u32			ver;
 };
 
 struct mlx5_bf {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f28f46e..a0df429 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -175,7 +175,7 @@
  * Special vmas that are non-mergable, non-mlock()able.
  * Note: mm/huge_memory.c VM_NO_THP depends on this definition.
  */
-#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP)
+#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
 
 /*
  * mapping from the currently active vm_flags protection bits (the
@@ -399,8 +399,18 @@
 
 static inline struct page *compound_head(struct page *page)
 {
-	if (unlikely(PageTail(page)))
-		return page->first_page;
+	if (unlikely(PageTail(page))) {
+		struct page *head = page->first_page;
+
+		/*
+		 * page->first_page may be a dangling pointer to an old
+		 * compound page, so recheck that it is still a tail
+		 * page before returning.
+		 */
+		smp_rmb();
+		if (likely(PageTail(page)))
+			return head;
+	}
 	return page;
 }
 
@@ -757,7 +767,7 @@
 #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
 static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
 {
-	return xchg(&page->_last_cpupid, cpupid);
+	return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK);
 }
 
 static inline int page_cpupid_last(struct page *page)
@@ -766,7 +776,7 @@
 }
 static inline void page_cpupid_reset_last(struct page *page)
 {
-	page->_last_cpupid = -1;
+	page->_last_cpupid = -1 & LAST_CPUPID_MASK;
 }
 #else
 static inline int page_cpupid_last(struct page *page)
@@ -1477,9 +1487,15 @@
 
 #if USE_SPLIT_PMD_PTLOCKS
 
+static struct page *pmd_to_page(pmd_t *pmd)
+{
+	unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1);
+	return virt_to_page((void *)((unsigned long) pmd & mask));
+}
+
 static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
-	return ptlock_ptr(virt_to_page(pmd));
+	return ptlock_ptr(pmd_to_page(pmd));
 }
 
 static inline bool pgtable_pmd_page_ctor(struct page *page)
@@ -1498,7 +1514,7 @@
 	ptlock_free(page);
 }
 
-#define pmd_huge_pte(mm, pmd) (virt_to_page(pmd)->pmd_huge_pte)
+#define pmd_huge_pte(mm, pmd) (pmd_to_page(pmd)->pmd_huge_pte)
 
 #else
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5f2052c..9b61b9b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -590,10 +590,10 @@
 
 /*
  * The NUMA zonelists are doubled because we need zonelists that restrict the
- * allocations to a single node for GFP_THISNODE.
+ * allocations to a single node for __GFP_THISNODE.
  *
  * [0]	: Zonelist with fallback
- * [1]	: No fallback (GFP_THISNODE)
+ * [1]	: No fallback (__GFP_THISNODE)
  */
 #define MAX_ZONELISTS 2
 
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 1005ebf..5a09a48 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -163,4 +163,11 @@
 /* changeable features with no special hardware requirements */
 #define NETIF_F_SOFT_FEATURES	(NETIF_F_GSO | NETIF_F_GRO)
 
+#define NETIF_F_VLAN_FEATURES	(NETIF_F_HW_VLAN_CTAG_FILTER | \
+				 NETIF_F_HW_VLAN_CTAG_RX | \
+				 NETIF_F_HW_VLAN_CTAG_TX | \
+				 NETIF_F_HW_VLAN_STAG_FILTER | \
+				 NETIF_F_HW_VLAN_STAG_RX | \
+				 NETIF_F_HW_VLAN_STAG_TX)
+
 #endif	/* _LINUX_NETDEV_FEATURES_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 440a02e..daafd95 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -752,6 +752,9 @@
 	unsigned char id_len;
 };
 
+typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
+				       struct sk_buff *skb);
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -783,7 +786,7 @@
  *	Required can not be NULL.
  *
  * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
- *                         void *accel_priv);
+ *                         void *accel_priv, select_queue_fallback_t fallback);
  *	Called to decide which queue to when device supports multiple
  *	transmit queues.
  *
@@ -1005,7 +1008,8 @@
 						   struct net_device *dev);
 	u16			(*ndo_select_queue)(struct net_device *dev,
 						    struct sk_buff *skb,
-						    void *accel_priv);
+						    void *accel_priv,
+						    select_queue_fallback_t fallback);
 	void			(*ndo_change_rx_flags)(struct net_device *dev,
 						       int flags);
 	void			(*ndo_set_rx_mode)(struct net_device *dev);
@@ -1551,7 +1555,6 @@
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
 				    void *accel_priv);
-u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb);
 
 /*
  * Net namespace inlines
@@ -2276,6 +2279,26 @@
 }
 
 /**
+ * 	netdev_cap_txqueue - check if selected tx queue exceeds device queues
+ * 	@dev: network device
+ * 	@queue_index: given tx queue index
+ *
+ * 	Returns 0 if given tx queue index >= number of device tx queues,
+ * 	otherwise returns the originally passed tx queue index.
+ */
+static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index)
+{
+	if (unlikely(queue_index >= dev->real_num_tx_queues)) {
+		net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
+				     dev->name, queue_index,
+				     dev->real_num_tx_queues);
+		return 0;
+	}
+
+	return queue_index;
+}
+
+/**
  *	netif_running - test if up
  *	@dev: network device
  *
@@ -2991,7 +3014,7 @@
 {
 	return __skb_gso_segment(skb, features, true);
 }
-__be16 skb_network_protocol(struct sk_buff *skb);
+__be16 skb_network_protocol(struct sk_buff *skb, int *depth);
 
 static inline bool can_checksum_protocol(netdev_features_t features,
 					 __be16 protocol)
@@ -3068,7 +3091,12 @@
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 					struct net_device *dev);
 
-netdev_features_t netif_skb_features(struct sk_buff *skb);
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+					 const struct net_device *dev);
+static inline netdev_features_t netif_skb_features(struct sk_buff *skb)
+{
+	return netif_skb_dev_features(skb, skb->dev);
+}
 
 static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 {
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 3ccfcec..5624e4e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -379,12 +379,14 @@
  * Arguments to the open_confirm call.
  */
 struct nfs_open_confirmargs {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *	fh;
 	nfs4_stateid *		stateid;
 	struct nfs_seqid *	seqid;
 };
 
 struct nfs_open_confirmres {
+	struct nfs4_sequence_res	seq_res;
 	nfs4_stateid            stateid;
 	struct nfs_seqid *	seqid;
 };
@@ -465,9 +467,14 @@
 };
 
 struct nfs_release_lockowner_args {
+	struct nfs4_sequence_args	seq_args;
 	struct nfs_lowner	lock_owner;
 };
 
+struct nfs_release_lockowner_res {
+	struct nfs4_sequence_res	seq_res;
+};
+
 struct nfs4_delegreturnargs {
 	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *fhandle;
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 26ebcf4..6b9aafe 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -80,13 +80,15 @@
 	struct dma_pool *prp_small_pool;
 	int instance;
 	int queue_count;
-	int db_stride;
+	u32 db_stride;
 	u32 ctrl_config;
 	struct msix_entry *entry;
 	struct nvme_bar __iomem *bar;
 	struct list_head namespaces;
 	struct kref kref;
 	struct miscdevice miscdev;
+	work_func_t reset_workfn;
+	struct work_struct reset_work;
 	char name[12];
 	char serial[20];
 	char model[40];
@@ -94,6 +96,8 @@
 	u32 max_hw_sectors;
 	u32 stripe_size;
 	u16 oncs;
+	u16 abort_limit;
+	u8 initialized;
 };
 
 /*
@@ -165,6 +169,7 @@
 struct sg_io_hdr;
 
 int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr);
+int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg);
 int nvme_sg_get_version_num(int __user *ip);
 
 #endif /* _LINUX_NVME_H */
diff --git a/include/linux/of.h b/include/linux/of.h
index 70c64ba..435cb99 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -169,35 +169,15 @@
 
 extern struct device_node *of_find_node_by_name(struct device_node *from,
 	const char *name);
-#define for_each_node_by_name(dn, name) \
-	for (dn = of_find_node_by_name(NULL, name); dn; \
-	     dn = of_find_node_by_name(dn, name))
 extern struct device_node *of_find_node_by_type(struct device_node *from,
 	const char *type);
-#define for_each_node_by_type(dn, type) \
-	for (dn = of_find_node_by_type(NULL, type); dn; \
-	     dn = of_find_node_by_type(dn, type))
 extern struct device_node *of_find_compatible_node(struct device_node *from,
 	const char *type, const char *compat);
-#define for_each_compatible_node(dn, type, compatible) \
-	for (dn = of_find_compatible_node(NULL, type, compatible); dn; \
-	     dn = of_find_compatible_node(dn, type, compatible))
 extern struct device_node *of_find_matching_node_and_match(
 	struct device_node *from,
 	const struct of_device_id *matches,
 	const struct of_device_id **match);
-static inline struct device_node *of_find_matching_node(
-	struct device_node *from,
-	const struct of_device_id *matches)
-{
-	return of_find_matching_node_and_match(from, matches, NULL);
-}
-#define for_each_matching_node(dn, matches) \
-	for (dn = of_find_matching_node(NULL, matches); dn; \
-	     dn = of_find_matching_node(dn, matches))
-#define for_each_matching_node_and_match(dn, matches, match) \
-	for (dn = of_find_matching_node_and_match(NULL, matches, match); \
-	     dn; dn = of_find_matching_node_and_match(dn, matches, match))
+
 extern struct device_node *of_find_node_by_path(const char *path);
 extern struct device_node *of_find_node_by_phandle(phandle handle);
 extern struct device_node *of_get_parent(const struct device_node *node);
@@ -209,43 +189,11 @@
 
 extern struct device_node *of_get_child_by_name(const struct device_node *node,
 					const char *name);
-#define for_each_child_of_node(parent, child) \
-	for (child = of_get_next_child(parent, NULL); child != NULL; \
-	     child = of_get_next_child(parent, child))
-
-#define for_each_available_child_of_node(parent, child) \
-	for (child = of_get_next_available_child(parent, NULL); child != NULL; \
-	     child = of_get_next_available_child(parent, child))
-
-static inline int of_get_child_count(const struct device_node *np)
-{
-	struct device_node *child;
-	int num = 0;
-
-	for_each_child_of_node(np, child)
-		num++;
-
-	return num;
-}
-
-static inline int of_get_available_child_count(const struct device_node *np)
-{
-	struct device_node *child;
-	int num = 0;
-
-	for_each_available_child_of_node(np, child)
-		num++;
-
-	return num;
-}
 
 /* cache lookup */
 extern struct device_node *of_find_next_cache_node(const struct device_node *);
 extern struct device_node *of_find_node_with_property(
 	struct device_node *from, const char *prop_name);
-#define for_each_node_with_property(dn, prop_name) \
-	for (dn = of_find_node_with_property(NULL, prop_name); dn; \
-	     dn = of_find_node_with_property(dn, prop_name))
 
 extern struct property *of_find_property(const struct device_node *np,
 					 const char *name,
@@ -367,27 +315,48 @@
 	return NULL;
 }
 
+static inline struct device_node *of_find_node_by_type(struct device_node *from,
+	const char *type)
+{
+	return NULL;
+}
+
+static inline struct device_node *of_find_matching_node_and_match(
+	struct device_node *from,
+	const struct of_device_id *matches,
+	const struct of_device_id **match)
+{
+	return NULL;
+}
+
 static inline struct device_node *of_get_parent(const struct device_node *node)
 {
 	return NULL;
 }
 
+static inline struct device_node *of_get_next_child(
+	const struct device_node *node, struct device_node *prev)
+{
+	return NULL;
+}
+
+static inline struct device_node *of_get_next_available_child(
+	const struct device_node *node, struct device_node *prev)
+{
+	return NULL;
+}
+
+static inline struct device_node *of_find_node_with_property(
+	struct device_node *from, const char *prop_name)
+{
+	return NULL;
+}
+
 static inline bool of_have_populated_dt(void)
 {
 	return false;
 }
 
-/* Kill an unused variable warning on a device_node pointer */
-static inline void __of_use_dn(const struct device_node *np)
-{
-}
-
-#define for_each_child_of_node(parent, child) \
-	while (__of_use_dn(parent), __of_use_dn(child), 0)
-
-#define for_each_available_child_of_node(parent, child) \
-	while (0)
-
 static inline struct device_node *of_get_child_by_name(
 					const struct device_node *node,
 					const char *name)
@@ -395,16 +364,6 @@
 	return NULL;
 }
 
-static inline int of_get_child_count(const struct device_node *np)
-{
-	return 0;
-}
-
-static inline int of_get_available_child_count(const struct device_node *np)
-{
-	return 0;
-}
-
 static inline int of_device_is_compatible(const struct device_node *device,
 					  const char *name)
 {
@@ -569,6 +528,13 @@
 static inline int of_node_to_nid(struct device_node *device) { return 0; }
 #endif
 
+static inline struct device_node *of_find_matching_node(
+	struct device_node *from,
+	const struct of_device_id *matches)
+{
+	return of_find_matching_node_and_match(from, matches, NULL);
+}
+
 /**
  * of_property_read_bool - Findfrom a property
  * @np:		device node from which the property value is to be read.
@@ -618,6 +584,55 @@
 		s;						\
 		s = of_prop_next_string(prop, s))
 
+#define for_each_node_by_name(dn, name) \
+	for (dn = of_find_node_by_name(NULL, name); dn; \
+	     dn = of_find_node_by_name(dn, name))
+#define for_each_node_by_type(dn, type) \
+	for (dn = of_find_node_by_type(NULL, type); dn; \
+	     dn = of_find_node_by_type(dn, type))
+#define for_each_compatible_node(dn, type, compatible) \
+	for (dn = of_find_compatible_node(NULL, type, compatible); dn; \
+	     dn = of_find_compatible_node(dn, type, compatible))
+#define for_each_matching_node(dn, matches) \
+	for (dn = of_find_matching_node(NULL, matches); dn; \
+	     dn = of_find_matching_node(dn, matches))
+#define for_each_matching_node_and_match(dn, matches, match) \
+	for (dn = of_find_matching_node_and_match(NULL, matches, match); \
+	     dn; dn = of_find_matching_node_and_match(dn, matches, match))
+
+#define for_each_child_of_node(parent, child) \
+	for (child = of_get_next_child(parent, NULL); child != NULL; \
+	     child = of_get_next_child(parent, child))
+#define for_each_available_child_of_node(parent, child) \
+	for (child = of_get_next_available_child(parent, NULL); child != NULL; \
+	     child = of_get_next_available_child(parent, child))
+
+#define for_each_node_with_property(dn, prop_name) \
+	for (dn = of_find_node_with_property(NULL, prop_name); dn; \
+	     dn = of_find_node_with_property(dn, prop_name))
+
+static inline int of_get_child_count(const struct device_node *np)
+{
+	struct device_node *child;
+	int num = 0;
+
+	for_each_child_of_node(np, child)
+		num++;
+
+	return num;
+}
+
+static inline int of_get_available_child_count(const struct device_node *np)
+{
+	struct device_node *child;
+	int num = 0;
+
+	for_each_available_child_of_node(np, child)
+		num++;
+
+	return num;
+}
+
 #if defined(CONFIG_PROC_FS) && defined(CONFIG_PROC_DEVICETREE)
 extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *);
 extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop);
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 8d7dd67..ef37021 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -78,11 +78,13 @@
 
 static inline void of_device_node_put(struct device *dev) { }
 
-static inline const struct of_device_id *of_match_device(
+static inline const struct of_device_id *__of_match_device(
 		const struct of_device_id *matches, const struct device *dev)
 {
 	return NULL;
 }
+#define of_match_device(matches, dev)	\
+	__of_match_device(of_match_ptr(matches), (dev))
 
 static inline struct device_node *of_cpu_device_node_get(int cpu)
 {
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index e464b4e..d1fe1a7 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -228,9 +228,9 @@
 TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
 PAGEFLAG(MappedToDisk, mappedtodisk)
 
-/* PG_readahead is only used for file reads; PG_reclaim is only for writes */
+/* PG_readahead is only used for reads; PG_reclaim is only for writes */
 PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim)
-PAGEFLAG(Readahead, reclaim)		/* Reminder to do async read-ahead */
+PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim)
 
 #ifdef CONFIG_HIGHMEM
 /*
diff --git a/include/linux/pci.h b/include/linux/pci.h
index fb57c89..33aa2ca 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1169,8 +1169,23 @@
 void pci_restore_msi_state(struct pci_dev *dev);
 int pci_msi_enabled(void);
 int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec);
+static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec)
+{
+	int rc = pci_enable_msi_range(dev, nvec, nvec);
+	if (rc < 0)
+		return rc;
+	return 0;
+}
 int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
 			  int minvec, int maxvec);
+static inline int pci_enable_msix_exact(struct pci_dev *dev,
+					struct msix_entry *entries, int nvec)
+{
+	int rc = pci_enable_msix_range(dev, entries, nvec, nvec);
+	if (rc < 0)
+		return rc;
+	return 0;
+}
 #else
 static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; }
 static inline int pci_enable_msi_block(struct pci_dev *dev, int nvec)
@@ -1189,9 +1204,14 @@
 static inline int pci_enable_msi_range(struct pci_dev *dev, int minvec,
 				       int maxvec)
 { return -ENOSYS; }
+static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec)
+{ return -ENOSYS; }
 static inline int pci_enable_msix_range(struct pci_dev *dev,
 		      struct msix_entry *entries, int minvec, int maxvec)
 { return -ENOSYS; }
+static inline int pci_enable_msix_exact(struct pci_dev *dev,
+		      struct msix_entry *entries, int nvec)
+{ return -ENOSYS; }
 #endif
 
 #ifdef CONFIG_PCIEPORTBUS
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 97fbecd..7399e6a 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2531,6 +2531,9 @@
 
 #define PCI_VENDOR_ID_INTEL		0x8086
 #define PCI_DEVICE_ID_INTEL_EESSC	0x0008
+#define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
+#define PCI_DEVICE_ID_INTEL_IVB_IMC	0x0154
+#define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_PXHD_0	0x0320
 #define PCI_DEVICE_ID_INTEL_PXHD_1	0x0321
 #define PCI_DEVICE_ID_INTEL_PXH_0	0x0329
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index e273e5a..3f83459 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -146,7 +146,9 @@
 	phy->attrs.bus_width = bus_width;
 }
 struct phy *phy_get(struct device *dev, const char *string);
+struct phy *phy_optional_get(struct device *dev, const char *string);
 struct phy *devm_phy_get(struct device *dev, const char *string);
+struct phy *devm_phy_optional_get(struct device *dev, const char *string);
 void phy_put(struct phy *phy);
 void devm_phy_put(struct device *dev, struct phy *phy);
 struct phy *of_phy_simple_xlate(struct device *dev,
@@ -232,11 +234,23 @@
 	return ERR_PTR(-ENOSYS);
 }
 
+static inline struct phy *phy_optional_get(struct device *dev,
+					   const char *string)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 static inline struct phy *devm_phy_get(struct device *dev, const char *string)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
+static inline struct phy *devm_phy_optional_get(struct device *dev,
+						const char *string)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 static inline void phy_put(struct phy *phy)
 {
 }
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index dbaf990..8183b46 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -247,9 +247,10 @@
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
 #define list_entry_rcu(ptr, type, member) \
-	({typeof (*ptr) __rcu *__ptr = (typeof (*ptr) __rcu __force *)ptr; \
-	 container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member); \
-	})
+({ \
+	typeof(*ptr) __rcu *__ptr = (typeof(*ptr) __rcu __force *)ptr; \
+	container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member); \
+})
 
 /**
  * Where are list_empty_rcu() and list_first_entry_rcu()?
@@ -285,11 +286,11 @@
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
 #define list_first_or_null_rcu(ptr, type, member) \
-	({struct list_head *__ptr = (ptr); \
-	  struct list_head *__next = ACCESS_ONCE(__ptr->next); \
-	  likely(__ptr != __next) ? \
-		list_entry_rcu(__next, type, member) : NULL; \
-	})
+({ \
+	struct list_head *__ptr = (ptr); \
+	struct list_head *__next = ACCESS_ONCE(__ptr->next); \
+	likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \
+})
 
 /**
  * list_for_each_entry_rcu	-	iterate over rcu list of given type
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index adff3c9..00a7fd6 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2001
  *
@@ -44,7 +44,9 @@
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
+#include <asm/barrier.h>
 
+extern int rcu_expedited; /* for sysctl */
 #ifdef CONFIG_RCU_TORTURE_TEST
 extern int rcutorture_runnable; /* for sysctl */
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
@@ -479,11 +481,9 @@
 	do {								\
 		rcu_preempt_sleep_check();				\
 		rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),	\
-				   "Illegal context switch in RCU-bh"	\
-				   " read-side critical section");	\
+				   "Illegal context switch in RCU-bh read-side critical section"); \
 		rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),	\
-				   "Illegal context switch in RCU-sched"\
-				   " read-side critical section");	\
+				   "Illegal context switch in RCU-sched read-side critical section"); \
 	} while (0)
 
 #else /* #ifdef CONFIG_PROVE_RCU */
@@ -510,43 +510,40 @@
 #endif /* #else #ifdef __CHECKER__ */
 
 #define __rcu_access_pointer(p, space) \
-	({ \
-		typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \
-		rcu_dereference_sparse(p, space); \
-		((typeof(*p) __force __kernel *)(_________p1)); \
-	})
+({ \
+	typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
+	rcu_dereference_sparse(p, space); \
+	((typeof(*p) __force __kernel *)(_________p1)); \
+})
 #define __rcu_dereference_check(p, c, space) \
-	({ \
-		typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \
-		rcu_lockdep_assert(c, "suspicious rcu_dereference_check()" \
-				      " usage"); \
-		rcu_dereference_sparse(p, space); \
-		smp_read_barrier_depends(); \
-		((typeof(*p) __force __kernel *)(_________p1)); \
-	})
+({ \
+	typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
+	rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \
+	rcu_dereference_sparse(p, space); \
+	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
+	((typeof(*p) __force __kernel *)(_________p1)); \
+})
 #define __rcu_dereference_protected(p, c, space) \
-	({ \
-		rcu_lockdep_assert(c, "suspicious rcu_dereference_protected()" \
-				      " usage"); \
-		rcu_dereference_sparse(p, space); \
-		((typeof(*p) __force __kernel *)(p)); \
-	})
+({ \
+	rcu_lockdep_assert(c, "suspicious rcu_dereference_protected() usage"); \
+	rcu_dereference_sparse(p, space); \
+	((typeof(*p) __force __kernel *)(p)); \
+})
 
 #define __rcu_access_index(p, space) \
-	({ \
-		typeof(p) _________p1 = ACCESS_ONCE(p); \
-		rcu_dereference_sparse(p, space); \
-		(_________p1); \
-	})
+({ \
+	typeof(p) _________p1 = ACCESS_ONCE(p); \
+	rcu_dereference_sparse(p, space); \
+	(_________p1); \
+})
 #define __rcu_dereference_index_check(p, c) \
-	({ \
-		typeof(p) _________p1 = ACCESS_ONCE(p); \
-		rcu_lockdep_assert(c, \
-				   "suspicious rcu_dereference_index_check()" \
-				   " usage"); \
-		smp_read_barrier_depends(); \
-		(_________p1); \
-	})
+({ \
+	typeof(p) _________p1 = ACCESS_ONCE(p); \
+	rcu_lockdep_assert(c, \
+			   "suspicious rcu_dereference_index_check() usage"); \
+	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
+	(_________p1); \
+})
 
 /**
  * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
@@ -585,12 +582,7 @@
  * please be careful when making changes to rcu_assign_pointer() and the
  * other macros that it invokes.
  */
-#define rcu_assign_pointer(p, v) \
-	do { \
-		smp_wmb(); \
-		ACCESS_ONCE(p) = RCU_INITIALIZER(v); \
-	} while (0)
-
+#define rcu_assign_pointer(p, v) smp_store_release(&p, RCU_INITIALIZER(v))
 
 /**
  * rcu_access_pointer() - fetch RCU pointer with no dereferencing
@@ -1015,11 +1007,21 @@
 #define kfree_rcu(ptr, rcu_head)					\
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
 
-#ifdef CONFIG_RCU_NOCB_CPU
+#if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL)
+static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
+{
+	*delta_jiffies = ULONG_MAX;
+	return 0;
+}
+#endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */
+
+#if defined(CONFIG_RCU_NOCB_CPU_ALL)
+static inline bool rcu_is_nocb_cpu(int cpu) { return true; }
+#elif defined(CONFIG_RCU_NOCB_CPU)
 bool rcu_is_nocb_cpu(int cpu);
 #else
 static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
-#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
+#endif
 
 
 /* Only for use by adaptive-ticks code. */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 6f01771..425c659 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
@@ -27,6 +27,16 @@
 
 #include <linux/cache.h>
 
+static inline unsigned long get_state_synchronize_rcu(void)
+{
+	return 0;
+}
+
+static inline void cond_synchronize_rcu(unsigned long oldstate)
+{
+	might_sleep();
+}
+
 static inline void rcu_barrier_bh(void)
 {
 	wait_rcu_gp(call_rcu_bh);
@@ -68,12 +78,6 @@
 	call_rcu(head, func);
 }
 
-static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
-{
-	*delta_jiffies = ULONG_MAX;
-	return 0;
-}
-
 static inline void rcu_note_context_switch(int cpu)
 {
 	rcu_sched_qs(cpu);
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 72137ee..a59ca05 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
@@ -31,7 +31,9 @@
 #define __LINUX_RCUTREE_H
 
 void rcu_note_context_switch(int cpu);
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
 int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies);
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 void rcu_cpu_stall_reset(void);
 
 /*
@@ -74,6 +76,8 @@
 void rcu_barrier(void);
 void rcu_barrier_bh(void);
 void rcu_barrier_sched(void);
+unsigned long get_state_synchronize_rcu(void);
+void cond_synchronize_rcu(unsigned long oldstate);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 1da693d..b66c211 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -250,8 +250,7 @@
 	int (*rmap_one)(struct page *page, struct vm_area_struct *vma,
 					unsigned long addr, void *arg);
 	int (*done)(struct page *page);
-	int (*file_nonlinear)(struct page *, struct address_space *,
-					struct vm_area_struct *vma);
+	int (*file_nonlinear)(struct page *, struct address_space *, void *arg);
 	struct anon_vma *(*anon_lock)(struct page *page);
 	bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
 };
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1ac566c..c399ed8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -3,6 +3,8 @@
 
 #include <uapi/linux/sched.h>
 
+#include <linux/sched/prio.h>
+
 
 struct sched_param {
 	int sched_priority;
@@ -128,6 +130,7 @@
 struct fs_struct;
 struct perf_event_context;
 struct blk_plug;
+struct filename;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -1076,6 +1079,7 @@
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	int			depth;
 	struct sched_entity	*parent;
 	/* rq on which this entity is (to be) queued: */
 	struct cfs_rq		*cfs_rq;
@@ -1459,6 +1463,9 @@
 	struct mutex perf_event_mutex;
 	struct list_head perf_event_list;
 #endif
+#ifdef CONFIG_DEBUG_PREEMPT
+	unsigned long preempt_disable_ip;
+#endif
 #ifdef CONFIG_NUMA
 	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
 	short il_next;
@@ -1469,9 +1476,10 @@
 	unsigned int numa_scan_period;
 	unsigned int numa_scan_period_max;
 	int numa_preferred_nid;
-	int numa_migrate_deferred;
 	unsigned long numa_migrate_retry;
 	u64 node_stamp;			/* migration stamp  */
+	u64 last_task_numa_placement;
+	u64 last_sum_exec_runtime;
 	struct callback_head numa_work;
 
 	struct list_head numa_entry;
@@ -1482,15 +1490,22 @@
 	 * Scheduling placement decisions are made based on the these counts.
 	 * The values remain static for the duration of a PTE scan
 	 */
-	unsigned long *numa_faults;
+	unsigned long *numa_faults_memory;
 	unsigned long total_numa_faults;
 
 	/*
 	 * numa_faults_buffer records faults per node during the current
-	 * scan window. When the scan completes, the counts in numa_faults
-	 * decay and these values are copied.
+	 * scan window. When the scan completes, the counts in
+	 * numa_faults_memory decay and these values are copied.
 	 */
-	unsigned long *numa_faults_buffer;
+	unsigned long *numa_faults_buffer_memory;
+
+	/*
+	 * Track the nodes the process was running on when a NUMA hinting
+	 * fault was incurred.
+	 */
+	unsigned long *numa_faults_cpu;
+	unsigned long *numa_faults_buffer_cpu;
 
 	/*
 	 * numa_faults_locality tracks if faults recorded during the last
@@ -1595,8 +1610,8 @@
 extern pid_t task_numa_group_id(struct task_struct *p);
 extern void set_numabalancing_state(bool enabled);
 extern void task_numa_free(struct task_struct *p);
-
-extern unsigned int sysctl_numa_balancing_migrate_deferred;
+extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
+					int src_nid, int dst_cpu);
 #else
 static inline void task_numa_fault(int last_node, int node, int pages,
 				   int flags)
@@ -1612,6 +1627,11 @@
 static inline void task_numa_free(struct task_struct *p)
 {
 }
+static inline bool should_numa_migrate_memory(struct task_struct *p,
+				struct page *page, int src_nid, int dst_cpu)
+{
+	return true;
+}
 #endif
 
 static inline struct pid *task_pid(struct task_struct *task)
@@ -2079,7 +2099,16 @@
 extern bool yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
-extern int task_nice(const struct task_struct *p);
+/**
+ * task_nice - return the nice value of a given task.
+ * @p: the task in question.
+ *
+ * Return: The nice value [ -20 ... 0 ... 19 ].
+ */
+static inline int task_nice(const struct task_struct *p)
+{
+	return PRIO_TO_NICE((p)->static_prio);
+}
 extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);
@@ -2311,7 +2340,7 @@
 extern int allow_signal(int);
 extern int disallow_signal(int);
 
-extern int do_execve(const char *,
+extern int do_execve(struct filename *,
 		     const char __user * const __user *,
 		     const char __user * const __user *);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h
new file mode 100644
index 0000000..ac32258
--- /dev/null
+++ b/include/linux/sched/prio.h
@@ -0,0 +1,44 @@
+#ifndef _SCHED_PRIO_H
+#define _SCHED_PRIO_H
+
+#define MAX_NICE	19
+#define MIN_NICE	-20
+#define NICE_WIDTH	(MAX_NICE - MIN_NICE + 1)
+
+/*
+ * Priority of a process goes from 0..MAX_PRIO-1, valid RT
+ * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
+ * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
+ * values are inverted: lower p->prio value means higher priority.
+ *
+ * The MAX_USER_RT_PRIO value allows the actual maximum
+ * RT priority to be separate from the value exported to
+ * user-space.  This allows kernel threads to set their
+ * priority to a value higher than any user task. Note:
+ * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
+ */
+
+#define MAX_USER_RT_PRIO	100
+#define MAX_RT_PRIO		MAX_USER_RT_PRIO
+
+#define MAX_PRIO		(MAX_RT_PRIO + NICE_WIDTH)
+#define DEFAULT_PRIO		(MAX_RT_PRIO + NICE_WIDTH / 2)
+
+/*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
+ * and back.
+ */
+#define NICE_TO_PRIO(nice)	((nice) + DEFAULT_PRIO)
+#define PRIO_TO_NICE(prio)	((prio) - DEFAULT_PRIO)
+
+/*
+ * 'User priority' is the nice value converted to something we
+ * can work with better when scaling various scheduler parameters,
+ * it's a [ 0 ... 39 ] range.
+ */
+#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
+#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
+#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
+
+#endif /* _SCHED_PRIO_H */
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 34e4ebe..6341f5b 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -1,24 +1,7 @@
 #ifndef _SCHED_RT_H
 #define _SCHED_RT_H
 
-/*
- * Priority of a process goes from 0..MAX_PRIO-1, valid RT
- * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
- * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
- * values are inverted: lower p->prio value means higher priority.
- *
- * The MAX_USER_RT_PRIO value allows the actual maximum
- * RT priority to be separate from the value exported to
- * user-space.  This allows kernel threads to set their
- * priority to a value higher than any user task. Note:
- * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
- */
-
-#define MAX_USER_RT_PRIO	100
-#define MAX_RT_PRIO		MAX_USER_RT_PRIO
-
-#define MAX_PRIO		(MAX_RT_PRIO + 40)
-#define DEFAULT_PRIO		(MAX_RT_PRIO + 20)
+#include <linux/sched/prio.h>
 
 static inline int rt_prio(int prio)
 {
@@ -35,6 +18,7 @@
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
+extern int rt_mutex_check_prio(struct task_struct *task, int newprio);
 extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
 static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
@@ -46,6 +30,12 @@
 {
 	return p->normal_prio;
 }
+
+static inline int rt_mutex_check_prio(struct task_struct *task, int newprio)
+{
+	return 0;
+}
+
 static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 {
 	return NULL;
diff --git a/include/linux/security.h b/include/linux/security.h
index 5623a7f..2fc42d1 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1040,6 +1040,7 @@
  *	Allocate a security structure to the xp->security field; the security
  *	field is initialized to NULL when the xfrm_policy is allocated.
  *	Return 0 if operation was successful (memory to allocate, legal context)
+ *	@gfp is to specify the context for the allocation
  * @xfrm_policy_clone_security:
  *	@old_ctx contains an existing xfrm_sec_ctx.
  *	@new_ctxp contains a new xfrm_sec_ctx being cloned from old.
@@ -1683,7 +1684,7 @@
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 	int (*xfrm_policy_alloc_security) (struct xfrm_sec_ctx **ctxp,
-			struct xfrm_user_sec_ctx *sec_ctx);
+			struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp);
 	int (*xfrm_policy_clone_security) (struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctx);
 	void (*xfrm_policy_free_security) (struct xfrm_sec_ctx *ctx);
 	int (*xfrm_policy_delete_security) (struct xfrm_sec_ctx *ctx);
@@ -2859,7 +2860,8 @@
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 
-int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx);
+int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
+			       struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp);
 int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctxp);
 void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx);
 int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx);
@@ -2877,7 +2879,9 @@
 
 #else	/* CONFIG_SECURITY_NETWORK_XFRM */
 
-static inline int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx)
+static inline int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
+					     struct xfrm_user_sec_ctx *sec_ctx,
+					     gfp_t gfp)
 {
 	return 0;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f589c9a..15ede6a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2451,8 +2451,8 @@
 		    unsigned int flags);
 void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
 unsigned int skb_zerocopy_headlen(const struct sk_buff *from);
-void skb_zerocopy(struct sk_buff *to, const struct sk_buff *from,
-		  int len, int hlen);
+int skb_zerocopy(struct sk_buff *to, struct sk_buff *from,
+		 int len, int hlen);
 void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len);
 int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen);
 void skb_scrub_packet(struct sk_buff *skb, bool xnet);
@@ -2725,7 +2725,7 @@
 
 static inline void nf_reset_trace(struct sk_buff *skb)
 {
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES)
 	skb->nf_trace = 0;
 #endif
 }
@@ -2742,6 +2742,9 @@
 	dst->nf_bridge  = src->nf_bridge;
 	nf_bridge_get(src->nf_bridge);
 #endif
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES)
+	dst->nf_trace = src->nf_trace;
+#endif
 }
 
 static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
@@ -2916,5 +2919,22 @@
 {
 	return !skb->head_frag || skb_cloned(skb);
 }
+
+/**
+ * skb_gso_network_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_network_seglen is used to determine the real size of the
+ * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP).
+ *
+ * The MAC/L2 header is not accounted for.
+ */
+static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
+{
+	unsigned int hdr_len = skb_transport_header(skb) -
+			       skb_network_header(skb);
+	return hdr_len + skb_gso_transport_seglen(skb);
+}
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/include/linux/slab.h b/include/linux/slab.h
index a060142..b5b2df6 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -205,8 +205,8 @@
 
 #ifdef CONFIG_SLUB
 /*
- * SLUB allocates up to order 2 pages directly and otherwise
- * passes the request to the page allocator.
+ * SLUB directly allocates requests fitting in to an order-1 page
+ * (PAGE_SIZE*2).  Larger requests are passed to the page allocator.
  */
 #define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
 #define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
@@ -217,12 +217,12 @@
 
 #ifdef CONFIG_SLOB
 /*
- * SLOB passes all page size and larger requests to the page allocator.
+ * SLOB passes all requests larger than one page to the page allocator.
  * No kmalloc array is necessary since objects of different sizes can
  * be allocated from the same page.
  */
-#define KMALLOC_SHIFT_MAX	30
 #define KMALLOC_SHIFT_HIGH	PAGE_SHIFT
+#define KMALLOC_SHIFT_MAX	30
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	3
 #endif
@@ -410,7 +410,7 @@
  *
  * %GFP_NOWAIT - Allocation will not sleep.
  *
- * %GFP_THISNODE - Allocate node-local memory only.
+ * %__GFP_THISNODE - Allocate node-local memory only.
  *
  * %GFP_DMA - Allocation suitable for DMA.
  *   Should only be used for kmalloc() caches. Otherwise, use a
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 3834f43..6ae004e 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -188,6 +188,9 @@
  */
 extern void arch_disable_smp_support(void);
 
+extern void arch_enable_nonboot_cpus_begin(void);
+extern void arch_enable_nonboot_cpus_end(void);
+
 void smp_setup_processor_id(void);
 
 #endif /* __LINUX_SMP_H */
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index a1d4ca2..4203c66 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -273,7 +273,7 @@
  *	message while queuing transfers that arrive in the meantime. When the
  *	driver is finished with this message, it must call
  *	spi_finalize_current_message() so the subsystem can issue the next
- *	transfer
+ *	message
  * @unprepare_transfer_hardware: there are currently no more messages on the
  *	queue so the subsystem notifies the driver that it may relax the
  *	hardware by issuing this call
@@ -287,7 +287,10 @@
  *                  - return 1 if the transfer is still in progress. When
  *                    the driver is finished with this transfer it must
  *                    call spi_finalize_current_transfer() so the subsystem
- *                    can issue the next transfer
+ *                    can issue the next transfer. Note: transfer_one and
+ *                    transfer_one_message are mutually exclusive; when both
+ *                    are set, the generic subsystem does not call your
+ *                    transfer_one callback.
  * @unprepare_message: undo any work done by prepare_message().
  * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
  *	number. Any individual value may be -ENOENT for CS lines that
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 9b058ee..a2783cb 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright (C) IBM Corporation, 2006
  * Copyright (C) Fujitsu, 2012
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 40ed9e9..1e67b7a 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -98,6 +98,8 @@
 #define __MAP(n,...) __MAP##n(__VA_ARGS__)
 
 #define __SC_DECL(t, a)	t a
+#define __TYPE_IS_L(t)	(__same_type((t)0, 0L))
+#define __TYPE_IS_UL(t)	(__same_type((t)0, 0UL))
 #define __TYPE_IS_LL(t) (__same_type((t)0, 0LL) || __same_type((t)0, 0ULL))
 #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a
 #define __SC_CAST(t, a)	(t) a
@@ -281,13 +283,15 @@
 asmlinkage long sys_sched_setparam(pid_t pid,
 					struct sched_param __user *param);
 asmlinkage long sys_sched_setattr(pid_t pid,
-					struct sched_attr __user *attr);
+					struct sched_attr __user *attr,
+					unsigned int flags);
 asmlinkage long sys_sched_getscheduler(pid_t pid);
 asmlinkage long sys_sched_getparam(pid_t pid,
 					struct sched_param __user *param);
 asmlinkage long sys_sched_getattr(pid_t pid,
 					struct sched_attr __user *attr,
-					unsigned int size);
+					unsigned int size,
+					unsigned int flags);
 asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
 					unsigned long __user *user_mask_ptr);
 asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
diff --git a/include/linux/torture.h b/include/linux/torture.h
new file mode 100644
index 0000000..b2e2b46
--- /dev/null
+++ b/include/linux/torture.h
@@ -0,0 +1,100 @@
+/*
+ * Common functions for in-kernel torture tests.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright IBM Corporation, 2014
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#ifndef __LINUX_TORTURE_H
+#define __LINUX_TORTURE_H
+
+#include <linux/types.h>
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/seqlock.h>
+#include <linux/lockdep.h>
+#include <linux/completion.h>
+#include <linux/debugobjects.h>
+#include <linux/bug.h>
+#include <linux/compiler.h>
+
+/* Definitions for a non-string torture-test module parameter. */
+#define torture_param(type, name, init, msg) \
+	static type name = init; \
+	module_param(name, type, 0444); \
+	MODULE_PARM_DESC(name, msg);
+
+#define TORTURE_FLAG "-torture:"
+#define TOROUT_STRING(s) \
+	pr_alert("%s" TORTURE_FLAG s "\n", torture_type)
+#define VERBOSE_TOROUT_STRING(s) \
+	do { if (verbose) pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s); } while (0)
+#define VERBOSE_TOROUT_ERRSTRING(s) \
+	do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); } while (0)
+
+/* Definitions for a non-string torture-test module parameter. */
+#define torture_parm(type, name, init, msg) \
+	static type name = init; \
+	module_param(name, type, 0444); \
+	MODULE_PARM_DESC(name, msg);
+
+/* Definitions for online/offline exerciser. */
+int torture_onoff_init(long ooholdoff, long oointerval);
+char *torture_onoff_stats(char *page);
+bool torture_onoff_failures(void);
+
+/* Low-rider random number generator. */
+struct torture_random_state {
+	unsigned long trs_state;
+	long trs_count;
+};
+#define DEFINE_TORTURE_RANDOM(name) struct torture_random_state name = { 0, 0 }
+unsigned long torture_random(struct torture_random_state *trsp);
+
+/* Task shuffler, which causes CPUs to occasionally go idle. */
+void torture_shuffle_task_register(struct task_struct *tp);
+int torture_shuffle_init(long shuffint);
+
+/* Test auto-shutdown handling. */
+void torture_shutdown_absorb(const char *title);
+int torture_shutdown_init(int ssecs, void (*cleanup)(void));
+
+/* Task stuttering, which forces load/no-load transitions. */
+void stutter_wait(const char *title);
+int torture_stutter_init(int s);
+
+/* Initialization and cleanup. */
+void torture_init_begin(char *ttype, bool v, int *runnable);
+void torture_init_end(void);
+bool torture_cleanup(void);
+bool torture_must_stop(void);
+bool torture_must_stop_irq(void);
+void torture_kthread_stopping(char *title);
+int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
+			     char *f, struct task_struct **tp);
+void _torture_stop_kthread(char *m, struct task_struct **tp);
+
+#define torture_create_kthread(n, arg, tp) \
+	_torture_create_kthread(n, (arg), #n, "Creating " #n " task", \
+				"Failed to create " #n, &(tp))
+#define torture_stop_kthread(n, tp) \
+	_torture_stop_kthread("Stopping " #n " task", &(tp))
+
+#endif /* __LINUX_TORTURE_H */
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index accc497..7159a0a 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -60,6 +60,12 @@
 	unsigned int num_tracepoints;
 	struct tracepoint * const *tracepoints_ptrs;
 };
+bool trace_module_has_bad_taint(struct module *mod);
+#else
+static inline bool trace_module_has_bad_taint(struct module *mod)
+{
+	return false;
+}
 #endif /* CONFIG_MODULES */
 
 struct tracepoint_iter {
diff --git a/include/linux/usb.h b/include/linux/usb.h
index c716da1..7f6eb85 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1265,8 +1265,6 @@
  * @sg: scatter gather buffer list, the buffer size of each element in
  * 	the list (except the last) must be divisible by the endpoint's
  * 	max packet size if no_sg_constraint isn't set in 'struct usb_bus'
- * 	(FIXME: scatter-gather under xHCI is broken for periodic transfers.
- * 	Do not use urb->sg for interrupt endpoints for now, only bulk.)
  * @num_mapped_sgs: (internal) number of mapped sg entries
  * @num_sgs: number of entries in the sg list
  * @transfer_buffer_length: How big is transfer_buffer.  The transfer may
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index c3fa807..2c14d9c 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -88,6 +88,7 @@
 #define cdc_ncm_data_intf_is_mbim(x)  ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB)
 
 struct cdc_ncm_ctx {
+	struct usb_cdc_ncm_ntb_parameters ncm_parm;
 	struct hrtimer tx_timer;
 	struct tasklet_struct bh;
 
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index e303eef..0662e98 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -30,7 +30,7 @@
 	struct driver_info	*driver_info;
 	const char		*driver_name;
 	void			*driver_priv;
-	wait_queue_head_t	*wait;
+	wait_queue_head_t	wait;
 	struct mutex		phy_mutex;
 	unsigned char		suspend_count;
 	unsigned char		pkt_cnt, pkt_err;
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index c557c6d..3a712e2 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -71,12 +71,14 @@
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
+#ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 		NR_TLB_REMOTE_FLUSH,	/* cpu tried to flush others' tlbs */
 		NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
-#endif
+#endif /* CONFIG_SMP */
 		NR_TLB_LOCAL_FLUSH_ALL,
 		NR_TLB_LOCAL_FLUSH_ONE,
+#endif /* CONFIG_DEBUG_TLBFLUSH */
 		NR_VM_EVENT_ITEMS
 };
 
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index a67b384..67ce70c 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -83,6 +83,14 @@
 #define count_vm_numa_events(x, y) do { (void)(y); } while (0)
 #endif /* CONFIG_NUMA_BALANCING */
 
+#ifdef CONFIG_DEBUG_TLBFLUSH
+#define count_vm_tlb_event(x)	   count_vm_event(x)
+#define count_vm_tlb_events(x, y)  count_vm_events(x, y)
+#else
+#define count_vm_tlb_event(x)     do {} while (0)
+#define count_vm_tlb_events(x, y) do { (void)(y); } while (0)
+#endif
+
 #define __count_zone_vm_events(item, zone, delta) \
 		__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
 		zone_idx(zone), delta)
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 594521b..5329946 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -177,17 +177,6 @@
 #define DECLARE_DEFERRABLE_WORK(n, f)					\
 	struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE)
 
-/*
- * initialize a work item's function pointer
- */
-#define PREPARE_WORK(_work, _func)					\
-	do {								\
-		(_work)->func = (_func);				\
-	} while (0)
-
-#define PREPARE_DELAYED_WORK(_work, _func)				\
-	PREPARE_WORK(&(_work)->work, (_func))
-
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 extern void __init_work(struct work_struct *work, int onstack);
 extern void destroy_work_on_stack(struct work_struct *work);
@@ -217,7 +206,7 @@
 		(_work)->data = (atomic_long_t) WORK_DATA_INIT();	\
 		lockdep_init_map(&(_work)->lockdep_map, #_work, &__key, 0); \
 		INIT_LIST_HEAD(&(_work)->entry);			\
-		PREPARE_WORK((_work), (_func));				\
+		(_work)->func = (_func);				\
 	} while (0)
 #else
 #define __INIT_WORK(_work, _func, _onstack)				\
@@ -225,7 +214,7 @@
 		__init_work((_work), _onstack);				\
 		(_work)->data = (atomic_long_t) WORK_DATA_INIT();	\
 		INIT_LIST_HEAD(&(_work)->entry);			\
-		PREPARE_WORK((_work), (_func));				\
+		(_work)->func = (_func);				\
 	} while (0)
 #endif
 
@@ -295,17 +284,11 @@
  * Documentation/workqueue.txt.
  */
 enum {
-	/*
-	 * All wqs are now non-reentrant making the following flag
-	 * meaningless.  Will be removed.
-	 */
-	WQ_NON_REENTRANT	= 1 << 0, /* DEPRECATED */
-
 	WQ_UNBOUND		= 1 << 1, /* not bound to any cpu */
 	WQ_FREEZABLE		= 1 << 2, /* freeze during suspend */
 	WQ_MEM_RECLAIM		= 1 << 3, /* may be used for memory reclaim */
 	WQ_HIGHPRI		= 1 << 4, /* high priority */
-	WQ_CPU_INTENSIVE	= 1 << 5, /* cpu instensive workqueue */
+	WQ_CPU_INTENSIVE	= 1 << 5, /* cpu intensive workqueue */
 	WQ_SYSFS		= 1 << 6, /* visible in sysfs, see wq_sysfs_register() */
 
 	/*
@@ -419,10 +402,7 @@
 	static struct lock_class_key __key;				\
 	const char *__lock_name;					\
 									\
-	if (__builtin_constant_p(fmt))					\
-		__lock_name = (fmt);					\
-	else								\
-		__lock_name = #fmt;					\
+	__lock_name = #fmt#args;					\
 									\
 	__alloc_workqueue_key((fmt), (flags), (max_active),		\
 			      &__key, __lock_name, ##args);		\
@@ -605,21 +585,6 @@
 	return system_wq != NULL;
 }
 
-/*
- * Like above, but uses del_timer() instead of del_timer_sync(). This means,
- * if it returns 0 the timer function may be running and the queueing is in
- * progress.
- */
-static inline bool __deprecated __cancel_delayed_work(struct delayed_work *work)
-{
-	bool ret;
-
-	ret = del_timer(&work->timer);
-	if (ret)
-		work_clear_pending(&work->work);
-	return ret;
-}
-
 /* used to be different but now identical to flush_work(), deprecated */
 static inline bool __deprecated flush_work_sync(struct work_struct *work)
 {
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index fc0e432..021b8a3 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -97,7 +97,7 @@
 int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason);
 int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
 				  enum wb_reason reason);
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this);
+void sync_inodes_sb(struct super_block *);
 void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
 void inode_wait_for_writeback(struct inode *inode);
 
diff --git a/include/net/datalink.h b/include/net/datalink.h
index deb7ca7..93cb18f 100644
--- a/include/net/datalink.h
+++ b/include/net/datalink.h
@@ -15,4 +15,6 @@
 	struct list_head node;
 };
 
+struct datalink_proto *make_EII_client(void);
+void destroy_EII_client(struct datalink_proto *dl);
 #endif
diff --git a/include/net/dn.h b/include/net/dn.h
index ccc1558..913b73d 100644
--- a/include/net/dn.h
+++ b/include/net/dn.h
@@ -200,6 +200,8 @@
 }
 
 unsigned int dn_mss_from_pmtu(struct net_device *dev, int mtu);
+void dn_register_sysctl(void);
+void dn_unregister_sysctl(void);
 
 #define DN_MENUVER_ACC 0x01
 #define DN_MENUVER_USR 0x02
diff --git a/include/net/dn_route.h b/include/net/dn_route.h
index b409ad6..55df993 100644
--- a/include/net/dn_route.h
+++ b/include/net/dn_route.h
@@ -20,6 +20,8 @@
 			 struct sock *sk, int flags);
 int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb);
 void dn_rt_cache_flush(int delay);
+int dn_route_rcv(struct sk_buff *skb, struct net_device *dev,
+		 struct packet_type *pt, struct net_device *orig_dev);
 
 /* Masks for flags field */
 #define DN_RT_F_PID 0x07 /* Mask for packet type                      */
diff --git a/include/net/ethoc.h b/include/net/ethoc.h
index 96f3789..2a2d6bb 100644
--- a/include/net/ethoc.h
+++ b/include/net/ethoc.h
@@ -16,6 +16,7 @@
 struct ethoc_platform_data {
 	u8 hwaddr[IFHWADDRLEN];
 	s8 phy_id;
+	u32 eth_clkfreq;
 };
 
 #endif /* !LINUX_NET_ETHOC_H */
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 9650a3f..b4956a5 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -31,8 +31,10 @@
 #define IF_PREFIX_AUTOCONF	0x02
 
 enum {
+	INET6_IFADDR_STATE_PREDAD,
 	INET6_IFADDR_STATE_DAD,
 	INET6_IFADDR_STATE_POSTDAD,
+	INET6_IFADDR_STATE_ERRDAD,
 	INET6_IFADDR_STATE_UP,
 	INET6_IFADDR_STATE_DEAD,
 };
@@ -58,7 +60,7 @@
 	unsigned long		cstamp;	/* created timestamp */
 	unsigned long		tstamp; /* updated timestamp */
 
-	struct timer_list	dad_timer;
+	struct delayed_work	dad_work;
 
 	struct inet6_dev	*idev;
 	struct rt6_info		*rt;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 48ed75c..e77c104 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -129,6 +129,7 @@
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 		      struct ip_tunnel_parm *p);
 void ip_tunnel_setup(struct net_device *dev, int net_id);
+void ip_tunnel_dst_reset_all(struct ip_tunnel *t);
 
 /* Extract dsfield from inner protocol */
 static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
diff --git a/include/net/ipx.h b/include/net/ipx.h
index 9e9e354..0143180 100644
--- a/include/net/ipx.h
+++ b/include/net/ipx.h
@@ -140,6 +140,17 @@
 }
 
 void ipxitf_down(struct ipx_interface *intrfc);
+struct ipx_interface *ipxitf_find_using_net(__be32 net);
+int ipxitf_send(struct ipx_interface *intrfc, struct sk_buff *skb, char *node);
+__be16 ipx_cksum(struct ipxhdr *packet, int length);
+int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc,
+		     unsigned char *node);
+void ipxrtr_del_routes(struct ipx_interface *intrfc);
+int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
+			struct iovec *iov, size_t len, int noblock);
+int ipxrtr_route_skb(struct sk_buff *skb);
+struct ipx_route *ipxrtr_lookup(__be32 net);
+int ipxrtr_ioctl(unsigned int cmd, void __user *arg);
 
 static __inline__ void ipxitf_put(struct ipx_interface *intrfc)
 {
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index da68c9a..991dcd9 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -162,6 +162,14 @@
 struct net *get_net_ns_by_pid(pid_t pid);
 struct net *get_net_ns_by_fd(int pid);
 
+#ifdef CONFIG_SYSCTL
+void ipx_register_sysctl(void);
+void ipx_unregister_sysctl(void);
+#else
+#define ipx_register_sysctl()
+#define ipx_unregister_sysctl()
+#endif
+
 #ifdef CONFIG_NET_NS
 void __put_net(struct net *net);
 
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 01ea6ee..b2ac624 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -284,6 +284,8 @@
 extern unsigned int nf_conntrack_hash_rnd;
 void init_nf_conntrack_hash_rnd(void);
 
+void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl);
+
 #define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
 
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 57c8ff7..e7e14ff 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -252,6 +252,7 @@
  *	@owner: module reference
  *	@policy: netlink attribute policy
  *	@maxattr: highest netlink attribute number
+ *	@family: address family for AF-specific types
  */
 struct nft_expr_type {
 	const struct nft_expr_ops	*(*select_ops)(const struct nft_ctx *,
@@ -262,6 +263,7 @@
 	struct module			*owner;
 	const struct nla_policy		*policy;
 	unsigned int			maxattr;
+	u8				family;
 };
 
 /**
@@ -320,7 +322,6 @@
  *	struct nft_rule - nf_tables rule
  *
  *	@list: used internally
- *	@rcu_head: used internally for rcu
  *	@handle: rule handle
  *	@genmask: generation mask
  *	@dlen: length of expression data
@@ -328,7 +329,6 @@
  */
 struct nft_rule {
 	struct list_head		list;
-	struct rcu_head			rcu_head;
 	u64				handle:46,
 					genmask:2,
 					dlen:16;
@@ -389,7 +389,6 @@
  *
  *	@rules: list of rules in the chain
  *	@list: used internally
- *	@rcu_head: used internally
  *	@net: net namespace that this chain belongs to
  *	@table: table that this chain belongs to
  *	@handle: chain handle
@@ -401,7 +400,6 @@
 struct nft_chain {
 	struct list_head		rules;
 	struct list_head		list;
-	struct rcu_head			rcu_head;
 	struct net			*net;
 	struct nft_table		*table;
 	u64				handle;
@@ -529,6 +527,9 @@
 #define MODULE_ALIAS_NFT_CHAIN(family, name) \
 	MODULE_ALIAS("nft-chain-" __stringify(family) "-" name)
 
+#define MODULE_ALIAS_NFT_AF_EXPR(family, name) \
+	MODULE_ALIAS("nft-expr-" __stringify(family) "-" name)
+
 #define MODULE_ALIAS_NFT_EXPR(name) \
 	MODULE_ALIAS("nft-expr-" name)
 
diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h
new file mode 100644
index 0000000..36b0da2
--- /dev/null
+++ b/include/net/netfilter/nft_reject.h
@@ -0,0 +1,25 @@
+#ifndef _NFT_REJECT_H_
+#define _NFT_REJECT_H_
+
+struct nft_reject {
+	enum nft_reject_types	type:8;
+	u8			icmp_code;
+};
+
+extern const struct nla_policy nft_reject_policy[];
+
+int nft_reject_init(const struct nft_ctx *ctx,
+		    const struct nft_expr *expr,
+		    const struct nlattr * const tb[]);
+
+int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr);
+
+void nft_reject_ipv4_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt);
+
+void nft_reject_ipv6_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt);
+
+#endif
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index d992ca3..6ee76c8 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1653,17 +1653,6 @@
 	/* This is the last advertised value of rwnd over a SACK chunk. */
 	__u32 a_rwnd;
 
-	/* Number of bytes by which the rwnd has slopped.  The rwnd is allowed
-	 * to slop over a maximum of the association's frag_point.
-	 */
-	__u32 rwnd_over;
-
-	/* Keeps treack of rwnd pressure.  This happens when we have
-	 * a window, but not recevie buffer (i.e small packets).  This one
-	 * is releases slowly (1 PMTU at a time ).
-	 */
-	__u32 rwnd_press;
-
 	/* This is the sndbuf size in use for the association.
 	 * This corresponds to the sndbuf size for the association,
 	 * as specified in the sk->sndbuf.
@@ -1892,8 +1881,7 @@
 __u32 sctp_association_get_next_tsn(struct sctp_association *);
 
 void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *);
-void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
-void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
+void sctp_assoc_rwnd_update(struct sctp_association *, bool);
 void sctp_assoc_set_primary(struct sctp_association *,
 			    struct sctp_transport *);
 void sctp_assoc_del_nonprimary_peers(struct sctp_association *,
diff --git a/include/net/sock.h b/include/net/sock.h
index 5c3f7c3..b9586a1 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1488,6 +1488,11 @@
  */
 #define sock_owned_by_user(sk)	((sk)->sk_lock.owned)
 
+static inline void sock_release_ownership(struct sock *sk)
+{
+	sk->sk_lock.owned = 0;
+}
+
 /*
  * Macro so as to not evaluate some arguments when
  * lockdep is not enabled.
@@ -2186,7 +2191,6 @@
 {
 #define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL)			| \
 			   (1UL << SOCK_RCVTSTAMP)			| \
-			   (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)	| \
 			   (1UL << SOCK_TIMESTAMPING_SOFTWARE)		| \
 			   (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE)	| \
 			   (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE))
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 56fc366..743acce 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -480,20 +480,21 @@
 #ifdef CONFIG_SYN_COOKIES
 #include <linux/ktime.h>
 
-/* Syncookies use a monotonic timer which increments every 64 seconds.
+/* Syncookies use a monotonic timer which increments every 60 seconds.
  * This counter is used both as a hash input and partially encoded into
  * the cookie value.  A cookie is only validated further if the delta
  * between the current counter value and the encoded one is less than this,
- * i.e. a sent cookie is valid only at most for 128 seconds (or less if
+ * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if
  * the counter advances immediately after a cookie is generated).
  */
 #define MAX_SYNCOOKIE_AGE 2
 
 static inline u32 tcp_cookie_time(void)
 {
-	struct timespec now;
-	getnstimeofday(&now);
-	return now.tv_sec >> 6; /* 64 seconds granularity */
+	u64 val = get_jiffies_64();
+
+	do_div(val, 60 * HZ);
+	return val;
 }
 
 u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
@@ -1303,7 +1304,8 @@
 	/* Fast Open cookie. Size 0 means a cookie request */
 	struct tcp_fastopen_cookie	cookie;
 	struct msghdr			*data;  /* data in MSG_FASTOPEN */
-	u16				copied;	/* queued in tcp_connect() */
+	size_t				size;
+	int				copied;	/* queued in tcp_connect() */
 };
 void tcp_free_fastopen_req(struct tcp_sock *tp);
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index afa5730..fb5654a 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1648,6 +1648,11 @@
 }
 #endif
 
+static inline int aead_len(struct xfrm_algo_aead *alg)
+{
+	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
+}
+
 static inline int xfrm_alg_len(const struct xfrm_algo *alg)
 {
 	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
@@ -1686,6 +1691,12 @@
 	return 0;
 }
 
+static inline struct xfrm_algo_aead *xfrm_algo_aead_clone(struct xfrm_algo_aead *orig)
+{
+	return kmemdup(orig, aead_len(orig), GFP_KERNEL);
+}
+
+
 static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig)
 {
 	return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 8d4a1c0..6793f32 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -226,7 +226,8 @@
 	IB_PORT_CAP_MASK_NOTICE_SUP		= 1 << 22,
 	IB_PORT_BOOT_MGMT_SUP			= 1 << 23,
 	IB_PORT_LINK_LATENCY_SUP		= 1 << 24,
-	IB_PORT_CLIENT_REG_SUP			= 1 << 25
+	IB_PORT_CLIENT_REG_SUP			= 1 << 25,
+	IB_PORT_IP_BASED_GIDS			= 1 << 26
 };
 
 enum ib_port_width {
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index f843dd8..ef7872c 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -172,7 +172,6 @@
         enum   ata_command_set command_set;
         struct smp_resp        rps_resp; /* report_phy_sata_resp */
         u8     port_no;        /* port number, if this is a PM (Port) */
-	int    pm_result;
 
 	struct ata_port *ap;
 	struct ata_host ata_host;
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 68d92e3..6e89ef6 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -449,14 +449,22 @@
 /* dapm audio pin control and status */
 int snd_soc_dapm_enable_pin(struct snd_soc_dapm_context *dapm,
 			    const char *pin);
+int snd_soc_dapm_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+				     const char *pin);
 int snd_soc_dapm_disable_pin(struct snd_soc_dapm_context *dapm,
 			     const char *pin);
+int snd_soc_dapm_disable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+				      const char *pin);
 int snd_soc_dapm_nc_pin(struct snd_soc_dapm_context *dapm, const char *pin);
+int snd_soc_dapm_nc_pin_unlocked(struct snd_soc_dapm_context *dapm,
+				 const char *pin);
 int snd_soc_dapm_get_pin_status(struct snd_soc_dapm_context *dapm,
 				const char *pin);
 int snd_soc_dapm_sync(struct snd_soc_dapm_context *dapm);
 int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm,
 				  const char *pin);
+int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+					   const char *pin);
 int snd_soc_dapm_ignore_suspend(struct snd_soc_dapm_context *dapm,
 				const char *pin);
 void snd_soc_dapm_auto_nc_codec_pins(struct snd_soc_codec *codec);
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index ae5a171..4483fad 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -12,6 +12,7 @@
 	int (*iscsit_setup_np)(struct iscsi_np *, struct __kernel_sockaddr_storage *);
 	int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *);
 	void (*iscsit_free_np)(struct iscsi_np *);
+	void (*iscsit_wait_conn)(struct iscsi_conn *);
 	void (*iscsit_free_conn)(struct iscsi_conn *);
 	int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *);
 	int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index c9c7912..1772fad 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -525,7 +525,6 @@
 #define CMD_T_COMPLETE		(1 << 2)
 #define CMD_T_SENT		(1 << 4)
 #define CMD_T_STOP		(1 << 5)
-#define CMD_T_FAILED		(1 << 6)
 #define CMD_T_DEV_ACTIVE	(1 << 7)
 #define CMD_T_REQUEST_STOP	(1 << 8)
 #define CMD_T_BUSY		(1 << 9)
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 9e9475c..e5bf9a7 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -42,7 +42,6 @@
 		u32 state,
 		u64 mperf,
 		u64 aperf,
-		u32 energy,
 		u32 freq
 		),
 
@@ -51,7 +50,6 @@
 		state,
 		mperf,
 		aperf,
-		energy,
 		freq
 		),
 
@@ -61,7 +59,6 @@
 		__field(u32, state)
 		__field(u64, mperf)
 		__field(u64, aperf)
-		__field(u32, energy)
 		__field(u32, freq)
 
 	),
@@ -72,17 +69,15 @@
 		__entry->state = state;
 		__entry->mperf = mperf;
 		__entry->aperf = aperf;
-		__entry->energy = energy;
 		__entry->freq = freq;
 		),
 
-	TP_printk("core_busy=%lu scaled=%lu state=%lu mperf=%llu aperf=%llu energy=%lu freq=%lu ",
+	TP_printk("core_busy=%lu scaled=%lu state=%lu mperf=%llu aperf=%llu freq=%lu ",
 		(unsigned long)__entry->core_busy,
 		(unsigned long)__entry->scaled_busy,
 		(unsigned long)__entry->state,
 		(unsigned long long)__entry->mperf,
 		(unsigned long long)__entry->aperf,
-		(unsigned long)__entry->energy,
 		(unsigned long)__entry->freq
 		)
 
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index ddc179b..1fef3e6 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -83,7 +83,7 @@
 		),
 
 	TP_fast_assign(
-		__entry->client_id = clnt->cl_clid;
+		__entry->client_id = clnt ? clnt->cl_clid : -1;
 		__entry->task_id = task->tk_pid;
 		__entry->action = action;
 		__entry->runstate = task->tk_runstate;
@@ -91,7 +91,7 @@
 		__entry->flags = task->tk_flags;
 		),
 
-	TP_printk("task:%u@%u flags=%4.4x state=%4.4lx status=%d action=%pf",
+	TP_printk("task:%u@%d flags=%4.4x state=%4.4lx status=%d action=%pf",
 		__entry->task_id, __entry->client_id,
 		__entry->flags,
 		__entry->runstate,
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index c7bbbe7..464ea82 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -287,11 +287,11 @@
 		__field(int,		reason)
 	),
 	TP_fast_assign(
-		unsigned long older_than_this = work->older_than_this;
+		unsigned long *older_than_this = work->older_than_this;
 		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
-		__entry->older	= older_than_this;
+		__entry->older	= older_than_this ?  *older_than_this : 0;
 		__entry->age	= older_than_this ?
-				  (jiffies - older_than_this) * 1000 / HZ : -1;
+				  (jiffies - *older_than_this) * 1000 / HZ : -1;
 		__entry->moved	= moved;
 		__entry->reason	= work->reason;
 	),
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 1a8b28d..1ee19a2 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -310,15 +310,12 @@
 #undef __array
 #define __array(type, item, len)					\
 	do {								\
-		mutex_lock(&event_storage_mutex);			\
+		char *type_str = #type"["__stringify(len)"]";		\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		snprintf(event_storage, sizeof(event_storage),		\
-			 "%s[%d]", #type, len);				\
-		ret = trace_define_field(event_call, event_storage, #item, \
+		ret = trace_define_field(event_call, type_str, #item,	\
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
 				 is_signed_type(type), FILTER_OTHER);	\
-		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
 	} while (0);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index a20a9b4..6db6678 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -191,6 +191,7 @@
 
 /* fs/readdir.c */
 #define __NR_getdents64 61
+#define __ARCH_WANT_COMPAT_SYS_GETDENTS64
 __SC_COMP(__NR_getdents64, sys_getdents64, compat_sys_getdents64)
 
 /* fs/read_write.c */
@@ -692,9 +693,13 @@
 __SYSCALL(__NR_kcmp, sys_kcmp)
 #define __NR_finit_module 273
 __SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
 
 #undef __NR_syscalls
-#define __NR_syscalls 274
+#define __NR_syscalls 276
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 3c9a833..b06c8ed 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -619,6 +619,8 @@
 #define  DRM_PRIME_CAP_EXPORT		0x2
 #define DRM_CAP_TIMESTAMP_MONOTONIC	0x6
 #define DRM_CAP_ASYNC_PAGE_FLIP		0x7
+#define DRM_CAP_CURSOR_WIDTH		0x8
+#define DRM_CAP_CURSOR_HEIGHT		0x9
 
 /** DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 9971c56..87792a5 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -87,6 +87,7 @@
 #define DRM_VMW_PARAM_MAX_SURF_MEMORY  7
 #define DRM_VMW_PARAM_3D_CAPS_SIZE     8
 #define DRM_VMW_PARAM_MAX_MOB_MEMORY   9
+#define DRM_VMW_PARAM_MAX_MOB_SIZE     10
 
 /**
  * struct drm_vmw_getparam_arg
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 1b8a0f4..b4d6909 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -558,7 +558,6 @@
 #define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, __u64)
 #define BTRFS_IOC_SPACE_INFO _IOWR(BTRFS_IOCTL_MAGIC, 20, \
 				    struct btrfs_ioctl_space_args)
-#define BTRFS_IOC_GLOBAL_RSV _IOR(BTRFS_IOCTL_MAGIC, 20, __u64)
 #define BTRFS_IOC_START_SYNC _IOR(BTRFS_IOCTL_MAGIC, 24, __u64)
 #define BTRFS_IOC_WAIT_SYNC  _IOW(BTRFS_IOCTL_MAGIC, 22, __u64)
 #define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 633b93c..e9a1d2d 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -128,22 +128,13 @@
  *	IPV6 extension headers
  */
 #if __UAPI_DEF_IPPROTO_V6
-enum {
-  IPPROTO_HOPOPTS = 0,		/* IPv6 hop-by-hop options      */
-#define IPPROTO_HOPOPTS		IPPROTO_HOPOPTS
-  IPPROTO_ROUTING = 43,		/* IPv6 routing header          */
-#define IPPROTO_ROUTING		IPPROTO_ROUTING
-  IPPROTO_FRAGMENT = 44,	/* IPv6 fragmentation header    */
-#define IPPROTO_FRAGMENT	IPPROTO_FRAGMENT
-  IPPROTO_ICMPV6 = 58,		/* ICMPv6                       */
-#define IPPROTO_ICMPV6		IPPROTO_ICMPV6
-  IPPROTO_NONE = 59,		/* IPv6 no next header          */
-#define IPPROTO_NONE		IPPROTO_NONE
-  IPPROTO_DSTOPTS = 60,		/* IPv6 destination options     */
-#define IPPROTO_DSTOPTS		IPPROTO_DSTOPTS
-  IPPROTO_MH = 135,		/* IPv6 mobility header         */
-#define IPPROTO_MH		IPPROTO_MH
-};
+#define IPPROTO_HOPOPTS		0	/* IPv6 hop-by-hop options	*/
+#define IPPROTO_ROUTING		43	/* IPv6 routing header		*/
+#define IPPROTO_FRAGMENT	44	/* IPv6 fragmentation header	*/
+#define IPPROTO_ICMPV6		58	/* ICMPv6			*/
+#define IPPROTO_NONE		59	/* IPv6 no next header		*/
+#define IPPROTO_DSTOPTS		60	/* IPv6 destination options	*/
+#define IPPROTO_MH		135	/* IPv6 mobility header		*/
 #endif /* __UAPI_DEF_IPPROTO_V6 */
 
 /*
diff --git a/include/uapi/linux/mic_ioctl.h b/include/uapi/linux/mic_ioctl.h
index 7fabba5..feb0b4c 100644
--- a/include/uapi/linux/mic_ioctl.h
+++ b/include/uapi/linux/mic_ioctl.h
@@ -39,7 +39,7 @@
 #else
 	struct iovec *iov;
 #endif
-	int iovcnt;
+	__u32 iovcnt;
 	__u8 vr_idx;
 	__u8 update_used;
 	__u32 out_len;
diff --git a/include/uapi/linux/nvme.h b/include/uapi/linux/nvme.h
index 989c04e..e5ab622 100644
--- a/include/uapi/linux/nvme.h
+++ b/include/uapi/linux/nvme.h
@@ -350,6 +350,16 @@
 	__u32			rsvd11[5];
 };
 
+struct nvme_abort_cmd {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__u32			rsvd1[9];
+	__le16			sqid;
+	__u16			cid;
+	__u32			rsvd11[5];
+};
+
 struct nvme_download_firmware {
 	__u8			opcode;
 	__u8			flags;
@@ -384,6 +394,7 @@
 		struct nvme_download_firmware dlfw;
 		struct nvme_format_cmd format;
 		struct nvme_dsm_cmd dsm;
+		struct nvme_abort_cmd abort;
 	};
 };
 
diff --git a/include/uapi/xen/Kbuild b/include/uapi/xen/Kbuild
index 61257cb..5c45962 100644
--- a/include/uapi/xen/Kbuild
+++ b/include/uapi/xen/Kbuild
@@ -1,3 +1,5 @@
 # UAPI Header export list
 header-y += evtchn.h
+header-y += gntalloc.h
+header-y += gntdev.h
 header-y += privcmd.h
diff --git a/include/xen/gntalloc.h b/include/uapi/xen/gntalloc.h
similarity index 100%
rename from include/xen/gntalloc.h
rename to include/uapi/xen/gntalloc.h
diff --git a/include/xen/gntdev.h b/include/uapi/xen/gntdev.h
similarity index 100%
rename from include/xen/gntdev.h
rename to include/uapi/xen/gntdev.h
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index 7ad033d..a5af2a2 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -191,15 +191,11 @@
 #define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr))
 
 int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
+		    struct gnttab_map_grant_ref *kmap_ops,
 		    struct page **pages, unsigned int count);
-int gnttab_map_refs_userspace(struct gnttab_map_grant_ref *map_ops,
-			      struct gnttab_map_grant_ref *kmap_ops,
-			      struct page **pages, unsigned int count);
 int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
+		      struct gnttab_map_grant_ref *kunmap_ops,
 		      struct page **pages, unsigned int count);
-int gnttab_unmap_refs_userspace(struct gnttab_unmap_grant_ref *unmap_ops,
-				struct gnttab_map_grant_ref *kunmap_ops,
-				struct page **pages, unsigned int count);
 
 /* Perform a batch of grant map/copy operations. Retry every batch slot
  * for which the hypervisor returns GNTST_eagain. This is typically due
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index ae665ac..32ec05a 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -113,13 +113,13 @@
  * it's less than the number provided by the backend. The indirect_grefs field
  * in blkif_request_indirect should be filled by the frontend with the
  * grant references of the pages that are holding the indirect segments.
- * This pages are filled with an array of blkif_request_segment_aligned
- * that hold the information about the segments. The number of indirect
- * pages to use is determined by the maximum number of segments
- * a indirect request contains. Every indirect page can contain a maximum
- * of 512 segments (PAGE_SIZE/sizeof(blkif_request_segment_aligned)),
- * so to calculate the number of indirect pages to use we have to do
- * ceil(indirect_segments/512).
+ * These pages are filled with an array of blkif_request_segment that hold the
+ * information about the segments. The number of indirect pages to use is
+ * determined by the number of segments an indirect request contains. Every
+ * indirect page can contain a maximum of
+ * (PAGE_SIZE / sizeof(struct blkif_request_segment)) segments, so to
+ * calculate the number of indirect pages to use we have to do
+ * ceil(indirect_segments / (PAGE_SIZE / sizeof(struct blkif_request_segment))).
  *
  * If a backend does not recognize BLKIF_OP_INDIRECT, it should *not*
  * create the "feature-max-indirect-segments" node!
@@ -135,13 +135,12 @@
 
 #define BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST 8
 
-struct blkif_request_segment_aligned {
-	grant_ref_t gref;        /* reference to I/O buffer frame        */
-	/* @first_sect: first sector in frame to transfer (inclusive).   */
-	/* @last_sect: last sector in frame to transfer (inclusive).     */
-	uint8_t     first_sect, last_sect;
-	uint16_t    _pad; /* padding to make it 8 bytes, so it's cache-aligned */
-} __attribute__((__packed__));
+struct blkif_request_segment {
+		grant_ref_t gref;        /* reference to I/O buffer frame        */
+		/* @first_sect: first sector in frame to transfer (inclusive).   */
+		/* @last_sect: last sector in frame to transfer (inclusive).     */
+		uint8_t     first_sect, last_sect;
+};
 
 struct blkif_request_rw {
 	uint8_t        nr_segments;  /* number of segments                   */
@@ -151,12 +150,7 @@
 #endif
 	uint64_t       id;           /* private guest value, echoed in resp  */
 	blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
-	struct blkif_request_segment {
-		grant_ref_t gref;        /* reference to I/O buffer frame        */
-		/* @first_sect: first sector in frame to transfer (inclusive).   */
-		/* @last_sect: last sector in frame to transfer (inclusive).     */
-		uint8_t     first_sect, last_sect;
-	} seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+	struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 } __attribute__((__packed__));
 
 struct blkif_request_discard {
diff --git a/include/xen/interface/xencomm.h b/include/xen/interface/xencomm.h
deleted file mode 100644
index ac45e07..0000000
--- a/include/xen/interface/xencomm.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/*
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to
- * deal in the Software without restriction, including without limitation the
- * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
- * sell copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- * Copyright (C) IBM Corp. 2006
- */
-
-#ifndef _XEN_XENCOMM_H_
-#define _XEN_XENCOMM_H_
-
-/* A xencomm descriptor is a scatter/gather list containing physical
- * addresses corresponding to a virtually contiguous memory area. The
- * hypervisor translates these physical addresses to machine addresses to copy
- * to and from the virtually contiguous area.
- */
-
-#define XENCOMM_MAGIC 0x58434F4D /* 'XCOM' */
-#define XENCOMM_INVALID (~0UL)
-
-struct xencomm_desc {
-    uint32_t magic;
-    uint32_t nr_addrs; /* the number of entries in address[] */
-    uint64_t address[0];
-};
-
-#endif /* _XEN_XENCOMM_H_ */
diff --git a/include/xen/xencomm.h b/include/xen/xencomm.h
deleted file mode 100644
index e43b039..0000000
--- a/include/xen/xencomm.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
- * Copyright (C) IBM Corp. 2006
- *
- * Authors: Hollis Blanchard <hollisb@us.ibm.com>
- *          Jerone Young <jyoung5@us.ibm.com>
- */
-
-#ifndef _LINUX_XENCOMM_H_
-#define _LINUX_XENCOMM_H_
-
-#include <xen/interface/xencomm.h>
-
-#define XENCOMM_MINI_ADDRS 3
-struct xencomm_mini {
-	struct xencomm_desc _desc;
-	uint64_t address[XENCOMM_MINI_ADDRS];
-};
-
-/* To avoid additionnal virt to phys conversion, an opaque structure is
-   presented.  */
-struct xencomm_handle;
-
-extern void xencomm_free(struct xencomm_handle *desc);
-extern struct xencomm_handle *xencomm_map(void *ptr, unsigned long bytes);
-extern struct xencomm_handle *__xencomm_map_no_alloc(void *ptr,
-			unsigned long bytes,  struct xencomm_mini *xc_area);
-
-#if 0
-#define XENCOMM_MINI_ALIGNED(xc_desc, n)				\
-	struct xencomm_mini xc_desc ## _base[(n)]			\
-	__attribute__((__aligned__(sizeof(struct xencomm_mini))));	\
-	struct xencomm_mini *xc_desc = &xc_desc ## _base[0];
-#else
-/*
- * gcc bug workaround:
- * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=16660
- * gcc doesn't handle properly stack variable with
- * __attribute__((__align__(sizeof(struct xencomm_mini))))
- */
-#define XENCOMM_MINI_ALIGNED(xc_desc, n)				\
-	unsigned char xc_desc ## _base[((n) + 1 ) *			\
-				       sizeof(struct xencomm_mini)];	\
-	struct xencomm_mini *xc_desc = (struct xencomm_mini *)		\
-		((unsigned long)xc_desc ## _base +			\
-		 (sizeof(struct xencomm_mini) -				\
-		  ((unsigned long)xc_desc ## _base) %			\
-		  sizeof(struct xencomm_mini)));
-#endif
-#define xencomm_map_no_alloc(ptr, bytes)			\
-	({ XENCOMM_MINI_ALIGNED(xc_desc, 1);			\
-		__xencomm_map_no_alloc(ptr, bytes, xc_desc); })
-
-/* provided by architecture code: */
-extern unsigned long xencomm_vtop(unsigned long vaddr);
-
-static inline void *xencomm_pa(void *ptr)
-{
-	return (void *)xencomm_vtop((unsigned long)ptr);
-}
-
-#define xen_guest_handle(hnd)  ((hnd).p)
-
-#endif /* _LINUX_XENCOMM_H_ */
diff --git a/init/main.c b/init/main.c
index 2fd9cef..9c7fd4c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -561,7 +561,6 @@
 	init_timers();
 	hrtimers_init();
 	softirq_init();
-	acpi_early_init();
 	timekeeping_init();
 	time_init();
 	sched_clock_postinit();
@@ -613,6 +612,7 @@
 	calibrate_delay();
 	pidmap_init();
 	anon_vma_init();
+	acpi_early_init();
 #ifdef CONFIG_X86
 	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
@@ -812,7 +812,7 @@
 static int run_init_process(const char *init_filename)
 {
 	argv_init[0] = init_filename;
-	return do_execve(init_filename,
+	return do_execve(getname_kernel(init_filename),
 		(const char __user *const __user *)argv_init,
 		(const char __user *const __user *)envp_init);
 }
diff --git a/ipc/compat.c b/ipc/compat.c
index f486b00..98b9016 100644
--- a/ipc/compat.c
+++ b/ipc/compat.c
@@ -430,9 +430,9 @@
 }
 
 COMPAT_SYSCALL_DEFINE5(msgrcv, int, msqid, compat_uptr_t, msgp,
-		       compat_ssize_t, msgsz, long, msgtyp, int, msgflg)
+		       compat_ssize_t, msgsz, compat_long_t, msgtyp, int, msgflg)
 {
-	return do_msgrcv(msqid, compat_ptr(msgp), (ssize_t)msgsz, msgtyp,
+	return do_msgrcv(msqid, compat_ptr(msgp), (ssize_t)msgsz, (long)msgtyp,
 			 msgflg, compat_do_msg_fill);
 }
 
@@ -498,7 +498,7 @@
 	return err;
 }
 
-long compat_sys_msgctl(int first, int second, void __user *uptr)
+COMPAT_SYSCALL_DEFINE3(msgctl, int, first, int, second, void __user *, uptr)
 {
 	int err, err2;
 	struct msqid64_ds m64;
@@ -668,7 +668,7 @@
 	return err;
 }
 
-long compat_sys_shmctl(int first, int second, void __user *uptr)
+COMPAT_SYSCALL_DEFINE3(shmctl, int, first, int, second, void __user *, uptr)
 {
 	void __user *p;
 	struct shmid64_ds s64;
@@ -749,8 +749,9 @@
 	return err;
 }
 
-long compat_sys_semtimedop(int semid, struct sembuf __user *tsems,
-		unsigned nsops, const struct compat_timespec __user *timeout)
+COMPAT_SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsems,
+		       unsigned, nsops,
+		       const struct compat_timespec __user *, timeout)
 {
 	struct timespec __user *ts64 = NULL;
 	if (timeout) {
diff --git a/ipc/compat_mq.c b/ipc/compat_mq.c
index 63d7c6de..d587472 100644
--- a/ipc/compat_mq.c
+++ b/ipc/compat_mq.c
@@ -46,9 +46,9 @@
 		| __put_user(attr->mq_curmsgs, &uattr->mq_curmsgs);
 }
 
-asmlinkage long compat_sys_mq_open(const char __user *u_name,
-			int oflag, compat_mode_t mode,
-			struct compat_mq_attr __user *u_attr)
+COMPAT_SYSCALL_DEFINE4(mq_open, const char __user *, u_name,
+		       int, oflag, compat_mode_t, mode,
+		       struct compat_mq_attr __user *, u_attr)
 {
 	void __user *p = NULL;
 	if (u_attr && oflag & O_CREAT) {
@@ -78,10 +78,10 @@
 	return 0;
 }
 
-asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes,
-			const char __user *u_msg_ptr,
-			size_t msg_len, unsigned int msg_prio,
-			const struct compat_timespec __user *u_abs_timeout)
+COMPAT_SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes,
+		       const char __user *, u_msg_ptr,
+		       compat_size_t, msg_len, unsigned int, msg_prio,
+		       const struct compat_timespec __user *, u_abs_timeout)
 {
 	struct timespec __user *u_ts;
 
@@ -92,10 +92,10 @@
 			msg_prio, u_ts);
 }
 
-asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes,
-			char __user *u_msg_ptr,
-			size_t msg_len, unsigned int __user *u_msg_prio,
-			const struct compat_timespec __user *u_abs_timeout)
+COMPAT_SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes,
+		       char __user *, u_msg_ptr,
+		       compat_size_t, msg_len, unsigned int __user *, u_msg_prio,
+		       const struct compat_timespec __user *, u_abs_timeout)
 {
 	struct timespec __user *u_ts;
 	if (compat_prepare_timeout(&u_ts, u_abs_timeout))
@@ -105,8 +105,8 @@
 			u_msg_prio, u_ts);
 }
 
-asmlinkage long compat_sys_mq_notify(mqd_t mqdes,
-			const struct compat_sigevent __user *u_notification)
+COMPAT_SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
+		       const struct compat_sigevent __user *, u_notification)
 {
 	struct sigevent __user *p = NULL;
 	if (u_notification) {
@@ -122,9 +122,9 @@
 	return sys_mq_notify(mqdes, p);
 }
 
-asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes,
-			const struct compat_mq_attr __user *u_mqstat,
-			struct compat_mq_attr __user *u_omqstat)
+COMPAT_SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
+		       const struct compat_mq_attr __user *, u_mqstat,
+		       struct compat_mq_attr __user *, u_omqstat)
 {
 	struct mq_attr mqstat;
 	struct mq_attr __user *p = compat_alloc_user_space(2 * sizeof(*p));
diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index 383d638..5bb8bfe 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -22,6 +22,16 @@
 	return which;
 }
 
+static int proc_mq_dointvec(ctl_table *table, int write,
+			    void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table mq_table;
+	memcpy(&mq_table, table, sizeof(mq_table));
+	mq_table.data = get_mq(table);
+
+	return proc_dointvec(&mq_table, write, buffer, lenp, ppos);
+}
+
 static int proc_mq_dointvec_minmax(ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -33,12 +43,10 @@
 					lenp, ppos);
 }
 #else
+#define proc_mq_dointvec NULL
 #define proc_mq_dointvec_minmax NULL
 #endif
 
-static int msg_queues_limit_min = MIN_QUEUESMAX;
-static int msg_queues_limit_max = HARD_QUEUESMAX;
-
 static int msg_max_limit_min = MIN_MSGMAX;
 static int msg_max_limit_max = HARD_MSGMAX;
 
@@ -51,9 +59,7 @@
 		.data		= &init_ipc_ns.mq_queues_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_mq_dointvec_minmax,
-		.extra1		= &msg_queues_limit_min,
-		.extra2		= &msg_queues_limit_max,
+		.proc_handler	= proc_mq_dointvec,
 	},
 	{
 		.procname	= "msg_max",
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index ccf1f9f..c3b3117 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -433,9 +433,9 @@
 		error = -EACCES;
 		goto out_unlock;
 	}
-	if (ipc_ns->mq_queues_count >= HARD_QUEUESMAX ||
-	    (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
-	     !capable(CAP_SYS_RESOURCE))) {
+
+	if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
+	    !capable(CAP_SYS_RESOURCE)) {
 		error = -ENOSPC;
 		goto out_unlock;
 	}
diff --git a/ipc/msg.c b/ipc/msg.c
index 245db11..6498531 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -901,6 +901,8 @@
 		return -EINVAL;
 
 	if (msgflg & MSG_COPY) {
+		if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT))
+			return -EINVAL;
 		copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
 		if (IS_ERR(copy))
 			return PTR_ERR(copy);
diff --git a/kernel/Makefile b/kernel/Makefile
index bc010ee..f2a8b62 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -18,11 +18,13 @@
 CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
+# cond_syscall is currently not LTO compatible
+CFLAGS_sys_ni.o = $(DISABLE_LTO)
+
 obj-y += sched/
 obj-y += locking/
 obj-y += power/
 obj-y += printk/
-obj-y += cpu/
 obj-y += irq/
 obj-y += rcu/
 
@@ -93,6 +95,7 @@
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
+obj-$(CONFIG_TORTURE_TEST) += torture.o
 
 $(obj)/configs.o: $(obj)/config_data.h
 
diff --git a/kernel/audit.c b/kernel/audit.c
index 34c5a23..95a20f3 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -182,7 +182,7 @@
 
 struct audit_reply {
 	__u32 portid;
-	pid_t pid;
+	struct net *net;	
 	struct sk_buff *skb;
 };
 
@@ -500,7 +500,7 @@
 {
 	struct audit_netlink_list *dest = _dest;
 	struct sk_buff *skb;
-	struct net *net = get_net_ns_by_pid(dest->pid);
+	struct net *net = dest->net;
 	struct audit_net *aunet = net_generic(net, audit_net_id);
 
 	/* wait for parent to finish and send an ACK */
@@ -510,6 +510,7 @@
 	while ((skb = __skb_dequeue(&dest->q)) != NULL)
 		netlink_unicast(aunet->nlsk, skb, dest->portid, 0);
 
+	put_net(net);
 	kfree(dest);
 
 	return 0;
@@ -543,7 +544,7 @@
 static int audit_send_reply_thread(void *arg)
 {
 	struct audit_reply *reply = (struct audit_reply *)arg;
-	struct net *net = get_net_ns_by_pid(reply->pid);
+	struct net *net = reply->net;
 	struct audit_net *aunet = net_generic(net, audit_net_id);
 
 	mutex_lock(&audit_cmd_mutex);
@@ -552,12 +553,13 @@
 	/* Ignore failure. It'll only happen if the sender goes away,
 	   because our timeout is set to infinite. */
 	netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0);
+	put_net(net);
 	kfree(reply);
 	return 0;
 }
 /**
  * audit_send_reply - send an audit reply message via netlink
- * @portid: netlink port to which to send reply
+ * @request_skb: skb of request we are replying to (used to target the reply)
  * @seq: sequence number
  * @type: audit message type
  * @done: done (last) flag
@@ -568,9 +570,11 @@
  * Allocates an skb, builds the netlink message, and sends it to the port id.
  * No failure notifications.
  */
-static void audit_send_reply(__u32 portid, int seq, int type, int done,
+static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done,
 			     int multi, const void *payload, int size)
 {
+	u32 portid = NETLINK_CB(request_skb).portid;
+	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
 	struct sk_buff *skb;
 	struct task_struct *tsk;
 	struct audit_reply *reply = kmalloc(sizeof(struct audit_reply),
@@ -583,8 +587,8 @@
 	if (!skb)
 		goto out;
 
+	reply->net = get_net(net);
 	reply->portid = portid;
-	reply->pid = task_pid_vnr(current);
 	reply->skb = skb;
 
 	tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
@@ -604,9 +608,19 @@
 	int err = 0;
 
 	/* Only support the initial namespaces for now. */
+	/*
+	 * We return ECONNREFUSED because it tricks userspace into thinking
+	 * that audit was not configured into the kernel.  Lots of users
+	 * configure their PAM stack (because that's what the distro does)
+	 * to reject login if unable to send messages to audit.  If we return
+	 * ECONNREFUSED the PAM stack thinks the kernel does not have audit
+	 * configured in and will let login proceed.  If we return EPERM
+	 * userspace will reject all logins.  This should be removed when we
+	 * support non init namespaces!!
+	 */
 	if ((current_user_ns() != &init_user_ns) ||
 	    (task_active_pid_ns(current) != &init_pid_ns))
-		return -EPERM;
+		return -ECONNREFUSED;
 
 	switch (msg_type) {
 	case AUDIT_LIST:
@@ -673,8 +687,7 @@
 
 	seq = nlmsg_hdr(skb)->nlmsg_seq;
 
-	audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
-			 &af, sizeof(af));
+	audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af));
 
 	return 0;
 }
@@ -794,8 +807,7 @@
 		s.backlog		= skb_queue_len(&audit_skb_queue);
 		s.version		= AUDIT_VERSION_LATEST;
 		s.backlog_wait_time	= audit_backlog_wait_time;
-		audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
-				 &s, sizeof(s));
+		audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
 		break;
 	}
 	case AUDIT_SET: {
@@ -905,7 +917,7 @@
 					   seq, data, nlmsg_len(nlh));
 		break;
 	case AUDIT_LIST_RULES:
-		err = audit_list_rules_send(NETLINK_CB(skb).portid, seq);
+		err = audit_list_rules_send(skb, seq);
 		break;
 	case AUDIT_TRIM:
 		audit_trim_trees();
@@ -970,8 +982,8 @@
 			memcpy(sig_data->ctx, ctx, len);
 			security_release_secctx(ctx, len);
 		}
-		audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_SIGNAL_INFO,
-				0, 0, sig_data, sizeof(*sig_data) + len);
+		audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0,
+				 sig_data, sizeof(*sig_data) + len);
 		kfree(sig_data);
 		break;
 	case AUDIT_TTY_GET: {
@@ -983,8 +995,7 @@
 		s.log_passwd = tsk->signal->audit_tty_log_passwd;
 		spin_unlock(&tsk->sighand->siglock);
 
-		audit_send_reply(NETLINK_CB(skb).portid, seq,
-				 AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
+		audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
 		break;
 	}
 	case AUDIT_TTY_SET: {
diff --git a/kernel/audit.h b/kernel/audit.h
index 57cc64d..8df13221 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -247,7 +247,7 @@
 
 struct audit_netlink_list {
 	__u32 portid;
-	pid_t pid;
+	struct net *net;
 	struct sk_buff_head q;
 };
 
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 67ccf0e..135944a 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -916,7 +916,7 @@
 				   struct fsnotify_mark *inode_mark,
 				   struct fsnotify_mark *vfsmount_mark,
 				   u32 mask, void *data, int data_type,
-				   const unsigned char *file_name)
+				   const unsigned char *file_name, u32 cookie)
 {
 	return 0;
 }
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 2596fac..70b4554 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -471,7 +471,7 @@
 				    struct fsnotify_mark *inode_mark,
 				    struct fsnotify_mark *vfsmount_mark,
 				    u32 mask, void *data, int data_type,
-				    const unsigned char *dname)
+				    const unsigned char *dname, u32 cookie)
 {
 	struct inode *inode;
 	struct audit_parent *parent;
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 14a78cc..92062fd 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -29,6 +29,8 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/security.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
 #include "audit.h"
 
 /*
@@ -1065,11 +1067,13 @@
 
 /**
  * audit_list_rules_send - list the audit rules
- * @portid: target portid for netlink audit messages
+ * @request_skb: skb of request we are replying to (used to target the reply)
  * @seq: netlink audit message sequence (serial) number
  */
-int audit_list_rules_send(__u32 portid, int seq)
+int audit_list_rules_send(struct sk_buff *request_skb, int seq)
 {
+	u32 portid = NETLINK_CB(request_skb).portid;
+	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
 	struct task_struct *tsk;
 	struct audit_netlink_list *dest;
 	int err = 0;
@@ -1083,8 +1087,8 @@
 	dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
 	if (!dest)
 		return -ENOMEM;
+	dest->net = get_net(net);
 	dest->portid = portid;
-	dest->pid = task_pid_vnr(current);
 	skb_queue_head_init(&dest->q);
 
 	mutex_lock(&audit_filter_mutex);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 10176cd..7aef2f4 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1719,7 +1719,7 @@
 	struct audit_context *context = current->audit_context;
 
 	BUG_ON(!context);
-	if (!context->in_syscall) {
+	if (!name->aname || !context->in_syscall) {
 #if AUDIT_DEBUG == 2
 		printk(KERN_ERR "%s:%d(:%d): final_putname(%p)\n",
 		       __FILE__, __LINE__, context->serial, name);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e2f46ba..0c753dd 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -886,7 +886,9 @@
 		 * per-subsystem and moved to css->id so that lookups are
 		 * successful until the target css is released.
 		 */
+		mutex_lock(&cgroup_mutex);
 		idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+		mutex_unlock(&cgroup_mutex);
 		cgrp->id = -1;
 
 		call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
@@ -1566,10 +1568,10 @@
 		mutex_lock(&cgroup_mutex);
 		mutex_lock(&cgroup_root_mutex);
 
-		root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp,
-					   0, 1, GFP_KERNEL);
-		if (root_cgrp->id < 0)
+		ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
+		if (ret < 0)
 			goto unlock_drop;
+		root_cgrp->id = ret;
 
 		/* Check for name clashes with existing mounts */
 		ret = -EBUSY;
@@ -2763,10 +2765,7 @@
 	 */
 	update_before = cgroup_serial_nr_next;
 
-	mutex_unlock(&cgroup_mutex);
-
 	/* add/rm files for all cgroups created before */
-	rcu_read_lock();
 	css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
 		struct cgroup *cgrp = css->cgroup;
 
@@ -2775,23 +2774,19 @@
 
 		inode = cgrp->dentry->d_inode;
 		dget(cgrp->dentry);
-		rcu_read_unlock();
-
 		dput(prev);
 		prev = cgrp->dentry;
 
+		mutex_unlock(&cgroup_mutex);
 		mutex_lock(&inode->i_mutex);
 		mutex_lock(&cgroup_mutex);
 		if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp))
 			ret = cgroup_addrm_files(cgrp, cfts, is_add);
-		mutex_unlock(&cgroup_mutex);
 		mutex_unlock(&inode->i_mutex);
-
-		rcu_read_lock();
 		if (ret)
 			break;
 	}
-	rcu_read_unlock();
+	mutex_unlock(&cgroup_mutex);
 	dput(prev);
 	deactivate_super(sb);
 	return ret;
@@ -2910,9 +2905,14 @@
 		 * We should check if the process is exiting, otherwise
 		 * it will race with cgroup_exit() in that the list
 		 * entry won't be deleted though the process has exited.
+		 * Do it while holding siglock so that we don't end up
+		 * racing against cgroup_exit().
 		 */
+		spin_lock_irq(&p->sighand->siglock);
 		if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
 			list_add(&p->cg_list, &task_css_set(p)->tasks);
+		spin_unlock_irq(&p->sighand->siglock);
+
 		task_unlock(p);
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
@@ -4112,17 +4112,17 @@
 
 	err = percpu_ref_init(&css->refcnt, css_release);
 	if (err)
-		goto err_free;
+		goto err_free_css;
 
 	init_css(css, ss, cgrp);
 
 	err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id);
 	if (err)
-		goto err_free;
+		goto err_free_percpu_ref;
 
 	err = online_css(css);
 	if (err)
-		goto err_free;
+		goto err_clear_dir;
 
 	dget(cgrp->dentry);
 	css_get(css->parent);
@@ -4138,8 +4138,11 @@
 
 	return 0;
 
-err_free:
+err_clear_dir:
+	cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id);
+err_free_percpu_ref:
 	percpu_ref_cancel_init(&css->refcnt);
+err_free_css:
 	ss->css_free(css);
 	return err;
 }
@@ -4158,7 +4161,7 @@
 	struct cgroup *cgrp;
 	struct cgroup_name *name;
 	struct cgroupfs_root *root = parent->root;
-	int ssid, err = 0;
+	int ssid, err;
 	struct cgroup_subsys *ss;
 	struct super_block *sb = root->sb;
 
@@ -4168,19 +4171,13 @@
 		return -ENOMEM;
 
 	name = cgroup_alloc_name(dentry);
-	if (!name)
+	if (!name) {
+		err = -ENOMEM;
 		goto err_free_cgrp;
+	}
 	rcu_assign_pointer(cgrp->name, name);
 
 	/*
-	 * Temporarily set the pointer to NULL, so idr_find() won't return
-	 * a half-baked cgroup.
-	 */
-	cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
-	if (cgrp->id < 0)
-		goto err_free_name;
-
-	/*
 	 * Only live parents can have children.  Note that the liveliness
 	 * check isn't strictly necessary because cgroup_mkdir() and
 	 * cgroup_rmdir() are fully synchronized by i_mutex; however, do it
@@ -4189,7 +4186,17 @@
 	 */
 	if (!cgroup_lock_live_group(parent)) {
 		err = -ENODEV;
-		goto err_free_id;
+		goto err_free_name;
+	}
+
+	/*
+	 * Temporarily set the pointer to NULL, so idr_find() won't return
+	 * a half-baked cgroup.
+	 */
+	cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
+	if (cgrp->id < 0) {
+		err = -ENOMEM;
+		goto err_unlock;
 	}
 
 	/* Grab a reference on the superblock so the hierarchy doesn't
@@ -4221,7 +4228,7 @@
 	 */
 	err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
 	if (err < 0)
-		goto err_unlock;
+		goto err_free_id;
 	lockdep_assert_held(&dentry->d_inode->i_mutex);
 
 	cgrp->serial_nr = cgroup_serial_nr_next++;
@@ -4257,12 +4264,12 @@
 
 	return 0;
 
-err_unlock:
-	mutex_unlock(&cgroup_mutex);
-	/* Release the reference count that we took on the superblock */
-	deactivate_super(sb);
 err_free_id:
 	idr_remove(&root->cgroup_idr, cgrp->id);
+	/* Release the reference count that we took on the superblock */
+	deactivate_super(sb);
+err_unlock:
+	mutex_unlock(&cgroup_mutex);
 err_free_name:
 	kfree(rcu_dereference_raw(cgrp->name));
 err_free_cgrp:
diff --git a/kernel/compat.c b/kernel/compat.c
index 0a09e48..488ff8c 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -110,8 +110,8 @@
 	return 0;
 }
 
-asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
-		struct timezone __user *tz)
+COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv,
+		       struct timezone __user *, tz)
 {
 	if (tv) {
 		struct timeval ktv;
@@ -127,8 +127,8 @@
 	return 0;
 }
 
-asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv,
-		struct timezone __user *tz)
+COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv,
+		       struct timezone __user *, tz)
 {
 	struct timespec kts;
 	struct timezone ktz;
@@ -236,8 +236,8 @@
 	return ret;
 }
 
-asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp,
-				     struct compat_timespec __user *rmtp)
+COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
+		       struct compat_timespec __user *, rmtp)
 {
 	struct timespec tu, rmt;
 	mm_segment_t oldfs;
@@ -328,7 +328,7 @@
 	return compat_jiffies_to_clock_t(clock_t_to_jiffies(x));
 }
 
-asmlinkage long compat_sys_times(struct compat_tms __user *tbuf)
+COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf)
 {
 	if (tbuf) {
 		struct tms tms;
@@ -354,7 +354,7 @@
  * types that can be passed to put_user()/get_user().
  */
 
-asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set)
+COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set)
 {
 	old_sigset_t s;
 	long ret;
@@ -424,8 +424,8 @@
 
 #endif
 
-asmlinkage long compat_sys_setrlimit(unsigned int resource,
-		struct compat_rlimit __user *rlim)
+COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource,
+		       struct compat_rlimit __user *, rlim)
 {
 	struct rlimit r;
 
@@ -443,8 +443,8 @@
 
 #ifdef COMPAT_RLIM_OLD_INFINITY
 
-asmlinkage long compat_sys_old_getrlimit(unsigned int resource,
-		struct compat_rlimit __user *rlim)
+COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
+		       struct compat_rlimit __user *, rlim)
 {
 	struct rlimit r;
 	int ret;
@@ -470,8 +470,8 @@
 
 #endif
 
-asmlinkage long compat_sys_getrlimit(unsigned int resource,
-		struct compat_rlimit __user *rlim)
+COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource,
+		       struct compat_rlimit __user *, rlim)
 {
 	struct rlimit r;
 	int ret;
@@ -596,9 +596,9 @@
 	return compat_get_bitmap(k, user_mask_ptr, len * 8);
 }
 
-asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid,
-					     unsigned int len,
-					     compat_ulong_t __user *user_mask_ptr)
+COMPAT_SYSCALL_DEFINE3(sched_setaffinity, compat_pid_t, pid,
+		       unsigned int, len,
+		       compat_ulong_t __user *, user_mask_ptr)
 {
 	cpumask_var_t new_mask;
 	int retval;
@@ -616,8 +616,8 @@
 	return retval;
 }
 
-asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
-					     compat_ulong_t __user *user_mask_ptr)
+COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t,  pid, unsigned int, len,
+		       compat_ulong_t __user *, user_mask_ptr)
 {
 	int ret;
 	cpumask_var_t mask;
@@ -662,9 +662,9 @@
 	return 0;
 }
 
-long compat_sys_timer_create(clockid_t which_clock,
-			struct compat_sigevent __user *timer_event_spec,
-			timer_t __user *created_timer_id)
+COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock,
+		       struct compat_sigevent __user *, timer_event_spec,
+		       timer_t __user *, created_timer_id)
 {
 	struct sigevent __user *event = NULL;
 
@@ -680,9 +680,9 @@
 	return sys_timer_create(which_clock, event, created_timer_id);
 }
 
-long compat_sys_timer_settime(timer_t timer_id, int flags,
-			  struct compat_itimerspec __user *new,
-			  struct compat_itimerspec __user *old)
+COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
+		       struct compat_itimerspec __user *, new,
+		       struct compat_itimerspec __user *, old)
 {
 	long err;
 	mm_segment_t oldfs;
@@ -703,8 +703,8 @@
 	return err;
 }
 
-long compat_sys_timer_gettime(timer_t timer_id,
-		struct compat_itimerspec __user *setting)
+COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
+		       struct compat_itimerspec __user *, setting)
 {
 	long err;
 	mm_segment_t oldfs;
@@ -720,8 +720,8 @@
 	return err;
 }
 
-long compat_sys_clock_settime(clockid_t which_clock,
-		struct compat_timespec __user *tp)
+COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock,
+		       struct compat_timespec __user *, tp)
 {
 	long err;
 	mm_segment_t oldfs;
@@ -737,8 +737,8 @@
 	return err;
 }
 
-long compat_sys_clock_gettime(clockid_t which_clock,
-		struct compat_timespec __user *tp)
+COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock,
+		       struct compat_timespec __user *, tp)
 {
 	long err;
 	mm_segment_t oldfs;
@@ -754,8 +754,8 @@
 	return err;
 }
 
-long compat_sys_clock_adjtime(clockid_t which_clock,
-		struct compat_timex __user *utp)
+COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock,
+		       struct compat_timex __user *, utp)
 {
 	struct timex txc;
 	mm_segment_t oldfs;
@@ -777,8 +777,8 @@
 	return ret;
 }
 
-long compat_sys_clock_getres(clockid_t which_clock,
-		struct compat_timespec __user *tp)
+COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock,
+		       struct compat_timespec __user *, tp)
 {
 	long err;
 	mm_segment_t oldfs;
@@ -818,9 +818,9 @@
 	return err;
 }
 
-long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
-			    struct compat_timespec __user *rqtp,
-			    struct compat_timespec __user *rmtp)
+COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
+		       struct compat_timespec __user *, rqtp,
+		       struct compat_timespec __user *, rmtp)
 {
 	long err;
 	mm_segment_t oldfs;
@@ -1010,7 +1010,7 @@
 
 /* compat_time_t is a 32 bit "long" and needs to get converted. */
 
-asmlinkage long compat_sys_time(compat_time_t __user * tloc)
+COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc)
 {
 	compat_time_t i;
 	struct timeval tv;
@@ -1026,7 +1026,7 @@
 	return i;
 }
 
-asmlinkage long compat_sys_stime(compat_time_t __user *tptr)
+COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr)
 {
 	struct timespec tv;
 	int err;
@@ -1046,7 +1046,7 @@
 
 #endif /* __ARCH_WANT_COMPAT_SYS_TIME */
 
-asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp)
+COMPAT_SYSCALL_DEFINE1(adjtimex, struct compat_timex __user *, utp)
 {
 	struct timex txc;
 	int err, ret;
@@ -1065,11 +1065,11 @@
 }
 
 #ifdef CONFIG_NUMA
-asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_pages,
-		compat_uptr_t __user *pages32,
-		const int __user *nodes,
-		int __user *status,
-		int flags)
+COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
+		       compat_uptr_t __user *, pages32,
+		       const int __user *, nodes,
+		       int __user *, status,
+		       int, flags)
 {
 	const void __user * __user *pages;
 	int i;
@@ -1085,10 +1085,10 @@
 	return sys_move_pages(pid, nr_pages, pages, nodes, status, flags);
 }
 
-asmlinkage long compat_sys_migrate_pages(compat_pid_t pid,
-			compat_ulong_t maxnode,
-			const compat_ulong_t __user *old_nodes,
-			const compat_ulong_t __user *new_nodes)
+COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid,
+		       compat_ulong_t, maxnode,
+		       const compat_ulong_t __user *, old_nodes,
+		       const compat_ulong_t __user *, new_nodes)
 {
 	unsigned long __user *old = NULL;
 	unsigned long __user *new = NULL;
diff --git a/kernel/cpu/Makefile b/kernel/cpu/Makefile
deleted file mode 100644
index 59ab052..0000000
--- a/kernel/cpu/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-y	= idle.o
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4410ac6..e6b1b66 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -974,12 +974,6 @@
  *    Temporarilly set tasks mems_allowed to target nodes of migration,
  *    so that the migration code can allocate pages on these nodes.
  *
- *    Call holding cpuset_mutex, so current's cpuset won't change
- *    during this call, as manage_mutex holds off any cpuset_attach()
- *    calls.  Therefore we don't need to take task_lock around the
- *    call to guarantee_online_mems(), as we know no one is changing
- *    our task's cpuset.
- *
  *    While the mm_struct we are migrating is typically from some
  *    other task, the task_struct mems_allowed that we are hacking
  *    is for our current task, which must allocate new pages for that
@@ -996,8 +990,10 @@
 
 	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
 
+	rcu_read_lock();
 	mems_cs = effective_nodemask_cpuset(task_cs(tsk));
 	guarantee_online_mems(mems_cs, &tsk->mems_allowed);
+	rcu_read_unlock();
 }
 
 /*
@@ -2486,9 +2482,9 @@
 
 	task_lock(current);
 	cs = nearest_hardwall_ancestor(task_cs(current));
+	allowed = node_isset(node, cs->mems_allowed);
 	task_unlock(current);
 
-	allowed = node_isset(node, cs->mems_allowed);
 	mutex_unlock(&callback_mutex);
 	return allowed;
 }
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 334b398..99982a7 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -1035,7 +1035,7 @@
  * otherwise as a quick means to stop program execution and "break" into
  * the debugger.
  */
-void kgdb_breakpoint(void)
+noinline void kgdb_breakpoint(void)
 {
 	atomic_inc(&kgdb_setting_breakpoint);
 	wmb(); /* Sync point before breakpoint */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 56003c6..661951a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -231,11 +231,29 @@
 #define NR_ACCUMULATED_SAMPLES 128
 static DEFINE_PER_CPU(u64, running_sample_length);
 
-void perf_sample_event_took(u64 sample_len_ns)
+static void perf_duration_warn(struct irq_work *w)
 {
+	u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
 	u64 avg_local_sample_len;
 	u64 local_samples_len;
+
+	local_samples_len = __get_cpu_var(running_sample_length);
+	avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
+
+	printk_ratelimited(KERN_WARNING
+			"perf interrupt took too long (%lld > %lld), lowering "
+			"kernel.perf_event_max_sample_rate to %d\n",
+			avg_local_sample_len, allowed_ns >> 1,
+			sysctl_perf_event_sample_rate);
+}
+
+static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn);
+
+void perf_sample_event_took(u64 sample_len_ns)
+{
 	u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
+	u64 avg_local_sample_len;
+	u64 local_samples_len;
 
 	if (allowed_ns == 0)
 		return;
@@ -263,13 +281,14 @@
 	sysctl_perf_event_sample_rate = max_samples_per_tick * HZ;
 	perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
 
-	printk_ratelimited(KERN_WARNING
-			"perf samples too long (%lld > %lld), lowering "
-			"kernel.perf_event_max_sample_rate to %d\n",
-			avg_local_sample_len, allowed_ns,
-			sysctl_perf_event_sample_rate);
-
 	update_perf_cpu_limits();
+
+	if (!irq_work_queue(&perf_duration_work)) {
+		early_printk("perf interrupt took too long (%lld > %lld), lowering "
+			     "kernel.perf_event_max_sample_rate to %d\n",
+			     avg_local_sample_len, allowed_ns >> 1,
+			     sysctl_perf_event_sample_rate);
+	}
 }
 
 static atomic64_t perf_event_id;
@@ -1714,7 +1733,7 @@
 	       struct perf_event_context *ctx)
 {
 	struct perf_event *event, *partial_group = NULL;
-	struct pmu *pmu = group_event->pmu;
+	struct pmu *pmu = ctx->pmu;
 	u64 now = ctx->time;
 	bool simulate = false;
 
@@ -2563,8 +2582,6 @@
 		if (cpuctx->ctx.nr_branch_stack > 0
 		    && pmu->flush_branch_stack) {
 
-			pmu = cpuctx->ctx.pmu;
-
 			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 
 			perf_pmu_disable(pmu);
@@ -6294,7 +6311,7 @@
  * Ensures all contexts with the same task_ctx_nr have the same
  * pmu_cpu_context too.
  */
-static void *find_pmu_context(int ctxn)
+static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
 {
 	struct pmu *pmu;
 
@@ -7856,14 +7873,14 @@
 static void __perf_event_exit_context(void *__info)
 {
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event, *tmp;
+	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
-	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
 		__perf_remove_from_context(event);
-	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
-		__perf_remove_from_context(event);
+	rcu_read_unlock();
 }
 
 static void perf_event_exit_cpu_context(int cpu)
@@ -7887,11 +7904,11 @@
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
+	perf_event_exit_cpu_context(cpu);
+
 	mutex_lock(&swhash->hlist_mutex);
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
-
-	perf_event_exit_cpu_context(cpu);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }
diff --git a/kernel/extable.c b/kernel/extable.c
index 763faf0..d8a6446 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -36,7 +36,7 @@
 extern struct exception_table_entry __stop___ex_table[];
 
 /* Cleared by build time tools if the table is already sorted. */
-u32 __initdata main_extable_sort_needed = 1;
+u32 __initdata __visible main_extable_sort_needed = 1;
 
 /* Sort the kernel's built-in exception table */
 void __init sort_main_extable(void)
diff --git a/kernel/fork.c b/kernel/fork.c
index a17621c..332688e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -237,6 +237,7 @@
 	WARN_ON(atomic_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	task_numa_free(tsk);
 	security_task_free(tsk);
 	exit_creds(tsk);
 	delayacct_tsk_free(tsk);
diff --git a/kernel/futex.c b/kernel/futex.c
index 5d17e3a..67dacaf 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -236,6 +236,7 @@
  * waiting on a futex.
  */
 struct futex_hash_bucket {
+	atomic_t waiters;
 	spinlock_t lock;
 	struct plist_head chain;
 } ____cacheline_aligned_in_smp;
@@ -255,22 +256,37 @@
 	smp_mb__after_atomic_inc();
 }
 
-static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+/*
+ * Reflects a new waiter being added to the waitqueue.
+ */
+static inline void hb_waiters_inc(struct futex_hash_bucket *hb)
 {
 #ifdef CONFIG_SMP
+	atomic_inc(&hb->waiters);
 	/*
-	 * Tasks trying to enter the critical region are most likely
-	 * potential waiters that will be added to the plist. Ensure
-	 * that wakers won't miss to-be-slept tasks in the window between
-	 * the wait call and the actual plist_add.
+	 * Full barrier (A), see the ordering comment above.
 	 */
-	if (spin_is_locked(&hb->lock))
-		return true;
-	smp_rmb(); /* Make sure we check the lock state first */
+	smp_mb__after_atomic_inc();
+#endif
+}
 
-	return !plist_head_empty(&hb->chain);
+/*
+ * Reflects a waiter being removed from the waitqueue by wakeup
+ * paths.
+ */
+static inline void hb_waiters_dec(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	atomic_dec(&hb->waiters);
+#endif
+}
+
+static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	return atomic_read(&hb->waiters);
 #else
-	return true;
+	return 1;
 #endif
 }
 
@@ -956,6 +972,7 @@
 
 	hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
 	plist_del(&q->list, &hb->chain);
+	hb_waiters_dec(hb);
 }
 
 /*
@@ -1259,7 +1276,9 @@
 	 */
 	if (likely(&hb1->chain != &hb2->chain)) {
 		plist_del(&q->list, &hb1->chain);
+		hb_waiters_dec(hb1);
 		plist_add(&q->list, &hb2->chain);
+		hb_waiters_inc(hb2);
 		q->lock_ptr = &hb2->lock;
 	}
 	get_futex_key_refs(key2);
@@ -1602,6 +1621,17 @@
 	struct futex_hash_bucket *hb;
 
 	hb = hash_futex(&q->key);
+
+	/*
+	 * Increment the counter before taking the lock so that
+	 * a potential waker won't miss a to-be-slept task that is
+	 * waiting for the spinlock. This is safe as all queue_lock()
+	 * users end up calling queue_me(). Similarly, for housekeeping,
+	 * decrement the counter at queue_unlock() when some error has
+	 * occurred and we don't end up adding the task to the list.
+	 */
+	hb_waiters_inc(hb);
+
 	q->lock_ptr = &hb->lock;
 
 	spin_lock(&hb->lock); /* implies MB (A) */
@@ -1613,6 +1643,7 @@
 	__releases(&hb->lock)
 {
 	spin_unlock(&hb->lock);
+	hb_waiters_dec(hb);
 }
 
 /**
@@ -2344,6 +2375,7 @@
 		 * Unqueue the futex_q and determine which it was.
 		 */
 		plist_del(&q->list, &hb->chain);
+		hb_waiters_dec(hb);
 
 		/* Handle spurious wakeups gracefully */
 		ret = -EWOULDBLOCK;
@@ -2886,6 +2918,7 @@
 	futex_detect_cmpxchg();
 
 	for (i = 0; i < futex_hashsize; i++) {
+		atomic_set(&futex_queues[i].waiters, 0);
 		plist_head_init(&futex_queues[i].chain);
 		spin_lock_init(&futex_queues[i].lock);
 	}
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 4a1fef0..07cbdfe 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -40,6 +40,7 @@
 # Generic configurable interrupt chip implementation
 config GENERIC_IRQ_CHIP
        bool
+       select IRQ_DOMAIN
 
 # Generic irq_domain hw <--> linux irq number translation
 config IRQ_DOMAIN
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index bd8e788..1ef0606 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -73,6 +73,51 @@
 EXPORT_SYMBOL(devm_request_threaded_irq);
 
 /**
+ *	devm_request_any_context_irq - allocate an interrupt line for a managed device
+ *	@dev: device to request interrupt for
+ *	@irq: Interrupt line to allocate
+ *	@handler: Function to be called when the IRQ occurs
+ *	@thread_fn: function to be called in a threaded interrupt context. NULL
+ *		    for devices which handle everything in @handler
+ *	@irqflags: Interrupt type flags
+ *	@devname: An ascii name for the claiming device
+ *	@dev_id: A cookie passed back to the handler function
+ *
+ *	Except for the extra @dev argument, this function takes the
+ *	same arguments and performs the same function as
+ *	request_any_context_irq().  IRQs requested with this function will be
+ *	automatically freed on driver detach.
+ *
+ *	If an IRQ allocated with this function needs to be freed
+ *	separately, devm_free_irq() must be used.
+ */
+int devm_request_any_context_irq(struct device *dev, unsigned int irq,
+			      irq_handler_t handler, unsigned long irqflags,
+			      const char *devname, void *dev_id)
+{
+	struct irq_devres *dr;
+	int rc;
+
+	dr = devres_alloc(devm_irq_release, sizeof(struct irq_devres),
+			  GFP_KERNEL);
+	if (!dr)
+		return -ENOMEM;
+
+	rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id);
+	if (rc) {
+		devres_free(dr);
+		return rc;
+	}
+
+	dr->irq = irq;
+	dr->dev_id = dev_id;
+	devres_add(dev, dr);
+
+	return 0;
+}
+EXPORT_SYMBOL(devm_request_any_context_irq);
+
+/**
  *	devm_free_irq - free an interrupt
  *	@dev: device to free interrupt for
  *	@irq: Interrupt line to free
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 192a302..8ab8e93 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -274,6 +274,7 @@
 {
 	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
 }
+EXPORT_SYMBOL(irq_to_desc);
 
 static void free_desc(unsigned int irq)
 {
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index cf68bb3..f140337 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -10,6 +10,7 @@
 #include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/of_irq.h>
 #include <linux/topology.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 481a13c..d3bf660 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -802,8 +802,7 @@
 
 static void wake_threads_waitq(struct irq_desc *desc)
 {
-	if (atomic_dec_and_test(&desc->threads_active) &&
-	    waitqueue_active(&desc->wait_for_threads))
+	if (atomic_dec_and_test(&desc->threads_active))
 		wake_up(&desc->wait_for_threads);
 }
 
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 55fcce6..a82170e 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -61,11 +61,11 @@
  *
  * Can be re-enqueued while the callback is still in progress.
  */
-void irq_work_queue(struct irq_work *work)
+bool irq_work_queue(struct irq_work *work)
 {
 	/* Only queue if not already pending */
 	if (!irq_work_claim(work))
-		return;
+		return false;
 
 	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
@@ -83,6 +83,8 @@
 	}
 
 	preempt_enable();
+
+	return true;
 }
 EXPORT_SYMBOL_GPL(irq_work_queue);
 
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 60bafbe..45601cf 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1039,10 +1039,10 @@
 {}
 
 #ifdef CONFIG_COMPAT
-asmlinkage long compat_sys_kexec_load(unsigned long entry,
-				unsigned long nr_segments,
-				struct compat_kexec_segment __user *segments,
-				unsigned long flags)
+COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry,
+		       compat_ulong_t, nr_segments,
+		       struct compat_kexec_segment __user *, segments,
+		       compat_ulong_t, flags)
 {
 	struct compat_kexec_segment in;
 	struct kexec_segment out, __user *ksegments;
diff --git a/kernel/kmod.c b/kernel/kmod.c
index b086006..6b375af 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -239,7 +239,7 @@
 
 	commit_creds(new);
 
-	retval = do_execve(sub_info->path,
+	retval = do_execve(getname_kernel(sub_info->path),
 			   (const char __user *const __user *)sub_info->argv,
 			   (const char __user *const __user *)sub_info->envp);
 	if (!retval)
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index d945a94..e660964 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -19,6 +19,8 @@
 #include <linux/sched.h>
 #include <linux/capability.h>
 
+#include <linux/rcupdate.h>	/* rcu_expedited */
+
 #define KERNEL_ATTR_RO(_name) \
 static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
 
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 2a9ee96..306a76b 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -23,3 +23,4 @@
 obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
 obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
+obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index bf0c6b0..b0e9467 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2557,7 +2557,7 @@
 	debug_atomic_inc(hardirqs_on_events);
 }
 
-void trace_hardirqs_on_caller(unsigned long ip)
+__visible void trace_hardirqs_on_caller(unsigned long ip)
 {
 	time_hardirqs_on(CALLER_ADDR0, ip);
 
@@ -2610,7 +2610,7 @@
 /*
  * Hardirqs were disabled:
  */
-void trace_hardirqs_off_caller(unsigned long ip)
+__visible void trace_hardirqs_off_caller(unsigned long ip)
 {
 	struct task_struct *curr = current;
 
@@ -4188,7 +4188,7 @@
 }
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
-void lockdep_sys_exit(void)
+asmlinkage void lockdep_sys_exit(void)
 {
 	struct task_struct *curr = current;
 
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
new file mode 100644
index 0000000..f26b1a1
--- /dev/null
+++ b/kernel/locking/locktorture.c
@@ -0,0 +1,452 @@
+/*
+ * Module-based torture test facility for locking
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2014
+ *
+ * Author: Paul E. McKenney <paulmck@us.ibm.com>
+ *	Based on kernel/rcu/torture.c.
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/freezer.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/trace_clock.h>
+#include <asm/byteorder.h>
+#include <linux/torture.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+
+torture_param(int, nwriters_stress, -1,
+	     "Number of write-locking stress-test threads");
+torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
+torture_param(int, onoff_interval, 0,
+	     "Time between CPU hotplugs (s), 0=disable");
+torture_param(int, shuffle_interval, 3,
+	     "Number of jiffies between shuffles, 0=disable");
+torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
+torture_param(int, stat_interval, 60,
+	     "Number of seconds between stats printk()s");
+torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
+torture_param(bool, verbose, true,
+	     "Enable verbose debugging printk()s");
+
+static char *torture_type = "spin_lock";
+module_param(torture_type, charp, 0444);
+MODULE_PARM_DESC(torture_type,
+		 "Type of lock to torture (spin_lock, spin_lock_irq, ...)");
+
+static atomic_t n_lock_torture_errors;
+
+static struct task_struct *stats_task;
+static struct task_struct **writer_tasks;
+
+static int nrealwriters_stress;
+static bool lock_is_write_held;
+
+struct lock_writer_stress_stats {
+	long n_write_lock_fail;
+	long n_write_lock_acquired;
+};
+static struct lock_writer_stress_stats *lwsa;
+
+#if defined(MODULE) || defined(CONFIG_LOCK_TORTURE_TEST_RUNNABLE)
+#define LOCKTORTURE_RUNNABLE_INIT 1
+#else
+#define LOCKTORTURE_RUNNABLE_INIT 0
+#endif
+int locktorture_runnable = LOCKTORTURE_RUNNABLE_INIT;
+module_param(locktorture_runnable, int, 0444);
+MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at boot");
+
+/* Forward reference. */
+static void lock_torture_cleanup(void);
+
+/*
+ * Operations vector for selecting different types of tests.
+ */
+struct lock_torture_ops {
+	void (*init)(void);
+	int (*writelock)(void);
+	void (*write_delay)(struct torture_random_state *trsp);
+	void (*writeunlock)(void);
+	unsigned long flags;
+	const char *name;
+};
+
+static struct lock_torture_ops *cur_ops;
+
+/*
+ * Definitions for lock torture testing.
+ */
+
+static int torture_lock_busted_write_lock(void)
+{
+	return 0;  /* BUGGY, do not use in real life!!! */
+}
+
+static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
+{
+	const unsigned long longdelay_us = 100;
+
+	/* We want a long delay occasionally to force massive contention.  */
+	if (!(torture_random(trsp) %
+	      (nrealwriters_stress * 2000 * longdelay_us)))
+		mdelay(longdelay_us);
+#ifdef CONFIG_PREEMPT
+	if (!(torture_random(trsp) % (nrealwriters_stress * 20000)))
+		preempt_schedule();  /* Allow test to be preempted. */
+#endif
+}
+
+static void torture_lock_busted_write_unlock(void)
+{
+	  /* BUGGY, do not use in real life!!! */
+}
+
+static struct lock_torture_ops lock_busted_ops = {
+	.writelock	= torture_lock_busted_write_lock,
+	.write_delay	= torture_lock_busted_write_delay,
+	.writeunlock	= torture_lock_busted_write_unlock,
+	.name		= "lock_busted"
+};
+
+static DEFINE_SPINLOCK(torture_spinlock);
+
+static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock)
+{
+	spin_lock(&torture_spinlock);
+	return 0;
+}
+
+static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
+{
+	const unsigned long shortdelay_us = 2;
+	const unsigned long longdelay_us = 100;
+
+	/* We want a short delay mostly to emulate likely code, and
+	 * we want a long delay occasionally to force massive contention.
+	 */
+	if (!(torture_random(trsp) %
+	      (nrealwriters_stress * 2000 * longdelay_us)))
+		mdelay(longdelay_us);
+	if (!(torture_random(trsp) %
+	      (nrealwriters_stress * 2 * shortdelay_us)))
+		udelay(shortdelay_us);
+#ifdef CONFIG_PREEMPT
+	if (!(torture_random(trsp) % (nrealwriters_stress * 20000)))
+		preempt_schedule();  /* Allow test to be preempted. */
+#endif
+}
+
+static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock)
+{
+	spin_unlock(&torture_spinlock);
+}
+
+static struct lock_torture_ops spin_lock_ops = {
+	.writelock	= torture_spin_lock_write_lock,
+	.write_delay	= torture_spin_lock_write_delay,
+	.writeunlock	= torture_spin_lock_write_unlock,
+	.name		= "spin_lock"
+};
+
+static int torture_spin_lock_write_lock_irq(void)
+__acquires(torture_spinlock_irq)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&torture_spinlock, flags);
+	cur_ops->flags = flags;
+	return 0;
+}
+
+static void torture_lock_spin_write_unlock_irq(void)
+__releases(torture_spinlock)
+{
+	spin_unlock_irqrestore(&torture_spinlock, cur_ops->flags);
+}
+
+static struct lock_torture_ops spin_lock_irq_ops = {
+	.writelock	= torture_spin_lock_write_lock_irq,
+	.write_delay	= torture_spin_lock_write_delay,
+	.writeunlock	= torture_lock_spin_write_unlock_irq,
+	.name		= "spin_lock_irq"
+};
+
+/*
+ * Lock torture writer kthread.  Repeatedly acquires and releases
+ * the lock, checking for duplicate acquisitions.
+ */
+static int lock_torture_writer(void *arg)
+{
+	struct lock_writer_stress_stats *lwsp = arg;
+	static DEFINE_TORTURE_RANDOM(rand);
+
+	VERBOSE_TOROUT_STRING("lock_torture_writer task started");
+	set_user_nice(current, 19);
+
+	do {
+		schedule_timeout_uninterruptible(1);
+		cur_ops->writelock();
+		if (WARN_ON_ONCE(lock_is_write_held))
+			lwsp->n_write_lock_fail++;
+		lock_is_write_held = 1;
+		lwsp->n_write_lock_acquired++;
+		cur_ops->write_delay(&rand);
+		lock_is_write_held = 0;
+		cur_ops->writeunlock();
+		stutter_wait("lock_torture_writer");
+	} while (!torture_must_stop());
+	torture_kthread_stopping("lock_torture_writer");
+	return 0;
+}
+
+/*
+ * Create an lock-torture-statistics message in the specified buffer.
+ */
+static void lock_torture_printk(char *page)
+{
+	bool fail = 0;
+	int i;
+	long max = 0;
+	long min = lwsa[0].n_write_lock_acquired;
+	long long sum = 0;
+
+	for (i = 0; i < nrealwriters_stress; i++) {
+		if (lwsa[i].n_write_lock_fail)
+			fail = true;
+		sum += lwsa[i].n_write_lock_acquired;
+		if (max < lwsa[i].n_write_lock_fail)
+			max = lwsa[i].n_write_lock_fail;
+		if (min > lwsa[i].n_write_lock_fail)
+			min = lwsa[i].n_write_lock_fail;
+	}
+	page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page,
+			"Writes:  Total: %lld  Max/Min: %ld/%ld %s  Fail: %d %s\n",
+			sum, max, min, max / 2 > min ? "???" : "",
+			fail, fail ? "!!!" : "");
+	if (fail)
+		atomic_inc(&n_lock_torture_errors);
+}
+
+/*
+ * Print torture statistics.  Caller must ensure that there is only one
+ * call to this function at a given time!!!  This is normally accomplished
+ * by relying on the module system to only have one copy of the module
+ * loaded, and then by giving the lock_torture_stats kthread full control
+ * (or the init/cleanup functions when lock_torture_stats thread is not
+ * running).
+ */
+static void lock_torture_stats_print(void)
+{
+	int size = nrealwriters_stress * 200 + 8192;
+	char *buf;
+
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf) {
+		pr_err("lock_torture_stats_print: Out of memory, need: %d",
+		       size);
+		return;
+	}
+	lock_torture_printk(buf);
+	pr_alert("%s", buf);
+	kfree(buf);
+}
+
+/*
+ * Periodically prints torture statistics, if periodic statistics printing
+ * was specified via the stat_interval module parameter.
+ *
+ * No need to worry about fullstop here, since this one doesn't reference
+ * volatile state or register callbacks.
+ */
+static int lock_torture_stats(void *arg)
+{
+	VERBOSE_TOROUT_STRING("lock_torture_stats task started");
+	do {
+		schedule_timeout_interruptible(stat_interval * HZ);
+		lock_torture_stats_print();
+		torture_shutdown_absorb("lock_torture_stats");
+	} while (!torture_must_stop());
+	torture_kthread_stopping("lock_torture_stats");
+	return 0;
+}
+
+static inline void
+lock_torture_print_module_parms(struct lock_torture_ops *cur_ops,
+				const char *tag)
+{
+	pr_alert("%s" TORTURE_FLAG
+		 "--- %s: nwriters_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
+		 torture_type, tag, nrealwriters_stress, stat_interval, verbose,
+		 shuffle_interval, stutter, shutdown_secs,
+		 onoff_interval, onoff_holdoff);
+}
+
+static void lock_torture_cleanup(void)
+{
+	int i;
+
+	if (torture_cleanup())
+		return;
+
+	if (writer_tasks) {
+		for (i = 0; i < nrealwriters_stress; i++)
+			torture_stop_kthread(lock_torture_writer,
+					     writer_tasks[i]);
+		kfree(writer_tasks);
+		writer_tasks = NULL;
+	}
+
+	torture_stop_kthread(lock_torture_stats, stats_task);
+	lock_torture_stats_print();  /* -After- the stats thread is stopped! */
+
+	if (atomic_read(&n_lock_torture_errors))
+		lock_torture_print_module_parms(cur_ops,
+						"End of test: FAILURE");
+	else if (torture_onoff_failures())
+		lock_torture_print_module_parms(cur_ops,
+						"End of test: LOCK_HOTPLUG");
+	else
+		lock_torture_print_module_parms(cur_ops,
+						"End of test: SUCCESS");
+}
+
+static int __init lock_torture_init(void)
+{
+	int i;
+	int firsterr = 0;
+	static struct lock_torture_ops *torture_ops[] = {
+		&lock_busted_ops, &spin_lock_ops, &spin_lock_irq_ops,
+	};
+
+	torture_init_begin(torture_type, verbose, &locktorture_runnable);
+
+	/* Process args and tell the world that the torturer is on the job. */
+	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
+		cur_ops = torture_ops[i];
+		if (strcmp(torture_type, cur_ops->name) == 0)
+			break;
+	}
+	if (i == ARRAY_SIZE(torture_ops)) {
+		pr_alert("lock-torture: invalid torture type: \"%s\"\n",
+			 torture_type);
+		pr_alert("lock-torture types:");
+		for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
+			pr_alert(" %s", torture_ops[i]->name);
+		pr_alert("\n");
+		torture_init_end();
+		return -EINVAL;
+	}
+	if (cur_ops->init)
+		cur_ops->init(); /* no "goto unwind" prior to this point!!! */
+
+	if (nwriters_stress >= 0)
+		nrealwriters_stress = nwriters_stress;
+	else
+		nrealwriters_stress = 2 * num_online_cpus();
+	lock_torture_print_module_parms(cur_ops, "Start of test");
+
+	/* Initialize the statistics so that each run gets its own numbers. */
+
+	lock_is_write_held = 0;
+	lwsa = kmalloc(sizeof(*lwsa) * nrealwriters_stress, GFP_KERNEL);
+	if (lwsa == NULL) {
+		VERBOSE_TOROUT_STRING("lwsa: Out of memory");
+		firsterr = -ENOMEM;
+		goto unwind;
+	}
+	for (i = 0; i < nrealwriters_stress; i++) {
+		lwsa[i].n_write_lock_fail = 0;
+		lwsa[i].n_write_lock_acquired = 0;
+	}
+
+	/* Start up the kthreads. */
+
+	if (onoff_interval > 0) {
+		firsterr = torture_onoff_init(onoff_holdoff * HZ,
+					      onoff_interval * HZ);
+		if (firsterr)
+			goto unwind;
+	}
+	if (shuffle_interval > 0) {
+		firsterr = torture_shuffle_init(shuffle_interval);
+		if (firsterr)
+			goto unwind;
+	}
+	if (shutdown_secs > 0) {
+		firsterr = torture_shutdown_init(shutdown_secs,
+						 lock_torture_cleanup);
+		if (firsterr)
+			goto unwind;
+	}
+	if (stutter > 0) {
+		firsterr = torture_stutter_init(stutter);
+		if (firsterr)
+			goto unwind;
+	}
+
+	writer_tasks = kzalloc(nrealwriters_stress * sizeof(writer_tasks[0]),
+			       GFP_KERNEL);
+	if (writer_tasks == NULL) {
+		VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
+		firsterr = -ENOMEM;
+		goto unwind;
+	}
+	for (i = 0; i < nrealwriters_stress; i++) {
+		firsterr = torture_create_kthread(lock_torture_writer, &lwsa[i],
+						  writer_tasks[i]);
+		if (firsterr)
+			goto unwind;
+	}
+	if (stat_interval > 0) {
+		firsterr = torture_create_kthread(lock_torture_stats, NULL,
+						  stats_task);
+		if (firsterr)
+			goto unwind;
+	}
+	torture_init_end();
+	return 0;
+
+unwind:
+	torture_init_end();
+	lock_torture_cleanup();
+	return firsterr;
+}
+
+module_init(lock_torture_init);
+module_exit(lock_torture_cleanup);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 14fe72c..bc73d33 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -75,8 +75,7 @@
  * We also put the fastpath first in the kernel image, to make sure the
  * branch is predicted by the CPU as default-untaken.
  */
-static __used noinline void __sched
-__mutex_lock_slowpath(atomic_t *lock_count);
+__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
 
 /**
  * mutex_lock - acquire the mutex
@@ -189,7 +188,8 @@
 }
 #endif
 
-static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
+__visible __used noinline
+void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
 
 /**
  * mutex_unlock - release the mutex
@@ -716,7 +716,7 @@
 /*
  * Release the lock, slowpath:
  */
-static __used noinline void
+__visible void
 __mutex_unlock_slowpath(atomic_t *lock_count)
 {
 	__mutex_unlock_common_slowpath(lock_count, 1);
@@ -773,7 +773,7 @@
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
-static __used noinline void __sched
+__visible void __sched
 __mutex_lock_slowpath(atomic_t *lock_count)
 {
 	struct mutex *lock = container_of(lock_count, struct mutex, count);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2e960a2..aa4dff0 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -213,6 +213,18 @@
 }
 
 /*
+ * Called by sched_setscheduler() to check whether the priority change
+ * is overruled by a possible priority boosting.
+ */
+int rt_mutex_check_prio(struct task_struct *task, int newprio)
+{
+	if (!task_has_pi_waiters(task))
+		return 0;
+
+	return task_top_pi_waiter(task)->task->prio <= newprio;
+}
+
+/*
  * Adjust the priority of a task, after its pi_waiters got modified.
  *
  * This can be both boosting and unboosting. task->pi_lock must be held.
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 19c5fa9..1d66e08 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -143,6 +143,7 @@
 /*
  * wait for the read lock to be granted
  */
+__visible
 struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 {
 	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
@@ -190,6 +191,7 @@
 /*
  * wait until we successfully acquire the write lock
  */
+__visible
 struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
 {
 	long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS;
@@ -252,6 +254,7 @@
  * handle waking up a waiter on the semaphore
  * - up_read/up_write has decremented the active part of count if we come here
  */
+__visible
 struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
@@ -272,6 +275,7 @@
  * - caller incremented waiting part of count and discovered it still negative
  * - just wake up any readers at the front of the queue
  */
+__visible
 struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
diff --git a/kernel/module.c b/kernel/module.c
index d24fcf2..8dc7f5e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1015,7 +1015,7 @@
 		buf[l++] = 'C';
 	/*
 	 * TAINT_FORCED_RMMOD: could be added.
-	 * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
+	 * TAINT_CPU_OUT_OF_SPEC, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
 	 * apply to modules.
 	 */
 	return l;
@@ -1948,6 +1948,10 @@
 
 		switch (sym[i].st_shndx) {
 		case SHN_COMMON:
+			/* Ignore common symbols */
+			if (!strncmp(name, "__gnu_lto", 9))
+				break;
+
 			/* We compiled with -fno-common.  These are not
 			   supposed to happen.  */
 			pr_debug("Common symbol: %s\n", name);
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 2d5cc4c..db4c8b0 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -309,7 +309,7 @@
 	 * racy then it does not matter what the result of the test
 	 * is, we re-check the list after having taken the lock anyway:
 	 */
-	if (rcu_dereference_raw(nh->head)) {
+	if (rcu_access_pointer(nh->head)) {
 		down_read(&nh->rwsem);
 		ret = notifier_call_chain(&nh->head, val, v, nr_to_call,
 					nr_calls);
diff --git a/kernel/panic.c b/kernel/panic.c
index 6d63003..cca8a91 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -199,7 +199,7 @@
 static const struct tnt tnts[] = {
 	{ TAINT_PROPRIETARY_MODULE,	'P', 'G' },
 	{ TAINT_FORCED_MODULE,		'F', ' ' },
-	{ TAINT_UNSAFE_SMP,		'S', ' ' },
+	{ TAINT_CPU_OUT_OF_SPEC,	'S', ' ' },
 	{ TAINT_FORCED_RMMOD,		'R', ' ' },
 	{ TAINT_MACHINE_CHECK,		'M', ' ' },
 	{ TAINT_BAD_PAGE,		'B', ' ' },
@@ -459,7 +459,7 @@
  * Called when gcc's -fstack-protector feature is used, and
  * gcc detects corruption of the on-stack canary value
  */
-void __stack_chk_fail(void)
+__visible void __stack_chk_fail(void)
 {
 	panic("stack-protector: Kernel stack is corrupted in: %p\n",
 		__builtin_return_address(0));
diff --git a/kernel/power/console.c b/kernel/power/console.c
index eacb8bd..aba9c54 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -9,6 +9,7 @@
 #include <linux/kbd_kern.h>
 #include <linux/vt.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include "power.h"
 
 #define SUSPEND_CONSOLE	(MAX_NR_CONSOLES-1)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index b1d255f..4dae9cb 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1076,7 +1076,6 @@
 		next_seq = log_next_seq;
 
 		len = 0;
-		prev = 0;
 		while (len >= 0 && seq < next_seq) {
 			struct printk_log *msg = log_from_idx(idx);
 			int textlen;
@@ -2788,7 +2787,6 @@
 	next_idx = idx;
 
 	l = 0;
-	prev = 0;
 	while (seq < dumper->next_seq) {
 		struct printk_log *msg = log_from_idx(idx);
 
diff --git a/kernel/profile.c b/kernel/profile.c
index 6631e1e..ebdd9c1 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -549,14 +549,14 @@
 		struct page *page;
 
 		page = alloc_pages_exact_node(node,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;
 		per_cpu(cpu_profile_hits, cpu)[1]
 				= (struct profile_hit *)page_address(page);
 		page = alloc_pages_exact_node(node,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1f4bcb3..adf9862 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -1180,8 +1180,8 @@
 	return ret;
 }
 
-asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
-				  compat_long_t addr, compat_long_t data)
+COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid,
+		       compat_long_t, addr, compat_long_t, data)
 {
 	struct task_struct *child;
 	long ret;
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 01e9ec3..807ccfb 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,5 +1,5 @@
 obj-y += update.o srcu.o
-obj-$(CONFIG_RCU_TORTURE_TEST) += torture.o
+obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += tree.o
 obj-$(CONFIG_TREE_PREEMPT_RCU) += tree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 79c3877..bfda272 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2011
  *
@@ -23,6 +23,7 @@
 #ifndef __LINUX_RCU_H
 #define __LINUX_RCU_H
 
+#include <trace/events/rcu.h>
 #ifdef CONFIG_RCU_TRACE
 #define RCU_TRACE(stmt) stmt
 #else /* #ifdef CONFIG_RCU_TRACE */
@@ -116,8 +117,6 @@
 	}
 }
 
-extern int rcu_expedited;
-
 #ifdef CONFIG_RCU_STALL_COMMON
 
 extern int rcu_cpu_stall_suppress;
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
new file mode 100644
index 0000000..bd30bc6
--- /dev/null
+++ b/kernel/rcu/rcutorture.c
@@ -0,0 +1,1582 @@
+/*
+ * Read-Copy Update module-based torture test facility
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2005, 2006
+ *
+ * Authors: Paul E. McKenney <paulmck@us.ibm.com>
+ *	  Josh Triplett <josh@freedesktop.org>
+ *
+ * See also:  Documentation/RCU/torture.txt
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/rcupdate.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/freezer.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/stat.h>
+#include <linux/srcu.h>
+#include <linux/slab.h>
+#include <linux/trace_clock.h>
+#include <asm/byteorder.h>
+#include <linux/torture.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>");
+
+
+torture_param(int, fqs_duration, 0,
+	      "Duration of fqs bursts (us), 0 to disable");
+torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
+torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)");
+torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
+torture_param(bool, gp_normal, false,
+	     "Use normal (non-expedited) GP wait primitives");
+torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers");
+torture_param(int, n_barrier_cbs, 0,
+	     "# of callbacks/kthreads for barrier testing");
+torture_param(int, nfakewriters, 4, "Number of RCU fake writer threads");
+torture_param(int, nreaders, -1, "Number of RCU reader threads");
+torture_param(int, object_debug, 0,
+	     "Enable debug-object double call_rcu() testing");
+torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
+torture_param(int, onoff_interval, 0,
+	     "Time between CPU hotplugs (s), 0=disable");
+torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
+torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
+torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
+torture_param(int, stall_cpu_holdoff, 10,
+	     "Time to wait before starting stall (s).");
+torture_param(int, stat_interval, 60,
+	     "Number of seconds between stats printk()s");
+torture_param(int, stutter, 5, "Number of seconds to run/halt test");
+torture_param(int, test_boost, 1, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
+torture_param(int, test_boost_duration, 4,
+	     "Duration of each boost test, seconds.");
+torture_param(int, test_boost_interval, 7,
+	     "Interval between boost tests, seconds.");
+torture_param(bool, test_no_idle_hz, true,
+	     "Test support for tickless idle CPUs");
+torture_param(bool, verbose, true,
+	     "Enable verbose debugging printk()s");
+
+static char *torture_type = "rcu";
+module_param(torture_type, charp, 0444);
+MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)");
+
+static int nrealreaders;
+static struct task_struct *writer_task;
+static struct task_struct **fakewriter_tasks;
+static struct task_struct **reader_tasks;
+static struct task_struct *stats_task;
+static struct task_struct *fqs_task;
+static struct task_struct *boost_tasks[NR_CPUS];
+static struct task_struct *stall_task;
+static struct task_struct **barrier_cbs_tasks;
+static struct task_struct *barrier_task;
+
+#define RCU_TORTURE_PIPE_LEN 10
+
+struct rcu_torture {
+	struct rcu_head rtort_rcu;
+	int rtort_pipe_count;
+	struct list_head rtort_free;
+	int rtort_mbtest;
+};
+
+static LIST_HEAD(rcu_torture_freelist);
+static struct rcu_torture __rcu *rcu_torture_current;
+static unsigned long rcu_torture_current_version;
+static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
+static DEFINE_SPINLOCK(rcu_torture_lock);
+static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1],
+		      rcu_torture_count) = { 0 };
+static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1],
+		      rcu_torture_batch) = { 0 };
+static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1];
+static atomic_t n_rcu_torture_alloc;
+static atomic_t n_rcu_torture_alloc_fail;
+static atomic_t n_rcu_torture_free;
+static atomic_t n_rcu_torture_mberror;
+static atomic_t n_rcu_torture_error;
+static long n_rcu_torture_barrier_error;
+static long n_rcu_torture_boost_ktrerror;
+static long n_rcu_torture_boost_rterror;
+static long n_rcu_torture_boost_failure;
+static long n_rcu_torture_boosts;
+static long n_rcu_torture_timers;
+static long n_barrier_attempts;
+static long n_barrier_successes;
+static struct list_head rcu_torture_removed;
+
+#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
+#define RCUTORTURE_RUNNABLE_INIT 1
+#else
+#define RCUTORTURE_RUNNABLE_INIT 0
+#endif
+int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
+module_param(rcutorture_runnable, int, 0444);
+MODULE_PARM_DESC(rcutorture_runnable, "Start rcutorture at boot");
+
+#if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU)
+#define rcu_can_boost() 1
+#else /* #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
+#define rcu_can_boost() 0
+#endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
+
+#ifdef CONFIG_RCU_TRACE
+static u64 notrace rcu_trace_clock_local(void)
+{
+	u64 ts = trace_clock_local();
+	unsigned long __maybe_unused ts_rem = do_div(ts, NSEC_PER_USEC);
+	return ts;
+}
+#else /* #ifdef CONFIG_RCU_TRACE */
+static u64 notrace rcu_trace_clock_local(void)
+{
+	return 0ULL;
+}
+#endif /* #else #ifdef CONFIG_RCU_TRACE */
+
+static unsigned long boost_starttime;	/* jiffies of next boost test start. */
+DEFINE_MUTEX(boost_mutex);		/* protect setting boost_starttime */
+					/*  and boost task create/destroy. */
+static atomic_t barrier_cbs_count;	/* Barrier callbacks registered. */
+static bool barrier_phase;		/* Test phase. */
+static atomic_t barrier_cbs_invoked;	/* Barrier callbacks invoked. */
+static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
+static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
+
+/*
+ * Allocate an element from the rcu_tortures pool.
+ */
+static struct rcu_torture *
+rcu_torture_alloc(void)
+{
+	struct list_head *p;
+
+	spin_lock_bh(&rcu_torture_lock);
+	if (list_empty(&rcu_torture_freelist)) {
+		atomic_inc(&n_rcu_torture_alloc_fail);
+		spin_unlock_bh(&rcu_torture_lock);
+		return NULL;
+	}
+	atomic_inc(&n_rcu_torture_alloc);
+	p = rcu_torture_freelist.next;
+	list_del_init(p);
+	spin_unlock_bh(&rcu_torture_lock);
+	return container_of(p, struct rcu_torture, rtort_free);
+}
+
+/*
+ * Free an element to the rcu_tortures pool.
+ */
+static void
+rcu_torture_free(struct rcu_torture *p)
+{
+	atomic_inc(&n_rcu_torture_free);
+	spin_lock_bh(&rcu_torture_lock);
+	list_add_tail(&p->rtort_free, &rcu_torture_freelist);
+	spin_unlock_bh(&rcu_torture_lock);
+}
+
+/*
+ * Operations vector for selecting different types of tests.
+ */
+
+struct rcu_torture_ops {
+	void (*init)(void);
+	int (*readlock)(void);
+	void (*read_delay)(struct torture_random_state *rrsp);
+	void (*readunlock)(int idx);
+	int (*completed)(void);
+	void (*deferred_free)(struct rcu_torture *p);
+	void (*sync)(void);
+	void (*exp_sync)(void);
+	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
+	void (*cb_barrier)(void);
+	void (*fqs)(void);
+	void (*stats)(char *page);
+	int irq_capable;
+	int can_boost;
+	const char *name;
+};
+
+static struct rcu_torture_ops *cur_ops;
+
+/*
+ * Definitions for rcu torture testing.
+ */
+
+static int rcu_torture_read_lock(void) __acquires(RCU)
+{
+	rcu_read_lock();
+	return 0;
+}
+
+static void rcu_read_delay(struct torture_random_state *rrsp)
+{
+	const unsigned long shortdelay_us = 200;
+	const unsigned long longdelay_ms = 50;
+
+	/* We want a short delay sometimes to make a reader delay the grace
+	 * period, and we want a long delay occasionally to trigger
+	 * force_quiescent_state. */
+
+	if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms);
+	if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
+		udelay(shortdelay_us);
+#ifdef CONFIG_PREEMPT
+	if (!preempt_count() &&
+	    !(torture_random(rrsp) % (nrealreaders * 20000)))
+		preempt_schedule();  /* No QS if preempt_disable() in effect */
+#endif
+}
+
+static void rcu_torture_read_unlock(int idx) __releases(RCU)
+{
+	rcu_read_unlock();
+}
+
+static int rcu_torture_completed(void)
+{
+	return rcu_batches_completed();
+}
+
+static void
+rcu_torture_cb(struct rcu_head *p)
+{
+	int i;
+	struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu);
+
+	if (torture_must_stop_irq()) {
+		/* Test is ending, just drop callbacks on the floor. */
+		/* The next initialization will pick up the pieces. */
+		return;
+	}
+	i = rp->rtort_pipe_count;
+	if (i > RCU_TORTURE_PIPE_LEN)
+		i = RCU_TORTURE_PIPE_LEN;
+	atomic_inc(&rcu_torture_wcount[i]);
+	if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
+		rp->rtort_mbtest = 0;
+		rcu_torture_free(rp);
+	} else {
+		cur_ops->deferred_free(rp);
+	}
+}
+
+static int rcu_no_completed(void)
+{
+	return 0;
+}
+
+static void rcu_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static void rcu_sync_torture_init(void)
+{
+	INIT_LIST_HEAD(&rcu_torture_removed);
+}
+
+static struct rcu_torture_ops rcu_ops = {
+	.init		= rcu_sync_torture_init,
+	.readlock	= rcu_torture_read_lock,
+	.read_delay	= rcu_read_delay,
+	.readunlock	= rcu_torture_read_unlock,
+	.completed	= rcu_torture_completed,
+	.deferred_free	= rcu_torture_deferred_free,
+	.sync		= synchronize_rcu,
+	.exp_sync	= synchronize_rcu_expedited,
+	.call		= call_rcu,
+	.cb_barrier	= rcu_barrier,
+	.fqs		= rcu_force_quiescent_state,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.can_boost	= rcu_can_boost(),
+	.name		= "rcu"
+};
+
+/*
+ * Definitions for rcu_bh torture testing.
+ */
+
+static int rcu_bh_torture_read_lock(void) __acquires(RCU_BH)
+{
+	rcu_read_lock_bh();
+	return 0;
+}
+
+static void rcu_bh_torture_read_unlock(int idx) __releases(RCU_BH)
+{
+	rcu_read_unlock_bh();
+}
+
+static int rcu_bh_torture_completed(void)
+{
+	return rcu_batches_completed_bh();
+}
+
+static void rcu_bh_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_bh(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops rcu_bh_ops = {
+	.init		= rcu_sync_torture_init,
+	.readlock	= rcu_bh_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= rcu_bh_torture_read_unlock,
+	.completed	= rcu_bh_torture_completed,
+	.deferred_free	= rcu_bh_torture_deferred_free,
+	.sync		= synchronize_rcu_bh,
+	.exp_sync	= synchronize_rcu_bh_expedited,
+	.call		= call_rcu_bh,
+	.cb_barrier	= rcu_barrier_bh,
+	.fqs		= rcu_bh_force_quiescent_state,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "rcu_bh"
+};
+
+/*
+ * Don't even think about trying any of these in real life!!!
+ * The names includes "busted", and they really means it!
+ * The only purpose of these functions is to provide a buggy RCU
+ * implementation to make sure that rcutorture correctly emits
+ * buggy-RCU error messages.
+ */
+static void rcu_busted_torture_deferred_free(struct rcu_torture *p)
+{
+	/* This is a deliberate bug for testing purposes only! */
+	rcu_torture_cb(&p->rtort_rcu);
+}
+
+static void synchronize_rcu_busted(void)
+{
+	/* This is a deliberate bug for testing purposes only! */
+}
+
+static void
+call_rcu_busted(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	/* This is a deliberate bug for testing purposes only! */
+	func(head);
+}
+
+static struct rcu_torture_ops rcu_busted_ops = {
+	.init		= rcu_sync_torture_init,
+	.readlock	= rcu_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= rcu_torture_read_unlock,
+	.completed	= rcu_no_completed,
+	.deferred_free	= rcu_busted_torture_deferred_free,
+	.sync		= synchronize_rcu_busted,
+	.exp_sync	= synchronize_rcu_busted,
+	.call		= call_rcu_busted,
+	.cb_barrier	= NULL,
+	.fqs		= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "rcu_busted"
+};
+
+/*
+ * Definitions for srcu torture testing.
+ */
+
+DEFINE_STATIC_SRCU(srcu_ctl);
+
+static int srcu_torture_read_lock(void) __acquires(&srcu_ctl)
+{
+	return srcu_read_lock(&srcu_ctl);
+}
+
+static void srcu_read_delay(struct torture_random_state *rrsp)
+{
+	long delay;
+	const long uspertick = 1000000 / HZ;
+	const long longdelay = 10;
+
+	/* We want there to be long-running readers, but not all the time. */
+
+	delay = torture_random(rrsp) %
+		(nrealreaders * 2 * longdelay * uspertick);
+	if (!delay)
+		schedule_timeout_interruptible(longdelay);
+	else
+		rcu_read_delay(rrsp);
+}
+
+static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
+{
+	srcu_read_unlock(&srcu_ctl, idx);
+}
+
+static int srcu_torture_completed(void)
+{
+	return srcu_batches_completed(&srcu_ctl);
+}
+
+static void srcu_torture_deferred_free(struct rcu_torture *rp)
+{
+	call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb);
+}
+
+static void srcu_torture_synchronize(void)
+{
+	synchronize_srcu(&srcu_ctl);
+}
+
+static void srcu_torture_call(struct rcu_head *head,
+			      void (*func)(struct rcu_head *head))
+{
+	call_srcu(&srcu_ctl, head, func);
+}
+
+static void srcu_torture_barrier(void)
+{
+	srcu_barrier(&srcu_ctl);
+}
+
+static void srcu_torture_stats(char *page)
+{
+	int cpu;
+	int idx = srcu_ctl.completed & 0x1;
+
+	page += sprintf(page, "%s%s per-CPU(idx=%d):",
+		       torture_type, TORTURE_FLAG, idx);
+	for_each_possible_cpu(cpu) {
+		page += sprintf(page, " %d(%lu,%lu)", cpu,
+			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
+			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
+	}
+	sprintf(page, "\n");
+}
+
+static void srcu_torture_synchronize_expedited(void)
+{
+	synchronize_srcu_expedited(&srcu_ctl);
+}
+
+static struct rcu_torture_ops srcu_ops = {
+	.init		= rcu_sync_torture_init,
+	.readlock	= srcu_torture_read_lock,
+	.read_delay	= srcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock,
+	.completed	= srcu_torture_completed,
+	.deferred_free	= srcu_torture_deferred_free,
+	.sync		= srcu_torture_synchronize,
+	.exp_sync	= srcu_torture_synchronize_expedited,
+	.call		= srcu_torture_call,
+	.cb_barrier	= srcu_torture_barrier,
+	.stats		= srcu_torture_stats,
+	.name		= "srcu"
+};
+
+/*
+ * Definitions for sched torture testing.
+ */
+
+static int sched_torture_read_lock(void)
+{
+	preempt_disable();
+	return 0;
+}
+
+static void sched_torture_read_unlock(int idx)
+{
+	preempt_enable();
+}
+
+static void rcu_sched_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_sched(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops sched_ops = {
+	.init		= rcu_sync_torture_init,
+	.readlock	= sched_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= sched_torture_read_unlock,
+	.completed	= rcu_no_completed,
+	.deferred_free	= rcu_sched_torture_deferred_free,
+	.sync		= synchronize_sched,
+	.exp_sync	= synchronize_sched_expedited,
+	.call		= call_rcu_sched,
+	.cb_barrier	= rcu_barrier_sched,
+	.fqs		= rcu_sched_force_quiescent_state,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "sched"
+};
+
+/*
+ * RCU torture priority-boost testing.  Runs one real-time thread per
+ * CPU for moderate bursts, repeatedly registering RCU callbacks and
+ * spinning waiting for them to be invoked.  If a given callback takes
+ * too long to be invoked, we assume that priority inversion has occurred.
+ */
+
+struct rcu_boost_inflight {
+	struct rcu_head rcu;
+	int inflight;
+};
+
+static void rcu_torture_boost_cb(struct rcu_head *head)
+{
+	struct rcu_boost_inflight *rbip =
+		container_of(head, struct rcu_boost_inflight, rcu);
+
+	smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
+	rbip->inflight = 0;
+}
+
+static int rcu_torture_boost(void *arg)
+{
+	unsigned long call_rcu_time;
+	unsigned long endtime;
+	unsigned long oldstarttime;
+	struct rcu_boost_inflight rbi = { .inflight = 0 };
+	struct sched_param sp;
+
+	VERBOSE_TOROUT_STRING("rcu_torture_boost started");
+
+	/* Set real-time priority. */
+	sp.sched_priority = 1;
+	if (sched_setscheduler(current, SCHED_FIFO, &sp) < 0) {
+		VERBOSE_TOROUT_STRING("rcu_torture_boost RT prio failed!");
+		n_rcu_torture_boost_rterror++;
+	}
+
+	init_rcu_head_on_stack(&rbi.rcu);
+	/* Each pass through the following loop does one boost-test cycle. */
+	do {
+		/* Wait for the next test interval. */
+		oldstarttime = boost_starttime;
+		while (ULONG_CMP_LT(jiffies, oldstarttime)) {
+			schedule_timeout_interruptible(oldstarttime - jiffies);
+			stutter_wait("rcu_torture_boost");
+			if (torture_must_stop())
+				goto checkwait;
+		}
+
+		/* Do one boost-test interval. */
+		endtime = oldstarttime + test_boost_duration * HZ;
+		call_rcu_time = jiffies;
+		while (ULONG_CMP_LT(jiffies, endtime)) {
+			/* If we don't have a callback in flight, post one. */
+			if (!rbi.inflight) {
+				smp_mb(); /* RCU core before ->inflight = 1. */
+				rbi.inflight = 1;
+				call_rcu(&rbi.rcu, rcu_torture_boost_cb);
+				if (jiffies - call_rcu_time >
+					 test_boost_duration * HZ - HZ / 2) {
+					VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
+					n_rcu_torture_boost_failure++;
+				}
+				call_rcu_time = jiffies;
+			}
+			cond_resched();
+			stutter_wait("rcu_torture_boost");
+			if (torture_must_stop())
+				goto checkwait;
+		}
+
+		/*
+		 * Set the start time of the next test interval.
+		 * Yes, this is vulnerable to long delays, but such
+		 * delays simply cause a false negative for the next
+		 * interval.  Besides, we are running at RT priority,
+		 * so delays should be relatively rare.
+		 */
+		while (oldstarttime == boost_starttime &&
+		       !kthread_should_stop()) {
+			if (mutex_trylock(&boost_mutex)) {
+				boost_starttime = jiffies +
+						  test_boost_interval * HZ;
+				n_rcu_torture_boosts++;
+				mutex_unlock(&boost_mutex);
+				break;
+			}
+			schedule_timeout_uninterruptible(1);
+		}
+
+		/* Go do the stutter. */
+checkwait:	stutter_wait("rcu_torture_boost");
+	} while (!torture_must_stop());
+
+	/* Clean up and exit. */
+	while (!kthread_should_stop() || rbi.inflight) {
+		torture_shutdown_absorb("rcu_torture_boost");
+		schedule_timeout_uninterruptible(1);
+	}
+	smp_mb(); /* order accesses to ->inflight before stack-frame death. */
+	destroy_rcu_head_on_stack(&rbi.rcu);
+	torture_kthread_stopping("rcu_torture_boost");
+	return 0;
+}
+
+/*
+ * RCU torture force-quiescent-state kthread.  Repeatedly induces
+ * bursts of calls to force_quiescent_state(), increasing the probability
+ * of occurrence of some important types of race conditions.
+ */
+static int
+rcu_torture_fqs(void *arg)
+{
+	unsigned long fqs_resume_time;
+	int fqs_burst_remaining;
+
+	VERBOSE_TOROUT_STRING("rcu_torture_fqs task started");
+	do {
+		fqs_resume_time = jiffies + fqs_stutter * HZ;
+		while (ULONG_CMP_LT(jiffies, fqs_resume_time) &&
+		       !kthread_should_stop()) {
+			schedule_timeout_interruptible(1);
+		}
+		fqs_burst_remaining = fqs_duration;
+		while (fqs_burst_remaining > 0 &&
+		       !kthread_should_stop()) {
+			cur_ops->fqs();
+			udelay(fqs_holdoff);
+			fqs_burst_remaining -= fqs_holdoff;
+		}
+		stutter_wait("rcu_torture_fqs");
+	} while (!torture_must_stop());
+	torture_kthread_stopping("rcu_torture_fqs");
+	return 0;
+}
+
+/*
+ * RCU torture writer kthread.  Repeatedly substitutes a new structure
+ * for that pointed to by rcu_torture_current, freeing the old structure
+ * after a series of grace periods (the "pipeline").
+ */
+static int
+rcu_torture_writer(void *arg)
+{
+	bool exp;
+	int i;
+	struct rcu_torture *rp;
+	struct rcu_torture *rp1;
+	struct rcu_torture *old_rp;
+	static DEFINE_TORTURE_RANDOM(rand);
+
+	VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
+	set_user_nice(current, MAX_NICE);
+
+	do {
+		schedule_timeout_uninterruptible(1);
+		rp = rcu_torture_alloc();
+		if (rp == NULL)
+			continue;
+		rp->rtort_pipe_count = 0;
+		udelay(torture_random(&rand) & 0x3ff);
+		old_rp = rcu_dereference_check(rcu_torture_current,
+					       current == writer_task);
+		rp->rtort_mbtest = 1;
+		rcu_assign_pointer(rcu_torture_current, rp);
+		smp_wmb(); /* Mods to old_rp must follow rcu_assign_pointer() */
+		if (old_rp) {
+			i = old_rp->rtort_pipe_count;
+			if (i > RCU_TORTURE_PIPE_LEN)
+				i = RCU_TORTURE_PIPE_LEN;
+			atomic_inc(&rcu_torture_wcount[i]);
+			old_rp->rtort_pipe_count++;
+			if (gp_normal == gp_exp)
+				exp = !!(torture_random(&rand) & 0x80);
+			else
+				exp = gp_exp;
+			if (!exp) {
+				cur_ops->deferred_free(old_rp);
+			} else {
+				cur_ops->exp_sync();
+				list_add(&old_rp->rtort_free,
+					 &rcu_torture_removed);
+				list_for_each_entry_safe(rp, rp1,
+							 &rcu_torture_removed,
+							 rtort_free) {
+					i = rp->rtort_pipe_count;
+					if (i > RCU_TORTURE_PIPE_LEN)
+						i = RCU_TORTURE_PIPE_LEN;
+					atomic_inc(&rcu_torture_wcount[i]);
+					if (++rp->rtort_pipe_count >=
+					    RCU_TORTURE_PIPE_LEN) {
+						rp->rtort_mbtest = 0;
+						list_del(&rp->rtort_free);
+						rcu_torture_free(rp);
+					}
+				 }
+			}
+		}
+		rcutorture_record_progress(++rcu_torture_current_version);
+		stutter_wait("rcu_torture_writer");
+	} while (!torture_must_stop());
+	torture_kthread_stopping("rcu_torture_writer");
+	return 0;
+}
+
+/*
+ * RCU torture fake writer kthread.  Repeatedly calls sync, with a random
+ * delay between calls.
+ */
+static int
+rcu_torture_fakewriter(void *arg)
+{
+	DEFINE_TORTURE_RANDOM(rand);
+
+	VERBOSE_TOROUT_STRING("rcu_torture_fakewriter task started");
+	set_user_nice(current, MAX_NICE);
+
+	do {
+		schedule_timeout_uninterruptible(1 + torture_random(&rand)%10);
+		udelay(torture_random(&rand) & 0x3ff);
+		if (cur_ops->cb_barrier != NULL &&
+		    torture_random(&rand) % (nfakewriters * 8) == 0) {
+			cur_ops->cb_barrier();
+		} else if (gp_normal == gp_exp) {
+			if (torture_random(&rand) & 0x80)
+				cur_ops->sync();
+			else
+				cur_ops->exp_sync();
+		} else if (gp_normal) {
+			cur_ops->sync();
+		} else {
+			cur_ops->exp_sync();
+		}
+		stutter_wait("rcu_torture_fakewriter");
+	} while (!torture_must_stop());
+
+	torture_kthread_stopping("rcu_torture_fakewriter");
+	return 0;
+}
+
+void rcutorture_trace_dump(void)
+{
+	static atomic_t beenhere = ATOMIC_INIT(0);
+
+	if (atomic_read(&beenhere))
+		return;
+	if (atomic_xchg(&beenhere, 1) != 0)
+		return;
+	ftrace_dump(DUMP_ALL);
+}
+
+/*
+ * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
+ * incrementing the corresponding element of the pipeline array.  The
+ * counter in the element should never be greater than 1, otherwise, the
+ * RCU implementation is broken.
+ */
+static void rcu_torture_timer(unsigned long unused)
+{
+	int idx;
+	int completed;
+	int completed_end;
+	static DEFINE_TORTURE_RANDOM(rand);
+	static DEFINE_SPINLOCK(rand_lock);
+	struct rcu_torture *p;
+	int pipe_count;
+	unsigned long long ts;
+
+	idx = cur_ops->readlock();
+	completed = cur_ops->completed();
+	ts = rcu_trace_clock_local();
+	p = rcu_dereference_check(rcu_torture_current,
+				  rcu_read_lock_bh_held() ||
+				  rcu_read_lock_sched_held() ||
+				  srcu_read_lock_held(&srcu_ctl));
+	if (p == NULL) {
+		/* Leave because rcu_torture_writer is not yet underway */
+		cur_ops->readunlock(idx);
+		return;
+	}
+	if (p->rtort_mbtest == 0)
+		atomic_inc(&n_rcu_torture_mberror);
+	spin_lock(&rand_lock);
+	cur_ops->read_delay(&rand);
+	n_rcu_torture_timers++;
+	spin_unlock(&rand_lock);
+	preempt_disable();
+	pipe_count = p->rtort_pipe_count;
+	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
+		/* Should not happen, but... */
+		pipe_count = RCU_TORTURE_PIPE_LEN;
+	}
+	completed_end = cur_ops->completed();
+	if (pipe_count > 1) {
+		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
+					  completed, completed_end);
+		rcutorture_trace_dump();
+	}
+	__this_cpu_inc(rcu_torture_count[pipe_count]);
+	completed = completed_end - completed;
+	if (completed > RCU_TORTURE_PIPE_LEN) {
+		/* Should not happen, but... */
+		completed = RCU_TORTURE_PIPE_LEN;
+	}
+	__this_cpu_inc(rcu_torture_batch[completed]);
+	preempt_enable();
+	cur_ops->readunlock(idx);
+}
+
+/*
+ * RCU torture reader kthread.  Repeatedly dereferences rcu_torture_current,
+ * incrementing the corresponding element of the pipeline array.  The
+ * counter in the element should never be greater than 1, otherwise, the
+ * RCU implementation is broken.
+ */
+static int
+rcu_torture_reader(void *arg)
+{
+	int completed;
+	int completed_end;
+	int idx;
+	DEFINE_TORTURE_RANDOM(rand);
+	struct rcu_torture *p;
+	int pipe_count;
+	struct timer_list t;
+	unsigned long long ts;
+
+	VERBOSE_TOROUT_STRING("rcu_torture_reader task started");
+	set_user_nice(current, MAX_NICE);
+	if (irqreader && cur_ops->irq_capable)
+		setup_timer_on_stack(&t, rcu_torture_timer, 0);
+
+	do {
+		if (irqreader && cur_ops->irq_capable) {
+			if (!timer_pending(&t))
+				mod_timer(&t, jiffies + 1);
+		}
+		idx = cur_ops->readlock();
+		completed = cur_ops->completed();
+		ts = rcu_trace_clock_local();
+		p = rcu_dereference_check(rcu_torture_current,
+					  rcu_read_lock_bh_held() ||
+					  rcu_read_lock_sched_held() ||
+					  srcu_read_lock_held(&srcu_ctl));
+		if (p == NULL) {
+			/* Wait for rcu_torture_writer to get underway */
+			cur_ops->readunlock(idx);
+			schedule_timeout_interruptible(HZ);
+			continue;
+		}
+		if (p->rtort_mbtest == 0)
+			atomic_inc(&n_rcu_torture_mberror);
+		cur_ops->read_delay(&rand);
+		preempt_disable();
+		pipe_count = p->rtort_pipe_count;
+		if (pipe_count > RCU_TORTURE_PIPE_LEN) {
+			/* Should not happen, but... */
+			pipe_count = RCU_TORTURE_PIPE_LEN;
+		}
+		completed_end = cur_ops->completed();
+		if (pipe_count > 1) {
+			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
+						  ts, completed, completed_end);
+			rcutorture_trace_dump();
+		}
+		__this_cpu_inc(rcu_torture_count[pipe_count]);
+		completed = completed_end - completed;
+		if (completed > RCU_TORTURE_PIPE_LEN) {
+			/* Should not happen, but... */
+			completed = RCU_TORTURE_PIPE_LEN;
+		}
+		__this_cpu_inc(rcu_torture_batch[completed]);
+		preempt_enable();
+		cur_ops->readunlock(idx);
+		schedule();
+		stutter_wait("rcu_torture_reader");
+	} while (!torture_must_stop());
+	if (irqreader && cur_ops->irq_capable)
+		del_timer_sync(&t);
+	torture_kthread_stopping("rcu_torture_reader");
+	return 0;
+}
+
+/*
+ * Create an RCU-torture statistics message in the specified buffer.
+ */
+static void
+rcu_torture_printk(char *page)
+{
+	int cpu;
+	int i;
+	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
+	long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
+
+	for_each_possible_cpu(cpu) {
+		for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
+			pipesummary[i] += per_cpu(rcu_torture_count, cpu)[i];
+			batchsummary[i] += per_cpu(rcu_torture_batch, cpu)[i];
+		}
+	}
+	for (i = RCU_TORTURE_PIPE_LEN - 1; i >= 0; i--) {
+		if (pipesummary[i] != 0)
+			break;
+	}
+	page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page,
+		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
+		       rcu_torture_current,
+		       rcu_torture_current_version,
+		       list_empty(&rcu_torture_freelist),
+		       atomic_read(&n_rcu_torture_alloc),
+		       atomic_read(&n_rcu_torture_alloc_fail),
+		       atomic_read(&n_rcu_torture_free));
+	page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
+		       atomic_read(&n_rcu_torture_mberror),
+		       n_rcu_torture_boost_ktrerror,
+		       n_rcu_torture_boost_rterror);
+	page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
+		       n_rcu_torture_boost_failure,
+		       n_rcu_torture_boosts,
+		       n_rcu_torture_timers);
+	page = torture_onoff_stats(page);
+	page += sprintf(page, "barrier: %ld/%ld:%ld",
+		       n_barrier_successes,
+		       n_barrier_attempts,
+		       n_rcu_torture_barrier_error);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
+	    n_rcu_torture_barrier_error != 0 ||
+	    n_rcu_torture_boost_ktrerror != 0 ||
+	    n_rcu_torture_boost_rterror != 0 ||
+	    n_rcu_torture_boost_failure != 0 ||
+	    i > 1) {
+		page += sprintf(page, "!!! ");
+		atomic_inc(&n_rcu_torture_error);
+		WARN_ON_ONCE(1);
+	}
+	page += sprintf(page, "Reader Pipe: ");
+	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
+		page += sprintf(page, " %ld", pipesummary[i]);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "Reader Batch: ");
+	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
+		page += sprintf(page, " %ld", batchsummary[i]);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "Free-Block Circulation: ");
+	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
+		page += sprintf(page, " %d",
+			       atomic_read(&rcu_torture_wcount[i]));
+	}
+	page += sprintf(page, "\n");
+	if (cur_ops->stats)
+		cur_ops->stats(page);
+}
+
+/*
+ * Print torture statistics.  Caller must ensure that there is only
+ * one call to this function at a given time!!!  This is normally
+ * accomplished by relying on the module system to only have one copy
+ * of the module loaded, and then by giving the rcu_torture_stats
+ * kthread full control (or the init/cleanup functions when rcu_torture_stats
+ * thread is not running).
+ */
+static void
+rcu_torture_stats_print(void)
+{
+	int size = nr_cpu_ids * 200 + 8192;
+	char *buf;
+
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf) {
+		pr_err("rcu-torture: Out of memory, need: %d", size);
+		return;
+	}
+	rcu_torture_printk(buf);
+	pr_alert("%s", buf);
+	kfree(buf);
+}
+
+/*
+ * Periodically prints torture statistics, if periodic statistics printing
+ * was specified via the stat_interval module parameter.
+ */
+static int
+rcu_torture_stats(void *arg)
+{
+	VERBOSE_TOROUT_STRING("rcu_torture_stats task started");
+	do {
+		schedule_timeout_interruptible(stat_interval * HZ);
+		rcu_torture_stats_print();
+		torture_shutdown_absorb("rcu_torture_stats");
+	} while (!torture_must_stop());
+	torture_kthread_stopping("rcu_torture_stats");
+	return 0;
+}
+
+static inline void
+rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
+{
+	pr_alert("%s" TORTURE_FLAG
+		 "--- %s: nreaders=%d nfakewriters=%d "
+		 "stat_interval=%d verbose=%d test_no_idle_hz=%d "
+		 "shuffle_interval=%d stutter=%d irqreader=%d "
+		 "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
+		 "test_boost=%d/%d test_boost_interval=%d "
+		 "test_boost_duration=%d shutdown_secs=%d "
+		 "stall_cpu=%d stall_cpu_holdoff=%d "
+		 "n_barrier_cbs=%d "
+		 "onoff_interval=%d onoff_holdoff=%d\n",
+		 torture_type, tag, nrealreaders, nfakewriters,
+		 stat_interval, verbose, test_no_idle_hz, shuffle_interval,
+		 stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
+		 test_boost, cur_ops->can_boost,
+		 test_boost_interval, test_boost_duration, shutdown_secs,
+		 stall_cpu, stall_cpu_holdoff,
+		 n_barrier_cbs,
+		 onoff_interval, onoff_holdoff);
+}
+
+static void rcutorture_booster_cleanup(int cpu)
+{
+	struct task_struct *t;
+
+	if (boost_tasks[cpu] == NULL)
+		return;
+	mutex_lock(&boost_mutex);
+	t = boost_tasks[cpu];
+	boost_tasks[cpu] = NULL;
+	mutex_unlock(&boost_mutex);
+
+	/* This must be outside of the mutex, otherwise deadlock! */
+	torture_stop_kthread(rcu_torture_boost, t);
+}
+
+static int rcutorture_booster_init(int cpu)
+{
+	int retval;
+
+	if (boost_tasks[cpu] != NULL)
+		return 0;  /* Already created, nothing more to do. */
+
+	/* Don't allow time recalculation while creating a new task. */
+	mutex_lock(&boost_mutex);
+	VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task");
+	boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL,
+						  cpu_to_node(cpu),
+						  "rcu_torture_boost");
+	if (IS_ERR(boost_tasks[cpu])) {
+		retval = PTR_ERR(boost_tasks[cpu]);
+		VERBOSE_TOROUT_STRING("rcu_torture_boost task create failed");
+		n_rcu_torture_boost_ktrerror++;
+		boost_tasks[cpu] = NULL;
+		mutex_unlock(&boost_mutex);
+		return retval;
+	}
+	kthread_bind(boost_tasks[cpu], cpu);
+	wake_up_process(boost_tasks[cpu]);
+	mutex_unlock(&boost_mutex);
+	return 0;
+}
+
+/*
+ * CPU-stall kthread.  It waits as specified by stall_cpu_holdoff, then
+ * induces a CPU stall for the time specified by stall_cpu.
+ */
+static int rcu_torture_stall(void *args)
+{
+	unsigned long stop_at;
+
+	VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
+	if (stall_cpu_holdoff > 0) {
+		VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff");
+		schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
+		VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
+	}
+	if (!kthread_should_stop()) {
+		stop_at = get_seconds() + stall_cpu;
+		/* RCU CPU stall is expected behavior in following code. */
+		pr_alert("rcu_torture_stall start.\n");
+		rcu_read_lock();
+		preempt_disable();
+		while (ULONG_CMP_LT(get_seconds(), stop_at))
+			continue;  /* Induce RCU CPU stall warning. */
+		preempt_enable();
+		rcu_read_unlock();
+		pr_alert("rcu_torture_stall end.\n");
+	}
+	torture_shutdown_absorb("rcu_torture_stall");
+	while (!kthread_should_stop())
+		schedule_timeout_interruptible(10 * HZ);
+	return 0;
+}
+
+/* Spawn CPU-stall kthread, if stall_cpu specified. */
+static int __init rcu_torture_stall_init(void)
+{
+	if (stall_cpu <= 0)
+		return 0;
+	return torture_create_kthread(rcu_torture_stall, NULL, stall_task);
+}
+
+/* Callback function for RCU barrier testing. */
+void rcu_torture_barrier_cbf(struct rcu_head *rcu)
+{
+	atomic_inc(&barrier_cbs_invoked);
+}
+
+/* kthread function to register callbacks used to test RCU barriers. */
+static int rcu_torture_barrier_cbs(void *arg)
+{
+	long myid = (long)arg;
+	bool lastphase = 0;
+	bool newphase;
+	struct rcu_head rcu;
+
+	init_rcu_head_on_stack(&rcu);
+	VERBOSE_TOROUT_STRING("rcu_torture_barrier_cbs task started");
+	set_user_nice(current, MAX_NICE);
+	do {
+		wait_event(barrier_cbs_wq[myid],
+			   (newphase =
+			    ACCESS_ONCE(barrier_phase)) != lastphase ||
+			   torture_must_stop());
+		lastphase = newphase;
+		smp_mb(); /* ensure barrier_phase load before ->call(). */
+		if (torture_must_stop())
+			break;
+		cur_ops->call(&rcu, rcu_torture_barrier_cbf);
+		if (atomic_dec_and_test(&barrier_cbs_count))
+			wake_up(&barrier_wq);
+	} while (!torture_must_stop());
+	cur_ops->cb_barrier();
+	destroy_rcu_head_on_stack(&rcu);
+	torture_kthread_stopping("rcu_torture_barrier_cbs");
+	return 0;
+}
+
+/* kthread function to drive and coordinate RCU barrier testing. */
+static int rcu_torture_barrier(void *arg)
+{
+	int i;
+
+	VERBOSE_TOROUT_STRING("rcu_torture_barrier task starting");
+	do {
+		atomic_set(&barrier_cbs_invoked, 0);
+		atomic_set(&barrier_cbs_count, n_barrier_cbs);
+		smp_mb(); /* Ensure barrier_phase after prior assignments. */
+		barrier_phase = !barrier_phase;
+		for (i = 0; i < n_barrier_cbs; i++)
+			wake_up(&barrier_cbs_wq[i]);
+		wait_event(barrier_wq,
+			   atomic_read(&barrier_cbs_count) == 0 ||
+			   torture_must_stop());
+		if (torture_must_stop())
+			break;
+		n_barrier_attempts++;
+		cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
+		if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
+			n_rcu_torture_barrier_error++;
+			WARN_ON_ONCE(1);
+		}
+		n_barrier_successes++;
+		schedule_timeout_interruptible(HZ / 10);
+	} while (!torture_must_stop());
+	torture_kthread_stopping("rcu_torture_barrier");
+	return 0;
+}
+
+/* Initialize RCU barrier testing. */
+static int rcu_torture_barrier_init(void)
+{
+	int i;
+	int ret;
+
+	if (n_barrier_cbs == 0)
+		return 0;
+	if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) {
+		pr_alert("%s" TORTURE_FLAG
+			 " Call or barrier ops missing for %s,\n",
+			 torture_type, cur_ops->name);
+		pr_alert("%s" TORTURE_FLAG
+			 " RCU barrier testing omitted from run.\n",
+			 torture_type);
+		return 0;
+	}
+	atomic_set(&barrier_cbs_count, 0);
+	atomic_set(&barrier_cbs_invoked, 0);
+	barrier_cbs_tasks =
+		kzalloc(n_barrier_cbs * sizeof(barrier_cbs_tasks[0]),
+			GFP_KERNEL);
+	barrier_cbs_wq =
+		kzalloc(n_barrier_cbs * sizeof(barrier_cbs_wq[0]),
+			GFP_KERNEL);
+	if (barrier_cbs_tasks == NULL || !barrier_cbs_wq)
+		return -ENOMEM;
+	for (i = 0; i < n_barrier_cbs; i++) {
+		init_waitqueue_head(&barrier_cbs_wq[i]);
+		ret = torture_create_kthread(rcu_torture_barrier_cbs,
+					     (void *)(long)i,
+					     barrier_cbs_tasks[i]);
+		if (ret)
+			return ret;
+	}
+	return torture_create_kthread(rcu_torture_barrier, NULL, barrier_task);
+}
+
+/* Clean up after RCU barrier testing. */
+static void rcu_torture_barrier_cleanup(void)
+{
+	int i;
+
+	torture_stop_kthread(rcu_torture_barrier, barrier_task);
+	if (barrier_cbs_tasks != NULL) {
+		for (i = 0; i < n_barrier_cbs; i++)
+			torture_stop_kthread(rcu_torture_barrier_cbs,
+					     barrier_cbs_tasks[i]);
+		kfree(barrier_cbs_tasks);
+		barrier_cbs_tasks = NULL;
+	}
+	if (barrier_cbs_wq != NULL) {
+		kfree(barrier_cbs_wq);
+		barrier_cbs_wq = NULL;
+	}
+}
+
+static int rcutorture_cpu_notify(struct notifier_block *self,
+				 unsigned long action, void *hcpu)
+{
+	long cpu = (long)hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
+		(void)rcutorture_booster_init(cpu);
+		break;
+	case CPU_DOWN_PREPARE:
+		rcutorture_booster_cleanup(cpu);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block rcutorture_cpu_nb = {
+	.notifier_call = rcutorture_cpu_notify,
+};
+
+static void
+rcu_torture_cleanup(void)
+{
+	int i;
+
+	rcutorture_record_test_transition();
+	if (torture_cleanup()) {
+		if (cur_ops->cb_barrier != NULL)
+			cur_ops->cb_barrier();
+		return;
+	}
+
+	rcu_torture_barrier_cleanup();
+	torture_stop_kthread(rcu_torture_stall, stall_task);
+	torture_stop_kthread(rcu_torture_writer, writer_task);
+
+	if (reader_tasks) {
+		for (i = 0; i < nrealreaders; i++)
+			torture_stop_kthread(rcu_torture_reader,
+					     reader_tasks[i]);
+		kfree(reader_tasks);
+	}
+	rcu_torture_current = NULL;
+
+	if (fakewriter_tasks) {
+		for (i = 0; i < nfakewriters; i++) {
+			torture_stop_kthread(rcu_torture_fakewriter,
+					     fakewriter_tasks[i]);
+		}
+		kfree(fakewriter_tasks);
+		fakewriter_tasks = NULL;
+	}
+
+	torture_stop_kthread(rcu_torture_stats, stats_task);
+	torture_stop_kthread(rcu_torture_fqs, fqs_task);
+	if ((test_boost == 1 && cur_ops->can_boost) ||
+	    test_boost == 2) {
+		unregister_cpu_notifier(&rcutorture_cpu_nb);
+		for_each_possible_cpu(i)
+			rcutorture_booster_cleanup(i);
+	}
+
+	/* Wait for all RCU callbacks to fire.  */
+
+	if (cur_ops->cb_barrier != NULL)
+		cur_ops->cb_barrier();
+
+	rcu_torture_stats_print();  /* -After- the stats thread is stopped! */
+
+	if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error)
+		rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE");
+	else if (torture_onoff_failures())
+		rcu_torture_print_module_parms(cur_ops,
+					       "End of test: RCU_HOTPLUG");
+	else
+		rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS");
+}
+
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+static void rcu_torture_leak_cb(struct rcu_head *rhp)
+{
+}
+
+static void rcu_torture_err_cb(struct rcu_head *rhp)
+{
+	/*
+	 * This -might- happen due to race conditions, but is unlikely.
+	 * The scenario that leads to this happening is that the
+	 * first of the pair of duplicate callbacks is queued,
+	 * someone else starts a grace period that includes that
+	 * callback, then the second of the pair must wait for the
+	 * next grace period.  Unlikely, but can happen.  If it
+	 * does happen, the debug-objects subsystem won't have splatted.
+	 */
+	pr_alert("rcutorture: duplicated callback was invoked.\n");
+}
+#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+
+/*
+ * Verify that double-free causes debug-objects to complain, but only
+ * if CONFIG_DEBUG_OBJECTS_RCU_HEAD=y.  Otherwise, say that the test
+ * cannot be carried out.
+ */
+static void rcu_test_debug_objects(void)
+{
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+	struct rcu_head rh1;
+	struct rcu_head rh2;
+
+	init_rcu_head_on_stack(&rh1);
+	init_rcu_head_on_stack(&rh2);
+	pr_alert("rcutorture: WARN: Duplicate call_rcu() test starting.\n");
+
+	/* Try to queue the rh2 pair of callbacks for the same grace period. */
+	preempt_disable(); /* Prevent preemption from interrupting test. */
+	rcu_read_lock(); /* Make it impossible to finish a grace period. */
+	call_rcu(&rh1, rcu_torture_leak_cb); /* Start grace period. */
+	local_irq_disable(); /* Make it harder to start a new grace period. */
+	call_rcu(&rh2, rcu_torture_leak_cb);
+	call_rcu(&rh2, rcu_torture_err_cb); /* Duplicate callback. */
+	local_irq_enable();
+	rcu_read_unlock();
+	preempt_enable();
+
+	/* Wait for them all to get done so we can safely return. */
+	rcu_barrier();
+	pr_alert("rcutorture: WARN: Duplicate call_rcu() test complete.\n");
+	destroy_rcu_head_on_stack(&rh1);
+	destroy_rcu_head_on_stack(&rh2);
+#else /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+	pr_alert("rcutorture: !CONFIG_DEBUG_OBJECTS_RCU_HEAD, not testing duplicate call_rcu()\n");
+#endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+}
+
+static int __init
+rcu_torture_init(void)
+{
+	int i;
+	int cpu;
+	int firsterr = 0;
+	static struct rcu_torture_ops *torture_ops[] = {
+		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
+	};
+
+	torture_init_begin(torture_type, verbose, &rcutorture_runnable);
+
+	/* Process args and tell the world that the torturer is on the job. */
+	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
+		cur_ops = torture_ops[i];
+		if (strcmp(torture_type, cur_ops->name) == 0)
+			break;
+	}
+	if (i == ARRAY_SIZE(torture_ops)) {
+		pr_alert("rcu-torture: invalid torture type: \"%s\"\n",
+			 torture_type);
+		pr_alert("rcu-torture types:");
+		for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
+			pr_alert(" %s", torture_ops[i]->name);
+		pr_alert("\n");
+		torture_init_end();
+		return -EINVAL;
+	}
+	if (cur_ops->fqs == NULL && fqs_duration != 0) {
+		pr_alert("rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n");
+		fqs_duration = 0;
+	}
+	if (cur_ops->init)
+		cur_ops->init(); /* no "goto unwind" prior to this point!!! */
+
+	if (nreaders >= 0)
+		nrealreaders = nreaders;
+	else
+		nrealreaders = 2 * num_online_cpus();
+	rcu_torture_print_module_parms(cur_ops, "Start of test");
+
+	/* Set up the freelist. */
+
+	INIT_LIST_HEAD(&rcu_torture_freelist);
+	for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++) {
+		rcu_tortures[i].rtort_mbtest = 0;
+		list_add_tail(&rcu_tortures[i].rtort_free,
+			      &rcu_torture_freelist);
+	}
+
+	/* Initialize the statistics so that each run gets its own numbers. */
+
+	rcu_torture_current = NULL;
+	rcu_torture_current_version = 0;
+	atomic_set(&n_rcu_torture_alloc, 0);
+	atomic_set(&n_rcu_torture_alloc_fail, 0);
+	atomic_set(&n_rcu_torture_free, 0);
+	atomic_set(&n_rcu_torture_mberror, 0);
+	atomic_set(&n_rcu_torture_error, 0);
+	n_rcu_torture_barrier_error = 0;
+	n_rcu_torture_boost_ktrerror = 0;
+	n_rcu_torture_boost_rterror = 0;
+	n_rcu_torture_boost_failure = 0;
+	n_rcu_torture_boosts = 0;
+	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
+		atomic_set(&rcu_torture_wcount[i], 0);
+	for_each_possible_cpu(cpu) {
+		for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
+			per_cpu(rcu_torture_count, cpu)[i] = 0;
+			per_cpu(rcu_torture_batch, cpu)[i] = 0;
+		}
+	}
+
+	/* Start up the kthreads. */
+
+	firsterr = torture_create_kthread(rcu_torture_writer, NULL,
+					  writer_task);
+	if (firsterr)
+		goto unwind;
+	fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]),
+				   GFP_KERNEL);
+	if (fakewriter_tasks == NULL) {
+		VERBOSE_TOROUT_ERRSTRING("out of memory");
+		firsterr = -ENOMEM;
+		goto unwind;
+	}
+	for (i = 0; i < nfakewriters; i++) {
+		firsterr = torture_create_kthread(rcu_torture_fakewriter,
+						  NULL, fakewriter_tasks[i]);
+		if (firsterr)
+			goto unwind;
+	}
+	reader_tasks = kzalloc(nrealreaders * sizeof(reader_tasks[0]),
+			       GFP_KERNEL);
+	if (reader_tasks == NULL) {
+		VERBOSE_TOROUT_ERRSTRING("out of memory");
+		firsterr = -ENOMEM;
+		goto unwind;
+	}
+	for (i = 0; i < nrealreaders; i++) {
+		firsterr = torture_create_kthread(rcu_torture_reader, NULL,
+						  reader_tasks[i]);
+		if (firsterr)
+			goto unwind;
+	}
+	if (stat_interval > 0) {
+		firsterr = torture_create_kthread(rcu_torture_stats, NULL,
+						  stats_task);
+		if (firsterr)
+			goto unwind;
+	}
+	if (test_no_idle_hz) {
+		firsterr = torture_shuffle_init(shuffle_interval * HZ);
+		if (firsterr)
+			goto unwind;
+	}
+	if (stutter < 0)
+		stutter = 0;
+	if (stutter) {
+		firsterr = torture_stutter_init(stutter * HZ);
+		if (firsterr)
+			goto unwind;
+	}
+	if (fqs_duration < 0)
+		fqs_duration = 0;
+	if (fqs_duration) {
+		/* Create the fqs thread */
+		torture_create_kthread(rcu_torture_fqs, NULL, fqs_task);
+		if (firsterr)
+			goto unwind;
+	}
+	if (test_boost_interval < 1)
+		test_boost_interval = 1;
+	if (test_boost_duration < 2)
+		test_boost_duration = 2;
+	if ((test_boost == 1 && cur_ops->can_boost) ||
+	    test_boost == 2) {
+
+		boost_starttime = jiffies + test_boost_interval * HZ;
+		register_cpu_notifier(&rcutorture_cpu_nb);
+		for_each_possible_cpu(i) {
+			if (cpu_is_offline(i))
+				continue;  /* Heuristic: CPU can go offline. */
+			firsterr = rcutorture_booster_init(i);
+			if (firsterr)
+				goto unwind;
+		}
+	}
+	firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
+	if (firsterr)
+		goto unwind;
+	firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ);
+	if (firsterr)
+		goto unwind;
+	firsterr = rcu_torture_stall_init();
+	if (firsterr)
+		goto unwind;
+	firsterr = rcu_torture_barrier_init();
+	if (firsterr)
+		goto unwind;
+	if (object_debug)
+		rcu_test_debug_objects();
+	rcutorture_record_test_transition();
+	torture_init_end();
+	return 0;
+
+unwind:
+	torture_init_end();
+	rcu_torture_cleanup();
+	return firsterr;
+}
+
+module_init(rcu_torture_init);
+module_exit(rcu_torture_cleanup);
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 3318d82..c639556 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright (C) IBM Corporation, 2006
  * Copyright (C) Fujitsu, 2012
@@ -36,8 +36,6 @@
 #include <linux/delay.h>
 #include <linux/srcu.h>
 
-#include <trace/events/rcu.h>
-
 #include "rcu.h"
 
 /*
@@ -398,7 +396,7 @@
 	rcu_batch_queue(&sp->batch_queue, head);
 	if (!sp->running) {
 		sp->running = true;
-		schedule_delayed_work(&sp->work, 0);
+		queue_delayed_work(system_power_efficient_wq, &sp->work, 0);
 	}
 	spin_unlock_irqrestore(&sp->queue_lock, flags);
 }
@@ -674,7 +672,8 @@
 	}
 
 	if (pending)
-		schedule_delayed_work(&sp->work, SRCU_INTERVAL);
+		queue_delayed_work(system_power_efficient_wq,
+				   &sp->work, SRCU_INTERVAL);
 }
 
 /*
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 1254f31..d9efcc1 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
@@ -37,10 +37,6 @@
 #include <linux/prefetch.h>
 #include <linux/ftrace_event.h>
 
-#ifdef CONFIG_RCU_TRACE
-#include <trace/events/rcu.h>
-#endif /* #else #ifdef CONFIG_RCU_TRACE */
-
 #include "rcu.h"
 
 /* Forward declarations for tiny_plugin.h. */
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index 280d06c..4315285 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -14,8 +14,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright (c) 2010 Linaro
  *
diff --git a/kernel/rcu/torture.c b/kernel/rcu/torture.c
deleted file mode 100644
index 732f8ae..0000000
--- a/kernel/rcu/torture.c
+++ /dev/null
@@ -1,2148 +0,0 @@
-/*
- * Read-Copy Update module-based torture test facility
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) IBM Corporation, 2005, 2006
- *
- * Authors: Paul E. McKenney <paulmck@us.ibm.com>
- *	  Josh Triplett <josh@freedesktop.org>
- *
- * See also:  Documentation/RCU/torture.txt
- */
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kthread.h>
-#include <linux/err.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/rcupdate.h>
-#include <linux/interrupt.h>
-#include <linux/sched.h>
-#include <linux/atomic.h>
-#include <linux/bitops.h>
-#include <linux/completion.h>
-#include <linux/moduleparam.h>
-#include <linux/percpu.h>
-#include <linux/notifier.h>
-#include <linux/reboot.h>
-#include <linux/freezer.h>
-#include <linux/cpu.h>
-#include <linux/delay.h>
-#include <linux/stat.h>
-#include <linux/srcu.h>
-#include <linux/slab.h>
-#include <linux/trace_clock.h>
-#include <asm/byteorder.h>
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>");
-
-MODULE_ALIAS("rcutorture");
-#ifdef MODULE_PARAM_PREFIX
-#undef MODULE_PARAM_PREFIX
-#endif
-#define MODULE_PARAM_PREFIX "rcutorture."
-
-static int fqs_duration;
-module_param(fqs_duration, int, 0444);
-MODULE_PARM_DESC(fqs_duration, "Duration of fqs bursts (us), 0 to disable");
-static int fqs_holdoff;
-module_param(fqs_holdoff, int, 0444);
-MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
-static int fqs_stutter = 3;
-module_param(fqs_stutter, int, 0444);
-MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
-static bool gp_exp;
-module_param(gp_exp, bool, 0444);
-MODULE_PARM_DESC(gp_exp, "Use expedited GP wait primitives");
-static bool gp_normal;
-module_param(gp_normal, bool, 0444);
-MODULE_PARM_DESC(gp_normal, "Use normal (non-expedited) GP wait primitives");
-static int irqreader = 1;
-module_param(irqreader, int, 0444);
-MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers");
-static int n_barrier_cbs;
-module_param(n_barrier_cbs, int, 0444);
-MODULE_PARM_DESC(n_barrier_cbs, "# of callbacks/kthreads for barrier testing");
-static int nfakewriters = 4;
-module_param(nfakewriters, int, 0444);
-MODULE_PARM_DESC(nfakewriters, "Number of RCU fake writer threads");
-static int nreaders = -1;
-module_param(nreaders, int, 0444);
-MODULE_PARM_DESC(nreaders, "Number of RCU reader threads");
-static int object_debug;
-module_param(object_debug, int, 0444);
-MODULE_PARM_DESC(object_debug, "Enable debug-object double call_rcu() testing");
-static int onoff_holdoff;
-module_param(onoff_holdoff, int, 0444);
-MODULE_PARM_DESC(onoff_holdoff, "Time after boot before CPU hotplugs (s)");
-static int onoff_interval;
-module_param(onoff_interval, int, 0444);
-MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable");
-static int shuffle_interval = 3;
-module_param(shuffle_interval, int, 0444);
-MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
-static int shutdown_secs;
-module_param(shutdown_secs, int, 0444);
-MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), <= zero to disable.");
-static int stall_cpu;
-module_param(stall_cpu, int, 0444);
-MODULE_PARM_DESC(stall_cpu, "Stall duration (s), zero to disable.");
-static int stall_cpu_holdoff = 10;
-module_param(stall_cpu_holdoff, int, 0444);
-MODULE_PARM_DESC(stall_cpu_holdoff, "Time to wait before starting stall (s).");
-static int stat_interval = 60;
-module_param(stat_interval, int, 0644);
-MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s");
-static int stutter = 5;
-module_param(stutter, int, 0444);
-MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
-static int test_boost = 1;
-module_param(test_boost, int, 0444);
-MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
-static int test_boost_duration = 4;
-module_param(test_boost_duration, int, 0444);
-MODULE_PARM_DESC(test_boost_duration, "Duration of each boost test, seconds.");
-static int test_boost_interval = 7;
-module_param(test_boost_interval, int, 0444);
-MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds.");
-static bool test_no_idle_hz = true;
-module_param(test_no_idle_hz, bool, 0444);
-MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
-static char *torture_type = "rcu";
-module_param(torture_type, charp, 0444);
-MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)");
-static bool verbose;
-module_param(verbose, bool, 0444);
-MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
-
-#define TORTURE_FLAG "-torture:"
-#define PRINTK_STRING(s) \
-	do { pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0)
-#define VERBOSE_PRINTK_STRING(s) \
-	do { if (verbose) pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0)
-#define VERBOSE_PRINTK_ERRSTRING(s) \
-	do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
-
-static int nrealreaders;
-static struct task_struct *writer_task;
-static struct task_struct **fakewriter_tasks;
-static struct task_struct **reader_tasks;
-static struct task_struct *stats_task;
-static struct task_struct *shuffler_task;
-static struct task_struct *stutter_task;
-static struct task_struct *fqs_task;
-static struct task_struct *boost_tasks[NR_CPUS];
-static struct task_struct *shutdown_task;
-#ifdef CONFIG_HOTPLUG_CPU
-static struct task_struct *onoff_task;
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-static struct task_struct *stall_task;
-static struct task_struct **barrier_cbs_tasks;
-static struct task_struct *barrier_task;
-
-#define RCU_TORTURE_PIPE_LEN 10
-
-struct rcu_torture {
-	struct rcu_head rtort_rcu;
-	int rtort_pipe_count;
-	struct list_head rtort_free;
-	int rtort_mbtest;
-};
-
-static LIST_HEAD(rcu_torture_freelist);
-static struct rcu_torture __rcu *rcu_torture_current;
-static unsigned long rcu_torture_current_version;
-static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
-static DEFINE_SPINLOCK(rcu_torture_lock);
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) =
-	{ 0 };
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) =
-	{ 0 };
-static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1];
-static atomic_t n_rcu_torture_alloc;
-static atomic_t n_rcu_torture_alloc_fail;
-static atomic_t n_rcu_torture_free;
-static atomic_t n_rcu_torture_mberror;
-static atomic_t n_rcu_torture_error;
-static long n_rcu_torture_barrier_error;
-static long n_rcu_torture_boost_ktrerror;
-static long n_rcu_torture_boost_rterror;
-static long n_rcu_torture_boost_failure;
-static long n_rcu_torture_boosts;
-static long n_rcu_torture_timers;
-static long n_offline_attempts;
-static long n_offline_successes;
-static unsigned long sum_offline;
-static int min_offline = -1;
-static int max_offline;
-static long n_online_attempts;
-static long n_online_successes;
-static unsigned long sum_online;
-static int min_online = -1;
-static int max_online;
-static long n_barrier_attempts;
-static long n_barrier_successes;
-static struct list_head rcu_torture_removed;
-static cpumask_var_t shuffle_tmp_mask;
-
-static int stutter_pause_test;
-
-#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
-#define RCUTORTURE_RUNNABLE_INIT 1
-#else
-#define RCUTORTURE_RUNNABLE_INIT 0
-#endif
-int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
-module_param(rcutorture_runnable, int, 0444);
-MODULE_PARM_DESC(rcutorture_runnable, "Start rcutorture at boot");
-
-#if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU)
-#define rcu_can_boost() 1
-#else /* #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
-#define rcu_can_boost() 0
-#endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
-
-#ifdef CONFIG_RCU_TRACE
-static u64 notrace rcu_trace_clock_local(void)
-{
-	u64 ts = trace_clock_local();
-	unsigned long __maybe_unused ts_rem = do_div(ts, NSEC_PER_USEC);
-	return ts;
-}
-#else /* #ifdef CONFIG_RCU_TRACE */
-static u64 notrace rcu_trace_clock_local(void)
-{
-	return 0ULL;
-}
-#endif /* #else #ifdef CONFIG_RCU_TRACE */
-
-static unsigned long shutdown_time;	/* jiffies to system shutdown. */
-static unsigned long boost_starttime;	/* jiffies of next boost test start. */
-DEFINE_MUTEX(boost_mutex);		/* protect setting boost_starttime */
-					/*  and boost task create/destroy. */
-static atomic_t barrier_cbs_count;	/* Barrier callbacks registered. */
-static bool barrier_phase;		/* Test phase. */
-static atomic_t barrier_cbs_invoked;	/* Barrier callbacks invoked. */
-static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
-static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
-
-/* Mediate rmmod and system shutdown.  Concurrent rmmod & shutdown illegal! */
-
-#define FULLSTOP_DONTSTOP 0	/* Normal operation. */
-#define FULLSTOP_SHUTDOWN 1	/* System shutdown with rcutorture running. */
-#define FULLSTOP_RMMOD    2	/* Normal rmmod of rcutorture. */
-static int fullstop = FULLSTOP_RMMOD;
-/*
- * Protect fullstop transitions and spawning of kthreads.
- */
-static DEFINE_MUTEX(fullstop_mutex);
-
-/* Forward reference. */
-static void rcu_torture_cleanup(void);
-
-/*
- * Detect and respond to a system shutdown.
- */
-static int
-rcutorture_shutdown_notify(struct notifier_block *unused1,
-			   unsigned long unused2, void *unused3)
-{
-	mutex_lock(&fullstop_mutex);
-	if (fullstop == FULLSTOP_DONTSTOP)
-		fullstop = FULLSTOP_SHUTDOWN;
-	else
-		pr_warn(/* but going down anyway, so... */
-		       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
-	mutex_unlock(&fullstop_mutex);
-	return NOTIFY_DONE;
-}
-
-/*
- * Absorb kthreads into a kernel function that won't return, so that
- * they won't ever access module text or data again.
- */
-static void rcutorture_shutdown_absorb(const char *title)
-{
-	if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
-		pr_notice(
-		       "rcutorture thread %s parking due to system shutdown\n",
-		       title);
-		schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
-	}
-}
-
-/*
- * Allocate an element from the rcu_tortures pool.
- */
-static struct rcu_torture *
-rcu_torture_alloc(void)
-{
-	struct list_head *p;
-
-	spin_lock_bh(&rcu_torture_lock);
-	if (list_empty(&rcu_torture_freelist)) {
-		atomic_inc(&n_rcu_torture_alloc_fail);
-		spin_unlock_bh(&rcu_torture_lock);
-		return NULL;
-	}
-	atomic_inc(&n_rcu_torture_alloc);
-	p = rcu_torture_freelist.next;
-	list_del_init(p);
-	spin_unlock_bh(&rcu_torture_lock);
-	return container_of(p, struct rcu_torture, rtort_free);
-}
-
-/*
- * Free an element to the rcu_tortures pool.
- */
-static void
-rcu_torture_free(struct rcu_torture *p)
-{
-	atomic_inc(&n_rcu_torture_free);
-	spin_lock_bh(&rcu_torture_lock);
-	list_add_tail(&p->rtort_free, &rcu_torture_freelist);
-	spin_unlock_bh(&rcu_torture_lock);
-}
-
-struct rcu_random_state {
-	unsigned long rrs_state;
-	long rrs_count;
-};
-
-#define RCU_RANDOM_MULT 39916801  /* prime */
-#define RCU_RANDOM_ADD	479001701 /* prime */
-#define RCU_RANDOM_REFRESH 10000
-
-#define DEFINE_RCU_RANDOM(name) struct rcu_random_state name = { 0, 0 }
-
-/*
- * Crude but fast random-number generator.  Uses a linear congruential
- * generator, with occasional help from cpu_clock().
- */
-static unsigned long
-rcu_random(struct rcu_random_state *rrsp)
-{
-	if (--rrsp->rrs_count < 0) {
-		rrsp->rrs_state += (unsigned long)local_clock();
-		rrsp->rrs_count = RCU_RANDOM_REFRESH;
-	}
-	rrsp->rrs_state = rrsp->rrs_state * RCU_RANDOM_MULT + RCU_RANDOM_ADD;
-	return swahw32(rrsp->rrs_state);
-}
-
-static void
-rcu_stutter_wait(const char *title)
-{
-	while (stutter_pause_test || !rcutorture_runnable) {
-		if (rcutorture_runnable)
-			schedule_timeout_interruptible(1);
-		else
-			schedule_timeout_interruptible(round_jiffies_relative(HZ));
-		rcutorture_shutdown_absorb(title);
-	}
-}
-
-/*
- * Operations vector for selecting different types of tests.
- */
-
-struct rcu_torture_ops {
-	void (*init)(void);
-	int (*readlock)(void);
-	void (*read_delay)(struct rcu_random_state *rrsp);
-	void (*readunlock)(int idx);
-	int (*completed)(void);
-	void (*deferred_free)(struct rcu_torture *p);
-	void (*sync)(void);
-	void (*exp_sync)(void);
-	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
-	void (*cb_barrier)(void);
-	void (*fqs)(void);
-	void (*stats)(char *page);
-	int irq_capable;
-	int can_boost;
-	const char *name;
-};
-
-static struct rcu_torture_ops *cur_ops;
-
-/*
- * Definitions for rcu torture testing.
- */
-
-static int rcu_torture_read_lock(void) __acquires(RCU)
-{
-	rcu_read_lock();
-	return 0;
-}
-
-static void rcu_read_delay(struct rcu_random_state *rrsp)
-{
-	const unsigned long shortdelay_us = 200;
-	const unsigned long longdelay_ms = 50;
-
-	/* We want a short delay sometimes to make a reader delay the grace
-	 * period, and we want a long delay occasionally to trigger
-	 * force_quiescent_state. */
-
-	if (!(rcu_random(rrsp) % (nrealreaders * 2000 * longdelay_ms)))
-		mdelay(longdelay_ms);
-	if (!(rcu_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
-		udelay(shortdelay_us);
-#ifdef CONFIG_PREEMPT
-	if (!preempt_count() && !(rcu_random(rrsp) % (nrealreaders * 20000)))
-		preempt_schedule();  /* No QS if preempt_disable() in effect */
-#endif
-}
-
-static void rcu_torture_read_unlock(int idx) __releases(RCU)
-{
-	rcu_read_unlock();
-}
-
-static int rcu_torture_completed(void)
-{
-	return rcu_batches_completed();
-}
-
-static void
-rcu_torture_cb(struct rcu_head *p)
-{
-	int i;
-	struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu);
-
-	if (fullstop != FULLSTOP_DONTSTOP) {
-		/* Test is ending, just drop callbacks on the floor. */
-		/* The next initialization will pick up the pieces. */
-		return;
-	}
-	i = rp->rtort_pipe_count;
-	if (i > RCU_TORTURE_PIPE_LEN)
-		i = RCU_TORTURE_PIPE_LEN;
-	atomic_inc(&rcu_torture_wcount[i]);
-	if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
-		rp->rtort_mbtest = 0;
-		rcu_torture_free(rp);
-	} else {
-		cur_ops->deferred_free(rp);
-	}
-}
-
-static int rcu_no_completed(void)
-{
-	return 0;
-}
-
-static void rcu_torture_deferred_free(struct rcu_torture *p)
-{
-	call_rcu(&p->rtort_rcu, rcu_torture_cb);
-}
-
-static void rcu_sync_torture_init(void)
-{
-	INIT_LIST_HEAD(&rcu_torture_removed);
-}
-
-static struct rcu_torture_ops rcu_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_torture_read_lock,
-	.read_delay	= rcu_read_delay,
-	.readunlock	= rcu_torture_read_unlock,
-	.completed	= rcu_torture_completed,
-	.deferred_free	= rcu_torture_deferred_free,
-	.sync		= synchronize_rcu,
-	.exp_sync	= synchronize_rcu_expedited,
-	.call		= call_rcu,
-	.cb_barrier	= rcu_barrier,
-	.fqs		= rcu_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.can_boost	= rcu_can_boost(),
-	.name		= "rcu"
-};
-
-/*
- * Definitions for rcu_bh torture testing.
- */
-
-static int rcu_bh_torture_read_lock(void) __acquires(RCU_BH)
-{
-	rcu_read_lock_bh();
-	return 0;
-}
-
-static void rcu_bh_torture_read_unlock(int idx) __releases(RCU_BH)
-{
-	rcu_read_unlock_bh();
-}
-
-static int rcu_bh_torture_completed(void)
-{
-	return rcu_batches_completed_bh();
-}
-
-static void rcu_bh_torture_deferred_free(struct rcu_torture *p)
-{
-	call_rcu_bh(&p->rtort_rcu, rcu_torture_cb);
-}
-
-static struct rcu_torture_ops rcu_bh_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_bh_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= rcu_bh_torture_read_unlock,
-	.completed	= rcu_bh_torture_completed,
-	.deferred_free	= rcu_bh_torture_deferred_free,
-	.sync		= synchronize_rcu_bh,
-	.exp_sync	= synchronize_rcu_bh_expedited,
-	.call		= call_rcu_bh,
-	.cb_barrier	= rcu_barrier_bh,
-	.fqs		= rcu_bh_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.name		= "rcu_bh"
-};
-
-/*
- * Definitions for srcu torture testing.
- */
-
-DEFINE_STATIC_SRCU(srcu_ctl);
-
-static int srcu_torture_read_lock(void) __acquires(&srcu_ctl)
-{
-	return srcu_read_lock(&srcu_ctl);
-}
-
-static void srcu_read_delay(struct rcu_random_state *rrsp)
-{
-	long delay;
-	const long uspertick = 1000000 / HZ;
-	const long longdelay = 10;
-
-	/* We want there to be long-running readers, but not all the time. */
-
-	delay = rcu_random(rrsp) % (nrealreaders * 2 * longdelay * uspertick);
-	if (!delay)
-		schedule_timeout_interruptible(longdelay);
-	else
-		rcu_read_delay(rrsp);
-}
-
-static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
-{
-	srcu_read_unlock(&srcu_ctl, idx);
-}
-
-static int srcu_torture_completed(void)
-{
-	return srcu_batches_completed(&srcu_ctl);
-}
-
-static void srcu_torture_deferred_free(struct rcu_torture *rp)
-{
-	call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb);
-}
-
-static void srcu_torture_synchronize(void)
-{
-	synchronize_srcu(&srcu_ctl);
-}
-
-static void srcu_torture_call(struct rcu_head *head,
-			      void (*func)(struct rcu_head *head))
-{
-	call_srcu(&srcu_ctl, head, func);
-}
-
-static void srcu_torture_barrier(void)
-{
-	srcu_barrier(&srcu_ctl);
-}
-
-static void srcu_torture_stats(char *page)
-{
-	int cpu;
-	int idx = srcu_ctl.completed & 0x1;
-
-	page += sprintf(page, "%s%s per-CPU(idx=%d):",
-		       torture_type, TORTURE_FLAG, idx);
-	for_each_possible_cpu(cpu) {
-		page += sprintf(page, " %d(%lu,%lu)", cpu,
-			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
-			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
-	}
-	sprintf(page, "\n");
-}
-
-static void srcu_torture_synchronize_expedited(void)
-{
-	synchronize_srcu_expedited(&srcu_ctl);
-}
-
-static struct rcu_torture_ops srcu_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= srcu_torture_read_lock,
-	.read_delay	= srcu_read_delay,
-	.readunlock	= srcu_torture_read_unlock,
-	.completed	= srcu_torture_completed,
-	.deferred_free	= srcu_torture_deferred_free,
-	.sync		= srcu_torture_synchronize,
-	.exp_sync	= srcu_torture_synchronize_expedited,
-	.call		= srcu_torture_call,
-	.cb_barrier	= srcu_torture_barrier,
-	.stats		= srcu_torture_stats,
-	.name		= "srcu"
-};
-
-/*
- * Definitions for sched torture testing.
- */
-
-static int sched_torture_read_lock(void)
-{
-	preempt_disable();
-	return 0;
-}
-
-static void sched_torture_read_unlock(int idx)
-{
-	preempt_enable();
-}
-
-static void rcu_sched_torture_deferred_free(struct rcu_torture *p)
-{
-	call_rcu_sched(&p->rtort_rcu, rcu_torture_cb);
-}
-
-static struct rcu_torture_ops sched_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= sched_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= sched_torture_read_unlock,
-	.completed	= rcu_no_completed,
-	.deferred_free	= rcu_sched_torture_deferred_free,
-	.sync		= synchronize_sched,
-	.exp_sync	= synchronize_sched_expedited,
-	.call		= call_rcu_sched,
-	.cb_barrier	= rcu_barrier_sched,
-	.fqs		= rcu_sched_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.name		= "sched"
-};
-
-/*
- * RCU torture priority-boost testing.  Runs one real-time thread per
- * CPU for moderate bursts, repeatedly registering RCU callbacks and
- * spinning waiting for them to be invoked.  If a given callback takes
- * too long to be invoked, we assume that priority inversion has occurred.
- */
-
-struct rcu_boost_inflight {
-	struct rcu_head rcu;
-	int inflight;
-};
-
-static void rcu_torture_boost_cb(struct rcu_head *head)
-{
-	struct rcu_boost_inflight *rbip =
-		container_of(head, struct rcu_boost_inflight, rcu);
-
-	smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
-	rbip->inflight = 0;
-}
-
-static int rcu_torture_boost(void *arg)
-{
-	unsigned long call_rcu_time;
-	unsigned long endtime;
-	unsigned long oldstarttime;
-	struct rcu_boost_inflight rbi = { .inflight = 0 };
-	struct sched_param sp;
-
-	VERBOSE_PRINTK_STRING("rcu_torture_boost started");
-
-	/* Set real-time priority. */
-	sp.sched_priority = 1;
-	if (sched_setscheduler(current, SCHED_FIFO, &sp) < 0) {
-		VERBOSE_PRINTK_STRING("rcu_torture_boost RT prio failed!");
-		n_rcu_torture_boost_rterror++;
-	}
-
-	init_rcu_head_on_stack(&rbi.rcu);
-	/* Each pass through the following loop does one boost-test cycle. */
-	do {
-		/* Wait for the next test interval. */
-		oldstarttime = boost_starttime;
-		while (ULONG_CMP_LT(jiffies, oldstarttime)) {
-			schedule_timeout_interruptible(oldstarttime - jiffies);
-			rcu_stutter_wait("rcu_torture_boost");
-			if (kthread_should_stop() ||
-			    fullstop != FULLSTOP_DONTSTOP)
-				goto checkwait;
-		}
-
-		/* Do one boost-test interval. */
-		endtime = oldstarttime + test_boost_duration * HZ;
-		call_rcu_time = jiffies;
-		while (ULONG_CMP_LT(jiffies, endtime)) {
-			/* If we don't have a callback in flight, post one. */
-			if (!rbi.inflight) {
-				smp_mb(); /* RCU core before ->inflight = 1. */
-				rbi.inflight = 1;
-				call_rcu(&rbi.rcu, rcu_torture_boost_cb);
-				if (jiffies - call_rcu_time >
-					 test_boost_duration * HZ - HZ / 2) {
-					VERBOSE_PRINTK_STRING("rcu_torture_boost boosting failed");
-					n_rcu_torture_boost_failure++;
-				}
-				call_rcu_time = jiffies;
-			}
-			cond_resched();
-			rcu_stutter_wait("rcu_torture_boost");
-			if (kthread_should_stop() ||
-			    fullstop != FULLSTOP_DONTSTOP)
-				goto checkwait;
-		}
-
-		/*
-		 * Set the start time of the next test interval.
-		 * Yes, this is vulnerable to long delays, but such
-		 * delays simply cause a false negative for the next
-		 * interval.  Besides, we are running at RT priority,
-		 * so delays should be relatively rare.
-		 */
-		while (oldstarttime == boost_starttime &&
-		       !kthread_should_stop()) {
-			if (mutex_trylock(&boost_mutex)) {
-				boost_starttime = jiffies +
-						  test_boost_interval * HZ;
-				n_rcu_torture_boosts++;
-				mutex_unlock(&boost_mutex);
-				break;
-			}
-			schedule_timeout_uninterruptible(1);
-		}
-
-		/* Go do the stutter. */
-checkwait:	rcu_stutter_wait("rcu_torture_boost");
-	} while (!kthread_should_stop() && fullstop  == FULLSTOP_DONTSTOP);
-
-	/* Clean up and exit. */
-	VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping");
-	rcutorture_shutdown_absorb("rcu_torture_boost");
-	while (!kthread_should_stop() || rbi.inflight)
-		schedule_timeout_uninterruptible(1);
-	smp_mb(); /* order accesses to ->inflight before stack-frame death. */
-	destroy_rcu_head_on_stack(&rbi.rcu);
-	return 0;
-}
-
-/*
- * RCU torture force-quiescent-state kthread.  Repeatedly induces
- * bursts of calls to force_quiescent_state(), increasing the probability
- * of occurrence of some important types of race conditions.
- */
-static int
-rcu_torture_fqs(void *arg)
-{
-	unsigned long fqs_resume_time;
-	int fqs_burst_remaining;
-
-	VERBOSE_PRINTK_STRING("rcu_torture_fqs task started");
-	do {
-		fqs_resume_time = jiffies + fqs_stutter * HZ;
-		while (ULONG_CMP_LT(jiffies, fqs_resume_time) &&
-		       !kthread_should_stop()) {
-			schedule_timeout_interruptible(1);
-		}
-		fqs_burst_remaining = fqs_duration;
-		while (fqs_burst_remaining > 0 &&
-		       !kthread_should_stop()) {
-			cur_ops->fqs();
-			udelay(fqs_holdoff);
-			fqs_burst_remaining -= fqs_holdoff;
-		}
-		rcu_stutter_wait("rcu_torture_fqs");
-	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-	VERBOSE_PRINTK_STRING("rcu_torture_fqs task stopping");
-	rcutorture_shutdown_absorb("rcu_torture_fqs");
-	while (!kthread_should_stop())
-		schedule_timeout_uninterruptible(1);
-	return 0;
-}
-
-/*
- * RCU torture writer kthread.  Repeatedly substitutes a new structure
- * for that pointed to by rcu_torture_current, freeing the old structure
- * after a series of grace periods (the "pipeline").
- */
-static int
-rcu_torture_writer(void *arg)
-{
-	bool exp;
-	int i;
-	struct rcu_torture *rp;
-	struct rcu_torture *rp1;
-	struct rcu_torture *old_rp;
-	static DEFINE_RCU_RANDOM(rand);
-
-	VERBOSE_PRINTK_STRING("rcu_torture_writer task started");
-	set_user_nice(current, 19);
-
-	do {
-		schedule_timeout_uninterruptible(1);
-		rp = rcu_torture_alloc();
-		if (rp == NULL)
-			continue;
-		rp->rtort_pipe_count = 0;
-		udelay(rcu_random(&rand) & 0x3ff);
-		old_rp = rcu_dereference_check(rcu_torture_current,
-					       current == writer_task);
-		rp->rtort_mbtest = 1;
-		rcu_assign_pointer(rcu_torture_current, rp);
-		smp_wmb(); /* Mods to old_rp must follow rcu_assign_pointer() */
-		if (old_rp) {
-			i = old_rp->rtort_pipe_count;
-			if (i > RCU_TORTURE_PIPE_LEN)
-				i = RCU_TORTURE_PIPE_LEN;
-			atomic_inc(&rcu_torture_wcount[i]);
-			old_rp->rtort_pipe_count++;
-			if (gp_normal == gp_exp)
-				exp = !!(rcu_random(&rand) & 0x80);
-			else
-				exp = gp_exp;
-			if (!exp) {
-				cur_ops->deferred_free(old_rp);
-			} else {
-				cur_ops->exp_sync();
-				list_add(&old_rp->rtort_free,
-					 &rcu_torture_removed);
-				list_for_each_entry_safe(rp, rp1,
-							 &rcu_torture_removed,
-							 rtort_free) {
-					i = rp->rtort_pipe_count;
-					if (i > RCU_TORTURE_PIPE_LEN)
-						i = RCU_TORTURE_PIPE_LEN;
-					atomic_inc(&rcu_torture_wcount[i]);
-					if (++rp->rtort_pipe_count >=
-					    RCU_TORTURE_PIPE_LEN) {
-						rp->rtort_mbtest = 0;
-						list_del(&rp->rtort_free);
-						rcu_torture_free(rp);
-					}
-				 }
-			}
-		}
-		rcutorture_record_progress(++rcu_torture_current_version);
-		rcu_stutter_wait("rcu_torture_writer");
-	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-	VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
-	rcutorture_shutdown_absorb("rcu_torture_writer");
-	while (!kthread_should_stop())
-		schedule_timeout_uninterruptible(1);
-	return 0;
-}
-
-/*
- * RCU torture fake writer kthread.  Repeatedly calls sync, with a random
- * delay between calls.
- */
-static int
-rcu_torture_fakewriter(void *arg)
-{
-	DEFINE_RCU_RANDOM(rand);
-
-	VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task started");
-	set_user_nice(current, 19);
-
-	do {
-		schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
-		udelay(rcu_random(&rand) & 0x3ff);
-		if (cur_ops->cb_barrier != NULL &&
-		    rcu_random(&rand) % (nfakewriters * 8) == 0) {
-			cur_ops->cb_barrier();
-		} else if (gp_normal == gp_exp) {
-			if (rcu_random(&rand) & 0x80)
-				cur_ops->sync();
-			else
-				cur_ops->exp_sync();
-		} else if (gp_normal) {
-			cur_ops->sync();
-		} else {
-			cur_ops->exp_sync();
-		}
-		rcu_stutter_wait("rcu_torture_fakewriter");
-	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-
-	VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
-	rcutorture_shutdown_absorb("rcu_torture_fakewriter");
-	while (!kthread_should_stop())
-		schedule_timeout_uninterruptible(1);
-	return 0;
-}
-
-void rcutorture_trace_dump(void)
-{
-	static atomic_t beenhere = ATOMIC_INIT(0);
-
-	if (atomic_read(&beenhere))
-		return;
-	if (atomic_xchg(&beenhere, 1) != 0)
-		return;
-	ftrace_dump(DUMP_ALL);
-}
-
-/*
- * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
- * incrementing the corresponding element of the pipeline array.  The
- * counter in the element should never be greater than 1, otherwise, the
- * RCU implementation is broken.
- */
-static void rcu_torture_timer(unsigned long unused)
-{
-	int idx;
-	int completed;
-	int completed_end;
-	static DEFINE_RCU_RANDOM(rand);
-	static DEFINE_SPINLOCK(rand_lock);
-	struct rcu_torture *p;
-	int pipe_count;
-	unsigned long long ts;
-
-	idx = cur_ops->readlock();
-	completed = cur_ops->completed();
-	ts = rcu_trace_clock_local();
-	p = rcu_dereference_check(rcu_torture_current,
-				  rcu_read_lock_bh_held() ||
-				  rcu_read_lock_sched_held() ||
-				  srcu_read_lock_held(&srcu_ctl));
-	if (p == NULL) {
-		/* Leave because rcu_torture_writer is not yet underway */
-		cur_ops->readunlock(idx);
-		return;
-	}
-	if (p->rtort_mbtest == 0)
-		atomic_inc(&n_rcu_torture_mberror);
-	spin_lock(&rand_lock);
-	cur_ops->read_delay(&rand);
-	n_rcu_torture_timers++;
-	spin_unlock(&rand_lock);
-	preempt_disable();
-	pipe_count = p->rtort_pipe_count;
-	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
-		/* Should not happen, but... */
-		pipe_count = RCU_TORTURE_PIPE_LEN;
-	}
-	completed_end = cur_ops->completed();
-	if (pipe_count > 1) {
-		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
-					  completed, completed_end);
-		rcutorture_trace_dump();
-	}
-	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = completed_end - completed;
-	if (completed > RCU_TORTURE_PIPE_LEN) {
-		/* Should not happen, but... */
-		completed = RCU_TORTURE_PIPE_LEN;
-	}
-	__this_cpu_inc(rcu_torture_batch[completed]);
-	preempt_enable();
-	cur_ops->readunlock(idx);
-}
-
-/*
- * RCU torture reader kthread.  Repeatedly dereferences rcu_torture_current,
- * incrementing the corresponding element of the pipeline array.  The
- * counter in the element should never be greater than 1, otherwise, the
- * RCU implementation is broken.
- */
-static int
-rcu_torture_reader(void *arg)
-{
-	int completed;
-	int completed_end;
-	int idx;
-	DEFINE_RCU_RANDOM(rand);
-	struct rcu_torture *p;
-	int pipe_count;
-	struct timer_list t;
-	unsigned long long ts;
-
-	VERBOSE_PRINTK_STRING("rcu_torture_reader task started");
-	set_user_nice(current, 19);
-	if (irqreader && cur_ops->irq_capable)
-		setup_timer_on_stack(&t, rcu_torture_timer, 0);
-
-	do {
-		if (irqreader && cur_ops->irq_capable) {
-			if (!timer_pending(&t))
-				mod_timer(&t, jiffies + 1);
-		}
-		idx = cur_ops->readlock();
-		completed = cur_ops->completed();
-		ts = rcu_trace_clock_local();
-		p = rcu_dereference_check(rcu_torture_current,
-					  rcu_read_lock_bh_held() ||
-					  rcu_read_lock_sched_held() ||
-					  srcu_read_lock_held(&srcu_ctl));
-		if (p == NULL) {
-			/* Wait for rcu_torture_writer to get underway */
-			cur_ops->readunlock(idx);
-			schedule_timeout_interruptible(HZ);
-			continue;
-		}
-		if (p->rtort_mbtest == 0)
-			atomic_inc(&n_rcu_torture_mberror);
-		cur_ops->read_delay(&rand);
-		preempt_disable();
-		pipe_count = p->rtort_pipe_count;
-		if (pipe_count > RCU_TORTURE_PIPE_LEN) {
-			/* Should not happen, but... */
-			pipe_count = RCU_TORTURE_PIPE_LEN;
-		}
-		completed_end = cur_ops->completed();
-		if (pipe_count > 1) {
-			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
-						  ts, completed, completed_end);
-			rcutorture_trace_dump();
-		}
-		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = completed_end - completed;
-		if (completed > RCU_TORTURE_PIPE_LEN) {
-			/* Should not happen, but... */
-			completed = RCU_TORTURE_PIPE_LEN;
-		}
-		__this_cpu_inc(rcu_torture_batch[completed]);
-		preempt_enable();
-		cur_ops->readunlock(idx);
-		schedule();
-		rcu_stutter_wait("rcu_torture_reader");
-	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
-	rcutorture_shutdown_absorb("rcu_torture_reader");
-	if (irqreader && cur_ops->irq_capable)
-		del_timer_sync(&t);
-	while (!kthread_should_stop())
-		schedule_timeout_uninterruptible(1);
-	return 0;
-}
-
-/*
- * Create an RCU-torture statistics message in the specified buffer.
- */
-static void
-rcu_torture_printk(char *page)
-{
-	int cpu;
-	int i;
-	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
-	long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
-
-	for_each_possible_cpu(cpu) {
-		for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
-			pipesummary[i] += per_cpu(rcu_torture_count, cpu)[i];
-			batchsummary[i] += per_cpu(rcu_torture_batch, cpu)[i];
-		}
-	}
-	for (i = RCU_TORTURE_PIPE_LEN - 1; i >= 0; i--) {
-		if (pipesummary[i] != 0)
-			break;
-	}
-	page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
-	page += sprintf(page,
-		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
-		       rcu_torture_current,
-		       rcu_torture_current_version,
-		       list_empty(&rcu_torture_freelist),
-		       atomic_read(&n_rcu_torture_alloc),
-		       atomic_read(&n_rcu_torture_alloc_fail),
-		       atomic_read(&n_rcu_torture_free));
-	page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
-		       atomic_read(&n_rcu_torture_mberror),
-		       n_rcu_torture_boost_ktrerror,
-		       n_rcu_torture_boost_rterror);
-	page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
-		       n_rcu_torture_boost_failure,
-		       n_rcu_torture_boosts,
-		       n_rcu_torture_timers);
-	page += sprintf(page,
-		       "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
-		       n_online_successes, n_online_attempts,
-		       n_offline_successes, n_offline_attempts,
-		       min_online, max_online,
-		       min_offline, max_offline,
-		       sum_online, sum_offline, HZ);
-	page += sprintf(page, "barrier: %ld/%ld:%ld",
-		       n_barrier_successes,
-		       n_barrier_attempts,
-		       n_rcu_torture_barrier_error);
-	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
-	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
-	    n_rcu_torture_barrier_error != 0 ||
-	    n_rcu_torture_boost_ktrerror != 0 ||
-	    n_rcu_torture_boost_rterror != 0 ||
-	    n_rcu_torture_boost_failure != 0 ||
-	    i > 1) {
-		page += sprintf(page, "!!! ");
-		atomic_inc(&n_rcu_torture_error);
-		WARN_ON_ONCE(1);
-	}
-	page += sprintf(page, "Reader Pipe: ");
-	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		page += sprintf(page, " %ld", pipesummary[i]);
-	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
-	page += sprintf(page, "Reader Batch: ");
-	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		page += sprintf(page, " %ld", batchsummary[i]);
-	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
-	page += sprintf(page, "Free-Block Circulation: ");
-	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
-		page += sprintf(page, " %d",
-			       atomic_read(&rcu_torture_wcount[i]));
-	}
-	page += sprintf(page, "\n");
-	if (cur_ops->stats)
-		cur_ops->stats(page);
-}
-
-/*
- * Print torture statistics.  Caller must ensure that there is only
- * one call to this function at a given time!!!  This is normally
- * accomplished by relying on the module system to only have one copy
- * of the module loaded, and then by giving the rcu_torture_stats
- * kthread full control (or the init/cleanup functions when rcu_torture_stats
- * thread is not running).
- */
-static void
-rcu_torture_stats_print(void)
-{
-	int size = nr_cpu_ids * 200 + 8192;
-	char *buf;
-
-	buf = kmalloc(size, GFP_KERNEL);
-	if (!buf) {
-		pr_err("rcu-torture: Out of memory, need: %d", size);
-		return;
-	}
-	rcu_torture_printk(buf);
-	pr_alert("%s", buf);
-	kfree(buf);
-}
-
-/*
- * Periodically prints torture statistics, if periodic statistics printing
- * was specified via the stat_interval module parameter.
- *
- * No need to worry about fullstop here, since this one doesn't reference
- * volatile state or register callbacks.
- */
-static int
-rcu_torture_stats(void *arg)
-{
-	VERBOSE_PRINTK_STRING("rcu_torture_stats task started");
-	do {
-		schedule_timeout_interruptible(stat_interval * HZ);
-		rcu_torture_stats_print();
-		rcutorture_shutdown_absorb("rcu_torture_stats");
-	} while (!kthread_should_stop());
-	VERBOSE_PRINTK_STRING("rcu_torture_stats task stopping");
-	return 0;
-}
-
-static int rcu_idle_cpu;	/* Force all torture tasks off this CPU */
-
-/* Shuffle tasks such that we allow @rcu_idle_cpu to become idle. A special case
- * is when @rcu_idle_cpu = -1, when we allow the tasks to run on all CPUs.
- */
-static void rcu_torture_shuffle_tasks(void)
-{
-	int i;
-
-	cpumask_setall(shuffle_tmp_mask);
-	get_online_cpus();
-
-	/* No point in shuffling if there is only one online CPU (ex: UP) */
-	if (num_online_cpus() == 1) {
-		put_online_cpus();
-		return;
-	}
-
-	if (rcu_idle_cpu != -1)
-		cpumask_clear_cpu(rcu_idle_cpu, shuffle_tmp_mask);
-
-	set_cpus_allowed_ptr(current, shuffle_tmp_mask);
-
-	if (reader_tasks) {
-		for (i = 0; i < nrealreaders; i++)
-			if (reader_tasks[i])
-				set_cpus_allowed_ptr(reader_tasks[i],
-						     shuffle_tmp_mask);
-	}
-	if (fakewriter_tasks) {
-		for (i = 0; i < nfakewriters; i++)
-			if (fakewriter_tasks[i])
-				set_cpus_allowed_ptr(fakewriter_tasks[i],
-						     shuffle_tmp_mask);
-	}
-	if (writer_task)
-		set_cpus_allowed_ptr(writer_task, shuffle_tmp_mask);
-	if (stats_task)
-		set_cpus_allowed_ptr(stats_task, shuffle_tmp_mask);
-	if (stutter_task)
-		set_cpus_allowed_ptr(stutter_task, shuffle_tmp_mask);
-	if (fqs_task)
-		set_cpus_allowed_ptr(fqs_task, shuffle_tmp_mask);
-	if (shutdown_task)
-		set_cpus_allowed_ptr(shutdown_task, shuffle_tmp_mask);
-#ifdef CONFIG_HOTPLUG_CPU
-	if (onoff_task)
-		set_cpus_allowed_ptr(onoff_task, shuffle_tmp_mask);
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-	if (stall_task)
-		set_cpus_allowed_ptr(stall_task, shuffle_tmp_mask);
-	if (barrier_cbs_tasks)
-		for (i = 0; i < n_barrier_cbs; i++)
-			if (barrier_cbs_tasks[i])
-				set_cpus_allowed_ptr(barrier_cbs_tasks[i],
-						     shuffle_tmp_mask);
-	if (barrier_task)
-		set_cpus_allowed_ptr(barrier_task, shuffle_tmp_mask);
-
-	if (rcu_idle_cpu == -1)
-		rcu_idle_cpu = num_online_cpus() - 1;
-	else
-		rcu_idle_cpu--;
-
-	put_online_cpus();
-}
-
-/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
- * system to become idle at a time and cut off its timer ticks. This is meant
- * to test the support for such tickless idle CPU in RCU.
- */
-static int
-rcu_torture_shuffle(void *arg)
-{
-	VERBOSE_PRINTK_STRING("rcu_torture_shuffle task started");
-	do {
-		schedule_timeout_interruptible(shuffle_interval * HZ);
-		rcu_torture_shuffle_tasks();
-		rcutorture_shutdown_absorb("rcu_torture_shuffle");
-	} while (!kthread_should_stop());
-	VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping");
-	return 0;
-}
-
-/* Cause the rcutorture test to "stutter", starting and stopping all
- * threads periodically.
- */
-static int
-rcu_torture_stutter(void *arg)
-{
-	VERBOSE_PRINTK_STRING("rcu_torture_stutter task started");
-	do {
-		schedule_timeout_interruptible(stutter * HZ);
-		stutter_pause_test = 1;
-		if (!kthread_should_stop())
-			schedule_timeout_interruptible(stutter * HZ);
-		stutter_pause_test = 0;
-		rcutorture_shutdown_absorb("rcu_torture_stutter");
-	} while (!kthread_should_stop());
-	VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
-	return 0;
-}
-
-static inline void
-rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
-{
-	pr_alert("%s" TORTURE_FLAG
-		 "--- %s: nreaders=%d nfakewriters=%d "
-		 "stat_interval=%d verbose=%d test_no_idle_hz=%d "
-		 "shuffle_interval=%d stutter=%d irqreader=%d "
-		 "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
-		 "test_boost=%d/%d test_boost_interval=%d "
-		 "test_boost_duration=%d shutdown_secs=%d "
-		 "stall_cpu=%d stall_cpu_holdoff=%d "
-		 "n_barrier_cbs=%d "
-		 "onoff_interval=%d onoff_holdoff=%d\n",
-		 torture_type, tag, nrealreaders, nfakewriters,
-		 stat_interval, verbose, test_no_idle_hz, shuffle_interval,
-		 stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
-		 test_boost, cur_ops->can_boost,
-		 test_boost_interval, test_boost_duration, shutdown_secs,
-		 stall_cpu, stall_cpu_holdoff,
-		 n_barrier_cbs,
-		 onoff_interval, onoff_holdoff);
-}
-
-static struct notifier_block rcutorture_shutdown_nb = {
-	.notifier_call = rcutorture_shutdown_notify,
-};
-
-static void rcutorture_booster_cleanup(int cpu)
-{
-	struct task_struct *t;
-
-	if (boost_tasks[cpu] == NULL)
-		return;
-	mutex_lock(&boost_mutex);
-	VERBOSE_PRINTK_STRING("Stopping rcu_torture_boost task");
-	t = boost_tasks[cpu];
-	boost_tasks[cpu] = NULL;
-	mutex_unlock(&boost_mutex);
-
-	/* This must be outside of the mutex, otherwise deadlock! */
-	kthread_stop(t);
-	boost_tasks[cpu] = NULL;
-}
-
-static int rcutorture_booster_init(int cpu)
-{
-	int retval;
-
-	if (boost_tasks[cpu] != NULL)
-		return 0;  /* Already created, nothing more to do. */
-
-	/* Don't allow time recalculation while creating a new task. */
-	mutex_lock(&boost_mutex);
-	VERBOSE_PRINTK_STRING("Creating rcu_torture_boost task");
-	boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL,
-						  cpu_to_node(cpu),
-						  "rcu_torture_boost");
-	if (IS_ERR(boost_tasks[cpu])) {
-		retval = PTR_ERR(boost_tasks[cpu]);
-		VERBOSE_PRINTK_STRING("rcu_torture_boost task create failed");
-		n_rcu_torture_boost_ktrerror++;
-		boost_tasks[cpu] = NULL;
-		mutex_unlock(&boost_mutex);
-		return retval;
-	}
-	kthread_bind(boost_tasks[cpu], cpu);
-	wake_up_process(boost_tasks[cpu]);
-	mutex_unlock(&boost_mutex);
-	return 0;
-}
-
-/*
- * Cause the rcutorture test to shutdown the system after the test has
- * run for the time specified by the shutdown_secs module parameter.
- */
-static int
-rcu_torture_shutdown(void *arg)
-{
-	long delta;
-	unsigned long jiffies_snap;
-
-	VERBOSE_PRINTK_STRING("rcu_torture_shutdown task started");
-	jiffies_snap = ACCESS_ONCE(jiffies);
-	while (ULONG_CMP_LT(jiffies_snap, shutdown_time) &&
-	       !kthread_should_stop()) {
-		delta = shutdown_time - jiffies_snap;
-		if (verbose)
-			pr_alert("%s" TORTURE_FLAG
-				 "rcu_torture_shutdown task: %lu jiffies remaining\n",
-				 torture_type, delta);
-		schedule_timeout_interruptible(delta);
-		jiffies_snap = ACCESS_ONCE(jiffies);
-	}
-	if (kthread_should_stop()) {
-		VERBOSE_PRINTK_STRING("rcu_torture_shutdown task stopping");
-		return 0;
-	}
-
-	/* OK, shut down the system. */
-
-	VERBOSE_PRINTK_STRING("rcu_torture_shutdown task shutting down system");
-	shutdown_task = NULL;	/* Avoid self-kill deadlock. */
-	rcu_torture_cleanup();	/* Get the success/failure message. */
-	kernel_power_off();	/* Shut down the system. */
-	return 0;
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-/*
- * Execute random CPU-hotplug operations at the interval specified
- * by the onoff_interval.
- */
-static int
-rcu_torture_onoff(void *arg)
-{
-	int cpu;
-	unsigned long delta;
-	int maxcpu = -1;
-	DEFINE_RCU_RANDOM(rand);
-	int ret;
-	unsigned long starttime;
-
-	VERBOSE_PRINTK_STRING("rcu_torture_onoff task started");
-	for_each_online_cpu(cpu)
-		maxcpu = cpu;
-	WARN_ON(maxcpu < 0);
-	if (onoff_holdoff > 0) {
-		VERBOSE_PRINTK_STRING("rcu_torture_onoff begin holdoff");
-		schedule_timeout_interruptible(onoff_holdoff * HZ);
-		VERBOSE_PRINTK_STRING("rcu_torture_onoff end holdoff");
-	}
-	while (!kthread_should_stop()) {
-		cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1);
-		if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) {
-			if (verbose)
-				pr_alert("%s" TORTURE_FLAG
-					 "rcu_torture_onoff task: offlining %d\n",
-					 torture_type, cpu);
-			starttime = jiffies;
-			n_offline_attempts++;
-			ret = cpu_down(cpu);
-			if (ret) {
-				if (verbose)
-					pr_alert("%s" TORTURE_FLAG
-						 "rcu_torture_onoff task: offline %d failed: errno %d\n",
-						 torture_type, cpu, ret);
-			} else {
-				if (verbose)
-					pr_alert("%s" TORTURE_FLAG
-						 "rcu_torture_onoff task: offlined %d\n",
-						 torture_type, cpu);
-				n_offline_successes++;
-				delta = jiffies - starttime;
-				sum_offline += delta;
-				if (min_offline < 0) {
-					min_offline = delta;
-					max_offline = delta;
-				}
-				if (min_offline > delta)
-					min_offline = delta;
-				if (max_offline < delta)
-					max_offline = delta;
-			}
-		} else if (cpu_is_hotpluggable(cpu)) {
-			if (verbose)
-				pr_alert("%s" TORTURE_FLAG
-					 "rcu_torture_onoff task: onlining %d\n",
-					 torture_type, cpu);
-			starttime = jiffies;
-			n_online_attempts++;
-			ret = cpu_up(cpu);
-			if (ret) {
-				if (verbose)
-					pr_alert("%s" TORTURE_FLAG
-						 "rcu_torture_onoff task: online %d failed: errno %d\n",
-						 torture_type, cpu, ret);
-			} else {
-				if (verbose)
-					pr_alert("%s" TORTURE_FLAG
-						 "rcu_torture_onoff task: onlined %d\n",
-						 torture_type, cpu);
-				n_online_successes++;
-				delta = jiffies - starttime;
-				sum_online += delta;
-				if (min_online < 0) {
-					min_online = delta;
-					max_online = delta;
-				}
-				if (min_online > delta)
-					min_online = delta;
-				if (max_online < delta)
-					max_online = delta;
-			}
-		}
-		schedule_timeout_interruptible(onoff_interval * HZ);
-	}
-	VERBOSE_PRINTK_STRING("rcu_torture_onoff task stopping");
-	return 0;
-}
-
-static int
-rcu_torture_onoff_init(void)
-{
-	int ret;
-
-	if (onoff_interval <= 0)
-		return 0;
-	onoff_task = kthread_run(rcu_torture_onoff, NULL, "rcu_torture_onoff");
-	if (IS_ERR(onoff_task)) {
-		ret = PTR_ERR(onoff_task);
-		onoff_task = NULL;
-		return ret;
-	}
-	return 0;
-}
-
-static void rcu_torture_onoff_cleanup(void)
-{
-	if (onoff_task == NULL)
-		return;
-	VERBOSE_PRINTK_STRING("Stopping rcu_torture_onoff task");
-	kthread_stop(onoff_task);
-	onoff_task = NULL;
-}
-
-#else /* #ifdef CONFIG_HOTPLUG_CPU */
-
-static int
-rcu_torture_onoff_init(void)
-{
-	return 0;
-}
-
-static void rcu_torture_onoff_cleanup(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
-/*
- * CPU-stall kthread.  It waits as specified by stall_cpu_holdoff, then
- * induces a CPU stall for the time specified by stall_cpu.
- */
-static int rcu_torture_stall(void *args)
-{
-	unsigned long stop_at;
-
-	VERBOSE_PRINTK_STRING("rcu_torture_stall task started");
-	if (stall_cpu_holdoff > 0) {
-		VERBOSE_PRINTK_STRING("rcu_torture_stall begin holdoff");
-		schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
-		VERBOSE_PRINTK_STRING("rcu_torture_stall end holdoff");
-	}
-	if (!kthread_should_stop()) {
-		stop_at = get_seconds() + stall_cpu;
-		/* RCU CPU stall is expected behavior in following code. */
-		pr_alert("rcu_torture_stall start.\n");
-		rcu_read_lock();
-		preempt_disable();
-		while (ULONG_CMP_LT(get_seconds(), stop_at))
-			continue;  /* Induce RCU CPU stall warning. */
-		preempt_enable();
-		rcu_read_unlock();
-		pr_alert("rcu_torture_stall end.\n");
-	}
-	rcutorture_shutdown_absorb("rcu_torture_stall");
-	while (!kthread_should_stop())
-		schedule_timeout_interruptible(10 * HZ);
-	return 0;
-}
-
-/* Spawn CPU-stall kthread, if stall_cpu specified. */
-static int __init rcu_torture_stall_init(void)
-{
-	int ret;
-
-	if (stall_cpu <= 0)
-		return 0;
-	stall_task = kthread_run(rcu_torture_stall, NULL, "rcu_torture_stall");
-	if (IS_ERR(stall_task)) {
-		ret = PTR_ERR(stall_task);
-		stall_task = NULL;
-		return ret;
-	}
-	return 0;
-}
-
-/* Clean up after the CPU-stall kthread, if one was spawned. */
-static void rcu_torture_stall_cleanup(void)
-{
-	if (stall_task == NULL)
-		return;
-	VERBOSE_PRINTK_STRING("Stopping rcu_torture_stall_task.");
-	kthread_stop(stall_task);
-	stall_task = NULL;
-}
-
-/* Callback function for RCU barrier testing. */
-void rcu_torture_barrier_cbf(struct rcu_head *rcu)
-{
-	atomic_inc(&barrier_cbs_invoked);
-}
-
-/* kthread function to register callbacks used to test RCU barriers. */
-static int rcu_torture_barrier_cbs(void *arg)
-{
-	long myid = (long)arg;
-	bool lastphase = 0;
-	bool newphase;
-	struct rcu_head rcu;
-
-	init_rcu_head_on_stack(&rcu);
-	VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task started");
-	set_user_nice(current, 19);
-	do {
-		wait_event(barrier_cbs_wq[myid],
-			   (newphase =
-			    ACCESS_ONCE(barrier_phase)) != lastphase ||
-			   kthread_should_stop() ||
-			   fullstop != FULLSTOP_DONTSTOP);
-		lastphase = newphase;
-		smp_mb(); /* ensure barrier_phase load before ->call(). */
-		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
-			break;
-		cur_ops->call(&rcu, rcu_torture_barrier_cbf);
-		if (atomic_dec_and_test(&barrier_cbs_count))
-			wake_up(&barrier_wq);
-	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-	VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task stopping");
-	rcutorture_shutdown_absorb("rcu_torture_barrier_cbs");
-	while (!kthread_should_stop())
-		schedule_timeout_interruptible(1);
-	cur_ops->cb_barrier();
-	destroy_rcu_head_on_stack(&rcu);
-	return 0;
-}
-
-/* kthread function to drive and coordinate RCU barrier testing. */
-static int rcu_torture_barrier(void *arg)
-{
-	int i;
-
-	VERBOSE_PRINTK_STRING("rcu_torture_barrier task starting");
-	do {
-		atomic_set(&barrier_cbs_invoked, 0);
-		atomic_set(&barrier_cbs_count, n_barrier_cbs);
-		smp_mb(); /* Ensure barrier_phase after prior assignments. */
-		barrier_phase = !barrier_phase;
-		for (i = 0; i < n_barrier_cbs; i++)
-			wake_up(&barrier_cbs_wq[i]);
-		wait_event(barrier_wq,
-			   atomic_read(&barrier_cbs_count) == 0 ||
-			   kthread_should_stop() ||
-			   fullstop != FULLSTOP_DONTSTOP);
-		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
-			break;
-		n_barrier_attempts++;
-		cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
-		if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
-			n_rcu_torture_barrier_error++;
-			WARN_ON_ONCE(1);
-		}
-		n_barrier_successes++;
-		schedule_timeout_interruptible(HZ / 10);
-	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-	VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping");
-	rcutorture_shutdown_absorb("rcu_torture_barrier");
-	while (!kthread_should_stop())
-		schedule_timeout_interruptible(1);
-	return 0;
-}
-
-/* Initialize RCU barrier testing. */
-static int rcu_torture_barrier_init(void)
-{
-	int i;
-	int ret;
-
-	if (n_barrier_cbs == 0)
-		return 0;
-	if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) {
-		pr_alert("%s" TORTURE_FLAG
-			 " Call or barrier ops missing for %s,\n",
-			 torture_type, cur_ops->name);
-		pr_alert("%s" TORTURE_FLAG
-			 " RCU barrier testing omitted from run.\n",
-			 torture_type);
-		return 0;
-	}
-	atomic_set(&barrier_cbs_count, 0);
-	atomic_set(&barrier_cbs_invoked, 0);
-	barrier_cbs_tasks =
-		kzalloc(n_barrier_cbs * sizeof(barrier_cbs_tasks[0]),
-			GFP_KERNEL);
-	barrier_cbs_wq =
-		kzalloc(n_barrier_cbs * sizeof(barrier_cbs_wq[0]),
-			GFP_KERNEL);
-	if (barrier_cbs_tasks == NULL || !barrier_cbs_wq)
-		return -ENOMEM;
-	for (i = 0; i < n_barrier_cbs; i++) {
-		init_waitqueue_head(&barrier_cbs_wq[i]);
-		barrier_cbs_tasks[i] = kthread_run(rcu_torture_barrier_cbs,
-						   (void *)(long)i,
-						   "rcu_torture_barrier_cbs");
-		if (IS_ERR(barrier_cbs_tasks[i])) {
-			ret = PTR_ERR(barrier_cbs_tasks[i]);
-			VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier_cbs");
-			barrier_cbs_tasks[i] = NULL;
-			return ret;
-		}
-	}
-	barrier_task = kthread_run(rcu_torture_barrier, NULL,
-				   "rcu_torture_barrier");
-	if (IS_ERR(barrier_task)) {
-		ret = PTR_ERR(barrier_task);
-		VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier");
-		barrier_task = NULL;
-	}
-	return 0;
-}
-
-/* Clean up after RCU barrier testing. */
-static void rcu_torture_barrier_cleanup(void)
-{
-	int i;
-
-	if (barrier_task != NULL) {
-		VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier task");
-		kthread_stop(barrier_task);
-		barrier_task = NULL;
-	}
-	if (barrier_cbs_tasks != NULL) {
-		for (i = 0; i < n_barrier_cbs; i++) {
-			if (barrier_cbs_tasks[i] != NULL) {
-				VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier_cbs task");
-				kthread_stop(barrier_cbs_tasks[i]);
-				barrier_cbs_tasks[i] = NULL;
-			}
-		}
-		kfree(barrier_cbs_tasks);
-		barrier_cbs_tasks = NULL;
-	}
-	if (barrier_cbs_wq != NULL) {
-		kfree(barrier_cbs_wq);
-		barrier_cbs_wq = NULL;
-	}
-}
-
-static int rcutorture_cpu_notify(struct notifier_block *self,
-				 unsigned long action, void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-		(void)rcutorture_booster_init(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-		rcutorture_booster_cleanup(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block rcutorture_cpu_nb = {
-	.notifier_call = rcutorture_cpu_notify,
-};
-
-static void
-rcu_torture_cleanup(void)
-{
-	int i;
-
-	mutex_lock(&fullstop_mutex);
-	rcutorture_record_test_transition();
-	if (fullstop == FULLSTOP_SHUTDOWN) {
-		pr_warn(/* but going down anyway, so... */
-		       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
-		mutex_unlock(&fullstop_mutex);
-		schedule_timeout_uninterruptible(10);
-		if (cur_ops->cb_barrier != NULL)
-			cur_ops->cb_barrier();
-		return;
-	}
-	fullstop = FULLSTOP_RMMOD;
-	mutex_unlock(&fullstop_mutex);
-	unregister_reboot_notifier(&rcutorture_shutdown_nb);
-	rcu_torture_barrier_cleanup();
-	rcu_torture_stall_cleanup();
-	if (stutter_task) {
-		VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
-		kthread_stop(stutter_task);
-	}
-	stutter_task = NULL;
-	if (shuffler_task) {
-		VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
-		kthread_stop(shuffler_task);
-		free_cpumask_var(shuffle_tmp_mask);
-	}
-	shuffler_task = NULL;
-
-	if (writer_task) {
-		VERBOSE_PRINTK_STRING("Stopping rcu_torture_writer task");
-		kthread_stop(writer_task);
-	}
-	writer_task = NULL;
-
-	if (reader_tasks) {
-		for (i = 0; i < nrealreaders; i++) {
-			if (reader_tasks[i]) {
-				VERBOSE_PRINTK_STRING(
-					"Stopping rcu_torture_reader task");
-				kthread_stop(reader_tasks[i]);
-			}
-			reader_tasks[i] = NULL;
-		}
-		kfree(reader_tasks);
-		reader_tasks = NULL;
-	}
-	rcu_torture_current = NULL;
-
-	if (fakewriter_tasks) {
-		for (i = 0; i < nfakewriters; i++) {
-			if (fakewriter_tasks[i]) {
-				VERBOSE_PRINTK_STRING(
-					"Stopping rcu_torture_fakewriter task");
-				kthread_stop(fakewriter_tasks[i]);
-			}
-			fakewriter_tasks[i] = NULL;
-		}
-		kfree(fakewriter_tasks);
-		fakewriter_tasks = NULL;
-	}
-
-	if (stats_task) {
-		VERBOSE_PRINTK_STRING("Stopping rcu_torture_stats task");
-		kthread_stop(stats_task);
-	}
-	stats_task = NULL;
-
-	if (fqs_task) {
-		VERBOSE_PRINTK_STRING("Stopping rcu_torture_fqs task");
-		kthread_stop(fqs_task);
-	}
-	fqs_task = NULL;
-	if ((test_boost == 1 && cur_ops->can_boost) ||
-	    test_boost == 2) {
-		unregister_cpu_notifier(&rcutorture_cpu_nb);
-		for_each_possible_cpu(i)
-			rcutorture_booster_cleanup(i);
-	}
-	if (shutdown_task != NULL) {
-		VERBOSE_PRINTK_STRING("Stopping rcu_torture_shutdown task");
-		kthread_stop(shutdown_task);
-	}
-	shutdown_task = NULL;
-	rcu_torture_onoff_cleanup();
-
-	/* Wait for all RCU callbacks to fire.  */
-
-	if (cur_ops->cb_barrier != NULL)
-		cur_ops->cb_barrier();
-
-	rcu_torture_stats_print();  /* -After- the stats thread is stopped! */
-
-	if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error)
-		rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE");
-	else if (n_online_successes != n_online_attempts ||
-		 n_offline_successes != n_offline_attempts)
-		rcu_torture_print_module_parms(cur_ops,
-					       "End of test: RCU_HOTPLUG");
-	else
-		rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS");
-}
-
-#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-static void rcu_torture_leak_cb(struct rcu_head *rhp)
-{
-}
-
-static void rcu_torture_err_cb(struct rcu_head *rhp)
-{
-	/*
-	 * This -might- happen due to race conditions, but is unlikely.
-	 * The scenario that leads to this happening is that the
-	 * first of the pair of duplicate callbacks is queued,
-	 * someone else starts a grace period that includes that
-	 * callback, then the second of the pair must wait for the
-	 * next grace period.  Unlikely, but can happen.  If it
-	 * does happen, the debug-objects subsystem won't have splatted.
-	 */
-	pr_alert("rcutorture: duplicated callback was invoked.\n");
-}
-#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-
-/*
- * Verify that double-free causes debug-objects to complain, but only
- * if CONFIG_DEBUG_OBJECTS_RCU_HEAD=y.  Otherwise, say that the test
- * cannot be carried out.
- */
-static void rcu_test_debug_objects(void)
-{
-#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-	struct rcu_head rh1;
-	struct rcu_head rh2;
-
-	init_rcu_head_on_stack(&rh1);
-	init_rcu_head_on_stack(&rh2);
-	pr_alert("rcutorture: WARN: Duplicate call_rcu() test starting.\n");
-
-	/* Try to queue the rh2 pair of callbacks for the same grace period. */
-	preempt_disable(); /* Prevent preemption from interrupting test. */
-	rcu_read_lock(); /* Make it impossible to finish a grace period. */
-	call_rcu(&rh1, rcu_torture_leak_cb); /* Start grace period. */
-	local_irq_disable(); /* Make it harder to start a new grace period. */
-	call_rcu(&rh2, rcu_torture_leak_cb);
-	call_rcu(&rh2, rcu_torture_err_cb); /* Duplicate callback. */
-	local_irq_enable();
-	rcu_read_unlock();
-	preempt_enable();
-
-	/* Wait for them all to get done so we can safely return. */
-	rcu_barrier();
-	pr_alert("rcutorture: WARN: Duplicate call_rcu() test complete.\n");
-	destroy_rcu_head_on_stack(&rh1);
-	destroy_rcu_head_on_stack(&rh2);
-#else /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-	pr_alert("rcutorture: !CONFIG_DEBUG_OBJECTS_RCU_HEAD, not testing duplicate call_rcu()\n");
-#endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-}
-
-static int __init
-rcu_torture_init(void)
-{
-	int i;
-	int cpu;
-	int firsterr = 0;
-	int retval;
-	static struct rcu_torture_ops *torture_ops[] = {
-		&rcu_ops, &rcu_bh_ops, &srcu_ops, &sched_ops,
-	};
-
-	mutex_lock(&fullstop_mutex);
-
-	/* Process args and tell the world that the torturer is on the job. */
-	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
-		cur_ops = torture_ops[i];
-		if (strcmp(torture_type, cur_ops->name) == 0)
-			break;
-	}
-	if (i == ARRAY_SIZE(torture_ops)) {
-		pr_alert("rcu-torture: invalid torture type: \"%s\"\n",
-			 torture_type);
-		pr_alert("rcu-torture types:");
-		for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
-			pr_alert(" %s", torture_ops[i]->name);
-		pr_alert("\n");
-		mutex_unlock(&fullstop_mutex);
-		return -EINVAL;
-	}
-	if (cur_ops->fqs == NULL && fqs_duration != 0) {
-		pr_alert("rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n");
-		fqs_duration = 0;
-	}
-	if (cur_ops->init)
-		cur_ops->init(); /* no "goto unwind" prior to this point!!! */
-
-	if (nreaders >= 0)
-		nrealreaders = nreaders;
-	else
-		nrealreaders = 2 * num_online_cpus();
-	rcu_torture_print_module_parms(cur_ops, "Start of test");
-	fullstop = FULLSTOP_DONTSTOP;
-
-	/* Set up the freelist. */
-
-	INIT_LIST_HEAD(&rcu_torture_freelist);
-	for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++) {
-		rcu_tortures[i].rtort_mbtest = 0;
-		list_add_tail(&rcu_tortures[i].rtort_free,
-			      &rcu_torture_freelist);
-	}
-
-	/* Initialize the statistics so that each run gets its own numbers. */
-
-	rcu_torture_current = NULL;
-	rcu_torture_current_version = 0;
-	atomic_set(&n_rcu_torture_alloc, 0);
-	atomic_set(&n_rcu_torture_alloc_fail, 0);
-	atomic_set(&n_rcu_torture_free, 0);
-	atomic_set(&n_rcu_torture_mberror, 0);
-	atomic_set(&n_rcu_torture_error, 0);
-	n_rcu_torture_barrier_error = 0;
-	n_rcu_torture_boost_ktrerror = 0;
-	n_rcu_torture_boost_rterror = 0;
-	n_rcu_torture_boost_failure = 0;
-	n_rcu_torture_boosts = 0;
-	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		atomic_set(&rcu_torture_wcount[i], 0);
-	for_each_possible_cpu(cpu) {
-		for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
-			per_cpu(rcu_torture_count, cpu)[i] = 0;
-			per_cpu(rcu_torture_batch, cpu)[i] = 0;
-		}
-	}
-
-	/* Start up the kthreads. */
-
-	VERBOSE_PRINTK_STRING("Creating rcu_torture_writer task");
-	writer_task = kthread_create(rcu_torture_writer, NULL,
-				     "rcu_torture_writer");
-	if (IS_ERR(writer_task)) {
-		firsterr = PTR_ERR(writer_task);
-		VERBOSE_PRINTK_ERRSTRING("Failed to create writer");
-		writer_task = NULL;
-		goto unwind;
-	}
-	wake_up_process(writer_task);
-	fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]),
-				   GFP_KERNEL);
-	if (fakewriter_tasks == NULL) {
-		VERBOSE_PRINTK_ERRSTRING("out of memory");
-		firsterr = -ENOMEM;
-		goto unwind;
-	}
-	for (i = 0; i < nfakewriters; i++) {
-		VERBOSE_PRINTK_STRING("Creating rcu_torture_fakewriter task");
-		fakewriter_tasks[i] = kthread_run(rcu_torture_fakewriter, NULL,
-						  "rcu_torture_fakewriter");
-		if (IS_ERR(fakewriter_tasks[i])) {
-			firsterr = PTR_ERR(fakewriter_tasks[i]);
-			VERBOSE_PRINTK_ERRSTRING("Failed to create fakewriter");
-			fakewriter_tasks[i] = NULL;
-			goto unwind;
-		}
-	}
-	reader_tasks = kzalloc(nrealreaders * sizeof(reader_tasks[0]),
-			       GFP_KERNEL);
-	if (reader_tasks == NULL) {
-		VERBOSE_PRINTK_ERRSTRING("out of memory");
-		firsterr = -ENOMEM;
-		goto unwind;
-	}
-	for (i = 0; i < nrealreaders; i++) {
-		VERBOSE_PRINTK_STRING("Creating rcu_torture_reader task");
-		reader_tasks[i] = kthread_run(rcu_torture_reader, NULL,
-					      "rcu_torture_reader");
-		if (IS_ERR(reader_tasks[i])) {
-			firsterr = PTR_ERR(reader_tasks[i]);
-			VERBOSE_PRINTK_ERRSTRING("Failed to create reader");
-			reader_tasks[i] = NULL;
-			goto unwind;
-		}
-	}
-	if (stat_interval > 0) {
-		VERBOSE_PRINTK_STRING("Creating rcu_torture_stats task");
-		stats_task = kthread_run(rcu_torture_stats, NULL,
-					"rcu_torture_stats");
-		if (IS_ERR(stats_task)) {
-			firsterr = PTR_ERR(stats_task);
-			VERBOSE_PRINTK_ERRSTRING("Failed to create stats");
-			stats_task = NULL;
-			goto unwind;
-		}
-	}
-	if (test_no_idle_hz) {
-		rcu_idle_cpu = num_online_cpus() - 1;
-
-		if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) {
-			firsterr = -ENOMEM;
-			VERBOSE_PRINTK_ERRSTRING("Failed to alloc mask");
-			goto unwind;
-		}
-
-		/* Create the shuffler thread */
-		shuffler_task = kthread_run(rcu_torture_shuffle, NULL,
-					  "rcu_torture_shuffle");
-		if (IS_ERR(shuffler_task)) {
-			free_cpumask_var(shuffle_tmp_mask);
-			firsterr = PTR_ERR(shuffler_task);
-			VERBOSE_PRINTK_ERRSTRING("Failed to create shuffler");
-			shuffler_task = NULL;
-			goto unwind;
-		}
-	}
-	if (stutter < 0)
-		stutter = 0;
-	if (stutter) {
-		/* Create the stutter thread */
-		stutter_task = kthread_run(rcu_torture_stutter, NULL,
-					  "rcu_torture_stutter");
-		if (IS_ERR(stutter_task)) {
-			firsterr = PTR_ERR(stutter_task);
-			VERBOSE_PRINTK_ERRSTRING("Failed to create stutter");
-			stutter_task = NULL;
-			goto unwind;
-		}
-	}
-	if (fqs_duration < 0)
-		fqs_duration = 0;
-	if (fqs_duration) {
-		/* Create the stutter thread */
-		fqs_task = kthread_run(rcu_torture_fqs, NULL,
-				       "rcu_torture_fqs");
-		if (IS_ERR(fqs_task)) {
-			firsterr = PTR_ERR(fqs_task);
-			VERBOSE_PRINTK_ERRSTRING("Failed to create fqs");
-			fqs_task = NULL;
-			goto unwind;
-		}
-	}
-	if (test_boost_interval < 1)
-		test_boost_interval = 1;
-	if (test_boost_duration < 2)
-		test_boost_duration = 2;
-	if ((test_boost == 1 && cur_ops->can_boost) ||
-	    test_boost == 2) {
-
-		boost_starttime = jiffies + test_boost_interval * HZ;
-		register_cpu_notifier(&rcutorture_cpu_nb);
-		for_each_possible_cpu(i) {
-			if (cpu_is_offline(i))
-				continue;  /* Heuristic: CPU can go offline. */
-			retval = rcutorture_booster_init(i);
-			if (retval < 0) {
-				firsterr = retval;
-				goto unwind;
-			}
-		}
-	}
-	if (shutdown_secs > 0) {
-		shutdown_time = jiffies + shutdown_secs * HZ;
-		shutdown_task = kthread_create(rcu_torture_shutdown, NULL,
-					       "rcu_torture_shutdown");
-		if (IS_ERR(shutdown_task)) {
-			firsterr = PTR_ERR(shutdown_task);
-			VERBOSE_PRINTK_ERRSTRING("Failed to create shutdown");
-			shutdown_task = NULL;
-			goto unwind;
-		}
-		wake_up_process(shutdown_task);
-	}
-	i = rcu_torture_onoff_init();
-	if (i != 0) {
-		firsterr = i;
-		goto unwind;
-	}
-	register_reboot_notifier(&rcutorture_shutdown_nb);
-	i = rcu_torture_stall_init();
-	if (i != 0) {
-		firsterr = i;
-		goto unwind;
-	}
-	retval = rcu_torture_barrier_init();
-	if (retval != 0) {
-		firsterr = retval;
-		goto unwind;
-	}
-	if (object_debug)
-		rcu_test_debug_objects();
-	rcutorture_record_test_transition();
-	mutex_unlock(&fullstop_mutex);
-	return 0;
-
-unwind:
-	mutex_unlock(&fullstop_mutex);
-	rcu_torture_cleanup();
-	return firsterr;
-}
-
-module_init(rcu_torture_init);
-module_exit(rcu_torture_cleanup);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b3d116c..0c47e30 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
@@ -58,8 +58,6 @@
 #include <linux/suspend.h>
 
 #include "tree.h"
-#include <trace/events/rcu.h>
-
 #include "rcu.h"
 
 MODULE_ALIAS("rcutree");
@@ -837,7 +835,7 @@
 	 * to the next.  Only do this for the primary flavor of RCU.
 	 */
 	if (rdp->rsp == rcu_state &&
-	    ULONG_CMP_GE(ACCESS_ONCE(jiffies), rdp->rsp->jiffies_resched)) {
+	    ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
 		rdp->rsp->jiffies_resched += 5;
 		resched_cpu(rdp->cpu);
 	}
@@ -847,7 +845,7 @@
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
-	unsigned long j = ACCESS_ONCE(jiffies);
+	unsigned long j = jiffies;
 	unsigned long j1;
 
 	rsp->gp_start = j;
@@ -1005,7 +1003,7 @@
 
 	if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp))
 		return;
-	j = ACCESS_ONCE(jiffies);
+	j = jiffies;
 
 	/*
 	 * Lots of memory barriers to reject false positives.
@@ -1423,13 +1421,14 @@
 
 	/* Advance to a new grace period and initialize state. */
 	record_gp_stall_check_time(rsp);
-	smp_wmb(); /* Record GP times before starting GP. */
-	rsp->gpnum++;
+	/* Record GP times before starting GP, hence smp_store_release(). */
+	smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
 	trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
 	raw_spin_unlock_irq(&rnp->lock);
 
 	/* Exclude any concurrent CPU-hotplug operations. */
 	mutex_lock(&rsp->onoff_mutex);
+	smp_mb__after_unlock_lock(); /* ->gpnum increment before GP! */
 
 	/*
 	 * Set the quiescent-state-needed bits in all the rcu_node
@@ -1557,10 +1556,11 @@
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
-	smp_mb__after_unlock_lock();
+	smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */
 	rcu_nocb_gp_set(rnp, nocb);
 
-	rsp->completed = rsp->gpnum; /* Declare grace period done. */
+	/* Declare grace period done. */
+	ACCESS_ONCE(rsp->completed) = rsp->gpnum;
 	trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
 	rsp->fqs_state = RCU_GP_IDLE;
 	rdp = this_cpu_ptr(rsp->rda);
@@ -2304,7 +2304,7 @@
 		if (rnp_old != NULL)
 			raw_spin_unlock(&rnp_old->fqslock);
 		if (ret) {
-			rsp->n_force_qs_lh++;
+			ACCESS_ONCE(rsp->n_force_qs_lh)++;
 			return;
 		}
 		rnp_old = rnp;
@@ -2316,7 +2316,7 @@
 	smp_mb__after_unlock_lock();
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
-		rsp->n_force_qs_lh++;
+		ACCESS_ONCE(rsp->n_force_qs_lh)++;
 		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 		return;  /* Someone beat us to it. */
 	}
@@ -2639,6 +2639,58 @@
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
 
+/**
+ * get_state_synchronize_rcu - Snapshot current RCU state
+ *
+ * Returns a cookie that is used by a later call to cond_synchronize_rcu()
+ * to determine whether or not a full grace period has elapsed in the
+ * meantime.
+ */
+unsigned long get_state_synchronize_rcu(void)
+{
+	/*
+	 * Any prior manipulation of RCU-protected data must happen
+	 * before the load from ->gpnum.
+	 */
+	smp_mb();  /* ^^^ */
+
+	/*
+	 * Make sure this load happens before the purportedly
+	 * time-consuming work between get_state_synchronize_rcu()
+	 * and cond_synchronize_rcu().
+	 */
+	return smp_load_acquire(&rcu_state->gpnum);
+}
+EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
+
+/**
+ * cond_synchronize_rcu - Conditionally wait for an RCU grace period
+ *
+ * @oldstate: return value from earlier call to get_state_synchronize_rcu()
+ *
+ * If a full RCU grace period has elapsed since the earlier call to
+ * get_state_synchronize_rcu(), just return.  Otherwise, invoke
+ * synchronize_rcu() to wait for a full grace period.
+ *
+ * Yes, this function does not take counter wrap into account.  But
+ * counter wrap is harmless.  If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for one additional grace period should be just fine.
+ */
+void cond_synchronize_rcu(unsigned long oldstate)
+{
+	unsigned long newstate;
+
+	/*
+	 * Ensure that this load happens before any RCU-destructive
+	 * actions the caller might carry out after we return.
+	 */
+	newstate = smp_load_acquire(&rcu_state->completed);
+	if (ULONG_CMP_GE(oldstate, newstate))
+		synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
+
 static int synchronize_sched_expedited_cpu_stop(void *data)
 {
 	/*
@@ -2880,7 +2932,7 @@
  * non-NULL, store an indication of whether all callbacks are lazy.
  * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
+static int __maybe_unused rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
 {
 	bool al = true;
 	bool hc = false;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8c19873..75dc3c3 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -13,8 +13,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 6e2ef4b..962d1d5 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -14,8 +14,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright Red Hat, 2009
  * Copyright IBM Corporation, 2009
@@ -1586,11 +1586,13 @@
  * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
  * any flavor of RCU.
  */
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
 int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 {
 	*delta_jiffies = ULONG_MAX;
 	return rcu_cpu_has_callbacks(cpu, NULL);
 }
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
  * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
@@ -1656,7 +1658,7 @@
  * only if it has been awhile since the last time we did so.  Afterwards,
  * if there are any callbacks ready for immediate invocation, return true.
  */
-static bool rcu_try_advance_all_cbs(void)
+static bool __maybe_unused rcu_try_advance_all_cbs(void)
 {
 	bool cbs_ready = false;
 	struct rcu_data *rdp;
@@ -1696,6 +1698,7 @@
  *
  * The caller must have disabled interrupts.
  */
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
 int rcu_needs_cpu(int cpu, unsigned long *dj)
 {
 	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
@@ -1726,6 +1729,7 @@
 	}
 	return 0;
 }
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
  * Prepare a CPU for idle from an RCU perspective.  The first major task
@@ -1739,6 +1743,7 @@
  */
 static void rcu_prepare_for_idle(int cpu)
 {
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
 	struct rcu_data *rdp;
 	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 	struct rcu_node *rnp;
@@ -1790,6 +1795,7 @@
 		rcu_accelerate_cbs(rsp, rnp, rdp);
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 	}
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 }
 
 /*
@@ -1799,11 +1805,12 @@
  */
 static void rcu_cleanup_after_idle(int cpu)
 {
-
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
 	if (rcu_is_nocb_cpu(cpu))
 		return;
 	if (rcu_try_advance_all_cbs())
 		invoke_rcu_core();
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 }
 
 /*
@@ -2101,6 +2108,7 @@
 	init_waitqueue_head(&rnp->nocb_gp_wq[1]);
 }
 
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
 /* Is the specified CPU a no-CPUs CPU? */
 bool rcu_is_nocb_cpu(int cpu)
 {
@@ -2108,6 +2116,7 @@
 		return cpumask_test_cpu(cpu, rcu_nocb_mask);
 	return false;
 }
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
  * Enqueue the specified string of rcu_head structures onto the specified
@@ -2893,7 +2902,7 @@
  * CPU unless the grace period has extended for too long.
  *
  * This code relies on the fact that all NO_HZ_FULL CPUs are also
- * CONFIG_RCU_NOCB_CPUs.
+ * CONFIG_RCU_NOCB_CPU CPUs.
  */
 static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
 {
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 4def475..5cdc62e 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
@@ -273,7 +273,7 @@
 	seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
 		   rsp->n_force_qs, rsp->n_force_qs_ngp,
 		   rsp->n_force_qs - rsp->n_force_qs_ngp,
-		   rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen);
+		   ACCESS_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
 	for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) {
 		if (rnp->level != level) {
 			seq_puts(m, "\n");
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index c54609f..4c0a9b0 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2001
  *
@@ -49,7 +49,6 @@
 #include <linux/module.h>
 
 #define CREATE_TRACE_POINTS
-#include <trace/events/rcu.h>
 
 #include "rcu.h"
 
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 9a95c8c..ab32b7b 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -13,7 +13,7 @@
 
 obj-y += core.o proc.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
-obj-y += wait.o completion.o
+obj-y += wait.o completion.o idle.o
 obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 4a07353..e73efba 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -203,7 +203,7 @@
 	struct autogroup *ag;
 	int err;
 
-	if (nice < -20 || nice > 19)
+	if (nice < MIN_NICE || nice > MAX_NICE)
 		return -EINVAL;
 
 	err = security_task_setnice(current, nice);
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 43c2bcc..b30a292 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -301,14 +301,14 @@
 	if (unlikely(!sched_clock_running))
 		return 0ull;
 
-	preempt_disable();
+	preempt_disable_notrace();
 	scd = cpu_sdc(cpu);
 
 	if (cpu != smp_processor_id())
 		clock = sched_clock_remote(scd);
 	else
 		clock = sched_clock_local(scd);
-	preempt_enable();
+	preempt_enable_notrace();
 
 	return clock;
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b14a188..d11a176 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1739,8 +1739,10 @@
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
-	p->numa_faults = NULL;
-	p->numa_faults_buffer = NULL;
+	p->numa_faults_memory = NULL;
+	p->numa_faults_buffer_memory = NULL;
+	p->last_task_numa_placement = 0;
+	p->last_sum_exec_runtime = 0;
 
 	INIT_LIST_HEAD(&p->numa_entry);
 	p->numa_group = NULL;
@@ -1946,7 +1948,7 @@
 {
 
 	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-	u64 period = attr->sched_period;
+	u64 period = attr->sched_period ?: attr->sched_deadline;
 	u64 runtime = attr->sched_runtime;
 	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
 	int cpus, err = -1;
@@ -2143,8 +2145,6 @@
 	if (mm)
 		mmdrop(mm);
 	if (unlikely(prev_state == TASK_DEAD)) {
-		task_numa_free(prev);
-
 		if (prev->sched_class->task_dead)
 			prev->sched_class->task_dead(prev);
 
@@ -2161,13 +2161,6 @@
 
 #ifdef CONFIG_SMP
 
-/* assumes rq->lock is held */
-static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
-{
-	if (prev->sched_class->pre_schedule)
-		prev->sched_class->pre_schedule(rq, prev);
-}
-
 /* rq->lock is NOT held, but preemption is disabled */
 static inline void post_schedule(struct rq *rq)
 {
@@ -2185,10 +2178,6 @@
 
 #else
 
-static inline void pre_schedule(struct rq *rq, struct task_struct *p)
-{
-}
-
 static inline void post_schedule(struct rq *rq)
 {
 }
@@ -2504,8 +2493,13 @@
 	DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
 				PREEMPT_MASK - 10);
 #endif
-	if (preempt_count() == val)
-		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+	if (preempt_count() == val) {
+		unsigned long ip = get_parent_ip(CALLER_ADDR1);
+#ifdef CONFIG_DEBUG_PREEMPT
+		current->preempt_disable_ip = ip;
+#endif
+		trace_preempt_off(CALLER_ADDR0, ip);
+	}
 }
 EXPORT_SYMBOL(preempt_count_add);
 
@@ -2548,6 +2542,13 @@
 	print_modules();
 	if (irqs_disabled())
 		print_irqtrace_events(prev);
+#ifdef CONFIG_DEBUG_PREEMPT
+	if (in_atomic_preempt_off()) {
+		pr_err("Preemption disabled at:");
+		print_ip_sym(current->preempt_disable_ip);
+		pr_cont("\n");
+	}
+#endif
 	dump_stack();
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
@@ -2571,36 +2572,34 @@
 	schedstat_inc(this_rq(), sched_count);
 }
 
-static void put_prev_task(struct rq *rq, struct task_struct *prev)
-{
-	if (prev->on_rq || rq->skip_clock_update < 0)
-		update_rq_clock(rq);
-	prev->sched_class->put_prev_task(rq, prev);
-}
-
 /*
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-pick_next_task(struct rq *rq)
+pick_next_task(struct rq *rq, struct task_struct *prev)
 {
-	const struct sched_class *class;
+	const struct sched_class *class = &fair_sched_class;
 	struct task_struct *p;
 
 	/*
 	 * Optimization: we know that if all tasks are in
 	 * the fair class we can call that function directly:
 	 */
-	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
-		p = fair_sched_class.pick_next_task(rq);
-		if (likely(p))
+	if (likely(prev->sched_class == class &&
+		   rq->nr_running == rq->cfs.h_nr_running)) {
+		p = fair_sched_class.pick_next_task(rq, prev);
+		if (likely(p && p != RETRY_TASK))
 			return p;
 	}
 
+again:
 	for_each_class(class) {
-		p = class->pick_next_task(rq);
-		if (p)
+		p = class->pick_next_task(rq, prev);
+		if (p) {
+			if (unlikely(p == RETRY_TASK))
+				goto again;
 			return p;
+		}
 	}
 
 	BUG(); /* the idle class will always have a runnable task */
@@ -2694,13 +2693,10 @@
 		switch_count = &prev->nvcsw;
 	}
 
-	pre_schedule(rq, prev);
+	if (prev->on_rq || rq->skip_clock_update < 0)
+		update_rq_clock(rq);
 
-	if (unlikely(!rq->nr_running))
-		idle_balance(cpu, rq);
-
-	put_prev_task(rq, prev);
-	next = pick_next_task(rq);
+	next = pick_next_task(rq, prev);
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
 	rq->skip_clock_update = 0;
@@ -2902,7 +2898,8 @@
  * This function changes the 'effective' priority of a task. It does
  * not touch ->normal_prio like __setscheduler().
  *
- * Used by the rt_mutex code to implement priority inheritance logic.
+ * Used by the rt_mutex code to implement priority inheritance
+ * logic. Call site only calls if the priority of the task changed.
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
@@ -2992,7 +2989,7 @@
 	unsigned long flags;
 	struct rq *rq;
 
-	if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
+	if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
 		return;
 	/*
 	 * We have to be careful, if called from sys_setpriority(),
@@ -3070,11 +3067,11 @@
 	if (increment > 40)
 		increment = 40;
 
-	nice = TASK_NICE(current) + increment;
-	if (nice < -20)
-		nice = -20;
-	if (nice > 19)
-		nice = 19;
+	nice = task_nice(current) + increment;
+	if (nice < MIN_NICE)
+		nice = MIN_NICE;
+	if (nice > MAX_NICE)
+		nice = MAX_NICE;
 
 	if (increment < 0 && !can_nice(current, nice))
 		return -EPERM;
@@ -3103,18 +3100,6 @@
 }
 
 /**
- * task_nice - return the nice value of a given task.
- * @p: the task in question.
- *
- * Return: The nice value [ -20 ... 0 ... 19 ].
- */
-int task_nice(const struct task_struct *p)
-{
-	return TASK_NICE(p);
-}
-EXPORT_SYMBOL(task_nice);
-
-/**
  * idle_cpu - is a given cpu idle currently?
  * @cpu: the processor in question.
  *
@@ -3183,9 +3168,8 @@
 	dl_se->dl_new = 1;
 }
 
-/* Actually do priority change: must hold pi & rq lock. */
-static void __setscheduler(struct rq *rq, struct task_struct *p,
-			   const struct sched_attr *attr)
+static void __setscheduler_params(struct task_struct *p,
+		const struct sched_attr *attr)
 {
 	int policy = attr->sched_policy;
 
@@ -3205,9 +3189,21 @@
 	 * getparam()/getattr() don't report silly values for !rt tasks.
 	 */
 	p->rt_priority = attr->sched_priority;
-
 	p->normal_prio = normal_prio(p);
-	p->prio = rt_mutex_getprio(p);
+	set_load_weight(p);
+}
+
+/* Actually do priority change: must hold pi & rq lock. */
+static void __setscheduler(struct rq *rq, struct task_struct *p,
+			   const struct sched_attr *attr)
+{
+	__setscheduler_params(p, attr);
+
+	/*
+	 * If we get here, there was no pi waiters boosting the
+	 * task. It is safe to use the normal prio.
+	 */
+	p->prio = normal_prio(p);
 
 	if (dl_prio(p->prio))
 		p->sched_class = &dl_sched_class;
@@ -3215,8 +3211,6 @@
 		p->sched_class = &rt_sched_class;
 	else
 		p->sched_class = &fair_sched_class;
-
-	set_load_weight(p);
 }
 
 static void
@@ -3269,6 +3263,8 @@
 				const struct sched_attr *attr,
 				bool user)
 {
+	int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
+		      MAX_RT_PRIO - 1 - attr->sched_priority;
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
 	int policy = attr->sched_policy;
 	unsigned long flags;
@@ -3313,7 +3309,7 @@
 	 */
 	if (user && !capable(CAP_SYS_NICE)) {
 		if (fair_policy(policy)) {
-			if (attr->sched_nice < TASK_NICE(p) &&
+			if (attr->sched_nice < task_nice(p) &&
 			    !can_nice(p, attr->sched_nice))
 				return -EPERM;
 		}
@@ -3332,12 +3328,21 @@
 				return -EPERM;
 		}
 
+		 /*
+		  * Can't set/change SCHED_DEADLINE policy at all for now
+		  * (safest behavior); in the future we would like to allow
+		  * unprivileged DL tasks to increase their relative deadline
+		  * or reduce their runtime (both ways reducing utilization)
+		  */
+		if (dl_policy(policy))
+			return -EPERM;
+
 		/*
 		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
 		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
 		 */
 		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
-			if (!can_nice(p, TASK_NICE(p)))
+			if (!can_nice(p, task_nice(p)))
 				return -EPERM;
 		}
 
@@ -3374,16 +3379,18 @@
 	}
 
 	/*
-	 * If not changing anything there's no need to proceed further:
+	 * If not changing anything there's no need to proceed further,
+	 * but store a possible modification of reset_on_fork.
 	 */
 	if (unlikely(policy == p->policy)) {
-		if (fair_policy(policy) && attr->sched_nice != TASK_NICE(p))
+		if (fair_policy(policy) && attr->sched_nice != task_nice(p))
 			goto change;
 		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
 			goto change;
 		if (dl_policy(policy))
 			goto change;
 
+		p->sched_reset_on_fork = reset_on_fork;
 		task_rq_unlock(rq, p, &flags);
 		return 0;
 	}
@@ -3437,6 +3444,24 @@
 		return -EBUSY;
 	}
 
+	p->sched_reset_on_fork = reset_on_fork;
+	oldprio = p->prio;
+
+	/*
+	 * Special case for priority boosted tasks.
+	 *
+	 * If the new priority is lower or equal (user space view)
+	 * than the current (boosted) priority, we just store the new
+	 * normal parameters and do not touch the scheduler class and
+	 * the runqueue. This will be done when the task deboost
+	 * itself.
+	 */
+	if (rt_mutex_check_prio(p, newprio)) {
+		__setscheduler_params(p, attr);
+		task_rq_unlock(rq, p, &flags);
+		return 0;
+	}
+
 	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
@@ -3444,16 +3469,18 @@
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
-	p->sched_reset_on_fork = reset_on_fork;
-
-	oldprio = p->prio;
 	prev_class = p->sched_class;
 	__setscheduler(rq, p, attr);
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq)
-		enqueue_task(rq, p, 0);
+	if (on_rq) {
+		/*
+		 * We enqueue to tail when the priority of a task is
+		 * increased (user space view).
+		 */
+		enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0);
+	}
 
 	check_class_changed(rq, p, prev_class, oldprio);
 	task_rq_unlock(rq, p, &flags);
@@ -3609,7 +3636,7 @@
 	 * XXX: do we want to be lenient like existing syscalls; or do we want
 	 * to be strict and return an error on out-of-bounds values?
 	 */
-	attr->sched_nice = clamp(attr->sched_nice, -20, 19);
+	attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);
 
 out:
 	return ret;
@@ -3655,13 +3682,14 @@
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
  */
-SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
+			       unsigned int, flags)
 {
 	struct sched_attr attr;
 	struct task_struct *p;
 	int retval;
 
-	if (!uattr || pid < 0)
+	if (!uattr || pid < 0 || flags)
 		return -EINVAL;
 
 	if (sched_copy_attr(uattr, &attr))
@@ -3780,7 +3808,7 @@
 		attr->size = usize;
 	}
 
-	ret = copy_to_user(uattr, attr, usize);
+	ret = copy_to_user(uattr, attr, attr->size);
 	if (ret)
 		return -EFAULT;
 
@@ -3798,8 +3826,8 @@
  * @uattr: structure containing the extended parameters.
  * @size: sizeof(attr) for fwd/bwd comp.
  */
-SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
-		unsigned int, size)
+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+		unsigned int, size, unsigned int, flags)
 {
 	struct sched_attr attr = {
 		.size = sizeof(struct sched_attr),
@@ -3808,7 +3836,7 @@
 	int retval;
 
 	if (!uattr || pid < 0 || size > PAGE_SIZE ||
-	    size < SCHED_ATTR_SIZE_VER0)
+	    size < SCHED_ATTR_SIZE_VER0 || flags)
 		return -EINVAL;
 
 	rcu_read_lock();
@@ -3829,7 +3857,7 @@
 	else if (task_has_rt_policy(p))
 		attr.sched_priority = p->rt_priority;
 	else
-		attr.sched_nice = TASK_NICE(p);
+		attr.sched_nice = task_nice(p);
 
 	rcu_read_unlock();
 
@@ -4467,6 +4495,7 @@
 	rcu_read_unlock();
 
 	rq->curr = rq->idle = idle;
+	idle->on_rq = 1;
 #if defined(CONFIG_SMP)
 	idle->on_cpu = 1;
 #endif
@@ -4686,8 +4715,10 @@
 
 	BUG_ON(cpu_online(smp_processor_id()));
 
-	if (mm != &init_mm)
+	if (mm != &init_mm) {
 		switch_mm(mm, &init_mm, current);
+		finish_arch_post_lock_switch();
+	}
 	mmdrop(mm);
 }
 
@@ -4705,6 +4736,22 @@
 		atomic_long_add(delta, &calc_load_tasks);
 }
 
+static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
+{
+}
+
+static const struct sched_class fake_sched_class = {
+	.put_prev_task = put_prev_task_fake,
+};
+
+static struct task_struct fake_task = {
+	/*
+	 * Avoid pull_{rt,dl}_task()
+	 */
+	.prio = MAX_PRIO + 1,
+	.sched_class = &fake_sched_class,
+};
+
 /*
  * Migrate all tasks from the rq, sleeping tasks will be migrated by
  * try_to_wake_up()->select_task_rq().
@@ -4745,7 +4792,7 @@
 		if (rq->nr_running == 1)
 			break;
 
-		next = pick_next_task(rq);
+		next = pick_next_task(rq, &fake_task);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 
@@ -4835,7 +4882,7 @@
 static struct ctl_table *
 sd_alloc_ctl_domain_table(struct sched_domain *sd)
 {
-	struct ctl_table *table = sd_alloc_ctl_entry(13);
+	struct ctl_table *table = sd_alloc_ctl_entry(14);
 
 	if (table == NULL)
 		return NULL;
@@ -4863,9 +4910,12 @@
 		sizeof(int), 0644, proc_dointvec_minmax, false);
 	set_table_entry(&table[10], "flags", &sd->flags,
 		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[11], "name", sd->name,
+	set_table_entry(&table[11], "max_newidle_lb_cost",
+		&sd->max_newidle_lb_cost,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[12], "name", sd->name,
 		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
-	/* &table[12] is terminator */
+	/* &table[13] is terminator */
 
 	return table;
 }
@@ -6842,7 +6892,6 @@
 
 		rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
 #ifdef CONFIG_RT_GROUP_SCHED
-		INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
 		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
 #endif
 
@@ -6931,7 +6980,8 @@
 	static unsigned long prev_jiffy;	/* ratelimiting */
 
 	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
-	if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
+	     !is_idle_task(current)) ||
 	    system_state != SYSTEM_RUNNING || oops_in_progress)
 		return;
 	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
@@ -6949,6 +6999,13 @@
 	debug_show_held_locks(current);
 	if (irqs_disabled())
 		print_irqtrace_events(current);
+#ifdef CONFIG_DEBUG_PREEMPT
+	if (!preempt_count_equals(preempt_offset)) {
+		pr_err("Preemption disabled at:");
+		print_ip_sym(current->preempt_disable_ip);
+		pr_cont("\n");
+	}
+#endif
 	dump_stack();
 }
 EXPORT_SYMBOL(__might_sleep);
@@ -7002,7 +7059,7 @@
 			 * Renice negative nice level userspace
 			 * tasks back to 0:
 			 */
-			if (TASK_NICE(p) < 0 && p->mm)
+			if (task_nice(p) < 0 && p->mm)
 				set_user_nice(p, 0);
 			continue;
 		}
@@ -7416,6 +7473,7 @@
 	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
 	int cpu, ret = 0;
+	unsigned long flags;
 
 	/*
 	 * Here we want to check the bandwidth not being set to some
@@ -7429,10 +7487,10 @@
 	for_each_possible_cpu(cpu) {
 		struct dl_bw *dl_b = dl_bw_of(cpu);
 
-		raw_spin_lock(&dl_b->lock);
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
 		if (new_bw < dl_b->total_bw)
 			ret = -EBUSY;
-		raw_spin_unlock(&dl_b->lock);
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
 		if (ret)
 			break;
@@ -7445,6 +7503,7 @@
 {
 	u64 new_bw = -1;
 	int cpu;
+	unsigned long flags;
 
 	def_dl_bandwidth.dl_period = global_rt_period();
 	def_dl_bandwidth.dl_runtime = global_rt_runtime();
@@ -7458,9 +7517,9 @@
 	for_each_possible_cpu(cpu) {
 		struct dl_bw *dl_b = dl_bw_of(cpu);
 
-		raw_spin_lock(&dl_b->lock);
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
 		dl_b->bw = new_bw;
-		raw_spin_unlock(&dl_b->lock);
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	}
 }
 
@@ -7469,7 +7528,8 @@
 	if (sysctl_sched_rt_period <= 0)
 		return -EINVAL;
 
-	if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
 		return -EINVAL;
 
 	return 0;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 045fc74..5b9bb42 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -70,7 +70,7 @@
 
 static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
 {
-	WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
+	WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
 
 	if (dl_time_before(new_dl, cp->elements[idx].dl)) {
 		cp->elements[idx].dl = new_dl;
@@ -117,7 +117,7 @@
 	}
 
 out:
-	WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1);
+	WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
 	return best_cpu;
 }
@@ -137,7 +137,7 @@
 	int old_idx, new_cpu;
 	unsigned long flags;
 
-	WARN_ON(cpu > num_present_cpus());
+	WARN_ON(!cpu_present(cpu));
 
 	raw_spin_lock_irqsave(&cp->lock, flags);
 	old_idx = cp->cpu_to_idx[cpu];
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index c91b097..a95097c 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -142,7 +142,7 @@
 	p->utimescaled += cputime_scaled;
 	account_group_user_time(p, cputime);
 
-	index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
+	index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
 
 	/* Add user time to cpustat. */
 	task_group_account_field(p, index, (__force u64) cputime);
@@ -169,7 +169,7 @@
 	p->gtime += cputime;
 
 	/* Add guest time to cpustat. */
-	if (TASK_NICE(p) > 0) {
+	if (task_nice(p) > 0) {
 		cpustat[CPUTIME_NICE] += (__force u64) cputime;
 		cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
 	} else {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0dd5e09..27ef409 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -121,7 +121,7 @@
 
 static void update_dl_migration(struct dl_rq *dl_rq)
 {
-	if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+	if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
 		if (!dl_rq->overloaded) {
 			dl_set_overload(rq_of_dl_rq(dl_rq));
 			dl_rq->overloaded = 1;
@@ -135,9 +135,7 @@
 static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	struct task_struct *p = dl_task_of(dl_se);
-	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
-	dl_rq->dl_nr_total++;
 	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory++;
 
@@ -147,9 +145,7 @@
 static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	struct task_struct *p = dl_task_of(dl_se);
-	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
-	dl_rq->dl_nr_total--;
 	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory--;
 
@@ -214,6 +210,16 @@
 
 static int push_dl_task(struct rq *rq);
 
+static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
+{
+	return dl_task(prev);
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+	rq->post_schedule = has_pushable_dl_tasks(rq);
+}
+
 #else
 
 static inline
@@ -236,6 +242,19 @@
 {
 }
 
+static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
+{
+	return false;
+}
+
+static inline int pull_dl_task(struct rq *rq)
+{
+	return 0;
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+}
 #endif /* CONFIG_SMP */
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
@@ -566,6 +585,8 @@
 	return 1;
 }
 
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
+
 /*
  * Update the current task's runtime statistics (provided it is still
  * a -deadline task and has not been removed from the dl_rq).
@@ -588,8 +609,8 @@
 	 * approach need further study.
 	 */
 	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
-	if (unlikely((s64)delta_exec < 0))
-		delta_exec = 0;
+	if (unlikely((s64)delta_exec <= 0))
+		return;
 
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
@@ -629,11 +650,13 @@
 		struct rt_rq *rt_rq = &rq->rt;
 
 		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_time += delta_exec;
 		/*
 		 * We'll let actual RT tasks worry about the overflow here, we
-		 * have our own CBS to keep us inline -- see above.
+		 * have our own CBS to keep us inline; only account when RT
+		 * bandwidth is relevant.
 		 */
+		if (sched_rt_bandwidth_account(rt_rq))
+			rt_rq->rt_time += delta_exec;
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 	}
 }
@@ -717,6 +740,7 @@
 
 	WARN_ON(!dl_prio(prio));
 	dl_rq->dl_nr_running++;
+	inc_nr_running(rq_of_dl_rq(dl_rq));
 
 	inc_dl_deadline(dl_rq, deadline);
 	inc_dl_migration(dl_se, dl_rq);
@@ -730,6 +754,7 @@
 	WARN_ON(!dl_prio(prio));
 	WARN_ON(!dl_rq->dl_nr_running);
 	dl_rq->dl_nr_running--;
+	dec_nr_running(rq_of_dl_rq(dl_rq));
 
 	dec_dl_deadline(dl_rq, dl_se->deadline);
 	dec_dl_migration(dl_se, dl_rq);
@@ -836,8 +861,6 @@
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
-
-	inc_nr_running(rq);
 }
 
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -850,8 +873,6 @@
 {
 	update_curr_dl(rq);
 	__dequeue_task_dl(rq, p, flags);
-
-	dec_nr_running(rq);
 }
 
 /*
@@ -944,6 +965,8 @@
 	resched_task(rq->curr);
 }
 
+static int pull_dl_task(struct rq *this_rq);
+
 #endif /* CONFIG_SMP */
 
 /*
@@ -990,7 +1013,7 @@
 	return rb_entry(left, struct sched_dl_entity, rb_node);
 }
 
-struct task_struct *pick_next_task_dl(struct rq *rq)
+struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
 {
 	struct sched_dl_entity *dl_se;
 	struct task_struct *p;
@@ -998,9 +1021,20 @@
 
 	dl_rq = &rq->dl;
 
+	if (need_pull_dl_task(rq, prev))
+		pull_dl_task(rq);
+	/*
+	 * When prev is DL, we may throttle it in put_prev_task().
+	 * So, we update time before we check for dl_nr_running.
+	 */
+	if (prev->sched_class == &dl_sched_class)
+		update_curr_dl(rq);
+
 	if (unlikely(!dl_rq->dl_nr_running))
 		return NULL;
 
+	put_prev_task(rq, prev);
+
 	dl_se = pick_next_dl_entity(rq, dl_rq);
 	BUG_ON(!dl_se);
 
@@ -1015,9 +1049,7 @@
 		start_hrtick_dl(rq, p);
 #endif
 
-#ifdef CONFIG_SMP
-	rq->post_schedule = has_pushable_dl_tasks(rq);
-#endif /* CONFIG_SMP */
+	set_post_schedule(rq);
 
 	return p;
 }
@@ -1426,13 +1458,6 @@
 	return ret;
 }
 
-static void pre_schedule_dl(struct rq *rq, struct task_struct *prev)
-{
-	/* Try to pull other tasks here */
-	if (dl_task(prev))
-		pull_dl_task(rq);
-}
-
 static void post_schedule_dl(struct rq *rq)
 {
 	push_dl_tasks(rq);
@@ -1560,7 +1585,7 @@
 	if (unlikely(p->dl.dl_throttled))
 		return;
 
-	if (p->on_rq || rq->curr != p) {
+	if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
 			/* Only reschedule if pushing failed */
@@ -1625,7 +1650,6 @@
 	.set_cpus_allowed       = set_cpus_allowed_dl,
 	.rq_online              = rq_online_dl,
 	.rq_offline             = rq_offline_dl,
-	.pre_schedule		= pre_schedule_dl,
 	.post_schedule		= post_schedule_dl,
 	.task_woken		= task_woken_dl,
 #endif
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index dd52e7f..f3344c3 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -321,6 +321,7 @@
 	P(sched_goidle);
 #ifdef CONFIG_SMP
 	P64(avg_idle);
+	P64(max_idle_balance_cost);
 #endif
 
 	P(ttwu_count);
@@ -533,15 +534,15 @@
 			unsigned long nr_faults = -1;
 			int cpu_current, home_node;
 
-			if (p->numa_faults)
-				nr_faults = p->numa_faults[2*node + i];
+			if (p->numa_faults_memory)
+				nr_faults = p->numa_faults_memory[2*node + i];
 
 			cpu_current = !i ? (task_node(p) == node) :
 				(pol && node_isset(node, pol->v.nodes));
 
 			home_node = (p->numa_preferred_nid == node);
 
-			SEQ_printf(m, "numa_faults, %d, %d, %d, %d, %ld\n",
+			SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n",
 				i, node, cpu_current, home_node, nr_faults);
 		}
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 966cc2b..7e9bd0b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -322,13 +322,13 @@
 	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
-static inline int
+static inline struct cfs_rq *
 is_same_group(struct sched_entity *se, struct sched_entity *pse)
 {
 	if (se->cfs_rq == pse->cfs_rq)
-		return 1;
+		return se->cfs_rq;
 
-	return 0;
+	return NULL;
 }
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
@@ -336,17 +336,6 @@
 	return se->parent;
 }
 
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
-{
-	int depth = 0;
-
-	for_each_sched_entity(se)
-		depth++;
-
-	return depth;
-}
-
 static void
 find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 {
@@ -360,8 +349,8 @@
 	 */
 
 	/* First walk up until both entities are at same depth */
-	se_depth = depth_se(*se);
-	pse_depth = depth_se(*pse);
+	se_depth = (*se)->depth;
+	pse_depth = (*pse)->depth;
 
 	while (se_depth > pse_depth) {
 		se_depth--;
@@ -426,12 +415,6 @@
 #define for_each_leaf_cfs_rq(rq, cfs_rq) \
 		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
 
-static inline int
-is_same_group(struct sched_entity *se, struct sched_entity *pse)
-{
-	return 1;
-}
-
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
 {
 	return NULL;
@@ -819,14 +802,6 @@
 /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
 unsigned int sysctl_numa_balancing_scan_delay = 1000;
 
-/*
- * After skipping a page migration on a shared page, skip N more numa page
- * migrations unconditionally. This reduces the number of NUMA migrations
- * in shared memory workloads, and has the effect of pulling tasks towards
- * where their memory lives, over pulling the memory towards the task.
- */
-unsigned int sysctl_numa_balancing_migrate_deferred = 16;
-
 static unsigned int task_nr_scan_windows(struct task_struct *p)
 {
 	unsigned long rss = 0;
@@ -893,10 +868,26 @@
 	struct list_head task_list;
 
 	struct rcu_head rcu;
+	nodemask_t active_nodes;
 	unsigned long total_faults;
+	/*
+	 * Faults_cpu is used to decide whether memory should move
+	 * towards the CPU. As a consequence, these stats are weighted
+	 * more by CPU use than by memory faults.
+	 */
+	unsigned long *faults_cpu;
 	unsigned long faults[0];
 };
 
+/* Shared or private faults. */
+#define NR_NUMA_HINT_FAULT_TYPES 2
+
+/* Memory and CPU locality */
+#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2)
+
+/* Averaged statistics, and temporary buffers. */
+#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2)
+
 pid_t task_numa_group_id(struct task_struct *p)
 {
 	return p->numa_group ? p->numa_group->gid : 0;
@@ -904,16 +895,16 @@
 
 static inline int task_faults_idx(int nid, int priv)
 {
-	return 2 * nid + priv;
+	return NR_NUMA_HINT_FAULT_TYPES * nid + priv;
 }
 
 static inline unsigned long task_faults(struct task_struct *p, int nid)
 {
-	if (!p->numa_faults)
+	if (!p->numa_faults_memory)
 		return 0;
 
-	return p->numa_faults[task_faults_idx(nid, 0)] +
-		p->numa_faults[task_faults_idx(nid, 1)];
+	return p->numa_faults_memory[task_faults_idx(nid, 0)] +
+		p->numa_faults_memory[task_faults_idx(nid, 1)];
 }
 
 static inline unsigned long group_faults(struct task_struct *p, int nid)
@@ -925,6 +916,12 @@
 		p->numa_group->faults[task_faults_idx(nid, 1)];
 }
 
+static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
+{
+	return group->faults_cpu[task_faults_idx(nid, 0)] +
+		group->faults_cpu[task_faults_idx(nid, 1)];
+}
+
 /*
  * These return the fraction of accesses done by a particular task, or
  * task group, on a particular numa node.  The group weight is given a
@@ -935,7 +932,7 @@
 {
 	unsigned long total_faults;
 
-	if (!p->numa_faults)
+	if (!p->numa_faults_memory)
 		return 0;
 
 	total_faults = p->total_numa_faults;
@@ -954,6 +951,69 @@
 	return 1000 * group_faults(p, nid) / p->numa_group->total_faults;
 }
 
+bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
+				int src_nid, int dst_cpu)
+{
+	struct numa_group *ng = p->numa_group;
+	int dst_nid = cpu_to_node(dst_cpu);
+	int last_cpupid, this_cpupid;
+
+	this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
+
+	/*
+	 * Multi-stage node selection is used in conjunction with a periodic
+	 * migration fault to build a temporal task<->page relation. By using
+	 * a two-stage filter we remove short/unlikely relations.
+	 *
+	 * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate
+	 * a task's usage of a particular page (n_p) per total usage of this
+	 * page (n_t) (in a given time-span) to a probability.
+	 *
+	 * Our periodic faults will sample this probability and getting the
+	 * same result twice in a row, given these samples are fully
+	 * independent, is then given by P(n)^2, provided our sample period
+	 * is sufficiently short compared to the usage pattern.
+	 *
+	 * This quadric squishes small probabilities, making it less likely we
+	 * act on an unlikely task<->page relation.
+	 */
+	last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+	if (!cpupid_pid_unset(last_cpupid) &&
+				cpupid_to_nid(last_cpupid) != dst_nid)
+		return false;
+
+	/* Always allow migrate on private faults */
+	if (cpupid_match_pid(p, last_cpupid))
+		return true;
+
+	/* A shared fault, but p->numa_group has not been set up yet. */
+	if (!ng)
+		return true;
+
+	/*
+	 * Do not migrate if the destination is not a node that
+	 * is actively used by this numa group.
+	 */
+	if (!node_isset(dst_nid, ng->active_nodes))
+		return false;
+
+	/*
+	 * Source is a node that is not actively used by this
+	 * numa group, while the destination is. Migrate.
+	 */
+	if (!node_isset(src_nid, ng->active_nodes))
+		return true;
+
+	/*
+	 * Both source and destination are nodes in active
+	 * use by this numa group. Maximize memory bandwidth
+	 * by migrating from more heavily used groups, to less
+	 * heavily used ones, spreading the load around.
+	 * Use a 1/4 hysteresis to avoid spurious page movement.
+	 */
+	return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4);
+}
+
 static unsigned long weighted_cpuload(const int cpu);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
@@ -1267,7 +1327,7 @@
 static void numa_migrate_preferred(struct task_struct *p)
 {
 	/* This task has no NUMA fault statistics yet */
-	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
+	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory))
 		return;
 
 	/* Periodically retry migrating the task to the preferred node */
@@ -1282,6 +1342,38 @@
 }
 
 /*
+ * Find the nodes on which the workload is actively running. We do this by
+ * tracking the nodes from which NUMA hinting faults are triggered. This can
+ * be different from the set of nodes where the workload's memory is currently
+ * located.
+ *
+ * The bitmask is used to make smarter decisions on when to do NUMA page
+ * migrations, To prevent flip-flopping, and excessive page migrations, nodes
+ * are added when they cause over 6/16 of the maximum number of faults, but
+ * only removed when they drop below 3/16.
+ */
+static void update_numa_active_node_mask(struct numa_group *numa_group)
+{
+	unsigned long faults, max_faults = 0;
+	int nid;
+
+	for_each_online_node(nid) {
+		faults = group_faults_cpu(numa_group, nid);
+		if (faults > max_faults)
+			max_faults = faults;
+	}
+
+	for_each_online_node(nid) {
+		faults = group_faults_cpu(numa_group, nid);
+		if (!node_isset(nid, numa_group->active_nodes)) {
+			if (faults > max_faults * 6 / 16)
+				node_set(nid, numa_group->active_nodes);
+		} else if (faults < max_faults * 3 / 16)
+			node_clear(nid, numa_group->active_nodes);
+	}
+}
+
+/*
  * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
  * increments. The more local the fault statistics are, the higher the scan
  * period will be for the next scan window. If local/remote ratio is below
@@ -1355,11 +1447,41 @@
 	memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 }
 
+/*
+ * Get the fraction of time the task has been running since the last
+ * NUMA placement cycle. The scheduler keeps similar statistics, but
+ * decays those on a 32ms period, which is orders of magnitude off
+ * from the dozens-of-seconds NUMA balancing period. Use the scheduler
+ * stats only if the task is so new there are no NUMA statistics yet.
+ */
+static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
+{
+	u64 runtime, delta, now;
+	/* Use the start of this time slice to avoid calculations. */
+	now = p->se.exec_start;
+	runtime = p->se.sum_exec_runtime;
+
+	if (p->last_task_numa_placement) {
+		delta = runtime - p->last_sum_exec_runtime;
+		*period = now - p->last_task_numa_placement;
+	} else {
+		delta = p->se.avg.runnable_avg_sum;
+		*period = p->se.avg.runnable_avg_period;
+	}
+
+	p->last_sum_exec_runtime = runtime;
+	p->last_task_numa_placement = now;
+
+	return delta;
+}
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq, nid, max_nid = -1, max_group_nid = -1;
 	unsigned long max_faults = 0, max_group_faults = 0;
 	unsigned long fault_types[2] = { 0, 0 };
+	unsigned long total_faults;
+	u64 runtime, period;
 	spinlock_t *group_lock = NULL;
 
 	seq = ACCESS_ONCE(p->mm->numa_scan_seq);
@@ -1368,6 +1490,10 @@
 	p->numa_scan_seq = seq;
 	p->numa_scan_period_max = task_scan_max(p);
 
+	total_faults = p->numa_faults_locality[0] +
+		       p->numa_faults_locality[1];
+	runtime = numa_get_avg_runtime(p, &period);
+
 	/* If the task is part of a group prevent parallel updates to group stats */
 	if (p->numa_group) {
 		group_lock = &p->numa_group->lock;
@@ -1379,24 +1505,37 @@
 		unsigned long faults = 0, group_faults = 0;
 		int priv, i;
 
-		for (priv = 0; priv < 2; priv++) {
-			long diff;
+		for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
+			long diff, f_diff, f_weight;
 
 			i = task_faults_idx(nid, priv);
-			diff = -p->numa_faults[i];
 
 			/* Decay existing window, copy faults since last scan */
-			p->numa_faults[i] >>= 1;
-			p->numa_faults[i] += p->numa_faults_buffer[i];
-			fault_types[priv] += p->numa_faults_buffer[i];
-			p->numa_faults_buffer[i] = 0;
+			diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2;
+			fault_types[priv] += p->numa_faults_buffer_memory[i];
+			p->numa_faults_buffer_memory[i] = 0;
 
-			faults += p->numa_faults[i];
-			diff += p->numa_faults[i];
+			/*
+			 * Normalize the faults_from, so all tasks in a group
+			 * count according to CPU use, instead of by the raw
+			 * number of faults. Tasks with little runtime have
+			 * little over-all impact on throughput, and thus their
+			 * faults are less important.
+			 */
+			f_weight = div64_u64(runtime << 16, period + 1);
+			f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) /
+				   (total_faults + 1);
+			f_diff = f_weight - p->numa_faults_cpu[i] / 2;
+			p->numa_faults_buffer_cpu[i] = 0;
+
+			p->numa_faults_memory[i] += diff;
+			p->numa_faults_cpu[i] += f_diff;
+			faults += p->numa_faults_memory[i];
 			p->total_numa_faults += diff;
 			if (p->numa_group) {
 				/* safe because we can only change our own group */
 				p->numa_group->faults[i] += diff;
+				p->numa_group->faults_cpu[i] += f_diff;
 				p->numa_group->total_faults += diff;
 				group_faults += p->numa_group->faults[i];
 			}
@@ -1416,6 +1555,7 @@
 	update_task_scan_period(p, fault_types[0], fault_types[1]);
 
 	if (p->numa_group) {
+		update_numa_active_node_mask(p->numa_group);
 		/*
 		 * If the preferred task and group nids are different,
 		 * iterate over the nodes again to find the best place.
@@ -1465,7 +1605,7 @@
 
 	if (unlikely(!p->numa_group)) {
 		unsigned int size = sizeof(struct numa_group) +
-				    2*nr_node_ids*sizeof(unsigned long);
+				    4*nr_node_ids*sizeof(unsigned long);
 
 		grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!grp)
@@ -1475,9 +1615,14 @@
 		spin_lock_init(&grp->lock);
 		INIT_LIST_HEAD(&grp->task_list);
 		grp->gid = p->pid;
+		/* Second half of the array tracks nids where faults happen */
+		grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
+						nr_node_ids;
 
-		for (i = 0; i < 2*nr_node_ids; i++)
-			grp->faults[i] = p->numa_faults[i];
+		node_set(task_node(current), grp->active_nodes);
+
+		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+			grp->faults[i] = p->numa_faults_memory[i];
 
 		grp->total_faults = p->total_numa_faults;
 
@@ -1534,9 +1679,9 @@
 
 	double_lock(&my_grp->lock, &grp->lock);
 
-	for (i = 0; i < 2*nr_node_ids; i++) {
-		my_grp->faults[i] -= p->numa_faults[i];
-		grp->faults[i] += p->numa_faults[i];
+	for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
+		my_grp->faults[i] -= p->numa_faults_memory[i];
+		grp->faults[i] += p->numa_faults_memory[i];
 	}
 	my_grp->total_faults -= p->total_numa_faults;
 	grp->total_faults += p->total_numa_faults;
@@ -1562,12 +1707,12 @@
 {
 	struct numa_group *grp = p->numa_group;
 	int i;
-	void *numa_faults = p->numa_faults;
+	void *numa_faults = p->numa_faults_memory;
 
 	if (grp) {
 		spin_lock(&grp->lock);
-		for (i = 0; i < 2*nr_node_ids; i++)
-			grp->faults[i] -= p->numa_faults[i];
+		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+			grp->faults[i] -= p->numa_faults_memory[i];
 		grp->total_faults -= p->total_numa_faults;
 
 		list_del(&p->numa_entry);
@@ -1577,18 +1722,21 @@
 		put_numa_group(grp);
 	}
 
-	p->numa_faults = NULL;
-	p->numa_faults_buffer = NULL;
+	p->numa_faults_memory = NULL;
+	p->numa_faults_buffer_memory = NULL;
+	p->numa_faults_cpu= NULL;
+	p->numa_faults_buffer_cpu = NULL;
 	kfree(numa_faults);
 }
 
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
-void task_numa_fault(int last_cpupid, int node, int pages, int flags)
+void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 {
 	struct task_struct *p = current;
 	bool migrated = flags & TNF_MIGRATED;
+	int cpu_node = task_node(current);
 	int priv;
 
 	if (!numabalancing_enabled)
@@ -1603,16 +1751,24 @@
 		return;
 
 	/* Allocate buffer to track faults on a per-node basis */
-	if (unlikely(!p->numa_faults)) {
-		int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
+	if (unlikely(!p->numa_faults_memory)) {
+		int size = sizeof(*p->numa_faults_memory) *
+			   NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids;
 
-		/* numa_faults and numa_faults_buffer share the allocation */
-		p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
-		if (!p->numa_faults)
+		p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
+		if (!p->numa_faults_memory)
 			return;
 
-		BUG_ON(p->numa_faults_buffer);
-		p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
+		BUG_ON(p->numa_faults_buffer_memory);
+		/*
+		 * The averaged statistics, shared & private, memory & cpu,
+		 * occupy the first half of the array. The second half of the
+		 * array is for current counters, which are averaged into the
+		 * first set by task_numa_placement.
+		 */
+		p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids);
+		p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids);
+		p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids);
 		p->total_numa_faults = 0;
 		memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 	}
@@ -1641,7 +1797,8 @@
 	if (migrated)
 		p->numa_pages_migrated += pages;
 
-	p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
+	p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages;
+	p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages;
 	p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
 }
 
@@ -1757,6 +1914,8 @@
 			start = end;
 			if (pages <= 0)
 				goto out;
+
+			cond_resched();
 		} while (end != vma->vm_end);
 	}
 
@@ -2217,13 +2376,20 @@
 		se->avg.load_avg_contrib >>= NICE_0_SHIFT;
 	}
 }
-#else
+
+static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
+{
+	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
+	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
+}
+#else /* CONFIG_FAIR_GROUP_SCHED */
 static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
 						 int force_update) {}
 static inline void __update_tg_runnable_avg(struct sched_avg *sa,
 						  struct cfs_rq *cfs_rq) {}
 static inline void __update_group_entity_contrib(struct sched_entity *se) {}
-#endif
+static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 static inline void __update_task_entity_contrib(struct sched_entity *se)
 {
@@ -2321,12 +2487,6 @@
 	__update_cfs_rq_tg_load_contrib(cfs_rq, force_update);
 }
 
-static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
-{
-	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
-	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
-}
-
 /* Add the load generated by se into cfs_rq's child load-average */
 static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 						  struct sched_entity *se,
@@ -2414,7 +2574,10 @@
 	update_rq_runnable_avg(this_rq, 0);
 }
 
-#else
+static int idle_balance(struct rq *this_rq);
+
+#else /* CONFIG_SMP */
+
 static inline void update_entity_load_avg(struct sched_entity *se,
 					  int update_cfs_rq) {}
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
@@ -2426,7 +2589,13 @@
 					   int sleep) {}
 static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
 					      int force_update) {}
-#endif
+
+static inline int idle_balance(struct rq *rq)
+{
+	return 0;
+}
+
+#endif /* CONFIG_SMP */
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -2576,10 +2745,10 @@
 {
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-		if (cfs_rq->last == se)
-			cfs_rq->last = NULL;
-		else
+		if (cfs_rq->last != se)
 			break;
+
+		cfs_rq->last = NULL;
 	}
 }
 
@@ -2587,10 +2756,10 @@
 {
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-		if (cfs_rq->next == se)
-			cfs_rq->next = NULL;
-		else
+		if (cfs_rq->next != se)
 			break;
+
+		cfs_rq->next = NULL;
 	}
 }
 
@@ -2598,10 +2767,10 @@
 {
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-		if (cfs_rq->skip == se)
-			cfs_rq->skip = NULL;
-		else
+		if (cfs_rq->skip != se)
 			break;
+
+		cfs_rq->skip = NULL;
 	}
 }
 
@@ -2744,17 +2913,36 @@
  * 3) pick the "last" process, for cache locality
  * 4) do not run the "skip" process, if something else is available
  */
-static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *
+pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 {
-	struct sched_entity *se = __pick_first_entity(cfs_rq);
-	struct sched_entity *left = se;
+	struct sched_entity *left = __pick_first_entity(cfs_rq);
+	struct sched_entity *se;
+
+	/*
+	 * If curr is set we have to see if its left of the leftmost entity
+	 * still in the tree, provided there was anything in the tree at all.
+	 */
+	if (!left || (curr && entity_before(curr, left)))
+		left = curr;
+
+	se = left; /* ideally we run the leftmost entity */
 
 	/*
 	 * Avoid running the skip buddy, if running something else can
 	 * be done without getting too unfair.
 	 */
 	if (cfs_rq->skip == se) {
-		struct sched_entity *second = __pick_next_entity(se);
+		struct sched_entity *second;
+
+		if (se == curr) {
+			second = __pick_first_entity(cfs_rq);
+		} else {
+			second = __pick_next_entity(se);
+			if (!second || (curr && entity_before(curr, second)))
+				second = curr;
+		}
+
 		if (second && wakeup_preempt_entity(second, left) < 1)
 			se = second;
 	}
@@ -2776,7 +2964,7 @@
 	return se;
 }
 
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 
 static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 {
@@ -3431,22 +3619,23 @@
 }
 
 /* conditionally throttle active cfs_rq's from put_prev_entity() */
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
 	if (!cfs_bandwidth_used())
-		return;
+		return false;
 
 	if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0))
-		return;
+		return false;
 
 	/*
 	 * it's possible for a throttled entity to be forced into a running
 	 * state (e.g. set_curr_task), in this case we're finished.
 	 */
 	if (cfs_rq_throttled(cfs_rq))
-		return;
+		return true;
 
 	throttle_cfs_rq(cfs_rq);
+	return true;
 }
 
 static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
@@ -3556,7 +3745,7 @@
 }
 
 static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 
@@ -4211,13 +4400,14 @@
 }
 
 /*
- * sched_balance_self: balance the current task (running on cpu) in domains
- * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
- * SD_BALANCE_EXEC.
+ * select_task_rq_fair: Select target runqueue for the waking task in domains
+ * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
+ * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
  *
- * Balance, ie. select the least loaded group.
+ * Balances load by selecting the idlest cpu in the idlest group, or under
+ * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set.
  *
- * Returns the target CPU number, or the same CPU if no balancing is needed.
+ * Returns the target cpu number.
  *
  * preempt must be disabled.
  */
@@ -4492,26 +4682,124 @@
 		set_last_buddy(se);
 }
 
-static struct task_struct *pick_next_task_fair(struct rq *rq)
+static struct task_struct *
+pick_next_task_fair(struct rq *rq, struct task_struct *prev)
 {
-	struct task_struct *p;
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
+	struct task_struct *p;
+	int new_tasks;
 
+again:
+#ifdef CONFIG_FAIR_GROUP_SCHED
 	if (!cfs_rq->nr_running)
-		return NULL;
+		goto idle;
+
+	if (prev->sched_class != &fair_sched_class)
+		goto simple;
+
+	/*
+	 * Because of the set_next_buddy() in dequeue_task_fair() it is rather
+	 * likely that a next task is from the same cgroup as the current.
+	 *
+	 * Therefore attempt to avoid putting and setting the entire cgroup
+	 * hierarchy, only change the part that actually changes.
+	 */
 
 	do {
-		se = pick_next_entity(cfs_rq);
+		struct sched_entity *curr = cfs_rq->curr;
+
+		/*
+		 * Since we got here without doing put_prev_entity() we also
+		 * have to consider cfs_rq->curr. If it is still a runnable
+		 * entity, update_curr() will update its vruntime, otherwise
+		 * forget we've ever seen it.
+		 */
+		if (curr && curr->on_rq)
+			update_curr(cfs_rq);
+		else
+			curr = NULL;
+
+		/*
+		 * This call to check_cfs_rq_runtime() will do the throttle and
+		 * dequeue its entity in the parent(s). Therefore the 'simple'
+		 * nr_running test will indeed be correct.
+		 */
+		if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+			goto simple;
+
+		se = pick_next_entity(cfs_rq, curr);
+		cfs_rq = group_cfs_rq(se);
+	} while (cfs_rq);
+
+	p = task_of(se);
+
+	/*
+	 * Since we haven't yet done put_prev_entity and if the selected task
+	 * is a different task than we started out with, try and touch the
+	 * least amount of cfs_rqs.
+	 */
+	if (prev != p) {
+		struct sched_entity *pse = &prev->se;
+
+		while (!(cfs_rq = is_same_group(se, pse))) {
+			int se_depth = se->depth;
+			int pse_depth = pse->depth;
+
+			if (se_depth <= pse_depth) {
+				put_prev_entity(cfs_rq_of(pse), pse);
+				pse = parent_entity(pse);
+			}
+			if (se_depth >= pse_depth) {
+				set_next_entity(cfs_rq_of(se), se);
+				se = parent_entity(se);
+			}
+		}
+
+		put_prev_entity(cfs_rq, pse);
+		set_next_entity(cfs_rq, se);
+	}
+
+	if (hrtick_enabled(rq))
+		hrtick_start_fair(rq, p);
+
+	return p;
+simple:
+	cfs_rq = &rq->cfs;
+#endif
+
+	if (!cfs_rq->nr_running)
+		goto idle;
+
+	put_prev_task(rq, prev);
+
+	do {
+		se = pick_next_entity(cfs_rq, NULL);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
 
 	p = task_of(se);
+
 	if (hrtick_enabled(rq))
 		hrtick_start_fair(rq, p);
 
 	return p;
+
+idle:
+	new_tasks = idle_balance(rq);
+	/*
+	 * Because idle_balance() releases (and re-acquires) rq->lock, it is
+	 * possible for any higher priority task to appear. In that case we
+	 * must re-start the pick_next_entity() loop.
+	 */
+	if (new_tasks < 0)
+		return RETRY_TASK;
+
+	if (new_tasks > 0)
+		goto again;
+
+	return NULL;
 }
 
 /*
@@ -4749,7 +5037,7 @@
  * Is this task likely cache-hot:
  */
 static int
-task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
+task_hot(struct task_struct *p, u64 now)
 {
 	s64 delta;
 
@@ -4783,7 +5071,7 @@
 {
 	int src_nid, dst_nid;
 
-	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
+	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory ||
 	    !(env->sd->flags & SD_NUMA)) {
 		return false;
 	}
@@ -4814,7 +5102,7 @@
 	if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
 		return false;
 
-	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+	if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA))
 		return false;
 
 	src_nid = cpu_to_node(env->src_cpu);
@@ -4910,7 +5198,7 @@
 	 * 2) task is cache cold, or
 	 * 3) too many balance attempts have failed.
 	 */
-	tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
+	tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq));
 	if (!tsk_cache_hot)
 		tsk_cache_hot = migrate_degrades_locality(p, env);
 
@@ -5773,12 +6061,10 @@
 	pwr_now /= SCHED_POWER_SCALE;
 
 	/* Amount of load we'd subtract */
-	tmp = (busiest->load_per_task * SCHED_POWER_SCALE) /
-		busiest->group_power;
-	if (busiest->avg_load > tmp) {
+	if (busiest->avg_load > scaled_busy_load_per_task) {
 		pwr_move += busiest->group_power *
 			    min(busiest->load_per_task,
-				busiest->avg_load - tmp);
+				busiest->avg_load - scaled_busy_load_per_task);
 	}
 
 	/* Amount of load we'd add */
@@ -6357,17 +6643,23 @@
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
-void idle_balance(int this_cpu, struct rq *this_rq)
+static int idle_balance(struct rq *this_rq)
 {
 	struct sched_domain *sd;
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
 	u64 curr_cost = 0;
+	int this_cpu = this_rq->cpu;
 
+	idle_enter_fair(this_rq);
+	/*
+	 * We must set idle_stamp _before_ calling idle_balance(), such that we
+	 * measure the duration of idle_balance() as idle time.
+	 */
 	this_rq->idle_stamp = rq_clock(this_rq);
 
 	if (this_rq->avg_idle < sysctl_sched_migration_cost)
-		return;
+		goto out;
 
 	/*
 	 * Drop the rq->lock, but keep IRQ/preempt disabled.
@@ -6405,15 +6697,22 @@
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
 			next_balance = sd->last_balance + interval;
-		if (pulled_task) {
-			this_rq->idle_stamp = 0;
+		if (pulled_task)
 			break;
-		}
 	}
 	rcu_read_unlock();
 
 	raw_spin_lock(&this_rq->lock);
 
+	/*
+	 * While browsing the domains, we released the rq lock.
+	 * A task could have be enqueued in the meantime
+	 */
+	if (this_rq->cfs.h_nr_running && !pulled_task) {
+		pulled_task = 1;
+		goto out;
+	}
+
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
 		/*
 		 * We are going idle. next_balance may be set based on
@@ -6424,6 +6723,20 @@
 
 	if (curr_cost > this_rq->max_idle_balance_cost)
 		this_rq->max_idle_balance_cost = curr_cost;
+
+out:
+	/* Is there a task of a high priority class? */
+	if (this_rq->nr_running != this_rq->cfs.h_nr_running &&
+	    (this_rq->dl.dl_nr_running ||
+	     (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt))))
+		pulled_task = -1;
+
+	if (pulled_task) {
+		idle_exit_fair(this_rq);
+		this_rq->idle_stamp = 0;
+	}
+
+	return pulled_task;
 }
 
 /*
@@ -6494,6 +6807,11 @@
 	return 0;
 }
 
+static inline int on_null_domain(struct rq *rq)
+{
+	return unlikely(!rcu_dereference_sched(rq->sd));
+}
+
 #ifdef CONFIG_NO_HZ_COMMON
 /*
  * idle load balancing details
@@ -6548,8 +6866,13 @@
 static inline void nohz_balance_exit_idle(int cpu)
 {
 	if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
-		cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
-		atomic_dec(&nohz.nr_cpus);
+		/*
+		 * Completely isolated CPUs don't ever set, so we must test.
+		 */
+		if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) {
+			cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
+			atomic_dec(&nohz.nr_cpus);
+		}
 		clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
 	}
 }
@@ -6603,6 +6926,12 @@
 	if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
 		return;
 
+	/*
+	 * If we're a completely isolated CPU, we don't play.
+	 */
+	if (on_null_domain(cpu_rq(cpu)))
+		return;
+
 	cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
 	atomic_inc(&nohz.nr_cpus);
 	set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
@@ -6865,11 +7194,6 @@
 	nohz_idle_balance(this_rq, idle);
 }
 
-static inline int on_null_domain(struct rq *rq)
-{
-	return !rcu_dereference_sched(rq->sd);
-}
-
 /*
  * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
  */
@@ -6999,15 +7323,15 @@
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 	/*
-	 * Ensure the task's vruntime is normalized, so that when its
+	 * Ensure the task's vruntime is normalized, so that when it's
 	 * switched back to the fair class the enqueue_entity(.flags=0) will
 	 * do the right thing.
 	 *
-	 * If it was on_rq, then the dequeue_entity(.flags=0) will already
-	 * have normalized the vruntime, if it was !on_rq, then only when
+	 * If it's on_rq, then the dequeue_entity(.flags=0) will already
+	 * have normalized the vruntime, if it's !on_rq, then only when
 	 * the task is sleeping will it still have non-normalized vruntime.
 	 */
-	if (!se->on_rq && p->state != TASK_RUNNING) {
+	if (!p->on_rq && p->state != TASK_RUNNING) {
 		/*
 		 * Fix up our vruntime so that the current sleep doesn't
 		 * cause 'unlimited' sleep bonus.
@@ -7034,7 +7358,15 @@
  */
 static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
-	if (!p->se.on_rq)
+	struct sched_entity *se = &p->se;
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	/*
+	 * Since the real-depth could have been changed (only FAIR
+	 * class maintain depth value), reset depth properly.
+	 */
+	se->depth = se->parent ? se->parent->depth + 1 : 0;
+#endif
+	if (!se->on_rq)
 		return;
 
 	/*
@@ -7082,7 +7414,9 @@
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void task_move_group_fair(struct task_struct *p, int on_rq)
 {
+	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq;
+
 	/*
 	 * If the task was not on the rq at the time of this cgroup movement
 	 * it must have been asleep, sleeping tasks keep their ->vruntime
@@ -7108,23 +7442,24 @@
 	 * To prevent boost or penalty in the new cfs_rq caused by delta
 	 * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
 	 */
-	if (!on_rq && (!p->se.sum_exec_runtime || p->state == TASK_WAKING))
+	if (!on_rq && (!se->sum_exec_runtime || p->state == TASK_WAKING))
 		on_rq = 1;
 
 	if (!on_rq)
-		p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
+		se->vruntime -= cfs_rq_of(se)->min_vruntime;
 	set_task_rq(p, task_cpu(p));
+	se->depth = se->parent ? se->parent->depth + 1 : 0;
 	if (!on_rq) {
-		cfs_rq = cfs_rq_of(&p->se);
-		p->se.vruntime += cfs_rq->min_vruntime;
+		cfs_rq = cfs_rq_of(se);
+		se->vruntime += cfs_rq->min_vruntime;
 #ifdef CONFIG_SMP
 		/*
 		 * migrate_task_rq_fair() will have removed our previous
 		 * contribution, but we must synchronize for ongoing future
 		 * decay.
 		 */
-		p->se.avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
-		cfs_rq->blocked_load_avg += p->se.avg.load_avg_contrib;
+		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
+		cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
 #endif
 	}
 }
@@ -7220,10 +7555,13 @@
 	if (!se)
 		return;
 
-	if (!parent)
+	if (!parent) {
 		se->cfs_rq = &rq->cfs;
-	else
+		se->depth = 0;
+	} else {
 		se->cfs_rq = parent->my_q;
+		se->depth = parent->depth + 1;
+	}
 
 	se->my_q = cfs_rq;
 	/* guarantee group entities always have weight */
diff --git a/kernel/cpu/idle.c b/kernel/sched/idle.c
similarity index 95%
rename from kernel/cpu/idle.c
rename to kernel/sched/idle.c
index 277f494..b7976a1 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/sched/idle.c
@@ -3,6 +3,7 @@
  */
 #include <linux/sched.h>
 #include <linux/cpu.h>
+#include <linux/cpuidle.h>
 #include <linux/tick.h>
 #include <linux/mm.h>
 #include <linux/stackprotector.h>
@@ -95,8 +96,10 @@
 				if (!current_clr_polling_and_test()) {
 					stop_critical_timings();
 					rcu_idle_enter();
-					arch_cpu_idle();
-					WARN_ON_ONCE(irqs_disabled());
+					if (cpuidle_idle_call())
+						arch_cpu_idle();
+					if (WARN_ON_ONCE(irqs_disabled()))
+						local_irq_enable();
 					rcu_idle_exit();
 					start_critical_timings();
 				} else {
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 516c3d9..879f2b7 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -13,18 +13,8 @@
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
-
-static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
-{
-	idle_exit_fair(rq);
-	rq_last_tick_reset(rq);
-}
-
-static void post_schedule_idle(struct rq *rq)
-{
-	idle_enter_fair(rq);
-}
 #endif /* CONFIG_SMP */
+
 /*
  * Idle tasks are unconditionally rescheduled:
  */
@@ -33,13 +23,12 @@
 	resched_task(rq->idle);
 }
 
-static struct task_struct *pick_next_task_idle(struct rq *rq)
+static struct task_struct *
+pick_next_task_idle(struct rq *rq, struct task_struct *prev)
 {
+	put_prev_task(rq, prev);
+
 	schedstat_inc(rq, sched_goidle);
-#ifdef CONFIG_SMP
-	/* Trigger the post schedule to do an idle_enter for CFS */
-	rq->post_schedule = 1;
-#endif
 	return rq->idle;
 }
 
@@ -58,6 +47,8 @@
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
+	idle_exit_fair(rq);
+	rq_last_tick_reset(rq);
 }
 
 static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
@@ -101,8 +92,6 @@
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_idle,
-	.pre_schedule		= pre_schedule_idle,
-	.post_schedule		= post_schedule_idle,
 #endif
 
 	.set_curr_task          = set_curr_task_idle,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a2740b7..d8cdf16 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -229,6 +229,14 @@
 
 #ifdef CONFIG_SMP
 
+static int pull_rt_task(struct rq *this_rq);
+
+static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
+{
+	/* Try to pull RT tasks here if we lower this rq's prio */
+	return rq->rt.highest_prio.curr > prev->prio;
+}
+
 static inline int rt_overloaded(struct rq *rq)
 {
 	return atomic_read(&rq->rd->rto_count);
@@ -315,6 +323,15 @@
 	return !plist_head_empty(&rq->rt.pushable_tasks);
 }
 
+static inline void set_post_schedule(struct rq *rq)
+{
+	/*
+	 * We detect this state here so that we can avoid taking the RQ
+	 * lock again later if there is no need to push
+	 */
+	rq->post_schedule = has_pushable_tasks(rq);
+}
+
 static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
 {
 	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
@@ -359,6 +376,19 @@
 {
 }
 
+static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
+{
+	return false;
+}
+
+static inline int pull_rt_task(struct rq *this_rq)
+{
+	return 0;
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+}
 #endif /* CONFIG_SMP */
 
 static inline int on_rt_rq(struct sched_rt_entity *rt_se)
@@ -440,11 +470,6 @@
 		dequeue_rt_entity(rt_se);
 }
 
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
-}
-
 static int rt_se_boosted(struct sched_rt_entity *rt_se)
 {
 	struct rt_rq *rt_rq = group_rt_rq(rt_se);
@@ -515,11 +540,6 @@
 {
 }
 
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_throttled;
-}
-
 static inline const struct cpumask *sched_rt_period_mask(void)
 {
 	return cpu_online_mask;
@@ -538,6 +558,14 @@
 
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
+{
+	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+	return (hrtimer_active(&rt_b->rt_period_timer) ||
+		rt_rq->rt_time < rt_b->rt_runtime);
+}
+
 #ifdef CONFIG_SMP
 /*
  * We ran out of runtime, see if we can borrow some from our neighbours.
@@ -1310,15 +1338,7 @@
 {
 	struct sched_rt_entity *rt_se;
 	struct task_struct *p;
-	struct rt_rq *rt_rq;
-
-	rt_rq = &rq->rt;
-
-	if (!rt_rq->rt_nr_running)
-		return NULL;
-
-	if (rt_rq_throttled(rt_rq))
-		return NULL;
+	struct rt_rq *rt_rq  = &rq->rt;
 
 	do {
 		rt_se = pick_next_rt_entity(rq, rt_rq);
@@ -1332,21 +1352,45 @@
 	return p;
 }
 
-static struct task_struct *pick_next_task_rt(struct rq *rq)
+static struct task_struct *
+pick_next_task_rt(struct rq *rq, struct task_struct *prev)
 {
-	struct task_struct *p = _pick_next_task_rt(rq);
+	struct task_struct *p;
+	struct rt_rq *rt_rq = &rq->rt;
+
+	if (need_pull_rt_task(rq, prev)) {
+		pull_rt_task(rq);
+		/*
+		 * pull_rt_task() can drop (and re-acquire) rq->lock; this
+		 * means a dl task can slip in, in which case we need to
+		 * re-start task selection.
+		 */
+		if (unlikely(rq->dl.dl_nr_running))
+			return RETRY_TASK;
+	}
+
+	/*
+	 * We may dequeue prev's rt_rq in put_prev_task().
+	 * So, we update time before rt_nr_running check.
+	 */
+	if (prev->sched_class == &rt_sched_class)
+		update_curr_rt(rq);
+
+	if (!rt_rq->rt_nr_running)
+		return NULL;
+
+	if (rt_rq_throttled(rt_rq))
+		return NULL;
+
+	put_prev_task(rq, prev);
+
+	p = _pick_next_task_rt(rq);
 
 	/* The running task is never eligible for pushing */
 	if (p)
 		dequeue_pushable_task(rq, p);
 
-#ifdef CONFIG_SMP
-	/*
-	 * We detect this state here so that we can avoid taking the RQ
-	 * lock again later if there is no need to push
-	 */
-	rq->post_schedule = has_pushable_tasks(rq);
-#endif
+	set_post_schedule(rq);
 
 	return p;
 }
@@ -1716,13 +1760,6 @@
 	return ret;
 }
 
-static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
-{
-	/* Try to pull RT tasks here if we lower this rq's prio */
-	if (rq->rt.highest_prio.curr > prev->prio)
-		pull_rt_task(rq);
-}
-
 static void post_schedule_rt(struct rq *rq)
 {
 	push_rt_tasks(rq);
@@ -1825,7 +1862,7 @@
 		resched_task(rq->curr);
 }
 
-void init_sched_rt_class(void)
+void __init init_sched_rt_class(void)
 {
 	unsigned int i;
 
@@ -1999,7 +2036,6 @@
 	.set_cpus_allowed       = set_cpus_allowed_rt,
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,
-	.pre_schedule		= pre_schedule_rt,
 	.post_schedule		= post_schedule_rt,
 	.task_woken		= task_woken_rt,
 	.switched_from		= switched_from_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 5ec9910..c9007f2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -24,24 +24,6 @@
 extern void update_cpu_load_active(struct rq *this_rq);
 
 /*
- * Convert user-nice values [ -20 ... 0 ... 19 ]
- * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
- * and back.
- */
-#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
-#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
-#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)
-
-/*
- * 'User priority' is the nice value converted to something we
- * can work with better when scaling various scheduler parameters,
- * it's a [ 0 ... 39 ] range.
- */
-#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
-#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
-#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
-
-/*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
 #define NS_TO_JIFFIES(TIME)	((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
@@ -441,6 +423,18 @@
 #endif
 };
 
+#ifdef CONFIG_RT_GROUP_SCHED
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+	return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
+}
+#else
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+	return rt_rq->rt_throttled;
+}
+#endif
+
 /* Deadline class' related fields in a runqueue */
 struct dl_rq {
 	/* runqueue is an rbtree, ordered by deadline */
@@ -462,7 +456,6 @@
 	} earliest_dl;
 
 	unsigned long dl_nr_migratory;
-	unsigned long dl_nr_total;
 	int overloaded;
 
 	/*
@@ -559,11 +552,9 @@
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this cpu: */
 	struct list_head leaf_cfs_rq_list;
-#endif /* CONFIG_FAIR_GROUP_SCHED */
 
-#ifdef CONFIG_RT_GROUP_SCHED
-	struct list_head leaf_rt_rq_list;
-#endif
+	struct sched_avg avg;
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 	/*
 	 * This is part of a global counter where only the total sum
@@ -652,8 +643,6 @@
 #ifdef CONFIG_SMP
 	struct llist_head wake_list;
 #endif
-
-	struct sched_avg avg;
 };
 
 static inline int cpu_of(struct rq *rq)
@@ -1113,6 +1102,8 @@
 
 #define DEQUEUE_SLEEP		1
 
+#define RETRY_TASK		((void *)-1UL)
+
 struct sched_class {
 	const struct sched_class *next;
 
@@ -1123,14 +1114,22 @@
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
-	struct task_struct * (*pick_next_task) (struct rq *rq);
+	/*
+	 * It is the responsibility of the pick_next_task() method that will
+	 * return the next task to call put_prev_task() on the @prev task or
+	 * something equivalent.
+	 *
+	 * May return RETRY_TASK when it finds a higher prio class has runnable
+	 * tasks.
+	 */
+	struct task_struct * (*pick_next_task) (struct rq *rq,
+						struct task_struct *prev);
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
 	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
 
-	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
 	void (*task_waking) (struct task_struct *task);
 	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
@@ -1160,6 +1159,11 @@
 #endif
 };
 
+static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
+{
+	prev->sched_class->put_prev_task(rq, prev);
+}
+
 #define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
@@ -1176,16 +1180,14 @@
 extern void update_group_power(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
-extern void idle_balance(int this_cpu, struct rq *this_rq);
 
 extern void idle_enter_fair(struct rq *this_rq);
 extern void idle_exit_fair(struct rq *this_rq);
 
-#else	/* CONFIG_SMP */
+#else
 
-static inline void idle_balance(int cpu, struct rq *rq)
-{
-}
+static inline void idle_enter_fair(struct rq *rq) { }
+static inline void idle_exit_fair(struct rq *rq) { }
 
 #endif
 
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index fdb6bb0..d6ce65d 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -23,16 +23,19 @@
 	/* we're never preempted */
 }
 
-static struct task_struct *pick_next_task_stop(struct rq *rq)
+static struct task_struct *
+pick_next_task_stop(struct rq *rq, struct task_struct *prev)
 {
 	struct task_struct *stop = rq->stop;
 
-	if (stop && stop->on_rq) {
-		stop->se.exec_start = rq_clock_task(rq);
-		return stop;
-	}
+	if (!stop || !stop->on_rq)
+		return NULL;
 
-	return NULL;
+	put_prev_task(rq, prev);
+
+	stop->se.exec_start = rq_clock_task(rq);
+
+	return stop;
 }
 
 static void
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 84571e0..01fbae5 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -293,7 +293,7 @@
 	 */
 	smp_call_function_single(min(cpu1, cpu2),
 				 &irq_cpu_stop_queue_work,
-				 &call_args, 0);
+				 &call_args, 1);
 	lg_local_unlock(&stop_cpus_lock);
 	preempt_enable();
 
diff --git a/kernel/sys.c b/kernel/sys.c
index c0a58be..adaeab6 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -174,10 +174,10 @@
 
 	/* normalize: avoid signed division (rounding problems) */
 	error = -ESRCH;
-	if (niceval < -20)
-		niceval = -20;
-	if (niceval > 19)
-		niceval = 19;
+	if (niceval < MIN_NICE)
+		niceval = MIN_NICE;
+	if (niceval > MAX_NICE)
+		niceval = MAX_NICE;
 
 	rcu_read_lock();
 	read_lock(&tasklist_lock);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 49e13e1..7754ff1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -386,13 +386,6 @@
 		.proc_handler	= proc_dointvec,
 	},
 	{
-		.procname       = "numa_balancing_migrate_deferred",
-		.data           = &sysctl_numa_balancing_migrate_deferred,
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
-	},
-	{
 		.procname	= "numa_balancing",
 		.data		= NULL, /* filled in by handler */
 		.maxlen		= sizeof(unsigned int),
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7a925ba..a6a5bf5 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -51,7 +51,13 @@
  * HZ shrinks, so values greater than 8 overflow 32bits when
  * HZ=100.
  */
+#if HZ < 34
+#define JIFFIES_SHIFT	6
+#elif HZ < 67
+#define JIFFIES_SHIFT	7
+#else
 #define JIFFIES_SHIFT	8
+#endif
 
 static cycle_t jiffies_read(struct clocksource *cs)
 {
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 0abb364..4d23dc4 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -116,20 +116,42 @@
 void __init sched_clock_register(u64 (*read)(void), int bits,
 				 unsigned long rate)
 {
+	u64 res, wrap, new_mask, new_epoch, cyc, ns;
+	u32 new_mult, new_shift;
+	ktime_t new_wrap_kt;
 	unsigned long r;
-	u64 res, wrap;
 	char r_unit;
 
 	if (cd.rate > rate)
 		return;
 
 	WARN_ON(!irqs_disabled());
-	read_sched_clock = read;
-	sched_clock_mask = CLOCKSOURCE_MASK(bits);
-	cd.rate = rate;
 
 	/* calculate the mult/shift to convert counter ticks to ns. */
-	clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600);
+	clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
+
+	new_mask = CLOCKSOURCE_MASK(bits);
+
+	/* calculate how many ns until we wrap */
+	wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask);
+	new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
+
+	/* update epoch for new counter and update epoch_ns from old counter*/
+	new_epoch = read();
+	cyc = read_sched_clock();
+	ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+			  cd.mult, cd.shift);
+
+	raw_write_seqcount_begin(&cd.seq);
+	read_sched_clock = read;
+	sched_clock_mask = new_mask;
+	cd.rate = rate;
+	cd.wrap_kt = new_wrap_kt;
+	cd.mult = new_mult;
+	cd.shift = new_shift;
+	cd.epoch_cyc = new_epoch;
+	cd.epoch_ns = ns;
+	raw_write_seqcount_end(&cd.seq);
 
 	r = rate;
 	if (r >= 4000000) {
@@ -141,22 +163,12 @@
 	} else
 		r_unit = ' ';
 
-	/* calculate how many ns until we wrap */
-	wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask);
-	cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
-
 	/* calculate the ns resolution of this counter */
-	res = cyc_to_ns(1ULL, cd.mult, cd.shift);
+	res = cyc_to_ns(1ULL, new_mult, new_shift);
+
 	pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
 		bits, r, r_unit, res, wrap);
 
-	update_sched_clock();
-
-	/*
-	 * Ensure that sched_clock() starts off at 0ns
-	 */
-	cd.epoch_ns = 0;
-
 	/* Enable IRQ time accounting if we have a fast enough sched_clock */
 	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
 		enable_sched_clock_irqtime();
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 43780ab..98977a5 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -756,6 +756,7 @@
 static void tick_broadcast_clear_oneshot(int cpu)
 {
 	cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
 }
 
 static void tick_broadcast_init_next_event(struct cpumask *mask,
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 0aa4ce8..5b40279 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1435,7 +1435,8 @@
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 	if (clock_set)
-		clock_was_set();
+		/* Have to call _delayed version, since in irq context*/
+		clock_was_set_delayed();
 }
 
 /**
diff --git a/kernel/timer.c b/kernel/timer.c
index accfd24..d78de04 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -52,7 +52,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/timer.h>
 
-u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
+__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
 
 EXPORT_SYMBOL(jiffies_64);
 
diff --git a/kernel/torture.c b/kernel/torture.c
new file mode 100644
index 0000000..acc9afc
--- /dev/null
+++ b/kernel/torture.c
@@ -0,0 +1,719 @@
+/*
+ * Common functions for in-kernel torture tests.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2014
+ *
+ * Author: Paul E. McKenney <paulmck@us.ibm.com>
+ *	Based on kernel/rcu/torture.c.
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/freezer.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/trace_clock.h>
+#include <asm/byteorder.h>
+#include <linux/torture.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+
+static char *torture_type;
+static bool verbose;
+
+/* Mediate rmmod and system shutdown.  Concurrent rmmod & shutdown illegal! */
+#define FULLSTOP_DONTSTOP 0	/* Normal operation. */
+#define FULLSTOP_SHUTDOWN 1	/* System shutdown with torture running. */
+#define FULLSTOP_RMMOD    2	/* Normal rmmod of torture. */
+static int fullstop = FULLSTOP_RMMOD;
+static DEFINE_MUTEX(fullstop_mutex);
+static int *torture_runnable;
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Variables for online-offline handling.  Only present if CPU hotplug
+ * is enabled, otherwise does nothing.
+ */
+
+static struct task_struct *onoff_task;
+static long onoff_holdoff;
+static long onoff_interval;
+static long n_offline_attempts;
+static long n_offline_successes;
+static unsigned long sum_offline;
+static int min_offline = -1;
+static int max_offline;
+static long n_online_attempts;
+static long n_online_successes;
+static unsigned long sum_online;
+static int min_online = -1;
+static int max_online;
+
+/*
+ * Execute random CPU-hotplug operations at the interval specified
+ * by the onoff_interval.
+ */
+static int
+torture_onoff(void *arg)
+{
+	int cpu;
+	unsigned long delta;
+	int maxcpu = -1;
+	DEFINE_TORTURE_RANDOM(rand);
+	int ret;
+	unsigned long starttime;
+
+	VERBOSE_TOROUT_STRING("torture_onoff task started");
+	for_each_online_cpu(cpu)
+		maxcpu = cpu;
+	WARN_ON(maxcpu < 0);
+	if (onoff_holdoff > 0) {
+		VERBOSE_TOROUT_STRING("torture_onoff begin holdoff");
+		schedule_timeout_interruptible(onoff_holdoff);
+		VERBOSE_TOROUT_STRING("torture_onoff end holdoff");
+	}
+	while (!torture_must_stop()) {
+		cpu = (torture_random(&rand) >> 4) % (maxcpu + 1);
+		if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) {
+			if (verbose)
+				pr_alert("%s" TORTURE_FLAG
+					 "torture_onoff task: offlining %d\n",
+					 torture_type, cpu);
+			starttime = jiffies;
+			n_offline_attempts++;
+			ret = cpu_down(cpu);
+			if (ret) {
+				if (verbose)
+					pr_alert("%s" TORTURE_FLAG
+						 "torture_onoff task: offline %d failed: errno %d\n",
+						 torture_type, cpu, ret);
+			} else {
+				if (verbose)
+					pr_alert("%s" TORTURE_FLAG
+						 "torture_onoff task: offlined %d\n",
+						 torture_type, cpu);
+				n_offline_successes++;
+				delta = jiffies - starttime;
+				sum_offline += delta;
+				if (min_offline < 0) {
+					min_offline = delta;
+					max_offline = delta;
+				}
+				if (min_offline > delta)
+					min_offline = delta;
+				if (max_offline < delta)
+					max_offline = delta;
+			}
+		} else if (cpu_is_hotpluggable(cpu)) {
+			if (verbose)
+				pr_alert("%s" TORTURE_FLAG
+					 "torture_onoff task: onlining %d\n",
+					 torture_type, cpu);
+			starttime = jiffies;
+			n_online_attempts++;
+			ret = cpu_up(cpu);
+			if (ret) {
+				if (verbose)
+					pr_alert("%s" TORTURE_FLAG
+						 "torture_onoff task: online %d failed: errno %d\n",
+						 torture_type, cpu, ret);
+			} else {
+				if (verbose)
+					pr_alert("%s" TORTURE_FLAG
+						 "torture_onoff task: onlined %d\n",
+						 torture_type, cpu);
+				n_online_successes++;
+				delta = jiffies - starttime;
+				sum_online += delta;
+				if (min_online < 0) {
+					min_online = delta;
+					max_online = delta;
+				}
+				if (min_online > delta)
+					min_online = delta;
+				if (max_online < delta)
+					max_online = delta;
+			}
+		}
+		schedule_timeout_interruptible(onoff_interval);
+	}
+	torture_kthread_stopping("torture_onoff");
+	return 0;
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
+ * Initiate online-offline handling.
+ */
+int torture_onoff_init(long ooholdoff, long oointerval)
+{
+	int ret = 0;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	onoff_holdoff = ooholdoff;
+	onoff_interval = oointerval;
+	if (onoff_interval <= 0)
+		return 0;
+	ret = torture_create_kthread(torture_onoff, NULL, onoff_task);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+	return ret;
+}
+EXPORT_SYMBOL_GPL(torture_onoff_init);
+
+/*
+ * Clean up after online/offline testing.
+ */
+static void torture_onoff_cleanup(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	if (onoff_task == NULL)
+		return;
+	VERBOSE_TOROUT_STRING("Stopping torture_onoff task");
+	kthread_stop(onoff_task);
+	onoff_task = NULL;
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+}
+EXPORT_SYMBOL_GPL(torture_onoff_cleanup);
+
+/*
+ * Print online/offline testing statistics.
+ */
+char *torture_onoff_stats(char *page)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	page += sprintf(page,
+		       "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
+		       n_online_successes, n_online_attempts,
+		       n_offline_successes, n_offline_attempts,
+		       min_online, max_online,
+		       min_offline, max_offline,
+		       sum_online, sum_offline, HZ);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+	return page;
+}
+EXPORT_SYMBOL_GPL(torture_onoff_stats);
+
+/*
+ * Were all the online/offline operations successful?
+ */
+bool torture_onoff_failures(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	return n_online_successes != n_online_attempts ||
+	       n_offline_successes != n_offline_attempts;
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+	return false;
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
+}
+EXPORT_SYMBOL_GPL(torture_onoff_failures);
+
+#define TORTURE_RANDOM_MULT	39916801  /* prime */
+#define TORTURE_RANDOM_ADD	479001701 /* prime */
+#define TORTURE_RANDOM_REFRESH	10000
+
+/*
+ * Crude but fast random-number generator.  Uses a linear congruential
+ * generator, with occasional help from cpu_clock().
+ */
+unsigned long
+torture_random(struct torture_random_state *trsp)
+{
+	if (--trsp->trs_count < 0) {
+		trsp->trs_state += (unsigned long)local_clock();
+		trsp->trs_count = TORTURE_RANDOM_REFRESH;
+	}
+	trsp->trs_state = trsp->trs_state * TORTURE_RANDOM_MULT +
+		TORTURE_RANDOM_ADD;
+	return swahw32(trsp->trs_state);
+}
+EXPORT_SYMBOL_GPL(torture_random);
+
+/*
+ * Variables for shuffling.  The idea is to ensure that each CPU stays
+ * idle for an extended period to test interactions with dyntick idle,
+ * as well as interactions with any per-CPU varibles.
+ */
+struct shuffle_task {
+	struct list_head st_l;
+	struct task_struct *st_t;
+};
+
+static long shuffle_interval;	/* In jiffies. */
+static struct task_struct *shuffler_task;
+static cpumask_var_t shuffle_tmp_mask;
+static int shuffle_idle_cpu;	/* Force all torture tasks off this CPU */
+static struct list_head shuffle_task_list = LIST_HEAD_INIT(shuffle_task_list);
+static DEFINE_MUTEX(shuffle_task_mutex);
+
+/*
+ * Register a task to be shuffled.  If there is no memory, just splat
+ * and don't bother registering.
+ */
+void torture_shuffle_task_register(struct task_struct *tp)
+{
+	struct shuffle_task *stp;
+
+	if (WARN_ON_ONCE(tp == NULL))
+		return;
+	stp = kmalloc(sizeof(*stp), GFP_KERNEL);
+	if (WARN_ON_ONCE(stp == NULL))
+		return;
+	stp->st_t = tp;
+	mutex_lock(&shuffle_task_mutex);
+	list_add(&stp->st_l, &shuffle_task_list);
+	mutex_unlock(&shuffle_task_mutex);
+}
+EXPORT_SYMBOL_GPL(torture_shuffle_task_register);
+
+/*
+ * Unregister all tasks, for example, at the end of the torture run.
+ */
+static void torture_shuffle_task_unregister_all(void)
+{
+	struct shuffle_task *stp;
+	struct shuffle_task *p;
+
+	mutex_lock(&shuffle_task_mutex);
+	list_for_each_entry_safe(stp, p, &shuffle_task_list, st_l) {
+		list_del(&stp->st_l);
+		kfree(stp);
+	}
+	mutex_unlock(&shuffle_task_mutex);
+}
+
+/* Shuffle tasks such that we allow shuffle_idle_cpu to become idle.
+ * A special case is when shuffle_idle_cpu = -1, in which case we allow
+ * the tasks to run on all CPUs.
+ */
+static void torture_shuffle_tasks(void)
+{
+	struct shuffle_task *stp;
+
+	cpumask_setall(shuffle_tmp_mask);
+	get_online_cpus();
+
+	/* No point in shuffling if there is only one online CPU (ex: UP) */
+	if (num_online_cpus() == 1) {
+		put_online_cpus();
+		return;
+	}
+
+	/* Advance to the next CPU.  Upon overflow, don't idle any CPUs. */
+	shuffle_idle_cpu = cpumask_next(shuffle_idle_cpu, shuffle_tmp_mask);
+	if (shuffle_idle_cpu >= nr_cpu_ids)
+		shuffle_idle_cpu = -1;
+	if (shuffle_idle_cpu != -1) {
+		cpumask_clear_cpu(shuffle_idle_cpu, shuffle_tmp_mask);
+		if (cpumask_empty(shuffle_tmp_mask)) {
+			put_online_cpus();
+			return;
+		}
+	}
+
+	mutex_lock(&shuffle_task_mutex);
+	list_for_each_entry(stp, &shuffle_task_list, st_l)
+		set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask);
+	mutex_unlock(&shuffle_task_mutex);
+
+	put_online_cpus();
+}
+
+/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
+ * system to become idle at a time and cut off its timer ticks. This is meant
+ * to test the support for such tickless idle CPU in RCU.
+ */
+static int torture_shuffle(void *arg)
+{
+	VERBOSE_TOROUT_STRING("torture_shuffle task started");
+	do {
+		schedule_timeout_interruptible(shuffle_interval);
+		torture_shuffle_tasks();
+		torture_shutdown_absorb("torture_shuffle");
+	} while (!torture_must_stop());
+	torture_kthread_stopping("torture_shuffle");
+	return 0;
+}
+
+/*
+ * Start the shuffler, with shuffint in jiffies.
+ */
+int torture_shuffle_init(long shuffint)
+{
+	shuffle_interval = shuffint;
+
+	shuffle_idle_cpu = -1;
+
+	if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) {
+		VERBOSE_TOROUT_ERRSTRING("Failed to alloc mask");
+		return -ENOMEM;
+	}
+
+	/* Create the shuffler thread */
+	return torture_create_kthread(torture_shuffle, NULL, shuffler_task);
+}
+EXPORT_SYMBOL_GPL(torture_shuffle_init);
+
+/*
+ * Stop the shuffling.
+ */
+static void torture_shuffle_cleanup(void)
+{
+	torture_shuffle_task_unregister_all();
+	if (shuffler_task) {
+		VERBOSE_TOROUT_STRING("Stopping torture_shuffle task");
+		kthread_stop(shuffler_task);
+		free_cpumask_var(shuffle_tmp_mask);
+	}
+	shuffler_task = NULL;
+}
+EXPORT_SYMBOL_GPL(torture_shuffle_cleanup);
+
+/*
+ * Variables for auto-shutdown.  This allows "lights out" torture runs
+ * to be fully scripted.
+ */
+static int shutdown_secs;		/* desired test duration in seconds. */
+static struct task_struct *shutdown_task;
+static unsigned long shutdown_time;	/* jiffies to system shutdown. */
+static void (*torture_shutdown_hook)(void);
+
+/*
+ * Absorb kthreads into a kernel function that won't return, so that
+ * they won't ever access module text or data again.
+ */
+void torture_shutdown_absorb(const char *title)
+{
+	while (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+		pr_notice("torture thread %s parking due to system shutdown\n",
+			  title);
+		schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
+	}
+}
+EXPORT_SYMBOL_GPL(torture_shutdown_absorb);
+
+/*
+ * Cause the torture test to shutdown the system after the test has
+ * run for the time specified by the shutdown_secs parameter.
+ */
+static int torture_shutdown(void *arg)
+{
+	long delta;
+	unsigned long jiffies_snap;
+
+	VERBOSE_TOROUT_STRING("torture_shutdown task started");
+	jiffies_snap = jiffies;
+	while (ULONG_CMP_LT(jiffies_snap, shutdown_time) &&
+	       !torture_must_stop()) {
+		delta = shutdown_time - jiffies_snap;
+		if (verbose)
+			pr_alert("%s" TORTURE_FLAG
+				 "torture_shutdown task: %lu jiffies remaining\n",
+				 torture_type, delta);
+		schedule_timeout_interruptible(delta);
+		jiffies_snap = jiffies;
+	}
+	if (torture_must_stop()) {
+		torture_kthread_stopping("torture_shutdown");
+		return 0;
+	}
+
+	/* OK, shut down the system. */
+
+	VERBOSE_TOROUT_STRING("torture_shutdown task shutting down system");
+	shutdown_task = NULL;	/* Avoid self-kill deadlock. */
+	if (torture_shutdown_hook)
+		torture_shutdown_hook();
+	else
+		VERBOSE_TOROUT_STRING("No torture_shutdown_hook(), skipping.");
+	kernel_power_off();	/* Shut down the system. */
+	return 0;
+}
+
+/*
+ * Start up the shutdown task.
+ */
+int torture_shutdown_init(int ssecs, void (*cleanup)(void))
+{
+	int ret = 0;
+
+	shutdown_secs = ssecs;
+	torture_shutdown_hook = cleanup;
+	if (shutdown_secs > 0) {
+		shutdown_time = jiffies + shutdown_secs * HZ;
+		ret = torture_create_kthread(torture_shutdown, NULL,
+					     shutdown_task);
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(torture_shutdown_init);
+
+/*
+ * Detect and respond to a system shutdown.
+ */
+static int torture_shutdown_notify(struct notifier_block *unused1,
+				   unsigned long unused2, void *unused3)
+{
+	mutex_lock(&fullstop_mutex);
+	if (ACCESS_ONCE(fullstop) == FULLSTOP_DONTSTOP) {
+		VERBOSE_TOROUT_STRING("Unscheduled system shutdown detected");
+		ACCESS_ONCE(fullstop) = FULLSTOP_SHUTDOWN;
+	} else {
+		pr_warn("Concurrent rmmod and shutdown illegal!\n");
+	}
+	mutex_unlock(&fullstop_mutex);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block torture_shutdown_nb = {
+	.notifier_call = torture_shutdown_notify,
+};
+
+/*
+ * Shut down the shutdown task.  Say what???  Heh!  This can happen if
+ * the torture module gets an rmmod before the shutdown time arrives.  ;-)
+ */
+static void torture_shutdown_cleanup(void)
+{
+	unregister_reboot_notifier(&torture_shutdown_nb);
+	if (shutdown_task != NULL) {
+		VERBOSE_TOROUT_STRING("Stopping torture_shutdown task");
+		kthread_stop(shutdown_task);
+	}
+	shutdown_task = NULL;
+}
+
+/*
+ * Variables for stuttering, which means to periodically pause and
+ * restart testing in order to catch bugs that appear when load is
+ * suddenly applied to or removed from the system.
+ */
+static struct task_struct *stutter_task;
+static int stutter_pause_test;
+static int stutter;
+
+/*
+ * Block until the stutter interval ends.  This must be called periodically
+ * by all running kthreads that need to be subject to stuttering.
+ */
+void stutter_wait(const char *title)
+{
+	while (ACCESS_ONCE(stutter_pause_test) ||
+	       (torture_runnable && !ACCESS_ONCE(*torture_runnable))) {
+		if (stutter_pause_test)
+			schedule_timeout_interruptible(1);
+		else
+			schedule_timeout_interruptible(round_jiffies_relative(HZ));
+		torture_shutdown_absorb(title);
+	}
+}
+EXPORT_SYMBOL_GPL(stutter_wait);
+
+/*
+ * Cause the torture test to "stutter", starting and stopping all
+ * threads periodically.
+ */
+static int torture_stutter(void *arg)
+{
+	VERBOSE_TOROUT_STRING("torture_stutter task started");
+	do {
+		if (!torture_must_stop()) {
+			schedule_timeout_interruptible(stutter);
+			ACCESS_ONCE(stutter_pause_test) = 1;
+		}
+		if (!torture_must_stop())
+			schedule_timeout_interruptible(stutter);
+		ACCESS_ONCE(stutter_pause_test) = 0;
+		torture_shutdown_absorb("torture_stutter");
+	} while (!torture_must_stop());
+	torture_kthread_stopping("torture_stutter");
+	return 0;
+}
+
+/*
+ * Initialize and kick off the torture_stutter kthread.
+ */
+int torture_stutter_init(int s)
+{
+	int ret;
+
+	stutter = s;
+	ret = torture_create_kthread(torture_stutter, NULL, stutter_task);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(torture_stutter_init);
+
+/*
+ * Cleanup after the torture_stutter kthread.
+ */
+static void torture_stutter_cleanup(void)
+{
+	if (!stutter_task)
+		return;
+	VERBOSE_TOROUT_STRING("Stopping torture_stutter task");
+	kthread_stop(stutter_task);
+	stutter_task = NULL;
+}
+
+/*
+ * Initialize torture module.  Please note that this is -not- invoked via
+ * the usual module_init() mechanism, but rather by an explicit call from
+ * the client torture module.  This call must be paired with a later
+ * torture_init_end().
+ *
+ * The runnable parameter points to a flag that controls whether or not
+ * the test is currently runnable.  If there is no such flag, pass in NULL.
+ */
+void __init torture_init_begin(char *ttype, bool v, int *runnable)
+{
+	mutex_lock(&fullstop_mutex);
+	torture_type = ttype;
+	verbose = v;
+	torture_runnable = runnable;
+	fullstop = FULLSTOP_DONTSTOP;
+
+}
+EXPORT_SYMBOL_GPL(torture_init_begin);
+
+/*
+ * Tell the torture module that initialization is complete.
+ */
+void __init torture_init_end(void)
+{
+	mutex_unlock(&fullstop_mutex);
+	register_reboot_notifier(&torture_shutdown_nb);
+}
+EXPORT_SYMBOL_GPL(torture_init_end);
+
+/*
+ * Clean up torture module.  Please note that this is -not- invoked via
+ * the usual module_exit() mechanism, but rather by an explicit call from
+ * the client torture module.  Returns true if a race with system shutdown
+ * is detected, otherwise, all kthreads started by functions in this file
+ * will be shut down.
+ *
+ * This must be called before the caller starts shutting down its own
+ * kthreads.
+ */
+bool torture_cleanup(void)
+{
+	mutex_lock(&fullstop_mutex);
+	if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+		pr_warn("Concurrent rmmod and shutdown illegal!\n");
+		mutex_unlock(&fullstop_mutex);
+		schedule_timeout_uninterruptible(10);
+		return true;
+	}
+	ACCESS_ONCE(fullstop) = FULLSTOP_RMMOD;
+	mutex_unlock(&fullstop_mutex);
+	torture_shutdown_cleanup();
+	torture_shuffle_cleanup();
+	torture_stutter_cleanup();
+	torture_onoff_cleanup();
+	return false;
+}
+EXPORT_SYMBOL_GPL(torture_cleanup);
+
+/*
+ * Is it time for the current torture test to stop?
+ */
+bool torture_must_stop(void)
+{
+	return torture_must_stop_irq() || kthread_should_stop();
+}
+EXPORT_SYMBOL_GPL(torture_must_stop);
+
+/*
+ * Is it time for the current torture test to stop?  This is the irq-safe
+ * version, hence no check for kthread_should_stop().
+ */
+bool torture_must_stop_irq(void)
+{
+	return ACCESS_ONCE(fullstop) != FULLSTOP_DONTSTOP;
+}
+EXPORT_SYMBOL_GPL(torture_must_stop_irq);
+
+/*
+ * Each kthread must wait for kthread_should_stop() before returning from
+ * its top-level function, otherwise segfaults ensue.  This function
+ * prints a "stopping" message and waits for kthread_should_stop(), and
+ * should be called from all torture kthreads immediately prior to
+ * returning.
+ */
+void torture_kthread_stopping(char *title)
+{
+	if (verbose)
+		VERBOSE_TOROUT_STRING(title);
+	while (!kthread_should_stop()) {
+		torture_shutdown_absorb(title);
+		schedule_timeout_uninterruptible(1);
+	}
+}
+EXPORT_SYMBOL_GPL(torture_kthread_stopping);
+
+/*
+ * Create a generic torture kthread that is immediately runnable.  If you
+ * need the kthread to be stopped so that you can do something to it before
+ * it starts, you will need to open-code your own.
+ */
+int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
+			    char *f, struct task_struct **tp)
+{
+	int ret = 0;
+
+	VERBOSE_TOROUT_STRING(m);
+	*tp = kthread_run(fn, arg, s);
+	if (IS_ERR(*tp)) {
+		ret = PTR_ERR(*tp);
+		VERBOSE_TOROUT_ERRSTRING(f);
+		*tp = NULL;
+	}
+	torture_shuffle_task_register(*tp);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(_torture_create_kthread);
+
+/*
+ * Stop a generic kthread, emitting a message.
+ */
+void _torture_stop_kthread(char *m, struct task_struct **tp)
+{
+	if (*tp == NULL)
+		return;
+	VERBOSE_TOROUT_STRING(m);
+	kthread_stop(*tp);
+	*tp = NULL;
+}
+EXPORT_SYMBOL_GPL(_torture_stop_kthread);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 294b8a2..fc4da2d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2397,6 +2397,13 @@
 	write &= RB_WRITE_MASK;
 	tail = write - length;
 
+	/*
+	 * If this is the first commit on the page, then it has the same
+	 * timestamp as the page itself.
+	 */
+	if (!tail)
+		delta = 0;
+
 	/* See if we shot pass the end of this buffer page */
 	if (unlikely(write > BUF_PAGE_SIZE))
 		return rb_move_tail(cpu_buffer, length, tail,
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index a5457d5..0434ff1 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -40,8 +40,8 @@
 module_param(write_iteration, uint, 0644);
 MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
 
-static int producer_nice = 19;
-static int consumer_nice = 19;
+static int producer_nice = MAX_NICE;
+static int consumer_nice = MAX_NICE;
 
 static int producer_fifo = -1;
 static int consumer_fifo = -1;
@@ -308,7 +308,7 @@
 
 	/* Let the user know that the test is running at low priority */
 	if (producer_fifo < 0 && consumer_fifo < 0 &&
-	    producer_nice == 19 && consumer_nice == 19)
+	    producer_nice == MAX_NICE && consumer_nice == MAX_NICE)
 		trace_printk("WARNING!!! This test is running at lowest priority.\n");
 
 	trace_printk("Time:     %lld (usecs)\n", time);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 815c878..24c1f23 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1600,15 +1600,31 @@
 }
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
 
+static struct ring_buffer *temp_buffer;
+
 struct ring_buffer_event *
 trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
 			  struct ftrace_event_file *ftrace_file,
 			  int type, unsigned long len,
 			  unsigned long flags, int pc)
 {
+	struct ring_buffer_event *entry;
+
 	*current_rb = ftrace_file->tr->trace_buffer.buffer;
-	return trace_buffer_lock_reserve(*current_rb,
+	entry = trace_buffer_lock_reserve(*current_rb,
 					 type, len, flags, pc);
+	/*
+	 * If tracing is off, but we have triggers enabled
+	 * we still need to look at the event data. Use the temp_buffer
+	 * to store the trace event for the tigger to use. It's recusive
+	 * safe and will not be recorded anywhere.
+	 */
+	if (!entry && ftrace_file->flags & FTRACE_EVENT_FL_TRIGGER_COND) {
+		*current_rb = temp_buffer;
+		entry = trace_buffer_lock_reserve(*current_rb,
+						  type, len, flags, pc);
+	}
+	return entry;
 }
 EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
 
@@ -6494,11 +6510,16 @@
 
 	raw_spin_lock_init(&global_trace.start_lock);
 
+	/* Used for event triggers */
+	temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE);
+	if (!temp_buffer)
+		goto out_free_cpumask;
+
 	/* TODO: make the number of buffers hot pluggable with CPUS */
 	if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
-		goto out_free_cpumask;
+		goto out_free_temp_buffer;
 	}
 
 	if (global_trace.buffer_disabled)
@@ -6540,6 +6561,8 @@
 
 	return 0;
 
+out_free_temp_buffer:
+	ring_buffer_free(temp_buffer);
 out_free_cpumask:
 	free_percpu(global_trace.trace_buffer.data);
 #ifdef CONFIG_TRACER_MAX_TRACE
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index e854f42..c894614 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -31,9 +31,25 @@
 	}
 
 	/* The ftrace function trace is allowed only for root. */
-	if (ftrace_event_is_function(tp_event) &&
-	    perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
+	if (ftrace_event_is_function(tp_event)) {
+		if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		/*
+		 * We don't allow user space callchains for  function trace
+		 * event, due to issues with page faults while tracing page
+		 * fault handler and its overall trickiness nature.
+		 */
+		if (!p_event->attr.exclude_callchain_user)
+			return -EINVAL;
+
+		/*
+		 * Same reason to disable user stack dump as for user space
+		 * callchains above.
+		 */
+		if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER)
+			return -EINVAL;
+	}
 
 	/* No tracing, just counting, so no obvious leak */
 	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e71ffd4..7b16d40 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,12 +27,6 @@
 
 DEFINE_MUTEX(event_mutex);
 
-DEFINE_MUTEX(event_storage_mutex);
-EXPORT_SYMBOL_GPL(event_storage_mutex);
-
-char event_storage[EVENT_STORAGE_SIZE];
-EXPORT_SYMBOL_GPL(event_storage);
-
 LIST_HEAD(ftrace_events);
 static LIST_HEAD(ftrace_common_fields);
 
@@ -1777,6 +1771,16 @@
 {
 	struct ftrace_event_call **call, **start, **end;
 
+	if (!mod->num_trace_events)
+		return;
+
+	/* Don't add infrastructure for mods without tracepoints */
+	if (trace_module_has_bad_taint(mod)) {
+		pr_err("%s: module has bad taint, not creating trace events\n",
+		       mod->name);
+		return;
+	}
+
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7c3e3e7..ee0a509 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -95,15 +95,12 @@
 #undef __array
 #define __array(type, item, len)					\
 	do {								\
+		char *type_str = #type"["__stringify(len)"]";		\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		mutex_lock(&event_storage_mutex);			\
-		snprintf(event_storage, sizeof(event_storage),		\
-			 "%s[%d]", #type, len);				\
-		ret = trace_define_field(event_call, event_storage, #item, \
+		ret = trace_define_field(event_call, type_str, #item,	\
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
 				 is_signed_type(type), filter_type);	\
-		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
 	} while (0);
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 2aefbee..887ef88 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -498,14 +498,14 @@
 }
 EXPORT_SYMBOL(trace_hardirqs_off);
 
-void trace_hardirqs_on_caller(unsigned long caller_addr)
+__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 {
 	if (!preempt_trace() && irq_trace())
 		stop_critical_timing(CALLER_ADDR0, caller_addr);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
 
-void trace_hardirqs_off_caller(unsigned long caller_addr)
+__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
 	if (!preempt_trace() && irq_trace())
 		start_critical_timing(CALLER_ADDR0, caller_addr);
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 29f2654..031cc56 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -631,6 +631,11 @@
 EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
 
 #ifdef CONFIG_MODULES
+bool trace_module_has_bad_taint(struct module *mod)
+{
+	return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
+}
+
 static int tracepoint_module_coming(struct module *mod)
 {
 	struct tp_module *tp_mod, *iter;
@@ -641,7 +646,7 @@
 	 * module headers (for forced load), to make sure we don't cause a crash.
 	 * Staging and out-of-tree GPL modules are fine.
 	 */
-	if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
+	if (trace_module_has_bad_taint(mod))
 		return 0;
 	mutex_lock(&tracepoints_mutex);
 	tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 240fb62..dd06439 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -225,7 +225,7 @@
  *
  *	When there is no mapping defined for the user-namespace uid
  *	pair INVALID_UID is returned.  Callers are expected to test
- *	for and handle handle INVALID_UID being returned.  INVALID_UID
+ *	for and handle INVALID_UID being returned.  INVALID_UID
  *	may be tested for using uid_valid().
  */
 kuid_t make_kuid(struct user_namespace *ns, uid_t uid)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 82ef9f3..3fa5b8f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1851,6 +1851,12 @@
 	if (worker->flags & WORKER_IDLE)
 		pool->nr_idle--;
 
+	/*
+	 * Once WORKER_DIE is set, the kworker may destroy itself at any
+	 * point.  Pin to ensure the task stays until we're done with it.
+	 */
+	get_task_struct(worker->task);
+
 	list_del_init(&worker->entry);
 	worker->flags |= WORKER_DIE;
 
@@ -1859,6 +1865,7 @@
 	spin_unlock_irq(&pool->lock);
 
 	kthread_stop(worker->task);
+	put_task_struct(worker->task);
 	kfree(worker);
 
 	spin_lock_irq(&pool->lock);
@@ -3218,7 +3225,7 @@
 		return -ENOMEM;
 
 	if (sscanf(buf, "%d", &attrs->nice) == 1 &&
-	    attrs->nice >= -20 && attrs->nice <= 19)
+	    attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE)
 		ret = apply_workqueue_attrs(wq, attrs);
 	else
 		ret = -EINVAL;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index dbf94a7..dd7f885 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -119,7 +119,7 @@
 
 config DEBUG_INFO
 	bool "Compile the kernel with debug info"
-	depends on DEBUG_KERNEL
+	depends on DEBUG_KERNEL && !COMPILE_TEST
 	help
           If you say Y here the resulting kernel image will include
 	  debugging info resulting in a larger kernel image.
@@ -980,6 +980,21 @@
 	  The following locking APIs are covered: spinlocks, rwlocks,
 	  mutexes and rwsems.
 
+config LOCK_TORTURE_TEST
+	tristate "torture tests for locking"
+	depends on DEBUG_KERNEL
+	select TORTURE_TEST
+	default n
+	help
+	  This option provides a kernel module that runs torture tests
+	  on kernel locking primitives.  The kernel module may be built
+	  after the fact on the running kernel to be tested, if desired.
+
+	  Say Y here if you want kernel locking-primitive torture tests
+	  to be built into the kernel.
+	  Say M if you want these torture tests to build as a module.
+	  Say N if you are unsure.
+
 endmenu # lock debugging
 
 config TRACE_IRQFLAGS
@@ -1141,9 +1156,14 @@
 
 	 Say N if you are unsure.
 
+config TORTURE_TEST
+	tristate
+	default n
+
 config RCU_TORTURE_TEST
 	tristate "torture tests for RCU"
 	depends on DEBUG_KERNEL
+	select TORTURE_TEST
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
diff --git a/lib/Makefile b/lib/Makefile
index 126b34f..48140e3 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -45,6 +45,7 @@
 obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
 obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
 
+GCOV_PROFILE_hweight.o := n
 CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 2defd13..98f2d7e 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -424,111 +424,134 @@
 EXPORT_SYMBOL(debug_dma_dump_mappings);
 
 /*
- * For each page mapped (initial page in the case of
- * dma_alloc_coherent/dma_map_{single|page}, or each page in a
- * scatterlist) insert into this tree using the pfn as the key. At
+ * For each mapping (initial cacheline in the case of
+ * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a
+ * scatterlist, or the cacheline specified in dma_map_single) insert
+ * into this tree using the cacheline as the key. At
  * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry.  If
- * the pfn already exists at insertion time add a tag as a reference
+ * the entry already exists at insertion time add a tag as a reference
  * count for the overlapping mappings.  For now, the overlap tracking
- * just ensures that 'unmaps' balance 'maps' before marking the pfn
- * idle, but we should also be flagging overlaps as an API violation.
+ * just ensures that 'unmaps' balance 'maps' before marking the
+ * cacheline idle, but we should also be flagging overlaps as an API
+ * violation.
  *
  * Memory usage is mostly constrained by the maximum number of available
  * dma-debug entries in that we need a free dma_debug_entry before
- * inserting into the tree.  In the case of dma_map_{single|page} and
- * dma_alloc_coherent there is only one dma_debug_entry and one pfn to
- * track per event.  dma_map_sg(), on the other hand,
- * consumes a single dma_debug_entry, but inserts 'nents' entries into
- * the tree.
+ * inserting into the tree.  In the case of dma_map_page and
+ * dma_alloc_coherent there is only one dma_debug_entry and one
+ * dma_active_cacheline entry to track per event.  dma_map_sg(), on the
+ * other hand, consumes a single dma_debug_entry, but inserts 'nents'
+ * entries into the tree.
  *
  * At any time debug_dma_assert_idle() can be called to trigger a
- * warning if the given page is in the active set.
+ * warning if any cachelines in the given page are in the active set.
  */
-static RADIX_TREE(dma_active_pfn, GFP_NOWAIT);
+static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
 static DEFINE_SPINLOCK(radix_lock);
-#define ACTIVE_PFN_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
+#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT)
 
-static int active_pfn_read_overlap(unsigned long pfn)
+static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry)
+{
+	return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) +
+		(entry->offset >> L1_CACHE_SHIFT);
+}
+
+static int active_cacheline_read_overlap(phys_addr_t cln)
 {
 	int overlap = 0, i;
 
 	for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
-		if (radix_tree_tag_get(&dma_active_pfn, pfn, i))
+		if (radix_tree_tag_get(&dma_active_cacheline, cln, i))
 			overlap |= 1 << i;
 	return overlap;
 }
 
-static int active_pfn_set_overlap(unsigned long pfn, int overlap)
+static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
 {
 	int i;
 
-	if (overlap > ACTIVE_PFN_MAX_OVERLAP || overlap < 0)
+	if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0)
 		return overlap;
 
 	for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
 		if (overlap & 1 << i)
-			radix_tree_tag_set(&dma_active_pfn, pfn, i);
+			radix_tree_tag_set(&dma_active_cacheline, cln, i);
 		else
-			radix_tree_tag_clear(&dma_active_pfn, pfn, i);
+			radix_tree_tag_clear(&dma_active_cacheline, cln, i);
 
 	return overlap;
 }
 
-static void active_pfn_inc_overlap(unsigned long pfn)
+static void active_cacheline_inc_overlap(phys_addr_t cln)
 {
-	int overlap = active_pfn_read_overlap(pfn);
+	int overlap = active_cacheline_read_overlap(cln);
 
-	overlap = active_pfn_set_overlap(pfn, ++overlap);
+	overlap = active_cacheline_set_overlap(cln, ++overlap);
 
 	/* If we overflowed the overlap counter then we're potentially
 	 * leaking dma-mappings.  Otherwise, if maps and unmaps are
 	 * balanced then this overflow may cause false negatives in
-	 * debug_dma_assert_idle() as the pfn may be marked idle
+	 * debug_dma_assert_idle() as the cacheline may be marked idle
 	 * prematurely.
 	 */
-	WARN_ONCE(overlap > ACTIVE_PFN_MAX_OVERLAP,
-		  "DMA-API: exceeded %d overlapping mappings of pfn %lx\n",
-		  ACTIVE_PFN_MAX_OVERLAP, pfn);
+	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
+		  "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n",
+		  ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
 }
 
-static int active_pfn_dec_overlap(unsigned long pfn)
+static int active_cacheline_dec_overlap(phys_addr_t cln)
 {
-	int overlap = active_pfn_read_overlap(pfn);
+	int overlap = active_cacheline_read_overlap(cln);
 
-	return active_pfn_set_overlap(pfn, --overlap);
+	return active_cacheline_set_overlap(cln, --overlap);
 }
 
-static int active_pfn_insert(struct dma_debug_entry *entry)
+static int active_cacheline_insert(struct dma_debug_entry *entry)
 {
+	phys_addr_t cln = to_cacheline_number(entry);
 	unsigned long flags;
 	int rc;
 
+	/* If the device is not writing memory then we don't have any
+	 * concerns about the cpu consuming stale data.  This mitigates
+	 * legitimate usages of overlapping mappings.
+	 */
+	if (entry->direction == DMA_TO_DEVICE)
+		return 0;
+
 	spin_lock_irqsave(&radix_lock, flags);
-	rc = radix_tree_insert(&dma_active_pfn, entry->pfn, entry);
+	rc = radix_tree_insert(&dma_active_cacheline, cln, entry);
 	if (rc == -EEXIST)
-		active_pfn_inc_overlap(entry->pfn);
+		active_cacheline_inc_overlap(cln);
 	spin_unlock_irqrestore(&radix_lock, flags);
 
 	return rc;
 }
 
-static void active_pfn_remove(struct dma_debug_entry *entry)
+static void active_cacheline_remove(struct dma_debug_entry *entry)
 {
+	phys_addr_t cln = to_cacheline_number(entry);
 	unsigned long flags;
 
+	/* ...mirror the insert case */
+	if (entry->direction == DMA_TO_DEVICE)
+		return;
+
 	spin_lock_irqsave(&radix_lock, flags);
 	/* since we are counting overlaps the final put of the
-	 * entry->pfn will occur when the overlap count is 0.
-	 * active_pfn_dec_overlap() returns -1 in that case
+	 * cacheline will occur when the overlap count is 0.
+	 * active_cacheline_dec_overlap() returns -1 in that case
 	 */
-	if (active_pfn_dec_overlap(entry->pfn) < 0)
-		radix_tree_delete(&dma_active_pfn, entry->pfn);
+	if (active_cacheline_dec_overlap(cln) < 0)
+		radix_tree_delete(&dma_active_cacheline, cln);
 	spin_unlock_irqrestore(&radix_lock, flags);
 }
 
 /**
  * debug_dma_assert_idle() - assert that a page is not undergoing dma
- * @page: page to lookup in the dma_active_pfn tree
+ * @page: page to lookup in the dma_active_cacheline tree
  *
  * Place a call to this routine in cases where the cpu touching the page
  * before the dma completes (page is dma_unmapped) will lead to data
@@ -536,22 +559,38 @@
  */
 void debug_dma_assert_idle(struct page *page)
 {
+	static struct dma_debug_entry *ents[CACHELINES_PER_PAGE];
+	struct dma_debug_entry *entry = NULL;
+	void **results = (void **) &ents;
+	unsigned int nents, i;
 	unsigned long flags;
-	struct dma_debug_entry *entry;
+	phys_addr_t cln;
 
 	if (!page)
 		return;
 
+	cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT;
 	spin_lock_irqsave(&radix_lock, flags);
-	entry = radix_tree_lookup(&dma_active_pfn, page_to_pfn(page));
+	nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln,
+				       CACHELINES_PER_PAGE);
+	for (i = 0; i < nents; i++) {
+		phys_addr_t ent_cln = to_cacheline_number(ents[i]);
+
+		if (ent_cln == cln) {
+			entry = ents[i];
+			break;
+		} else if (ent_cln >= cln + CACHELINES_PER_PAGE)
+			break;
+	}
 	spin_unlock_irqrestore(&radix_lock, flags);
 
 	if (!entry)
 		return;
 
+	cln = to_cacheline_number(entry);
 	err_printk(entry->dev, entry,
-		   "DMA-API: cpu touching an active dma mapped page "
-		   "[pfn=0x%lx]\n", entry->pfn);
+		   "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n",
+		   &cln);
 }
 
 /*
@@ -568,9 +607,9 @@
 	hash_bucket_add(bucket, entry);
 	put_hash_bucket(bucket, &flags);
 
-	rc = active_pfn_insert(entry);
+	rc = active_cacheline_insert(entry);
 	if (rc == -ENOMEM) {
-		pr_err("DMA-API: pfn tracking ENOMEM, dma-debug disabled\n");
+		pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n");
 		global_disable = true;
 	}
 
@@ -631,7 +670,7 @@
 {
 	unsigned long flags;
 
-	active_pfn_remove(entry);
+	active_cacheline_remove(entry);
 
 	/*
 	 * add to beginning of the list - this way the entries are
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 7be235f..93d145e 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -54,9 +54,7 @@
 /*
  * Try to steal tags from a remote cpu's percpu freelist.
  *
- * We first check how many percpu freelists have tags - we don't steal tags
- * unless enough percpu freelists have tags on them that it's possible more than
- * half the total tags could be stuck on remote percpu freelists.
+ * We first check how many percpu freelists have tags
  *
  * Then we iterate through the cpus until we find some tags - we don't attempt
  * to find the "best" cpu to steal from, to keep cacheline bouncing to a
@@ -69,8 +67,7 @@
 	struct percpu_ida_cpu *remote;
 
 	for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags);
-	     cpus_have_tags * pool->percpu_max_size > pool->nr_tags / 2;
-	     cpus_have_tags--) {
+	     cpus_have_tags; cpus_have_tags--) {
 		cpu = cpumask_next(cpu, &pool->cpus_have_tags);
 
 		if (cpu >= nr_cpu_ids) {
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 7811ed3..bd4a8df 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1253,8 +1253,10 @@
 
 		node = indirect_to_ptr(node);
 		max_index = radix_tree_maxindex(node->height);
-		if (cur_index > max_index)
+		if (cur_index > max_index) {
+			rcu_read_unlock();
 			break;
+		}
 
 		cur_index = __locate(node, item, cur_index, &found_index);
 		rcu_read_unlock();
diff --git a/lib/random32.c b/lib/random32.c
index 1e5b2df..6148967 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -244,8 +244,19 @@
 	static bool latch = false;
 	static DEFINE_SPINLOCK(lock);
 
+	/* Asking for random bytes might result in bytes getting
+	 * moved into the nonblocking pool and thus marking it
+	 * as initialized. In this case we would double back into
+	 * this function and attempt to do a late reseed.
+	 * Ignore the pointless attempt to reseed again if we're
+	 * already waiting for bytes when the nonblocking pool
+	 * got initialized.
+	 */
+
 	/* only allow initial seeding (late == false) once */
-	spin_lock_irqsave(&lock, flags);
+	if (!spin_trylock_irqsave(&lock, flags))
+		return;
+
 	if (latch && !late)
 		goto out;
 	latch = true;
diff --git a/lib/string.c b/lib/string.c
index e5878de..9b1f906 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -648,7 +648,7 @@
  * @count: The size of the area.
  */
 #undef memcmp
-int memcmp(const void *cs, const void *ct, size_t count)
+__visible int memcmp(const void *cs, const void *ct, size_t count)
 {
 	const unsigned char *su1, *su2;
 	int res = 0;
diff --git a/mm/Kconfig b/mm/Kconfig
index 2d9f150..2888024 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -575,5 +575,5 @@
 	  then you should select this. This causes zsmalloc to use page table
 	  mapping rather than copying for object mapping.
 
-	  You can check speed with zsmalloc benchmark[1].
-	  [1] https://github.com/spartacus06/zsmalloc
+	  You can check speed with zsmalloc benchmark:
+	  https://github.com/spartacus06/zsmapbench
diff --git a/mm/compaction.c b/mm/compaction.c
index b48c525..9185775 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -251,7 +251,6 @@
 {
 	int nr_scanned = 0, total_isolated = 0;
 	struct page *cursor, *valid_page = NULL;
-	unsigned long nr_strict_required = end_pfn - blockpfn;
 	unsigned long flags;
 	bool locked = false;
 
@@ -264,11 +263,12 @@
 
 		nr_scanned++;
 		if (!pfn_valid_within(blockpfn))
-			continue;
+			goto isolate_fail;
+
 		if (!valid_page)
 			valid_page = page;
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/*
 		 * The zone lock must be held to isolate freepages.
@@ -289,12 +289,10 @@
 
 		/* Recheck this is a buddy page under lock */
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
-		if (!isolated && strict)
-			break;
 		total_isolated += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
@@ -305,7 +303,15 @@
 		if (isolated) {
 			blockpfn += isolated - 1;
 			cursor += isolated - 1;
+			continue;
 		}
+
+isolate_fail:
+		if (strict)
+			break;
+		else
+			continue;
+
 	}
 
 	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
@@ -315,7 +321,7 @@
 	 * pages requested were isolated. If there were any failures, 0 is
 	 * returned and CMA will fail.
 	 */
-	if (strict && nr_strict_required > total_isolated)
+	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
 	if (locked)
diff --git a/mm/filemap.c b/mm/filemap.c
index d56d3c1..7a13f6a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2553,8 +2553,8 @@
 	if (ret > 0) {
 		ssize_t err;
 
-		err = generic_write_sync(file, pos, ret);
-		if (err < 0 && ret > 0)
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+		if (err < 0)
 			ret = err;
 	}
 	return ret;
diff --git a/mm/fremap.c b/mm/fremap.c
index bbc4d66..34feba6 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -23,28 +23,44 @@
 
 #include "internal.h"
 
+static int mm_counter(struct page *page)
+{
+	return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES;
+}
+
 static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = *ptep;
+	struct page *page;
+	swp_entry_t entry;
 
 	if (pte_present(pte)) {
-		struct page *page;
-
 		flush_cache_page(vma, addr, pte_pfn(pte));
 		pte = ptep_clear_flush(vma, addr, ptep);
 		page = vm_normal_page(vma, addr, pte);
 		if (page) {
 			if (pte_dirty(pte))
 				set_page_dirty(page);
+			update_hiwater_rss(mm);
+			dec_mm_counter(mm, mm_counter(page));
 			page_remove_rmap(page);
 			page_cache_release(page);
-			update_hiwater_rss(mm);
-			dec_mm_counter(mm, MM_FILEPAGES);
 		}
-	} else {
-		if (!pte_file(pte))
-			free_swap_and_cache(pte_to_swp_entry(pte));
+	} else {	/* zap_pte() is not called when pte_none() */
+		if (!pte_file(pte)) {
+			update_hiwater_rss(mm);
+			entry = pte_to_swp_entry(pte);
+			if (non_swap_entry(entry)) {
+				if (is_migration_entry(entry)) {
+					page = migration_entry_to_page(entry);
+					dec_mm_counter(mm, mm_counter(page));
+				}
+			} else {
+				free_swap_and_cache(entry);
+				dec_mm_counter(mm, MM_SWAPENTS);
+			}
+		}
 		pte_clear_not_present_full(mm, addr, ptep, 0);
 	}
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 82166bf..1546655 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1166,8 +1166,10 @@
 		} else {
 			ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 					pmd, orig_pmd, page, haddr);
-			if (ret & VM_FAULT_OOM)
+			if (ret & VM_FAULT_OOM) {
 				split_huge_page(page);
+				ret |= VM_FAULT_FALLBACK;
+			}
 			put_page(page);
 		}
 		count_vm_event(THP_FAULT_FALLBACK);
@@ -1179,9 +1181,10 @@
 		if (page) {
 			split_huge_page(page);
 			put_page(page);
-		}
+		} else
+			split_huge_page_pmd(vma, address, pmd);
+		ret |= VM_FAULT_FALLBACK;
 		count_vm_event(THP_FAULT_FALLBACK);
-		ret |= VM_FAULT_OOM;
 		goto out;
 	}
 
@@ -1545,6 +1548,7 @@
 				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
 			ret = HPAGE_PMD_NR;
+			set_pmd_at(mm, addr, pmd, entry);
 			BUG_ON(pmd_write(entry));
 		} else {
 			struct page *page = pmd_page(*pmd);
@@ -1557,16 +1561,10 @@
 			 */
 			if (!is_huge_zero_page(page) &&
 			    !pmd_numa(*pmd)) {
-				entry = *pmd;
-				entry = pmd_mknuma(entry);
+				pmdp_set_numa(mm, addr, pmd);
 				ret = HPAGE_PMD_NR;
 			}
 		}
-
-		/* Set PMD if cleared earlier */
-		if (ret == HPAGE_PMD_NR)
-			set_pmd_at(mm, addr, pmd, entry);
-
 		spin_unlock(ptl);
 	}
 
@@ -1963,7 +1961,7 @@
 	return ret;
 }
 
-#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE)
+#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
 
 int hugepage_madvise(struct vm_area_struct *vma,
 		     unsigned long *vm_flags, int advice)
diff --git a/mm/ksm.c b/mm/ksm.c
index aa4c7c7..68710e8 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -444,7 +444,7 @@
 static struct page *page_trans_compound_anon(struct page *page)
 {
 	if (PageTransCompound(page)) {
-		struct page *head = compound_trans_head(page);
+		struct page *head = compound_head(page);
 		/*
 		 * head may actually be splitted and freed from under
 		 * us but it's ok here.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 53385cd..5b6b003 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1127,8 +1127,8 @@
 	 * skipping css reference should be safe.
 	 */
 	if (next_css) {
-		if ((next_css->flags & CSS_ONLINE) &&
-				(next_css == &root->css || css_tryget(next_css)))
+		if ((next_css == &root->css) ||
+		    ((next_css->flags & CSS_ONLINE) && css_tryget(next_css)))
 			return mem_cgroup_from_css(next_css);
 
 		prev_css = next_css;
@@ -1687,7 +1687,7 @@
 	 * protects memcg_name and makes sure that parallel ooms do not
 	 * interleave
 	 */
-	static DEFINE_SPINLOCK(oom_info_lock);
+	static DEFINE_MUTEX(oom_info_lock);
 	struct cgroup *task_cgrp;
 	struct cgroup *mem_cgrp;
 	static char memcg_name[PATH_MAX];
@@ -1698,7 +1698,7 @@
 	if (!p)
 		return;
 
-	spin_lock(&oom_info_lock);
+	mutex_lock(&oom_info_lock);
 	rcu_read_lock();
 
 	mem_cgrp = memcg->css.cgroup;
@@ -1767,7 +1767,7 @@
 
 		pr_cont("\n");
 	}
-	spin_unlock(&oom_info_lock);
+	mutex_unlock(&oom_info_lock);
 }
 
 /*
@@ -6595,6 +6595,7 @@
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_event *event, *tmp;
+	struct cgroup_subsys_state *iter;
 
 	/*
 	 * Unregister events and notify userspace.
@@ -6611,7 +6612,14 @@
 	kmem_cgroup_css_offline(memcg);
 
 	mem_cgroup_invalidate_reclaim_iterators(memcg);
-	mem_cgroup_reparent_charges(memcg);
+
+	/*
+	 * This requires that offlining is serialized.  Right now that is
+	 * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
+	 */
+	css_for_each_descendant_post(iter, css)
+		mem_cgroup_reparent_charges(mem_cgroup_from_css(iter));
+
 	mem_cgroup_destroy_all_caches(memcg);
 	vmpressure_cleanup(&memcg->vmpressure);
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4f08a2d..90002ea 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -945,8 +945,10 @@
 			 * to it. Similarly, page lock is shifted.
 			 */
 			if (hpage != p) {
-				put_page(hpage);
-				get_page(p);
+				if (!(flags & MF_COUNT_INCREASED)) {
+					put_page(hpage);
+					get_page(p);
+				}
 				lock_page(p);
 				unlock_page(hpage);
 				*hpagep = p;
@@ -1649,7 +1651,7 @@
 {
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
-	struct page *hpage = compound_trans_head(page);
+	struct page *hpage = compound_head(page);
 
 	if (PageHWPoison(page)) {
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
diff --git a/mm/memory.c b/mm/memory.c
index be6a0c0..22dfa61 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3348,6 +3348,7 @@
 		if (ret & VM_FAULT_LOCKED)
 			unlock_page(vmf.page);
 		ret = VM_FAULT_HWPOISON;
+		page_cache_release(vmf.page);
 		goto uncharge_out;
 	}
 
@@ -3703,7 +3704,6 @@
 	if (unlikely(is_vm_hugetlb_page(vma)))
 		return hugetlb_fault(mm, vma, address, flags);
 
-retry:
 	pgd = pgd_offset(mm, address);
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
@@ -3741,20 +3741,13 @@
 			if (dirty && !pmd_write(orig_pmd)) {
 				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
 							  orig_pmd);
-				/*
-				 * If COW results in an oom, the huge pmd will
-				 * have been split, so retry the fault on the
-				 * pte for a smaller charge.
-				 */
-				if (unlikely(ret & VM_FAULT_OOM))
-					goto retry;
-				return ret;
+				if (!(ret & VM_FAULT_FALLBACK))
+					return ret;
 			} else {
 				huge_pmd_set_accessed(mm, vma, address, pmd,
 						      orig_pmd, dirty);
+				return 0;
 			}
-
-			return 0;
 		}
 	}
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ae3c8f3..4755c85 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1556,10 +1556,10 @@
 
 #ifdef CONFIG_COMPAT
 
-asmlinkage long compat_sys_get_mempolicy(int __user *policy,
-				     compat_ulong_t __user *nmask,
-				     compat_ulong_t maxnode,
-				     compat_ulong_t addr, compat_ulong_t flags)
+COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
+		       compat_ulong_t __user *, nmask,
+		       compat_ulong_t, maxnode,
+		       compat_ulong_t, addr, compat_ulong_t, flags)
 {
 	long err;
 	unsigned long __user *nm = NULL;
@@ -1586,8 +1586,8 @@
 	return err;
 }
 
-asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
-				     compat_ulong_t maxnode)
+COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
+		       compat_ulong_t, maxnode)
 {
 	long err = 0;
 	unsigned long __user *nm = NULL;
@@ -1609,9 +1609,9 @@
 	return sys_set_mempolicy(mode, nm, nr_bits+1);
 }
 
-asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
-			     compat_ulong_t mode, compat_ulong_t __user *nmask,
-			     compat_ulong_t maxnode, compat_ulong_t flags)
+COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
+		       compat_ulong_t, mode, compat_ulong_t __user *, nmask,
+		       compat_ulong_t, maxnode, compat_ulong_t, flags)
 {
 	long err = 0;
 	unsigned long __user *nm = NULL;
@@ -2301,35 +2301,6 @@
 	kmem_cache_free(sn_cache, n);
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
-{
-	/* Never defer a private fault */
-	if (cpupid_match_pid(p, last_cpupid))
-		return false;
-
-	if (p->numa_migrate_deferred) {
-		p->numa_migrate_deferred--;
-		return true;
-	}
-	return false;
-}
-
-static inline void defer_numa_migrate(struct task_struct *p)
-{
-	p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred;
-}
-#else
-static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
-{
-	return false;
-}
-
-static inline void defer_numa_migrate(struct task_struct *p)
-{
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 /**
  * mpol_misplaced - check whether current page node is valid in policy
  *
@@ -2403,52 +2374,9 @@
 
 	/* Migrate the page towards the node whose CPU is referencing it */
 	if (pol->flags & MPOL_F_MORON) {
-		int last_cpupid;
-		int this_cpupid;
-
 		polnid = thisnid;
-		this_cpupid = cpu_pid_to_cpupid(thiscpu, current->pid);
 
-		/*
-		 * Multi-stage node selection is used in conjunction
-		 * with a periodic migration fault to build a temporal
-		 * task<->page relation. By using a two-stage filter we
-		 * remove short/unlikely relations.
-		 *
-		 * Using P(p) ~ n_p / n_t as per frequentist
-		 * probability, we can equate a task's usage of a
-		 * particular page (n_p) per total usage of this
-		 * page (n_t) (in a given time-span) to a probability.
-		 *
-		 * Our periodic faults will sample this probability and
-		 * getting the same result twice in a row, given these
-		 * samples are fully independent, is then given by
-		 * P(n)^2, provided our sample period is sufficiently
-		 * short compared to the usage pattern.
-		 *
-		 * This quadric squishes small probabilities, making
-		 * it less likely we act on an unlikely task<->page
-		 * relation.
-		 */
-		last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
-		if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) {
-
-			/* See sysctl_numa_balancing_migrate_deferred comment */
-			if (!cpupid_match_pid(current, last_cpupid))
-				defer_numa_migrate(current);
-
-			goto out;
-		}
-
-		/*
-		 * The quadratic filter above reduces extraneous migration
-		 * of shared pages somewhat. This code reduces it even more,
-		 * reducing the overhead of page migrations of shared pages.
-		 * This makes workloads with shared pages rely more on
-		 * "move task near its memory", and less on "move memory
-		 * towards its task", which is exactly what we want.
-		 */
-		if (numa_migrate_deferred(current, last_cpupid))
+		if (!should_numa_migrate_memory(current, page, curnid, thiscpu))
 			goto out;
 	}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 482a33d..bed4880 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -178,6 +178,37 @@
 }
 
 /*
+ * Congratulations to trinity for discovering this bug.
+ * mm/fremap.c's remap_file_pages() accepts any range within a single vma to
+ * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then
+ * replace the specified range by file ptes throughout (maybe populated after).
+ * If page migration finds a page within that range, while it's still located
+ * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem:
+ * zap_pte() clears the temporary migration entry before mmap_sem is dropped.
+ * But if the migrating page is in a part of the vma outside the range to be
+ * remapped, then it will not be cleared, and remove_migration_ptes() needs to
+ * deal with it.  Fortunately, this part of the vma is of course still linear,
+ * so we just need to use linear location on the nonlinear list.
+ */
+static int remove_linear_migration_ptes_from_nonlinear(struct page *page,
+		struct address_space *mapping, void *arg)
+{
+	struct vm_area_struct *vma;
+	/* hugetlbfs does not support remap_pages, so no huge pgoff worries */
+	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	unsigned long addr;
+
+	list_for_each_entry(vma,
+		&mapping->i_mmap_nonlinear, shared.nonlinear) {
+
+		addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+		if (addr >= vma->vm_start && addr < vma->vm_end)
+			remove_migration_pte(page, vma, addr, arg);
+	}
+	return SWAP_AGAIN;
+}
+
+/*
  * Get rid of all migration entries and replace them by
  * references to the indicated page.
  */
@@ -186,6 +217,7 @@
 	struct rmap_walk_control rwc = {
 		.rmap_one = remove_migration_pte,
 		.arg = old,
+		.file_nonlinear = remove_linear_migration_ptes_from_nonlinear,
 	};
 
 	rmap_walk(new, &rwc);
@@ -1158,7 +1190,7 @@
 					pm->node);
 	else
 		return alloc_pages_exact_node(pm->node,
-				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
+				GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0);
 }
 
 /*
@@ -1544,9 +1576,9 @@
 	struct page *newpage;
 
 	newpage = alloc_pages_exact_node(nid,
-					 (GFP_HIGHUSER_MOVABLE | GFP_THISNODE |
-					  __GFP_NOMEMALLOC | __GFP_NORETRY |
-					  __GFP_NOWARN) &
+					 (GFP_HIGHUSER_MOVABLE |
+					  __GFP_THISNODE | __GFP_NOMEMALLOC |
+					  __GFP_NORETRY | __GFP_NOWARN) &
 					 ~GFP_IOFS, 0);
 
 	return newpage;
@@ -1747,7 +1779,8 @@
 		goto out_dropref;
 
 	new_page = alloc_pages_node(node,
-		(GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
+		(GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT,
+		HPAGE_PMD_ORDER);
 	if (!new_page)
 		goto out_fail;
 
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index 8a8cd02..f802c2d 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -31,6 +31,9 @@
 	tsk->mm = mm;
 	switch_mm(active_mm, mm, tsk);
 	task_unlock(tsk);
+#ifdef finish_arch_post_lock_switch
+	finish_arch_post_lock_switch();
+#endif
 
 	if (active_mm != mm)
 		mmdrop(active_mm);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 7332c17..769a67a 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -58,36 +58,27 @@
 				if (pte_numa(ptent))
 					ptent = pte_mknonnuma(ptent);
 				ptent = pte_modify(ptent, newprot);
+				/*
+				 * Avoid taking write faults for pages we
+				 * know to be dirty.
+				 */
+				if (dirty_accountable && pte_dirty(ptent))
+					ptent = pte_mkwrite(ptent);
+				ptep_modify_prot_commit(mm, addr, pte, ptent);
 				updated = true;
 			} else {
 				struct page *page;
 
-				ptent = *pte;
 				page = vm_normal_page(vma, addr, oldpte);
 				if (page && !PageKsm(page)) {
 					if (!pte_numa(oldpte)) {
-						ptent = pte_mknuma(ptent);
-						set_pte_at(mm, addr, pte, ptent);
+						ptep_set_numa(mm, addr, pte);
 						updated = true;
 					}
 				}
 			}
-
-			/*
-			 * Avoid taking write faults for pages we know to be
-			 * dirty.
-			 */
-			if (dirty_accountable && pte_dirty(ptent)) {
-				ptent = pte_mkwrite(ptent);
-				updated = true;
-			}
-
 			if (updated)
 				pages++;
-
-			/* Only !prot_numa always clears the pte */
-			if (!prot_numa)
-				ptep_modify_prot_commit(mm, addr, pte, ptent);
 		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 2d30e2c..7106cb1 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2173,11 +2173,12 @@
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
 		struct address_space *mapping2;
+		unsigned long flags;
 
 		if (!mapping)
 			return 1;
 
-		spin_lock_irq(&mapping->tree_lock);
+		spin_lock_irqsave(&mapping->tree_lock, flags);
 		mapping2 = page_mapping(page);
 		if (mapping2) { /* Race with truncate? */
 			BUG_ON(mapping2 != mapping);
@@ -2186,7 +2187,7 @@
 			radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 		}
-		spin_unlock_irq(&mapping->tree_lock);
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		if (mapping->host) {
 			/* !PageAnon && !swapper_space */
 			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e3758a0..3bac76a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -369,9 +369,11 @@
 	__SetPageHead(page);
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
-		__SetPageTail(p);
 		set_page_count(p, 0);
 		p->first_page = page;
+		/* Make sure p->first_page is always valid for PageTail() */
+		smp_wmb();
+		__SetPageTail(p);
 	}
 }
 
@@ -1236,6 +1238,15 @@
 	}
 	local_irq_restore(flags);
 }
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+	return (gfp_mask & GFP_THISNODE) == GFP_THISNODE;
+}
+#else
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+	return false;
+}
 #endif
 
 /*
@@ -1572,7 +1583,13 @@
 					  get_pageblock_migratetype(page));
 	}
 
-	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+	/*
+	 * NOTE: GFP_THISNODE allocations do not partake in the kswapd
+	 * aging protocol, so they can't be fair.
+	 */
+	if (!gfp_thisnode_allocation(gfp_flags))
+		__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
 	local_irq_restore(flags);
@@ -1944,8 +1961,12 @@
 		 * ultimately fall back to remote zones that do not
 		 * partake in the fairness round-robin cycle of this
 		 * zonelist.
+		 *
+		 * NOTE: GFP_THISNODE allocations do not partake in
+		 * the kswapd aging protocol, so they can't be fair.
 		 */
-		if (alloc_flags & ALLOC_WMARK_LOW) {
+		if ((alloc_flags & ALLOC_WMARK_LOW) &&
+		    !gfp_thisnode_allocation(gfp_mask)) {
 			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
 				continue;
 			if (!zone_local(preferred_zone, zone))
@@ -2501,8 +2522,7 @@
 	 * allowed per node queues are empty and that nodes are
 	 * over allocated.
 	 */
-	if (IS_ENABLED(CONFIG_NUMA) &&
-			(gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+	if (gfp_thisnode_allocation(gfp_mask))
 		goto nopage;
 
 restart:
diff --git a/mm/percpu.c b/mm/percpu.c
index 036cfe0..63e24fb 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -102,10 +102,11 @@
 	int			free_size;	/* free bytes in the chunk */
 	int			contig_hint;	/* max contiguous size hint */
 	void			*base_addr;	/* base address of this chunk */
-	int			map_used;	/* # of map entries used */
+	int			map_used;	/* # of map entries used before the sentry */
 	int			map_alloc;	/* # of map entries allocated */
 	int			*map;		/* allocation map */
 	void			*data;		/* chunk data */
+	int			first_free;	/* no free below this */
 	bool			immutable;	/* no [de]population allowed */
 	unsigned long		populated[];	/* populated bitmap */
 };
@@ -356,11 +357,11 @@
 {
 	int new_alloc;
 
-	if (chunk->map_alloc >= chunk->map_used + 2)
+	if (chunk->map_alloc >= chunk->map_used + 3)
 		return 0;
 
 	new_alloc = PCPU_DFL_MAP_ALLOC;
-	while (new_alloc < chunk->map_used + 2)
+	while (new_alloc < chunk->map_used + 3)
 		new_alloc *= 2;
 
 	return new_alloc;
@@ -418,48 +419,6 @@
 }
 
 /**
- * pcpu_split_block - split a map block
- * @chunk: chunk of interest
- * @i: index of map block to split
- * @head: head size in bytes (can be 0)
- * @tail: tail size in bytes (can be 0)
- *
- * Split the @i'th map block into two or three blocks.  If @head is
- * non-zero, @head bytes block is inserted before block @i moving it
- * to @i+1 and reducing its size by @head bytes.
- *
- * If @tail is non-zero, the target block, which can be @i or @i+1
- * depending on @head, is reduced by @tail bytes and @tail byte block
- * is inserted after the target block.
- *
- * @chunk->map must have enough free slots to accommodate the split.
- *
- * CONTEXT:
- * pcpu_lock.
- */
-static void pcpu_split_block(struct pcpu_chunk *chunk, int i,
-			     int head, int tail)
-{
-	int nr_extra = !!head + !!tail;
-
-	BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra);
-
-	/* insert new subblocks */
-	memmove(&chunk->map[i + nr_extra], &chunk->map[i],
-		sizeof(chunk->map[0]) * (chunk->map_used - i));
-	chunk->map_used += nr_extra;
-
-	if (head) {
-		chunk->map[i + 1] = chunk->map[i] - head;
-		chunk->map[i++] = head;
-	}
-	if (tail) {
-		chunk->map[i++] -= tail;
-		chunk->map[i] = tail;
-	}
-}
-
-/**
  * pcpu_alloc_area - allocate area from a pcpu_chunk
  * @chunk: chunk of interest
  * @size: wanted size in bytes
@@ -483,19 +442,27 @@
 	int oslot = pcpu_chunk_slot(chunk);
 	int max_contig = 0;
 	int i, off;
+	bool seen_free = false;
+	int *p;
 
-	for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) {
-		bool is_last = i + 1 == chunk->map_used;
+	for (i = chunk->first_free, p = chunk->map + i; i < chunk->map_used; i++, p++) {
 		int head, tail;
+		int this_size;
+
+		off = *p;
+		if (off & 1)
+			continue;
 
 		/* extra for alignment requirement */
 		head = ALIGN(off, align) - off;
-		BUG_ON(i == 0 && head != 0);
 
-		if (chunk->map[i] < 0)
-			continue;
-		if (chunk->map[i] < head + size) {
-			max_contig = max(chunk->map[i], max_contig);
+		this_size = (p[1] & ~1) - off;
+		if (this_size < head + size) {
+			if (!seen_free) {
+				chunk->first_free = i;
+				seen_free = true;
+			}
+			max_contig = max(this_size, max_contig);
 			continue;
 		}
 
@@ -505,44 +472,59 @@
 		 * than sizeof(int), which is very small but isn't too
 		 * uncommon for percpu allocations.
 		 */
-		if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) {
-			if (chunk->map[i - 1] > 0)
-				chunk->map[i - 1] += head;
-			else {
-				chunk->map[i - 1] -= head;
+		if (head && (head < sizeof(int) || !(p[-1] & 1))) {
+			*p = off += head;
+			if (p[-1] & 1)
 				chunk->free_size -= head;
-			}
-			chunk->map[i] -= head;
-			off += head;
+			else
+				max_contig = max(*p - p[-1], max_contig);
+			this_size -= head;
 			head = 0;
 		}
 
 		/* if tail is small, just keep it around */
-		tail = chunk->map[i] - head - size;
-		if (tail < sizeof(int))
+		tail = this_size - head - size;
+		if (tail < sizeof(int)) {
 			tail = 0;
+			size = this_size - head;
+		}
 
 		/* split if warranted */
 		if (head || tail) {
-			pcpu_split_block(chunk, i, head, tail);
+			int nr_extra = !!head + !!tail;
+
+			/* insert new subblocks */
+			memmove(p + nr_extra + 1, p + 1,
+				sizeof(chunk->map[0]) * (chunk->map_used - i));
+			chunk->map_used += nr_extra;
+
 			if (head) {
-				i++;
-				off += head;
-				max_contig = max(chunk->map[i - 1], max_contig);
+				if (!seen_free) {
+					chunk->first_free = i;
+					seen_free = true;
+				}
+				*++p = off += head;
+				++i;
+				max_contig = max(head, max_contig);
 			}
-			if (tail)
-				max_contig = max(chunk->map[i + 1], max_contig);
+			if (tail) {
+				p[1] = off + size;
+				max_contig = max(tail, max_contig);
+			}
 		}
 
+		if (!seen_free)
+			chunk->first_free = i + 1;
+
 		/* update hint and mark allocated */
-		if (is_last)
+		if (i + 1 == chunk->map_used)
 			chunk->contig_hint = max_contig; /* fully scanned */
 		else
 			chunk->contig_hint = max(chunk->contig_hint,
 						 max_contig);
 
-		chunk->free_size -= chunk->map[i];
-		chunk->map[i] = -chunk->map[i];
+		chunk->free_size -= size;
+		*p |= 1;
 
 		pcpu_chunk_relocate(chunk, oslot);
 		return off;
@@ -570,34 +552,50 @@
 static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
 {
 	int oslot = pcpu_chunk_slot(chunk);
-	int i, off;
+	int off = 0;
+	unsigned i, j;
+	int to_free = 0;
+	int *p;
 
-	for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++]))
-		if (off == freeme)
-			break;
+	freeme |= 1;	/* we are searching for <given offset, in use> pair */
+
+	i = 0;
+	j = chunk->map_used;
+	while (i != j) {
+		unsigned k = (i + j) / 2;
+		off = chunk->map[k];
+		if (off < freeme)
+			i = k + 1;
+		else if (off > freeme)
+			j = k;
+		else
+			i = j = k;
+	}
 	BUG_ON(off != freeme);
-	BUG_ON(chunk->map[i] > 0);
 
-	chunk->map[i] = -chunk->map[i];
-	chunk->free_size += chunk->map[i];
+	if (i < chunk->first_free)
+		chunk->first_free = i;
 
-	/* merge with previous? */
-	if (i > 0 && chunk->map[i - 1] >= 0) {
-		chunk->map[i - 1] += chunk->map[i];
-		chunk->map_used--;
-		memmove(&chunk->map[i], &chunk->map[i + 1],
-			(chunk->map_used - i) * sizeof(chunk->map[0]));
-		i--;
-	}
+	p = chunk->map + i;
+	*p = off &= ~1;
+	chunk->free_size += (p[1] & ~1) - off;
+
 	/* merge with next? */
-	if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) {
-		chunk->map[i] += chunk->map[i + 1];
-		chunk->map_used--;
-		memmove(&chunk->map[i + 1], &chunk->map[i + 2],
-			(chunk->map_used - (i + 1)) * sizeof(chunk->map[0]));
+	if (!(p[1] & 1))
+		to_free++;
+	/* merge with previous? */
+	if (i > 0 && !(p[-1] & 1)) {
+		to_free++;
+		i--;
+		p--;
+	}
+	if (to_free) {
+		chunk->map_used -= to_free;
+		memmove(p + 1, p + 1 + to_free,
+			(chunk->map_used - i) * sizeof(chunk->map[0]));
 	}
 
-	chunk->contig_hint = max(chunk->map[i], chunk->contig_hint);
+	chunk->contig_hint = max(chunk->map[i + 1] - chunk->map[i] - 1, chunk->contig_hint);
 	pcpu_chunk_relocate(chunk, oslot);
 }
 
@@ -617,7 +615,9 @@
 	}
 
 	chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
-	chunk->map[chunk->map_used++] = pcpu_unit_size;
+	chunk->map[0] = 0;
+	chunk->map[1] = pcpu_unit_size | 1;
+	chunk->map_used = 1;
 
 	INIT_LIST_HEAD(&chunk->list);
 	chunk->free_size = pcpu_unit_size;
@@ -713,6 +713,16 @@
 	unsigned long flags;
 	void __percpu *ptr;
 
+	/*
+	 * We want the lowest bit of offset available for in-use/free
+	 * indicator, so force >= 16bit alignment and make size even.
+	 */
+	if (unlikely(align < 2))
+		align = 2;
+
+	if (unlikely(size & 1))
+		size++;
+
 	if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
 		WARN(true, "illegal size (%zu) or align (%zu) for "
 		     "percpu allocation\n", size, align);
@@ -1343,9 +1353,13 @@
 	}
 	schunk->contig_hint = schunk->free_size;
 
-	schunk->map[schunk->map_used++] = -ai->static_size;
+	schunk->map[0] = 1;
+	schunk->map[1] = ai->static_size;
+	schunk->map_used = 1;
 	if (schunk->free_size)
-		schunk->map[schunk->map_used++] = schunk->free_size;
+		schunk->map[++schunk->map_used] = 1 | (ai->static_size + schunk->free_size);
+	else
+		schunk->map[1] |= 1;
 
 	/* init dynamic chunk if necessary */
 	if (dyn_size) {
@@ -1358,8 +1372,10 @@
 		bitmap_fill(dchunk->populated, pcpu_unit_pages);
 
 		dchunk->contig_hint = dchunk->free_size = dyn_size;
-		dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit;
-		dchunk->map[dchunk->map_used++] = dchunk->free_size;
+		dchunk->map[0] = 1;
+		dchunk->map[1] = pcpu_reserved_chunk_limit;
+		dchunk->map[2] = (pcpu_reserved_chunk_limit + dchunk->free_size) | 1;
+		dchunk->map_used = 2;
 	}
 
 	/* link the first chunk in */
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index fd26d04..3c5cf68 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -456,25 +456,23 @@
 	return rc;
 }
 
-asmlinkage ssize_t
-compat_sys_process_vm_readv(compat_pid_t pid,
-			    const struct compat_iovec __user *lvec,
-			    unsigned long liovcnt,
-			    const struct compat_iovec __user *rvec,
-			    unsigned long riovcnt,
-			    unsigned long flags)
+COMPAT_SYSCALL_DEFINE6(process_vm_readv, compat_pid_t, pid,
+		       const struct compat_iovec __user *, lvec,
+		       compat_ulong_t, liovcnt,
+		       const struct compat_iovec __user *, rvec,
+		       compat_ulong_t, riovcnt,
+		       compat_ulong_t, flags)
 {
 	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
 				    riovcnt, flags, 0);
 }
 
-asmlinkage ssize_t
-compat_sys_process_vm_writev(compat_pid_t pid,
-			     const struct compat_iovec __user *lvec,
-			     unsigned long liovcnt,
-			     const struct compat_iovec __user *rvec,
-			     unsigned long riovcnt,
-			     unsigned long flags)
+COMPAT_SYSCALL_DEFINE6(process_vm_writev, compat_pid_t, pid,
+		       const struct compat_iovec __user *, lvec,
+		       compat_ulong_t, liovcnt,
+		       const struct compat_iovec __user *, rvec,
+		       compat_ulong_t, riovcnt,
+		       compat_ulong_t, flags)
 {
 	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
 				    riovcnt, flags, 1);
diff --git a/mm/rmap.c b/mm/rmap.c
index d9d4231..11cf322 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1165,6 +1165,16 @@
 		}
 		set_pte_at(mm, address, pte,
 			   swp_entry_to_pte(make_hwpoison_entry(page)));
+	} else if (pte_unused(pteval)) {
+		/*
+		 * The guest indicated that the page content is of no
+		 * interest anymore. Simply discard the pte, vmscan
+		 * will take care of the rest.
+		 */
+		if (PageAnon(page))
+			dec_mm_counter(mm, MM_ANONPAGES);
+		else
+			dec_mm_counter(mm, MM_FILEPAGES);
 	} else if (PageAnon(page)) {
 		swp_entry_t entry = { .val = page_private(page) };
 		pte_t swp_pte;
@@ -1360,8 +1370,9 @@
 }
 
 static int try_to_unmap_nonlinear(struct page *page,
-		struct address_space *mapping, struct vm_area_struct *vma)
+		struct address_space *mapping, void *arg)
 {
+	struct vm_area_struct *vma;
 	int ret = SWAP_AGAIN;
 	unsigned long cursor;
 	unsigned long max_nl_cursor = 0;
@@ -1663,7 +1674,7 @@
 	if (list_empty(&mapping->i_mmap_nonlinear))
 		goto done;
 
-	ret = rwc->file_nonlinear(page, mapping, vma);
+	ret = rwc->file_nonlinear(page, mapping, rwc->arg);
 
 done:
 	mutex_unlock(&mapping->i_mmap_mutex);
diff --git a/mm/slab.c b/mm/slab.c
index eb043bf..b264214 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1946,7 +1946,7 @@
 /**
  * slab_destroy - destroy and release all objects in a slab
  * @cachep: cache pointer being destroyed
- * @slabp: slab pointer being destroyed
+ * @page: page pointer being destroyed
  *
  * Destroy all the objs in a slab, and release the mem back to the system.
  * Before calling the slab must have been unlinked from the cache.  The
diff --git a/mm/slub.c b/mm/slub.c
index 2b1a697..25f14ad 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1000,8 +1000,6 @@
 
 /*
  * Tracking of fully allocated slabs for debugging purposes.
- *
- * list_lock must be held.
  */
 static void add_full(struct kmem_cache *s,
 	struct kmem_cache_node *n, struct page *page)
@@ -1009,17 +1007,16 @@
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
+	lockdep_assert_held(&n->list_lock);
 	list_add(&page->lru, &n->full);
 }
 
-/*
- * list_lock must be held.
- */
-static void remove_full(struct kmem_cache *s, struct page *page)
+static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page)
 {
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
+	lockdep_assert_held(&n->list_lock);
 	list_del(&page->lru);
 }
 
@@ -1265,7 +1262,8 @@
 			void *object, u8 val) { return 1; }
 static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct page *page) {}
-static inline void remove_full(struct kmem_cache *s, struct page *page) {}
+static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
+					struct page *page) {}
 static inline unsigned long kmem_cache_flags(unsigned long object_size,
 	unsigned long flags, const char *name,
 	void (*ctor)(void *))
@@ -1519,11 +1517,9 @@
 
 /*
  * Management of partially allocated slabs.
- *
- * list_lock must be held.
  */
-static inline void add_partial(struct kmem_cache_node *n,
-				struct page *page, int tail)
+static inline void
+__add_partial(struct kmem_cache_node *n, struct page *page, int tail)
 {
 	n->nr_partial++;
 	if (tail == DEACTIVATE_TO_TAIL)
@@ -1532,23 +1528,32 @@
 		list_add(&page->lru, &n->partial);
 }
 
-/*
- * list_lock must be held.
- */
-static inline void remove_partial(struct kmem_cache_node *n,
-					struct page *page)
+static inline void add_partial(struct kmem_cache_node *n,
+				struct page *page, int tail)
+{
+	lockdep_assert_held(&n->list_lock);
+	__add_partial(n, page, tail);
+}
+
+static inline void
+__remove_partial(struct kmem_cache_node *n, struct page *page)
 {
 	list_del(&page->lru);
 	n->nr_partial--;
 }
 
+static inline void remove_partial(struct kmem_cache_node *n,
+					struct page *page)
+{
+	lockdep_assert_held(&n->list_lock);
+	__remove_partial(n, page);
+}
+
 /*
  * Remove slab from the partial list, freeze it and
  * return the pointer to the freelist.
  *
  * Returns a list of objects or NULL if it fails.
- *
- * Must hold list_lock since we modify the partial list.
  */
 static inline void *acquire_slab(struct kmem_cache *s,
 		struct kmem_cache_node *n, struct page *page,
@@ -1558,6 +1563,8 @@
 	unsigned long counters;
 	struct page new;
 
+	lockdep_assert_held(&n->list_lock);
+
 	/*
 	 * Zap the freelist and set the frozen bit.
 	 * The old freelist is the list of objects for the
@@ -1902,7 +1909,7 @@
 
 		else if (l == M_FULL)
 
-			remove_full(s, page);
+			remove_full(s, n, page);
 
 		if (m == M_PARTIAL) {
 
@@ -2556,7 +2563,7 @@
 		new.inuse--;
 		if ((!new.inuse || !prior) && !was_frozen) {
 
-			if (kmem_cache_has_cpu_partial(s) && !prior)
+			if (kmem_cache_has_cpu_partial(s) && !prior) {
 
 				/*
 				 * Slab was on no list before and will be
@@ -2566,7 +2573,7 @@
 				 */
 				new.frozen = 1;
 
-			else { /* Needs to be taken off a list */
+			} else { /* Needs to be taken off a list */
 
 	                        n = get_node(s, page_to_nid(page));
 				/*
@@ -2615,7 +2622,7 @@
 	 */
 	if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) {
 		if (kmem_cache_debug(s))
-			remove_full(s, page);
+			remove_full(s, n, page);
 		add_partial(n, page, DEACTIVATE_TO_TAIL);
 		stat(s, FREE_ADD_PARTIAL);
 	}
@@ -2629,9 +2636,10 @@
 		 */
 		remove_partial(n, page);
 		stat(s, FREE_REMOVE_PARTIAL);
-	} else
+	} else {
 		/* Slab must be on the full list */
-		remove_full(s, page);
+		remove_full(s, n, page);
+	}
 
 	spin_unlock_irqrestore(&n->list_lock, flags);
 	stat(s, FREE_SLAB);
@@ -2905,7 +2913,11 @@
 	init_kmem_cache_node(n);
 	inc_slabs_node(kmem_cache_node, node, page->objects);
 
-	add_partial(n, page, DEACTIVATE_TO_HEAD);
+	/*
+	 * No locks need to be taken here as it has just been
+	 * initialized and there is no concurrent access.
+	 */
+	__add_partial(n, page, DEACTIVATE_TO_HEAD);
 }
 
 static void free_kmem_cache_nodes(struct kmem_cache *s)
@@ -3191,7 +3203,7 @@
 
 	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
-			remove_partial(n, page);
+			__remove_partial(n, page);
 			discard_slab(s, page);
 		} else {
 			list_slab_objects(s, page,
@@ -4314,7 +4326,13 @@
 
 			page = ACCESS_ONCE(c->partial);
 			if (page) {
-				x = page->pobjects;
+				node = page_to_nid(page);
+				if (flags & SO_TOTAL)
+					WARN_ON_ONCE(1);
+				else if (flags & SO_OBJECTS)
+					WARN_ON_ONCE(1);
+				else
+					x = page->pages;
 				total += x;
 				nodes[node] += x;
 			}
@@ -5178,7 +5196,7 @@
 	}
 
 	s->kobj.kset = slab_kset;
-	err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, name);
+	err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
 	if (err) {
 		kobject_put(&s->kobj);
 		return err;
diff --git a/mm/swap.c b/mm/swap.c
index b31ba67..0092097 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -98,7 +98,7 @@
 	}
 
 	/* __split_huge_page_refcount can run under us */
-	page_head = compound_trans_head(page);
+	page_head = compound_head(page);
 
 	/*
 	 * THP can not break up slab pages so avoid taking
@@ -253,7 +253,7 @@
 	 */
 	unsigned long flags;
 	bool got;
-	struct page *page_head = compound_trans_head(page);
+	struct page *page_head = compound_head(page);
 
 	/* Ref to put_compound_page() comment. */
 	if (!__compound_tail_refcounted(page_head)) {
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 98e85e9..e76ace3 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -63,6 +63,8 @@
 	return ret;
 }
 
+static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
+
 void show_swap_cache_info(void)
 {
 	printk("%lu pages in swap cache\n", total_swapcache_pages());
@@ -286,8 +288,11 @@
 
 	page = find_get_page(swap_address_space(entry), entry.val);
 
-	if (page)
+	if (page) {
 		INC_CACHE_INFO(find_success);
+		if (TestClearPageReadahead(page))
+			atomic_inc(&swapin_readahead_hits);
+	}
 
 	INC_CACHE_INFO(find_total);
 	return page;
@@ -389,6 +394,50 @@
 	return found_page;
 }
 
+static unsigned long swapin_nr_pages(unsigned long offset)
+{
+	static unsigned long prev_offset;
+	unsigned int pages, max_pages, last_ra;
+	static atomic_t last_readahead_pages;
+
+	max_pages = 1 << ACCESS_ONCE(page_cluster);
+	if (max_pages <= 1)
+		return 1;
+
+	/*
+	 * This heuristic has been found to work well on both sequential and
+	 * random loads, swapping to hard disk or to SSD: please don't ask
+	 * what the "+ 2" means, it just happens to work well, that's all.
+	 */
+	pages = atomic_xchg(&swapin_readahead_hits, 0) + 2;
+	if (pages == 2) {
+		/*
+		 * We can have no readahead hits to judge by: but must not get
+		 * stuck here forever, so check for an adjacent offset instead
+		 * (and don't even bother to check whether swap type is same).
+		 */
+		if (offset != prev_offset + 1 && offset != prev_offset - 1)
+			pages = 1;
+		prev_offset = offset;
+	} else {
+		unsigned int roundup = 4;
+		while (roundup < pages)
+			roundup <<= 1;
+		pages = roundup;
+	}
+
+	if (pages > max_pages)
+		pages = max_pages;
+
+	/* Don't shrink readahead too fast */
+	last_ra = atomic_read(&last_readahead_pages) / 2;
+	if (pages < last_ra)
+		pages = last_ra;
+	atomic_set(&last_readahead_pages, pages);
+
+	return pages;
+}
+
 /**
  * swapin_readahead - swap in pages in hope we need them soon
  * @entry: swap entry of this memory
@@ -412,11 +461,16 @@
 			struct vm_area_struct *vma, unsigned long addr)
 {
 	struct page *page;
-	unsigned long offset = swp_offset(entry);
+	unsigned long entry_offset = swp_offset(entry);
+	unsigned long offset = entry_offset;
 	unsigned long start_offset, end_offset;
-	unsigned long mask = (1UL << page_cluster) - 1;
+	unsigned long mask;
 	struct blk_plug plug;
 
+	mask = swapin_nr_pages(offset) - 1;
+	if (!mask)
+		goto skip;
+
 	/* Read a page_cluster sized and aligned cluster around offset. */
 	start_offset = offset & ~mask;
 	end_offset = offset | mask;
@@ -430,10 +484,13 @@
 						gfp_mask, vma, addr);
 		if (!page)
 			continue;
+		if (offset != entry_offset)
+			SetPageReadahead(page);
 		page_cache_release(page);
 	}
 	blk_finish_plug(&plug);
 
 	lru_add_drain();	/* Push any new pages onto the LRU now */
+skip:
 	return read_swap_cache_async(entry, gfp_mask, vma, addr);
 }
diff --git a/mm/swapfile.c b/mm/swapfile.c
index c6c13b05..4a7f7e6 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1923,7 +1923,6 @@
 	p->swap_map = NULL;
 	cluster_info = p->cluster_info;
 	p->cluster_info = NULL;
-	p->flags = 0;
 	frontswap_map = frontswap_map_get(p);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
@@ -1949,6 +1948,16 @@
 		mutex_unlock(&inode->i_mutex);
 	}
 	filp_close(swap_file, NULL);
+
+	/*
+	 * Clear the SWP_USED flag after all resources are freed so that swapon
+	 * can reuse this swap_info in alloc_swap_info() safely.  It is ok to
+	 * not hold p->lock after we cleared its SWP_WRITEOK.
+	 */
+	spin_lock(&swap_lock);
+	p->flags = 0;
+	spin_unlock(&swap_lock);
+
 	err = 0;
 	atomic_inc(&proc_poll_event);
 	wake_up_interruptible(&proc_poll_wait);
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 196970a..d4042e7 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h>
 #include <linux/vmstat.h>
 #include <linux/eventfd.h>
+#include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/printk.h>
 #include <linux/vmpressure.h>
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7249614..def5dd2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -851,12 +851,14 @@
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif
+#ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
 	"nr_tlb_remote_flush_received",
-#endif
+#endif /* CONFIG_SMP */
 	"nr_tlb_local_flush_all",
 	"nr_tlb_local_flush_one",
+#endif /* CONFIG_DEBUG_TLBFLUSH */
 
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index ec99099..175273f 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -307,9 +307,11 @@
 static void vlan_transfer_features(struct net_device *dev,
 				   struct net_device *vlandev)
 {
+	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
+
 	vlandev->gso_max_size = dev->gso_max_size;
 
-	if (dev->features & NETIF_F_HW_VLAN_CTAG_TX)
+	if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
 		vlandev->hard_header_len = dev->hard_header_len;
 	else
 		vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index de51c48..27bfe2f 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -538,6 +538,9 @@
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
 
+	if (saddr == NULL)
+		saddr = dev->dev_addr;
+
 	return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
 }
 
@@ -575,6 +578,9 @@
 
 	dev->features |= real_dev->vlan_features | NETIF_F_LLTX;
 	dev->gso_max_size = real_dev->gso_max_size;
+	if (dev->features & NETIF_F_VLAN_FEATURES)
+		netdev_warn(real_dev, "VLAN features are set incorrectly.  Q-in-Q configurations may not work correctly.\n");
+
 
 	/* ipv6 shared card related stuff */
 	dev->dev_id = real_dev->dev_id;
@@ -589,7 +595,8 @@
 #endif
 
 	dev->needed_headroom = real_dev->needed_headroom;
-	if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
+	if (vlan_hw_offload_capable(real_dev->features,
+				    vlan_dev_priv(dev)->vlan_proto)) {
 		dev->header_ops      = &vlan_passthru_header_ops;
 		dev->hard_header_len = real_dev->hard_header_len;
 	} else {
diff --git a/net/9p/client.c b/net/9p/client.c
index a5e4d2d..9186550 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -204,7 +204,7 @@
 	return ret;
 }
 
-struct p9_fcall *p9_fcall_alloc(int alloc_msize)
+static struct p9_fcall *p9_fcall_alloc(int alloc_msize)
 {
 	struct p9_fcall *fc;
 	fc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, GFP_NOFS);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index cd1e1ed..ac2666c 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -340,7 +340,10 @@
 		int count = nr_pages;
 		while (nr_pages) {
 			s = rest_of_page(data);
-			pages[index++] = kmap_to_page(data);
+			if (is_vmalloc_addr(data))
+				pages[index++] = vmalloc_to_page(data);
+			else
+				pages[index++] = kmap_to_page(data);
 			data += s;
 			nr_pages--;
 		}
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 512159b..8323bce 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -241,19 +241,19 @@
 	size = bat_priv->num_ifaces * sizeof(uint8_t);
 	orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC);
 	if (!orig_node->bat_iv.bcast_own_sum)
-		goto free_bcast_own;
+		goto free_orig_node;
 
 	hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig,
 				     batadv_choose_orig, orig_node,
 				     &orig_node->hash_entry);
 	if (hash_added != 0)
-		goto free_bcast_own;
+		goto free_orig_node;
 
 	return orig_node;
 
-free_bcast_own:
-	kfree(orig_node->bat_iv.bcast_own);
 free_orig_node:
+	/* free twice, as batadv_orig_node_new sets refcount to 2 */
+	batadv_orig_node_free_ref(orig_node);
 	batadv_orig_node_free_ref(orig_node);
 
 	return NULL;
@@ -266,7 +266,7 @@
 			struct batadv_orig_node *orig_neigh)
 {
 	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
-	struct batadv_neigh_node *neigh_node;
+	struct batadv_neigh_node *neigh_node, *tmp_neigh_node;
 
 	neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, orig_node);
 	if (!neigh_node)
@@ -281,14 +281,24 @@
 	neigh_node->orig_node = orig_neigh;
 	neigh_node->if_incoming = hard_iface;
 
-	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-		   "Creating new neighbor %pM for orig_node %pM on interface %s\n",
-		   neigh_addr, orig_node->orig, hard_iface->net_dev->name);
-
 	spin_lock_bh(&orig_node->neigh_list_lock);
-	hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list);
+	tmp_neigh_node = batadv_neigh_node_get(orig_node, hard_iface,
+					       neigh_addr);
+	if (!tmp_neigh_node) {
+		hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list);
+	} else {
+		kfree(neigh_node);
+		batadv_hardif_free_ref(hard_iface);
+		neigh_node = tmp_neigh_node;
+	}
 	spin_unlock_bh(&orig_node->neigh_list_lock);
 
+	if (!tmp_neigh_node)
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "Creating new neighbor %pM for orig_node %pM on interface %s\n",
+			   neigh_addr, orig_node->orig,
+			   hard_iface->net_dev->name);
+
 out:
 	return neigh_node;
 }
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 3d417d3..b851cc5 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -241,7 +241,7 @@
 {
 	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
 	const struct batadv_hard_iface *hard_iface;
-	int min_mtu = ETH_DATA_LEN;
+	int min_mtu = INT_MAX;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
@@ -256,8 +256,6 @@
 	}
 	rcu_read_unlock();
 
-	atomic_set(&bat_priv->packet_size_max, min_mtu);
-
 	if (atomic_read(&bat_priv->fragmentation) == 0)
 		goto out;
 
@@ -268,13 +266,21 @@
 	min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE);
 	min_mtu -= sizeof(struct batadv_frag_packet);
 	min_mtu *= BATADV_FRAG_MAX_FRAGMENTS;
-	atomic_set(&bat_priv->packet_size_max, min_mtu);
-
-	/* with fragmentation enabled we can fragment external packets easily */
-	min_mtu = min_t(int, min_mtu, ETH_DATA_LEN);
 
 out:
-	return min_mtu - batadv_max_header_len();
+	/* report to the other components the maximum amount of bytes that
+	 * batman-adv can send over the wire (without considering the payload
+	 * overhead). For example, this value is used by TT to compute the
+	 * maximum local table table size
+	 */
+	atomic_set(&bat_priv->packet_size_max, min_mtu);
+
+	/* the real soft-interface MTU is computed by removing the payload
+	 * overhead from the maximum amount of bytes that was just computed.
+	 *
+	 * However batman-adv does not support MTUs bigger than ETH_DATA_LEN
+	 */
+	return min_t(int, min_mtu - batadv_max_header_len(), ETH_DATA_LEN);
 }
 
 /* adjusts the MTU if a new interface with a smaller MTU appeared. */
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 6df12a2..8539416 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -458,6 +458,42 @@
 }
 
 /**
+ * batadv_neigh_node_get - retrieve a neighbour from the list
+ * @orig_node: originator which the neighbour belongs to
+ * @hard_iface: the interface where this neighbour is connected to
+ * @addr: the address of the neighbour
+ *
+ * Looks for and possibly returns a neighbour belonging to this originator list
+ * which is connected through the provided hard interface.
+ * Returns NULL if the neighbour is not found.
+ */
+struct batadv_neigh_node *
+batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
+		      const struct batadv_hard_iface *hard_iface,
+		      const uint8_t *addr)
+{
+	struct batadv_neigh_node *tmp_neigh_node, *res = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) {
+		if (!batadv_compare_eth(tmp_neigh_node->addr, addr))
+			continue;
+
+		if (tmp_neigh_node->if_incoming != hard_iface)
+			continue;
+
+		if (!atomic_inc_not_zero(&tmp_neigh_node->refcount))
+			continue;
+
+		res = tmp_neigh_node;
+		break;
+	}
+	rcu_read_unlock();
+
+	return res;
+}
+
+/**
  * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object
  * @rcu: rcu pointer of the orig_ifinfo object
  */
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index 37be290..db3a9ed 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -29,6 +29,10 @@
 struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 					      const uint8_t *addr);
 struct batadv_neigh_node *
+batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
+		      const struct batadv_hard_iface *hard_iface,
+		      const uint8_t *addr);
+struct batadv_neigh_node *
 batadv_neigh_node_new(struct batadv_hard_iface *hard_iface,
 		      const uint8_t *neigh_addr,
 		      struct batadv_orig_node *orig_node);
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 1ed9f7c..a953d5b 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -688,7 +688,7 @@
 	int is_old_ttvn;
 
 	/* check if there is enough data before accessing it */
-	if (pskb_may_pull(skb, hdr_len + ETH_HLEN) < 0)
+	if (!pskb_may_pull(skb, hdr_len + ETH_HLEN))
 		return 0;
 
 	/* create a copy of the skb (in case of for re-routing) to modify it. */
@@ -918,6 +918,8 @@
 
 	if (ret != NET_RX_SUCCESS)
 		ret = batadv_route_unicast_packet(skb, recv_if);
+	else
+		consume_skb(skb);
 
 	return ret;
 }
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 579f5f0..843febd 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -254,9 +254,9 @@
 				   struct batadv_orig_node *orig_node,
 				   unsigned short vid)
 {
-	struct ethhdr *ethhdr = (struct ethhdr *)skb->data;
+	struct ethhdr *ethhdr;
 	struct batadv_unicast_packet *unicast_packet;
-	int ret = NET_XMIT_DROP;
+	int ret = NET_XMIT_DROP, hdr_size;
 
 	if (!orig_node)
 		goto out;
@@ -265,12 +265,16 @@
 	case BATADV_UNICAST:
 		if (!batadv_send_skb_prepare_unicast(skb, orig_node))
 			goto out;
+
+		hdr_size = sizeof(*unicast_packet);
 		break;
 	case BATADV_UNICAST_4ADDR:
 		if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb,
 							   orig_node,
 							   packet_subtype))
 			goto out;
+
+		hdr_size = sizeof(struct batadv_unicast_4addr_packet);
 		break;
 	default:
 		/* this function supports UNICAST and UNICAST_4ADDR only. It
@@ -279,6 +283,7 @@
 		goto out;
 	}
 
+	ethhdr = (struct ethhdr *)(skb->data + hdr_size);
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
 
 	/* inform the destination node that we are still missing a correct route
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index b6071f6..959dde7 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -1975,6 +1975,7 @@
 	struct hlist_head *head;
 	uint32_t i, crc_tmp, crc = 0;
 	uint8_t flags;
+	__be16 tmp_vid;
 
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
@@ -2011,8 +2012,11 @@
 							     orig_node))
 				continue;
 
-			crc_tmp = crc32c(0, &tt_common->vid,
-					 sizeof(tt_common->vid));
+			/* use network order to read the VID: this ensures that
+			 * every node reads the bytes in the same order.
+			 */
+			tmp_vid = htons(tt_common->vid);
+			crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid));
 
 			/* compute the CRC on flags that have to be kept in sync
 			 * among nodes
@@ -2046,6 +2050,7 @@
 	struct hlist_head *head;
 	uint32_t i, crc_tmp, crc = 0;
 	uint8_t flags;
+	__be16 tmp_vid;
 
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
@@ -2064,8 +2069,11 @@
 			if (tt_common->flags & BATADV_TT_CLIENT_NEW)
 				continue;
 
-			crc_tmp = crc32c(0, &tt_common->vid,
-					 sizeof(tt_common->vid));
+			/* use network order to read the VID: this ensures that
+			 * every node reads the bytes in the same order.
+			 */
+			tmp_vid = htons(tt_common->vid);
+			crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid));
 
 			/* compute the CRC on flags that have to be kept in sync
 			 * among nodes
@@ -2262,6 +2270,7 @@
 {
 	struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp;
 	struct batadv_orig_node_vlan *vlan;
+	uint32_t crc;
 	int i;
 
 	/* check if each received CRC matches the locally stored one */
@@ -2281,7 +2290,10 @@
 		if (!vlan)
 			return false;
 
-		if (vlan->tt.crc != ntohl(tt_vlan_tmp->crc))
+		crc = vlan->tt.crc;
+		batadv_orig_node_vlan_free_ref(vlan);
+
+		if (crc != ntohl(tt_vlan_tmp->crc))
 			return false;
 	}
 
@@ -3218,7 +3230,6 @@
 
 		spin_lock_bh(&orig_node->tt_lock);
 
-		tt_change = (struct batadv_tvlv_tt_change *)tt_buff;
 		batadv_tt_update_changes(bat_priv, orig_node, tt_num_changes,
 					 ttvn, tt_change);
 
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 292e619..d9fb934 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -430,6 +430,16 @@
 		del_timer(&session->timer);
 }
 
+static void hidp_process_report(struct hidp_session *session,
+				int type, const u8 *data, int len, int intr)
+{
+	if (len > HID_MAX_BUFFER_SIZE)
+		len = HID_MAX_BUFFER_SIZE;
+
+	memcpy(session->input_buf, data, len);
+	hid_input_report(session->hid, type, session->input_buf, len, intr);
+}
+
 static void hidp_process_handshake(struct hidp_session *session,
 					unsigned char param)
 {
@@ -502,7 +512,8 @@
 			hidp_input_report(session, skb);
 
 		if (session->hid)
-			hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 0);
+			hidp_process_report(session, HID_INPUT_REPORT,
+					    skb->data, skb->len, 0);
 		break;
 
 	case HIDP_DATA_RTYPE_OTHER:
@@ -584,7 +595,8 @@
 			hidp_input_report(session, skb);
 
 		if (session->hid) {
-			hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 1);
+			hidp_process_report(session, HID_INPUT_REPORT,
+					    skb->data, skb->len, 1);
 			BT_DBG("report len %d", skb->len);
 		}
 	} else {
diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h
index ab52414..8798492 100644
--- a/net/bluetooth/hidp/hidp.h
+++ b/net/bluetooth/hidp/hidp.h
@@ -24,6 +24,7 @@
 #define __HIDP_H
 
 #include <linux/types.h>
+#include <linux/hid.h>
 #include <linux/kref.h>
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/l2cap.h>
@@ -179,6 +180,9 @@
 
 	/* Used in hidp_output_raw_report() */
 	int output_report_success; /* boolean */
+
+	/* temporary input buffer */
+	u8 input_buf[HID_MAX_BUFFER_SIZE];
 };
 
 /* HIDP init defines */
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index e4401a5..8fe8b71 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -49,14 +49,14 @@
 	brstats->tx_bytes += skb->len;
 	u64_stats_update_end(&brstats->syncp);
 
-	if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
-		goto out;
-
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);
 	skb_pull(skb, ETH_HLEN);
 
+	if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
+		goto out;
+
 	if (is_broadcast_ether_addr(dest))
 		br_flood_deliver(br, skb, false);
 	else if (is_multicast_ether_addr(dest)) {
@@ -187,8 +187,7 @@
 
 	spin_lock_bh(&br->lock);
 	if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) {
-		memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
-		br_fdb_change_mac_address(br, addr->sa_data);
+		/* Mac address will be changed in br_stp_change_bridge_id(). */
 		br_stp_change_bridge_id(br, addr->sa_data);
 	}
 	spin_unlock_bh(&br->lock);
@@ -226,37 +225,11 @@
 		br_netpoll_disable(p);
 }
 
-static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
-			    gfp_t gfp)
-{
-	struct net_bridge *br = netdev_priv(dev);
-	struct net_bridge_port *p;
-	int err = 0;
-
-	list_for_each_entry(p, &br->port_list, list) {
-		if (!p->dev)
-			continue;
-		err = br_netpoll_enable(p, gfp);
-		if (err)
-			goto fail;
-	}
-
-out:
-	return err;
-
-fail:
-	br_netpoll_cleanup(dev);
-	goto out;
-}
-
-int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
+static int __br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
 {
 	struct netpoll *np;
 	int err;
 
-	if (!p->br->dev->npinfo)
-		return 0;
-
 	np = kzalloc(sizeof(*p->np), gfp);
 	if (!np)
 		return -ENOMEM;
@@ -271,6 +244,37 @@
 	return err;
 }
 
+int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
+{
+	if (!p->br->dev->npinfo)
+		return 0;
+
+	return __br_netpoll_enable(p, gfp);
+}
+
+static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
+			    gfp_t gfp)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct net_bridge_port *p;
+	int err = 0;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (!p->dev)
+			continue;
+		err = __br_netpoll_enable(p, gfp);
+		if (err)
+			goto fail;
+	}
+
+out:
+	return err;
+
+fail:
+	br_netpoll_cleanup(dev);
+	goto out;
+}
+
 void br_netpoll_disable(struct net_bridge_port *p)
 {
 	struct netpoll *np = p->np;
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index c5f5a4a..9203d5a 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -27,6 +27,9 @@
 #include "br_private.h"
 
 static struct kmem_cache *br_fdb_cache __read_mostly;
+static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head,
+					     const unsigned char *addr,
+					     __u16 vid);
 static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
 		      const unsigned char *addr, u16 vid);
 static void fdb_notify(struct net_bridge *br,
@@ -89,11 +92,57 @@
 	call_rcu(&f->rcu, fdb_rcu_free);
 }
 
+/* Delete a local entry if no other port had the same address. */
+static void fdb_delete_local(struct net_bridge *br,
+			     const struct net_bridge_port *p,
+			     struct net_bridge_fdb_entry *f)
+{
+	const unsigned char *addr = f->addr.addr;
+	u16 vid = f->vlan_id;
+	struct net_bridge_port *op;
+
+	/* Maybe another port has same hw addr? */
+	list_for_each_entry(op, &br->port_list, list) {
+		if (op != p && ether_addr_equal(op->dev->dev_addr, addr) &&
+		    (!vid || nbp_vlan_find(op, vid))) {
+			f->dst = op;
+			f->added_by_user = 0;
+			return;
+		}
+	}
+
+	/* Maybe bridge device has same hw addr? */
+	if (p && ether_addr_equal(br->dev->dev_addr, addr) &&
+	    (!vid || br_vlan_find(br, vid))) {
+		f->dst = NULL;
+		f->added_by_user = 0;
+		return;
+	}
+
+	fdb_delete(br, f);
+}
+
+void br_fdb_find_delete_local(struct net_bridge *br,
+			      const struct net_bridge_port *p,
+			      const unsigned char *addr, u16 vid)
+{
+	struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
+	struct net_bridge_fdb_entry *f;
+
+	spin_lock_bh(&br->hash_lock);
+	f = fdb_find(head, addr, vid);
+	if (f && f->is_local && !f->added_by_user && f->dst == p)
+		fdb_delete_local(br, p, f);
+	spin_unlock_bh(&br->hash_lock);
+}
+
 void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
 {
 	struct net_bridge *br = p->br;
-	bool no_vlan = (nbp_get_vlan_info(p) == NULL) ? true : false;
+	struct net_port_vlans *pv = nbp_get_vlan_info(p);
+	bool no_vlan = !pv;
 	int i;
+	u16 vid;
 
 	spin_lock_bh(&br->hash_lock);
 
@@ -104,38 +153,34 @@
 			struct net_bridge_fdb_entry *f;
 
 			f = hlist_entry(h, struct net_bridge_fdb_entry, hlist);
-			if (f->dst == p && f->is_local) {
-				/* maybe another port has same hw addr? */
-				struct net_bridge_port *op;
-				u16 vid = f->vlan_id;
-				list_for_each_entry(op, &br->port_list, list) {
-					if (op != p &&
-					    ether_addr_equal(op->dev->dev_addr,
-							     f->addr.addr) &&
-					    nbp_vlan_find(op, vid)) {
-						f->dst = op;
-						goto insert;
-					}
-				}
-
+			if (f->dst == p && f->is_local && !f->added_by_user) {
 				/* delete old one */
-				fdb_delete(br, f);
-insert:
-				/* insert new address,  may fail if invalid
-				 * address or dup.
-				 */
-				fdb_insert(br, p, newaddr, vid);
+				fdb_delete_local(br, p, f);
 
 				/* if this port has no vlan information
 				 * configured, we can safely be done at
 				 * this point.
 				 */
 				if (no_vlan)
-					goto done;
+					goto insert;
 			}
 		}
 	}
 
+insert:
+	/* insert new address,  may fail if invalid address or dup. */
+	fdb_insert(br, p, newaddr, 0);
+
+	if (no_vlan)
+		goto done;
+
+	/* Now add entries for every VLAN configured on the port.
+	 * This function runs under RTNL so the bitmap will not change
+	 * from under us.
+	 */
+	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
+		fdb_insert(br, p, newaddr, vid);
+
 done:
 	spin_unlock_bh(&br->hash_lock);
 }
@@ -146,10 +191,12 @@
 	struct net_port_vlans *pv;
 	u16 vid = 0;
 
+	spin_lock_bh(&br->hash_lock);
+
 	/* If old entry was unassociated with any port, then delete it. */
 	f = __br_fdb_get(br, br->dev->dev_addr, 0);
 	if (f && f->is_local && !f->dst)
-		fdb_delete(br, f);
+		fdb_delete_local(br, NULL, f);
 
 	fdb_insert(br, NULL, newaddr, 0);
 
@@ -159,14 +206,16 @@
 	 */
 	pv = br_get_vlan_info(br);
 	if (!pv)
-		return;
+		goto out;
 
 	for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) {
 		f = __br_fdb_get(br, br->dev->dev_addr, vid);
 		if (f && f->is_local && !f->dst)
-			fdb_delete(br, f);
+			fdb_delete_local(br, NULL, f);
 		fdb_insert(br, NULL, newaddr, vid);
 	}
+out:
+	spin_unlock_bh(&br->hash_lock);
 }
 
 void br_fdb_cleanup(unsigned long _data)
@@ -235,25 +284,11 @@
 
 			if (f->is_static && !do_all)
 				continue;
-			/*
-			 * if multiple ports all have the same device address
-			 * then when one port is deleted, assign
-			 * the local entry to other port
-			 */
-			if (f->is_local) {
-				struct net_bridge_port *op;
-				list_for_each_entry(op, &br->port_list, list) {
-					if (op != p &&
-					    ether_addr_equal(op->dev->dev_addr,
-							     f->addr.addr)) {
-						f->dst = op;
-						goto skip_delete;
-					}
-				}
-			}
 
-			fdb_delete(br, f);
-		skip_delete: ;
+			if (f->is_local)
+				fdb_delete_local(br, p, f);
+			else
+				fdb_delete(br, f);
 		}
 	}
 	spin_unlock_bh(&br->hash_lock);
@@ -397,6 +432,7 @@
 		fdb->vlan_id = vid;
 		fdb->is_local = 0;
 		fdb->is_static = 0;
+		fdb->added_by_user = 0;
 		fdb->updated = fdb->used = jiffies;
 		hlist_add_head_rcu(&fdb->hlist, head);
 	}
@@ -447,7 +483,7 @@
 }
 
 void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
-		   const unsigned char *addr, u16 vid)
+		   const unsigned char *addr, u16 vid, bool added_by_user)
 {
 	struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
 	struct net_bridge_fdb_entry *fdb;
@@ -473,13 +509,18 @@
 			/* fastpath: update of existing entry */
 			fdb->dst = source;
 			fdb->updated = jiffies;
+			if (unlikely(added_by_user))
+				fdb->added_by_user = 1;
 		}
 	} else {
 		spin_lock(&br->hash_lock);
 		if (likely(!fdb_find(head, addr, vid))) {
 			fdb = fdb_create(head, source, addr, vid);
-			if (fdb)
+			if (fdb) {
+				if (unlikely(added_by_user))
+					fdb->added_by_user = 1;
 				fdb_notify(br, fdb, RTM_NEWNEIGH);
+			}
 		}
 		/* else  we lose race and someone else inserts
 		 * it first, don't bother updating
@@ -647,6 +688,7 @@
 
 		modified = true;
 	}
+	fdb->added_by_user = 1;
 
 	fdb->used = jiffies;
 	if (modified) {
@@ -664,7 +706,7 @@
 
 	if (ndm->ndm_flags & NTF_USE) {
 		rcu_read_lock();
-		br_fdb_update(p->br, p, addr, vid);
+		br_fdb_update(p->br, p, addr, vid, true);
 		rcu_read_unlock();
 	} else {
 		spin_lock_bh(&p->br->hash_lock);
@@ -749,8 +791,7 @@
 	return err;
 }
 
-int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr,
-		       u16 vlan)
+static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vlan)
 {
 	struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)];
 	struct net_bridge_fdb_entry *fdb;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index cffe1d6..54d207d 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -389,6 +389,9 @@
 	if (br->dev->needed_headroom < dev->needed_headroom)
 		br->dev->needed_headroom = dev->needed_headroom;
 
+	if (br_fdb_insert(br, p, dev->dev_addr, 0))
+		netdev_err(dev, "failed insert local address bridge forwarding table\n");
+
 	spin_lock_bh(&br->lock);
 	changed_addr = br_stp_recalculate_bridge_id(br);
 
@@ -404,9 +407,6 @@
 
 	dev_set_mtu(br->dev, br_min_mtu(br));
 
-	if (br_fdb_insert(br, p, dev->dev_addr, 0))
-		netdev_err(dev, "failed insert local address bridge forwarding table\n");
-
 	kobject_uevent(&p->kobj, KOBJ_ADD);
 
 	return 0;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index bf8dc7d..d0cca3c 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -29,6 +29,7 @@
 	struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
 	struct net_bridge *br = netdev_priv(brdev);
 	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
+	struct net_port_vlans *pv;
 
 	u64_stats_update_begin(&brstats->syncp);
 	brstats->rx_packets++;
@@ -39,18 +40,18 @@
 	 * packet is allowed except in promisc modue when someone
 	 * may be running packet capture.
 	 */
+	pv = br_get_vlan_info(br);
 	if (!(brdev->flags & IFF_PROMISC) &&
-	    !br_allowed_egress(br, br_get_vlan_info(br), skb)) {
+	    !br_allowed_egress(br, pv, skb)) {
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
 
-	skb = br_handle_vlan(br, br_get_vlan_info(br), skb);
-	if (!skb)
-		return NET_RX_DROP;
-
 	indev = skb->dev;
 	skb->dev = brdev;
+	skb = br_handle_vlan(br, pv, skb);
+	if (!skb)
+		return NET_RX_DROP;
 
 	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL,
 		       netif_receive_skb);
@@ -77,7 +78,7 @@
 	/* insert into forwarding database after filtering to avoid spoofing */
 	br = p->br;
 	if (p->flags & BR_LEARNING)
-		br_fdb_update(br, p, eth_hdr(skb)->h_source, vid);
+		br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
 
 	if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) &&
 	    br_multicast_rcv(br, p, skb, vid))
@@ -148,7 +149,7 @@
 
 	br_vlan_get_tag(skb, &vid);
 	if (p->flags & BR_LEARNING)
-		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid);
+		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
 	return 0;	 /* process further */
 }
 
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index ef66365..93067ec 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1127,9 +1127,10 @@
 					struct net_bridge_port *port,
 					struct bridge_mcast_querier *querier,
 					int saddr,
+					bool is_general_query,
 					unsigned long max_delay)
 {
-	if (saddr)
+	if (saddr && is_general_query)
 		br_multicast_update_querier_timer(br, querier, max_delay);
 	else if (timer_pending(&querier->timer))
 		return;
@@ -1181,8 +1182,16 @@
 			    IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1;
 	}
 
+	/* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer
+	 * all-systems destination addresses (224.0.0.1) for general queries
+	 */
+	if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	br_multicast_query_received(br, port, &br->ip4_querier, !!iph->saddr,
-				    max_delay);
+				    !group, max_delay);
 
 	if (!group)
 		goto out;
@@ -1228,6 +1237,7 @@
 	unsigned long max_delay;
 	unsigned long now = jiffies;
 	const struct in6_addr *group = NULL;
+	bool is_general_query;
 	int err = 0;
 
 	spin_lock(&br->multicast_lock);
@@ -1235,6 +1245,12 @@
 	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
+	/* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+	if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (skb->len == sizeof(*mld)) {
 		if (!pskb_may_pull(skb, sizeof(*mld))) {
 			err = -EINVAL;
@@ -1256,8 +1272,19 @@
 		max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL);
 	}
 
+	is_general_query = group && ipv6_addr_any(group);
+
+	/* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer
+	 * all-nodes destination address (ff02::1) for general queries
+	 */
+	if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	br_multicast_query_received(br, port, &br->ip6_querier,
-				    !ipv6_addr_any(&ip6h->saddr), max_delay);
+				    !ipv6_addr_any(&ip6h->saddr),
+				    is_general_query, max_delay);
 
 	if (!group)
 		goto out;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index fcd1233..3ba11bc 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -104,6 +104,7 @@
 	mac_addr			addr;
 	unsigned char			is_local;
 	unsigned char			is_static;
+	unsigned char			added_by_user;
 	__u16				vlan_id;
 };
 
@@ -370,6 +371,9 @@
 int br_fdb_init(void);
 void br_fdb_fini(void);
 void br_fdb_flush(struct net_bridge *br);
+void br_fdb_find_delete_local(struct net_bridge *br,
+			      const struct net_bridge_port *p,
+			      const unsigned char *addr, u16 vid);
 void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr);
 void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr);
 void br_fdb_cleanup(unsigned long arg);
@@ -383,8 +387,7 @@
 int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
 		  const unsigned char *addr, u16 vid);
 void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
-		   const unsigned char *addr, u16 vid);
-int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vid);
+		   const unsigned char *addr, u16 vid, bool added_by_user);
 
 int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 		  struct net_device *dev, const unsigned char *addr);
@@ -584,6 +587,7 @@
 int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
 int br_vlan_delete(struct net_bridge *br, u16 vid);
 void br_vlan_flush(struct net_bridge *br);
+bool br_vlan_find(struct net_bridge *br, u16 vid);
 int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
 int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
 int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
@@ -665,6 +669,11 @@
 {
 }
 
+static inline bool br_vlan_find(struct net_bridge *br, u16 vid)
+{
+	return false;
+}
+
 static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
 {
 	return -EOPNOTSUPP;
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 656a6f3..189ba1e 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -194,6 +194,8 @@
 
 	wasroot = br_is_root_bridge(br);
 
+	br_fdb_change_mac_address(br, addr);
+
 	memcpy(oldaddr, br->bridge_id.addr, ETH_ALEN);
 	memcpy(br->bridge_id.addr, addr, ETH_ALEN);
 	memcpy(br->dev->dev_addr, addr, ETH_ALEN);
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 4ca4d0a..f23c74b 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -119,22 +119,6 @@
 	kfree_rcu(v, rcu);
 }
 
-/* Strip the tag from the packet.  Will return skb with tci set 0.  */
-static struct sk_buff *br_vlan_untag(struct sk_buff *skb)
-{
-	if (skb->protocol != htons(ETH_P_8021Q)) {
-		skb->vlan_tci = 0;
-		return skb;
-	}
-
-	skb->vlan_tci = 0;
-	skb = vlan_untag(skb);
-	if (skb)
-		skb->vlan_tci = 0;
-
-	return skb;
-}
-
 struct sk_buff *br_handle_vlan(struct net_bridge *br,
 			       const struct net_port_vlans *pv,
 			       struct sk_buff *skb)
@@ -144,13 +128,27 @@
 	if (!br->vlan_enabled)
 		goto out;
 
+	/* Vlan filter table must be configured at this point.  The
+	 * only exception is the bridge is set in promisc mode and the
+	 * packet is destined for the bridge device.  In this case
+	 * pass the packet as is.
+	 */
+	if (!pv) {
+		if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) {
+			goto out;
+		} else {
+			kfree_skb(skb);
+			return NULL;
+		}
+	}
+
 	/* At this point, we know that the frame was filtered and contains
 	 * a valid vlan id.  If the vlan id is set in the untagged bitmap,
 	 * send untagged; otherwise, send tagged.
 	 */
 	br_vlan_get_tag(skb, &vid);
 	if (test_bit(vid, pv->untagged_bitmap))
-		skb = br_vlan_untag(skb);
+		skb->vlan_tci = 0;
 
 out:
 	return skb;
@@ -174,6 +172,18 @@
 	if (!v)
 		return false;
 
+	/* If vlan tx offload is disabled on bridge device and frame was
+	 * sent from vlan device on the bridge device, it does not have
+	 * HW accelerated vlan tag.
+	 */
+	if (unlikely(!vlan_tx_tag_present(skb) &&
+		     (skb->protocol == htons(ETH_P_8021Q) ||
+		      skb->protocol == htons(ETH_P_8021AD)))) {
+		skb = vlan_untag(skb);
+		if (unlikely(!skb))
+			return false;
+	}
+
 	err = br_vlan_get_tag(skb, vid);
 	if (!*vid) {
 		u16 pvid = br_get_pvid(v);
@@ -275,9 +285,7 @@
 	if (!pv)
 		return -EINVAL;
 
-	spin_lock_bh(&br->hash_lock);
-	fdb_delete_by_addr(br, br->dev->dev_addr, vid);
-	spin_unlock_bh(&br->hash_lock);
+	br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid);
 
 	__vlan_del(pv, vid);
 	return 0;
@@ -295,6 +303,25 @@
 	__vlan_flush(pv);
 }
 
+bool br_vlan_find(struct net_bridge *br, u16 vid)
+{
+	struct net_port_vlans *pv;
+	bool found = false;
+
+	rcu_read_lock();
+	pv = rcu_dereference(br->vlan_info);
+
+	if (!pv)
+		goto out;
+
+	if (test_bit(vid, pv->vlan_bitmap))
+		found = true;
+
+out:
+	rcu_read_unlock();
+	return found;
+}
+
 int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val)
 {
 	if (!rtnl_trylock())
@@ -359,9 +386,7 @@
 	if (!pv)
 		return -EINVAL;
 
-	spin_lock_bh(&port->br->hash_lock);
-	fdb_delete_by_addr(port->br, port->dev->dev_addr, vid);
-	spin_unlock_bh(&port->br->hash_lock);
+	br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid);
 
 	return __vlan_del(pv, vid);
 }
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index 4dca159..edbca46 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -22,6 +22,7 @@
 #include <net/pkt_sched.h>
 #include <net/caif/caif_device.h>
 #include <net/caif/caif_layer.h>
+#include <net/caif/caif_dev.h>
 #include <net/caif/cfpkt.h>
 #include <net/caif/cfcnfg.h>
 #include <net/caif/cfserl.h>
diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c
index 353f793..a6e1154 100644
--- a/net/caif/cfsrvl.c
+++ b/net/caif/cfsrvl.c
@@ -15,6 +15,7 @@
 #include <net/caif/caif_layer.h>
 #include <net/caif/cfsrvl.h>
 #include <net/caif/cfpkt.h>
+#include <net/caif/caif_dev.h>
 
 #define SRVL_CTRL_PKT_SIZE 1
 #define SRVL_FLOW_OFF 0x81
diff --git a/net/can/af_can.c b/net/can/af_can.c
index d249874..a27f8aa 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -57,6 +57,7 @@
 #include <linux/skbuff.h>
 #include <linux/can.h>
 #include <linux/can/core.h>
+#include <linux/can/skb.h>
 #include <linux/ratelimit.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
@@ -290,7 +291,7 @@
 				return -ENOMEM;
 			}
 
-			newskb->sk = skb->sk;
+			can_skb_set_owner(newskb, skb->sk);
 			newskb->ip_summed = CHECKSUM_UNNECESSARY;
 			newskb->pkt_type = PACKET_BROADCAST;
 		}
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 3fc737b..dcb75c0 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -268,7 +268,7 @@
 
 	/* send with loopback */
 	skb->dev = dev;
-	skb->sk = op->sk;
+	can_skb_set_owner(skb, op->sk);
 	can_send(skb, 1);
 
 	/* update statistics */
@@ -1223,7 +1223,7 @@
 
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	skb->dev = dev;
-	skb->sk  = sk;
+	can_skb_set_owner(skb, sk);
 	err = can_send(skb, 1); /* send with loopback */
 	dev_put(dev);
 
diff --git a/net/can/raw.c b/net/can/raw.c
index 07d72d8..081e81f 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -121,13 +121,9 @@
 	if (!ro->recv_own_msgs && oskb->sk == sk)
 		return;
 
-	/* do not pass frames with DLC > 8 to a legacy socket */
-	if (!ro->fd_frames) {
-		struct canfd_frame *cfd = (struct canfd_frame *)oskb->data;
-
-		if (unlikely(cfd->len > CAN_MAX_DLEN))
-			return;
-	}
+	/* do not pass non-CAN2.0 frames to a legacy socket */
+	if (!ro->fd_frames && oskb->len != CAN_MTU)
+		return;
 
 	/* clone the given skb to be able to enqueue it into the rcv queue */
 	skb = skb_clone(oskb, GFP_ATOMIC);
@@ -715,6 +711,7 @@
 
 	skb->dev = dev;
 	skb->sk  = sk;
+	skb->priority = sk->sk_priority;
 
 	err = can_send(skb, ro->loopback);
 
@@ -737,9 +734,7 @@
 		       struct msghdr *msg, size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct raw_sock *ro = raw_sk(sk);
 	struct sk_buff *skb;
-	int rxmtu;
 	int err = 0;
 	int noblock;
 
@@ -750,20 +745,10 @@
 	if (!skb)
 		return err;
 
-	/*
-	 * when serving a legacy socket the DLC <= 8 is already checked inside
-	 * raw_rcv(). Now check if we need to pass a canfd_frame to a legacy
-	 * socket and cut the possible CANFD_MTU/CAN_MTU length to CAN_MTU
-	 */
-	if (!ro->fd_frames)
-		rxmtu = CAN_MTU;
-	else
-		rxmtu = skb->len;
-
-	if (size < rxmtu)
+	if (size < skb->len)
 		msg->msg_flags |= MSG_TRUNC;
 	else
-		size = rxmtu;
+		size = skb->len;
 
 	err = memcpy_toiovec(msg->msg_iov, skb->data, size);
 	if (err < 0) {
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 0e478a0..30efc5c 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -840,9 +840,13 @@
 
 	if (!cursor->bvec_iter.bi_size) {
 		bio = bio->bi_next;
-		cursor->bvec_iter = bio->bi_iter;
+		cursor->bio = bio;
+		if (bio)
+			cursor->bvec_iter = bio->bi_iter;
+		else
+			memset(&cursor->bvec_iter, 0,
+			       sizeof(cursor->bvec_iter));
 	}
-	cursor->bio = bio;
 
 	if (!cursor->last_piece) {
 		BUG_ON(!cursor->resid);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 010ff3b..0676f2b 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1427,6 +1427,40 @@
 }
 
 /*
+ * Caller should hold map_sem for read and request_mutex.
+ */
+static int __ceph_osdc_start_request(struct ceph_osd_client *osdc,
+				     struct ceph_osd_request *req,
+				     bool nofail)
+{
+	int rc;
+
+	__register_request(osdc, req);
+	req->r_sent = 0;
+	req->r_got_reply = 0;
+	rc = __map_request(osdc, req, 0);
+	if (rc < 0) {
+		if (nofail) {
+			dout("osdc_start_request failed map, "
+				" will retry %lld\n", req->r_tid);
+			rc = 0;
+		} else {
+			__unregister_request(osdc, req);
+		}
+		return rc;
+	}
+
+	if (req->r_osd == NULL) {
+		dout("send_request %p no up osds in pg\n", req);
+		ceph_monc_request_next_osdmap(&osdc->client->monc);
+	} else {
+		__send_queued(osdc);
+	}
+
+	return 0;
+}
+
+/*
  * Timeout callback, called every N seconds when 1 or more osd
  * requests has been active for more than N seconds.  When this
  * happens, we ping all OSDs with requests who have timed out to
@@ -1653,6 +1687,7 @@
 	osdmap_epoch = ceph_decode_32(&p);
 
 	/* lookup */
+	down_read(&osdc->map_sem);
 	mutex_lock(&osdc->request_mutex);
 	req = __lookup_request(osdc, tid);
 	if (req == NULL) {
@@ -1709,7 +1744,6 @@
 		dout("redirect pool %lld\n", redir.oloc.pool);
 
 		__unregister_request(osdc, req);
-		mutex_unlock(&osdc->request_mutex);
 
 		req->r_target_oloc = redir.oloc; /* struct */
 
@@ -1721,10 +1755,10 @@
 		 * successfully.  In the future we might want to follow
 		 * original request's nofail setting here.
 		 */
-		err = ceph_osdc_start_request(osdc, req, true);
+		err = __ceph_osdc_start_request(osdc, req, true);
 		BUG_ON(err);
 
-		goto done;
+		goto out_unlock;
 	}
 
 	already_completed = req->r_got_reply;
@@ -1742,8 +1776,7 @@
 		req->r_got_reply = 1;
 	} else if ((flags & CEPH_OSD_FLAG_ONDISK) == 0) {
 		dout("handle_reply tid %llu dup ack\n", tid);
-		mutex_unlock(&osdc->request_mutex);
-		goto done;
+		goto out_unlock;
 	}
 
 	dout("handle_reply tid %llu flags %d\n", tid, flags);
@@ -1758,6 +1791,7 @@
 		__unregister_request(osdc, req);
 
 	mutex_unlock(&osdc->request_mutex);
+	up_read(&osdc->map_sem);
 
 	if (!already_completed) {
 		if (req->r_unsafe_callback &&
@@ -1775,10 +1809,14 @@
 		complete_request(req);
 	}
 
-done:
+out:
 	dout("req=%p req->r_linger=%d\n", req, req->r_linger);
 	ceph_osdc_put_request(req);
 	return;
+out_unlock:
+	mutex_unlock(&osdc->request_mutex);
+	up_read(&osdc->map_sem);
+	goto out;
 
 bad_put:
 	req->r_result = -EIO;
@@ -1791,6 +1829,7 @@
 	ceph_osdc_put_request(req);
 bad_mutex:
 	mutex_unlock(&osdc->request_mutex);
+	up_read(&osdc->map_sem);
 bad:
 	pr_err("corrupt osd_op_reply got %d %d\n",
 	       (int)msg->front.iov_len, le32_to_cpu(msg->hdr.front_len));
@@ -2351,34 +2390,16 @@
 			    struct ceph_osd_request *req,
 			    bool nofail)
 {
-	int rc = 0;
+	int rc;
 
 	down_read(&osdc->map_sem);
 	mutex_lock(&osdc->request_mutex);
-	__register_request(osdc, req);
-	req->r_sent = 0;
-	req->r_got_reply = 0;
-	rc = __map_request(osdc, req, 0);
-	if (rc < 0) {
-		if (nofail) {
-			dout("osdc_start_request failed map, "
-				" will retry %lld\n", req->r_tid);
-			rc = 0;
-		} else {
-			__unregister_request(osdc, req);
-		}
-		goto out_unlock;
-	}
-	if (req->r_osd == NULL) {
-		dout("send_request %p no up osds in pg\n", req);
-		ceph_monc_request_next_osdmap(&osdc->client->monc);
-	} else {
-		__send_queued(osdc);
-	}
-	rc = 0;
-out_unlock:
+
+	rc = __ceph_osdc_start_request(osdc, req, nofail);
+
 	mutex_unlock(&osdc->request_mutex);
 	up_read(&osdc->map_sem);
+
 	return rc;
 }
 EXPORT_SYMBOL(ceph_osdc_start_request);
@@ -2504,9 +2525,12 @@
 	err = -ENOMEM;
 	osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify");
 	if (!osdc->notify_wq)
-		goto out_msgpool;
+		goto out_msgpool_reply;
+
 	return 0;
 
+out_msgpool_reply:
+	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
 out_msgpool:
 	ceph_msgpool_destroy(&osdc->msgpool_op);
 out_mempool:
diff --git a/net/compat.c b/net/compat.c
index f50161f..9a76eaf 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -384,8 +384,8 @@
 	return sock_setsockopt(sock, level, optname, optval, optlen);
 }
 
-asmlinkage long compat_sys_setsockopt(int fd, int level, int optname,
-				char __user *optval, unsigned int optlen)
+COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
+		       char __user *, optval, unsigned int, optlen)
 {
 	int err;
 	struct socket *sock = sockfd_lookup(fd, &err);
@@ -504,8 +504,8 @@
 }
 EXPORT_SYMBOL(compat_sock_get_timestampns);
 
-asmlinkage long compat_sys_getsockopt(int fd, int level, int optname,
-				char __user *optval, int __user *optlen)
+COMPAT_SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
+		       char __user *, optval, int __user *, optlen)
 {
 	int err;
 	struct socket *sock = sockfd_lookup(fd, &err);
@@ -735,15 +735,15 @@
 };
 #undef AL
 
-asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags)
+COMPAT_SYSCALL_DEFINE3(sendmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags)
 {
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
 	return __sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
 }
 
-asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg,
-				    unsigned int vlen, unsigned int flags)
+COMPAT_SYSCALL_DEFINE4(sendmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
+		       unsigned int, vlen, unsigned int, flags)
 {
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
@@ -751,28 +751,28 @@
 			      flags | MSG_CMSG_COMPAT);
 }
 
-asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags)
+COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags)
 {
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
 	return __sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
 }
 
-asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len, unsigned int flags)
+COMPAT_SYSCALL_DEFINE4(recv, int, fd, void __user *, buf, compat_size_t, len, unsigned int, flags)
 {
 	return sys_recv(fd, buf, len, flags | MSG_CMSG_COMPAT);
 }
 
-asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, size_t len,
-				    unsigned int flags, struct sockaddr __user *addr,
-				    int __user *addrlen)
+COMPAT_SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, buf, compat_size_t, len,
+		       unsigned int, flags, struct sockaddr __user *, addr,
+		       int __user *, addrlen)
 {
 	return sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr, addrlen);
 }
 
-asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg,
-				    unsigned int vlen, unsigned int flags,
-				    struct compat_timespec __user *timeout)
+COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
+		       unsigned int, vlen, unsigned int, flags,
+		       struct compat_timespec __user *, timeout)
 {
 	int datagrams;
 	struct timespec ktspec;
@@ -795,7 +795,7 @@
 	return datagrams;
 }
 
-asmlinkage long compat_sys_socketcall(int call, u32 __user *args)
+COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
 {
 	int ret;
 	u32 a[6];
diff --git a/net/core/dev.c b/net/core/dev.c
index 3721db7..45fa2f1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2286,7 +2286,7 @@
 }
 EXPORT_SYMBOL(skb_checksum_help);
 
-__be16 skb_network_protocol(struct sk_buff *skb)
+__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
 	__be16 type = skb->protocol;
 	int vlan_depth = ETH_HLEN;
@@ -2313,6 +2313,8 @@
 		vlan_depth += VLAN_HLEN;
 	}
 
+	*depth = vlan_depth;
+
 	return type;
 }
 
@@ -2326,12 +2328,13 @@
 {
 	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
 	struct packet_offload *ptype;
-	__be16 type = skb_network_protocol(skb);
+	int vlan_depth = skb->mac_len;
+	__be16 type = skb_network_protocol(skb, &vlan_depth);
 
 	if (unlikely(!type))
 		return ERR_PTR(-EINVAL);
 
-	__skb_pull(skb, skb->mac_len);
+	__skb_pull(skb, vlan_depth);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, &offload_base, list) {
@@ -2420,7 +2423,7 @@
  * 2. No high memory really exists on this machine.
  */
 
-static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_HIGHMEM
 	int i;
@@ -2495,34 +2498,38 @@
 }
 
 static netdev_features_t harmonize_features(struct sk_buff *skb,
-	netdev_features_t features)
+					    const struct net_device *dev,
+					    netdev_features_t features)
 {
+	int tmp;
+
 	if (skb->ip_summed != CHECKSUM_NONE &&
-	    !can_checksum_protocol(features, skb_network_protocol(skb))) {
+	    !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
 		features &= ~NETIF_F_ALL_CSUM;
-	} else if (illegal_highdma(skb->dev, skb)) {
+	} else if (illegal_highdma(dev, skb)) {
 		features &= ~NETIF_F_SG;
 	}
 
 	return features;
 }
 
-netdev_features_t netif_skb_features(struct sk_buff *skb)
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+					 const struct net_device *dev)
 {
 	__be16 protocol = skb->protocol;
-	netdev_features_t features = skb->dev->features;
+	netdev_features_t features = dev->features;
 
-	if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+	if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
 	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
 	} else if (!vlan_tx_tag_present(skb)) {
-		return harmonize_features(skb, features);
+		return harmonize_features(skb, dev, features);
 	}
 
-	features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+	features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
 					       NETIF_F_HW_VLAN_STAG_TX);
 
 	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
@@ -2530,9 +2537,9 @@
 				NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_STAG_TX;
 
-	return harmonize_features(skb, features);
+	return harmonize_features(skb, dev, features);
 }
-EXPORT_SYMBOL(netif_skb_features);
+EXPORT_SYMBOL(netif_skb_dev_features);
 
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			struct netdev_queue *txq)
@@ -2803,7 +2810,7 @@
  *      the BH enable code must have IRQs enabled so that it will not deadlock.
  *          --BLG
  */
-int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
+static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 {
 	struct net_device *dev = skb->dev;
 	struct netdev_queue *txq;
@@ -4637,7 +4644,7 @@
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
 
-int netdev_adjacent_sysfs_add(struct net_device *dev,
+static int netdev_adjacent_sysfs_add(struct net_device *dev,
 			      struct net_device *adj_dev,
 			      struct list_head *dev_list)
 {
@@ -4647,7 +4654,7 @@
 	return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj),
 				 linkname);
 }
-void netdev_adjacent_sysfs_del(struct net_device *dev,
+static void netdev_adjacent_sysfs_del(struct net_device *dev,
 			       char *name,
 			       struct list_head *dev_list)
 {
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index f409e0b..185c341 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -745,6 +745,13 @@
 			attach_rules(&ops->rules_list, dev);
 		break;
 
+	case NETDEV_CHANGENAME:
+		list_for_each_entry(ops, &net->rules_ops, list) {
+			detach_rules(&ops->rules_list, dev);
+			attach_rules(&ops->rules_list, dev);
+		}
+		break;
+
 	case NETDEV_UNREGISTER:
 		list_for_each_entry(ops, &net->rules_ops, list)
 			detach_rules(&ops->rules_list, dev);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 87577d4..e29e810 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -323,17 +323,6 @@
 	return poff;
 }
 
-static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
-{
-	if (unlikely(queue_index >= dev->real_num_tx_queues)) {
-		net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
-				     dev->name, queue_index,
-				     dev->real_num_tx_queues);
-		return 0;
-	}
-	return queue_index;
-}
-
 static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_XPS
@@ -372,7 +361,7 @@
 #endif
 }
 
-u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
 	int queue_index = sk_tx_queue_get(sk);
@@ -392,7 +381,6 @@
 
 	return queue_index;
 }
-EXPORT_SYMBOL(__netdev_pick_tx);
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
@@ -403,13 +391,13 @@
 	if (dev->real_num_tx_queues != 1) {
 		const struct net_device_ops *ops = dev->netdev_ops;
 		if (ops->ndo_select_queue)
-			queue_index = ops->ndo_select_queue(dev, skb,
-							    accel_priv);
+			queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+							    __netdev_pick_tx);
 		else
 			queue_index = __netdev_pick_tx(dev, skb);
 
 		if (!accel_priv)
-			queue_index = dev_cap_txqueue(dev, queue_index);
+			queue_index = netdev_cap_txqueue(dev, queue_index);
 	}
 
 	skb_set_queue_mapping(skb, queue_index);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index b9e9e0d..e161290 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -766,9 +766,6 @@
 	nht = rcu_dereference_protected(tbl->nht,
 					lockdep_is_held(&tbl->lock));
 
-	if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
-		goto out;
-
 	/*
 	 *	periodically recompute ReachableTime from random function
 	 */
@@ -781,6 +778,9 @@
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
 	}
 
+	if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
+		goto out;
+
 	for (i = 0 ; i < (1 << nht->hash_shift); i++) {
 		np = &nht->hash_buckets[i];
 
@@ -3046,7 +3046,7 @@
 	if (!t)
 		goto err;
 
-	for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) {
+	for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) {
 		t->neigh_vars[i].data += (long) p;
 		t->neigh_vars[i].extra1 = dev;
 		t->neigh_vars[i].extra2 = p;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index c03f3de..df9e6b1 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -742,7 +742,7 @@
 	struct nd_msg *msg;
 	struct ipv6hdr *hdr;
 
-	if (skb->protocol != htons(ETH_P_ARP))
+	if (skb->protocol != htons(ETH_P_IPV6))
 		return false;
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
 		return false;
@@ -948,6 +948,7 @@
 {
 	char *cur=opt, *delim;
 	int ipv6;
+	bool ipversion_set = false;
 
 	if (*cur != '@') {
 		if ((delim = strchr(cur, '@')) == NULL)
@@ -960,6 +961,7 @@
 	cur++;
 
 	if (*cur != '/') {
+		ipversion_set = true;
 		if ((delim = strchr(cur, '/')) == NULL)
 			goto parse_failed;
 		*delim = 0;
@@ -1002,7 +1004,7 @@
 	ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
 	if (ipv6 < 0)
 		goto parse_failed;
-	else if (np->ipv6 != (bool)ipv6)
+	else if (ipversion_set && np->ipv6 != (bool)ipv6)
 		goto parse_failed;
 	else
 		np->ipv6 = (bool)ipv6;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 393b1bc..120eecc 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -374,7 +374,7 @@
 	if (!master_dev)
 		return 0;
 	ops = master_dev->rtnl_link_ops;
-	if (!ops->get_slave_size)
+	if (!ops || !ops->get_slave_size)
 		return 0;
 	/* IFLA_INFO_SLAVE_DATA + nested data */
 	return nla_total_size(sizeof(struct nlattr)) +
@@ -1963,16 +1963,21 @@
 
 		dev->ifindex = ifm->ifi_index;
 
-		if (ops->newlink)
+		if (ops->newlink) {
 			err = ops->newlink(net, dev, tb, data);
-		else
+			/* Drivers should call free_netdev() in ->destructor
+			 * and unregister it on failure so that device could be
+			 * finally freed in rtnl_unlock.
+			 */
+			if (err < 0)
+				goto out;
+		} else {
 			err = register_netdevice(dev);
-
-		if (err < 0) {
-			free_netdev(dev);
-			goto out;
+			if (err < 0) {
+				free_netdev(dev);
+				goto out;
+			}
 		}
-
 		err = rtnl_configure_link(dev, ifm);
 		if (err < 0)
 			unregister_netdevice(dev);
@@ -2116,12 +2121,13 @@
 static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
 				   struct net_device *dev,
 				   u8 *addr, u32 pid, u32 seq,
-				   int type, unsigned int flags)
+				   int type, unsigned int flags,
+				   int nlflags)
 {
 	struct nlmsghdr *nlh;
 	struct ndmsg *ndm;
 
-	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags);
 	if (!nlh)
 		return -EMSGSIZE;
 
@@ -2159,7 +2165,7 @@
 	if (!skb)
 		goto errout;
 
-	err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF);
+	err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto errout;
@@ -2384,7 +2390,8 @@
 
 		err = nlmsg_populate_fdb_fill(skb, dev, ha->addr,
 					      portid, seq,
-					      RTM_NEWNEIGH, NTF_SELF);
+					      RTM_NEWNEIGH, NTF_SELF,
+					      NLM_F_MULTI);
 		if (err < 0)
 			return err;
 skip:
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5976ef0..90b96a1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -707,9 +707,6 @@
 	new->mark		= old->mark;
 	new->skb_iif		= old->skb_iif;
 	__nf_copy(new, old);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-	new->nf_trace		= old->nf_trace;
-#endif
 #ifdef CONFIG_NET_SCHED
 	new->tc_index		= old->tc_index;
 #ifdef CONFIG_NET_CLS_ACT
@@ -2130,25 +2127,31 @@
  *
  *	The `hlen` as calculated by skb_zerocopy_headlen() specifies the
  *	headroom in the `to` buffer.
+ *
+ *	Return value:
+ *	0: everything is OK
+ *	-ENOMEM: couldn't orphan frags of @from due to lack of memory
+ *	-EFAULT: skb_copy_bits() found some problem with skb geometry
  */
-void
-skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
+int
+skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
 {
 	int i, j = 0;
 	int plen = 0; /* length of skb->head fragment */
+	int ret;
 	struct page *page;
 	unsigned int offset;
 
 	BUG_ON(!from->head_frag && !hlen);
 
 	/* dont bother with small payloads */
-	if (len <= skb_tailroom(to)) {
-		skb_copy_bits(from, 0, skb_put(to, len), len);
-		return;
-	}
+	if (len <= skb_tailroom(to))
+		return skb_copy_bits(from, 0, skb_put(to, len), len);
 
 	if (hlen) {
-		skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+		ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+		if (unlikely(ret))
+			return ret;
 		len -= hlen;
 	} else {
 		plen = min_t(int, skb_headlen(from), len);
@@ -2166,6 +2169,11 @@
 	to->len += len + plen;
 	to->data_len += len + plen;
 
+	if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) {
+		skb_tx_error(from);
+		return -ENOMEM;
+	}
+
 	for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
 		if (!len)
 			break;
@@ -2176,6 +2184,8 @@
 		j++;
 	}
 	skb_shinfo(to)->nr_frags = j;
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(skb_zerocopy);
 
@@ -2841,81 +2851,85 @@
 
 /**
  *	skb_segment - Perform protocol segmentation on skb.
- *	@skb: buffer to segment
+ *	@head_skb: buffer to segment
  *	@features: features for the output path (see dev->features)
  *
  *	This function performs segmentation on the given skb.  It returns
  *	a pointer to the first in a list of new skbs for the segments.
  *	In case of error it returns ERR_PTR(err).
  */
-struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
+struct sk_buff *skb_segment(struct sk_buff *head_skb,
+			    netdev_features_t features)
 {
 	struct sk_buff *segs = NULL;
 	struct sk_buff *tail = NULL;
-	struct sk_buff *fskb = skb_shinfo(skb)->frag_list;
-	skb_frag_t *skb_frag = skb_shinfo(skb)->frags;
-	unsigned int mss = skb_shinfo(skb)->gso_size;
-	unsigned int doffset = skb->data - skb_mac_header(skb);
+	struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
+	skb_frag_t *frag = skb_shinfo(head_skb)->frags;
+	unsigned int mss = skb_shinfo(head_skb)->gso_size;
+	unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
+	struct sk_buff *frag_skb = head_skb;
 	unsigned int offset = doffset;
-	unsigned int tnl_hlen = skb_tnl_header_len(skb);
+	unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
 	unsigned int headroom;
 	unsigned int len;
 	__be16 proto;
 	bool csum;
 	int sg = !!(features & NETIF_F_SG);
-	int nfrags = skb_shinfo(skb)->nr_frags;
+	int nfrags = skb_shinfo(head_skb)->nr_frags;
 	int err = -ENOMEM;
 	int i = 0;
 	int pos;
+	int dummy;
 
-	proto = skb_network_protocol(skb);
+	proto = skb_network_protocol(head_skb, &dummy);
 	if (unlikely(!proto))
 		return ERR_PTR(-EINVAL);
 
 	csum = !!can_checksum_protocol(features, proto);
-	__skb_push(skb, doffset);
-	headroom = skb_headroom(skb);
-	pos = skb_headlen(skb);
+	__skb_push(head_skb, doffset);
+	headroom = skb_headroom(head_skb);
+	pos = skb_headlen(head_skb);
 
 	do {
 		struct sk_buff *nskb;
-		skb_frag_t *frag;
+		skb_frag_t *nskb_frag;
 		int hsize;
 		int size;
 
-		len = skb->len - offset;
+		len = head_skb->len - offset;
 		if (len > mss)
 			len = mss;
 
-		hsize = skb_headlen(skb) - offset;
+		hsize = skb_headlen(head_skb) - offset;
 		if (hsize < 0)
 			hsize = 0;
 		if (hsize > len || !sg)
 			hsize = len;
 
-		if (!hsize && i >= nfrags && skb_headlen(fskb) &&
-		    (skb_headlen(fskb) == len || sg)) {
-			BUG_ON(skb_headlen(fskb) > len);
+		if (!hsize && i >= nfrags && skb_headlen(list_skb) &&
+		    (skb_headlen(list_skb) == len || sg)) {
+			BUG_ON(skb_headlen(list_skb) > len);
 
 			i = 0;
-			nfrags = skb_shinfo(fskb)->nr_frags;
-			skb_frag = skb_shinfo(fskb)->frags;
-			pos += skb_headlen(fskb);
+			nfrags = skb_shinfo(list_skb)->nr_frags;
+			frag = skb_shinfo(list_skb)->frags;
+			frag_skb = list_skb;
+			pos += skb_headlen(list_skb);
 
 			while (pos < offset + len) {
 				BUG_ON(i >= nfrags);
 
-				size = skb_frag_size(skb_frag);
+				size = skb_frag_size(frag);
 				if (pos + size > offset + len)
 					break;
 
 				i++;
 				pos += size;
-				skb_frag++;
+				frag++;
 			}
 
-			nskb = skb_clone(fskb, GFP_ATOMIC);
-			fskb = fskb->next;
+			nskb = skb_clone(list_skb, GFP_ATOMIC);
+			list_skb = list_skb->next;
 
 			if (unlikely(!nskb))
 				goto err;
@@ -2936,7 +2950,7 @@
 			__skb_push(nskb, doffset);
 		} else {
 			nskb = __alloc_skb(hsize + doffset + headroom,
-					   GFP_ATOMIC, skb_alloc_rx_flag(skb),
+					   GFP_ATOMIC, skb_alloc_rx_flag(head_skb),
 					   NUMA_NO_NODE);
 
 			if (unlikely(!nskb))
@@ -2952,12 +2966,12 @@
 			segs = nskb;
 		tail = nskb;
 
-		__copy_skb_header(nskb, skb);
-		nskb->mac_len = skb->mac_len;
+		__copy_skb_header(nskb, head_skb);
+		nskb->mac_len = head_skb->mac_len;
 
 		skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
 
-		skb_copy_from_linear_data_offset(skb, -tnl_hlen,
+		skb_copy_from_linear_data_offset(head_skb, -tnl_hlen,
 						 nskb->data - tnl_hlen,
 						 doffset + tnl_hlen);
 
@@ -2966,30 +2980,32 @@
 
 		if (!sg) {
 			nskb->ip_summed = CHECKSUM_NONE;
-			nskb->csum = skb_copy_and_csum_bits(skb, offset,
+			nskb->csum = skb_copy_and_csum_bits(head_skb, offset,
 							    skb_put(nskb, len),
 							    len, 0);
 			continue;
 		}
 
-		frag = skb_shinfo(nskb)->frags;
+		nskb_frag = skb_shinfo(nskb)->frags;
 
-		skb_copy_from_linear_data_offset(skb, offset,
+		skb_copy_from_linear_data_offset(head_skb, offset,
 						 skb_put(nskb, hsize), hsize);
 
-		skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
+		skb_shinfo(nskb)->tx_flags = skb_shinfo(head_skb)->tx_flags &
+			SKBTX_SHARED_FRAG;
 
 		while (pos < offset + len) {
 			if (i >= nfrags) {
-				BUG_ON(skb_headlen(fskb));
+				BUG_ON(skb_headlen(list_skb));
 
 				i = 0;
-				nfrags = skb_shinfo(fskb)->nr_frags;
-				skb_frag = skb_shinfo(fskb)->frags;
+				nfrags = skb_shinfo(list_skb)->nr_frags;
+				frag = skb_shinfo(list_skb)->frags;
+				frag_skb = list_skb;
 
 				BUG_ON(!nfrags);
 
-				fskb = fskb->next;
+				list_skb = list_skb->next;
 			}
 
 			if (unlikely(skb_shinfo(nskb)->nr_frags >=
@@ -3000,27 +3016,30 @@
 				goto err;
 			}
 
-			*frag = *skb_frag;
-			__skb_frag_ref(frag);
-			size = skb_frag_size(frag);
+			if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC)))
+				goto err;
+
+			*nskb_frag = *frag;
+			__skb_frag_ref(nskb_frag);
+			size = skb_frag_size(nskb_frag);
 
 			if (pos < offset) {
-				frag->page_offset += offset - pos;
-				skb_frag_size_sub(frag, offset - pos);
+				nskb_frag->page_offset += offset - pos;
+				skb_frag_size_sub(nskb_frag, offset - pos);
 			}
 
 			skb_shinfo(nskb)->nr_frags++;
 
 			if (pos + size <= offset + len) {
 				i++;
-				skb_frag++;
+				frag++;
 				pos += size;
 			} else {
-				skb_frag_size_sub(frag, pos + size - (offset + len));
+				skb_frag_size_sub(nskb_frag, pos + size - (offset + len));
 				goto skip_fraglist;
 			}
 
-			frag++;
+			nskb_frag++;
 		}
 
 skip_fraglist:
@@ -3034,7 +3053,7 @@
 						  nskb->len - doffset, 0);
 			nskb->ip_summed = CHECKSUM_NONE;
 		}
-	} while ((offset += len) < skb->len);
+	} while ((offset += len) < head_skb->len);
 
 	return segs;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 0c127dc..c0fc6bd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1775,7 +1775,9 @@
 			while (order) {
 				if (npages >= 1 << order) {
 					page = alloc_pages(sk->sk_allocation |
-							   __GFP_COMP | __GFP_NOWARN,
+							   __GFP_COMP |
+							   __GFP_NOWARN |
+							   __GFP_NORETRY,
 							   order);
 					if (page)
 						goto fill_page;
@@ -1845,7 +1847,7 @@
 		gfp_t gfp = prio;
 
 		if (order)
-			gfp |= __GFP_COMP | __GFP_NOWARN;
+			gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
 		pfrag->page = alloc_pages(gfp, order);
 		if (likely(pfrag->page)) {
 			pfrag->offset = 0;
@@ -2355,10 +2357,13 @@
 	if (sk->sk_backlog.tail)
 		__release_sock(sk);
 
+	/* Warning : release_cb() might need to release sk ownership,
+	 * ie call sock_release_ownership(sk) before us.
+	 */
 	if (sk->sk_prot->release_cb)
 		sk->sk_prot->release_cb(sk);
 
-	sk->sk_lock.owned = 0;
+	sock_release_ownership(sk);
 	if (waitqueue_active(&sk->sk_lock.wq))
 		wake_up(&sk->sk_lock.wq);
 	spin_unlock_bh(&sk->sk_lock.slock);
diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c
index c073b81..62b5828 100644
--- a/net/dccp/ccids/lib/tfrc.c
+++ b/net/dccp/ccids/lib/tfrc.c
@@ -8,7 +8,7 @@
 #include "tfrc.h"
 
 #ifdef CONFIG_IP_DCCP_TFRC_DEBUG
-static bool tfrc_debug;
+bool tfrc_debug;
 module_param(tfrc_debug, bool, 0644);
 MODULE_PARM_DESC(tfrc_debug, "Enable TFRC debug messages");
 #endif
diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h
index a3d8f7c..40ee7d6 100644
--- a/net/dccp/ccids/lib/tfrc.h
+++ b/net/dccp/ccids/lib/tfrc.h
@@ -21,6 +21,7 @@
 #include "packet_history.h"
 
 #ifdef CONFIG_IP_DCCP_TFRC_DEBUG
+extern bool tfrc_debug;
 #define tfrc_pr_debug(format, a...)	DCCP_PR_DEBUG(tfrc_debug, format, ##a)
 #else
 #define tfrc_pr_debug(format, a...)
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 2954dcb..4c04848 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -2104,8 +2104,6 @@
 	.notifier_call = dn_device_event,
 };
 
-extern int dn_route_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *);
-
 static struct packet_type dn_dix_packet_type __read_mostly = {
 	.type =		cpu_to_be16(ETH_P_DNA_RT),
 	.func =		dn_route_rcv,
@@ -2353,9 +2351,6 @@
 	.sendpage =	sock_no_sendpage,
 };
 
-void dn_register_sysctl(void);
-void dn_unregister_sysctl(void);
-
 MODULE_DESCRIPTION("The Linux DECnet Network Protocol");
 MODULE_AUTHOR("Linux DECnet Project Team");
 MODULE_LICENSE("GPL");
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 327060c..7ae0d7f6 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -297,7 +297,7 @@
 
 void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx)
 {
-	if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) {
+	if ((dev_idx < 0) || (dev_idx >= HSR_MAX_SLAVE)) {
 		WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx);
 		return;
 	}
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
index 48b25c0..8edfea5 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan.c
@@ -106,7 +106,6 @@
 			   unsigned short type, const void *_daddr,
 			   const void *_saddr, unsigned int len)
 {
-	struct ipv6hdr *hdr;
 	const u8 *saddr = _saddr;
 	const u8 *daddr = _daddr;
 	struct ieee802154_addr sa, da;
@@ -117,8 +116,6 @@
 	if (type != ETH_P_IPV6)
 		return 0;
 
-	hdr = ipv6_hdr(skb);
-
 	if (!saddr)
 		saddr = dev->dev_addr;
 
@@ -533,7 +530,27 @@
 	.create	= lowpan_header_create,
 };
 
+static struct lock_class_key lowpan_tx_busylock;
+static struct lock_class_key lowpan_netdev_xmit_lock_key;
+
+static void lowpan_set_lockdep_class_one(struct net_device *dev,
+					 struct netdev_queue *txq,
+					 void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock,
+			  &lowpan_netdev_xmit_lock_key);
+}
+
+
+static int lowpan_dev_init(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, lowpan_set_lockdep_class_one, NULL);
+	dev->qdisc_tx_busylock = &lowpan_tx_busylock;
+	return 0;
+}
+
 static const struct net_device_ops lowpan_netdev_ops = {
+	.ndo_init		= lowpan_dev_init,
 	.ndo_start_xmit		= lowpan_xmit,
 	.ndo_set_mac_address	= lowpan_set_address,
 };
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ecd2c3f..19ab78a 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1296,8 +1296,11 @@
 
 	segs = ERR_PTR(-EPROTONOSUPPORT);
 
-	/* Note : following gso_segment() might change skb->encapsulation */
-	udpfrag = !skb->encapsulation && proto == IPPROTO_UDP;
+	if (skb->encapsulation &&
+	    skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+		udpfrag = proto == IPPROTO_UDP && encap;
+	else
+		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
 
 	ops = rcu_dereference(inet_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment))
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ac2dff3..bdbf68b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1443,7 +1443,8 @@
 	       + nla_total_size(4) /* IFA_LOCAL */
 	       + nla_total_size(4) /* IFA_BROADCAST */
 	       + nla_total_size(IFNAMSIZ) /* IFA_LABEL */
-	       + nla_total_size(4);  /* IFA_FLAGS */
+	       + nla_total_size(4)  /* IFA_FLAGS */
+	       + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */
 }
 
 static inline u32 cstamp_delta(unsigned long cstamp)
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 1863422f..250be74 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -182,6 +182,14 @@
 	int i;
 	bool csum_err = false;
 
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+	if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
+		/* Looped back packet, drop it! */
+		if (rt_is_output_route(skb_rtable(skb)))
+			goto drop;
+	}
+#endif
+
 	if (parse_gre_header(skb, &tpi, &csum_err) < 0)
 		goto drop;
 
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index bb075fc..3b01959 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -208,7 +208,7 @@
 	}
 
 	work = frag_mem_limit(nf) - nf->low_thresh;
-	while (work > 0) {
+	while (work > 0 || force) {
 		spin_lock(&nf->lru_lock);
 
 		if (list_empty(&nf->lru_list)) {
@@ -278,9 +278,10 @@
 
 	atomic_inc(&qp->refcnt);
 	hlist_add_head(&qp->list, &hb->chain);
+	inet_frag_lru_add(nf, qp);
 	spin_unlock(&hb->chain_lock);
 	read_unlock(&f->lock);
-	inet_frag_lru_add(nf, qp);
+
 	return qp;
 }
 
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index e9f1217..f3869c1 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,71 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+	       !skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu || skb->local_df)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+	unsigned int mtu;
+
+	if (skb->local_df || !skb_is_gso(skb))
+		return false;
+
+	mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
+
+	/* if seglen > mtu, do software segmentation for IP fragmentation on
+	 * output.  DF bit cannot be set since ip_forward would have sent
+	 * icmp error.
+	 */
+	return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	features = netif_skb_dev_features(skb, dst->dev);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = dst_output(segs);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
+
+	return ret;
+}
+
 static int ip_forward_finish(struct sk_buff *skb)
 {
 	struct ip_options *opt	= &(IPCB(skb)->opt);
@@ -49,6 +114,9 @@
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
+	if (ip_gso_exceeds_dst_mtu(skb))
+		return ip_forward_finish_gso(skb);
+
 	return dst_output(skb);
 }
 
@@ -91,8 +159,7 @@
 
 	IPCB(skb)->flags |= IPSKB_FORWARDED;
 	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
-	if (unlikely(skb->len > mtu && !skb_is_gso(skb) &&
-		     (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+	if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) {
 		IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 			  htonl(mtu));
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8971780..73c6b63 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -422,9 +422,6 @@
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-	to->nf_trace = from->nf_trace;
-#endif
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	to->ipvs_property = from->ipvs_property;
 #endif
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index bd28f38..a82a22d 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -93,84 +93,33 @@
 	tunnel_dst_set(t, NULL);
 }
 
-static void tunnel_dst_reset_all(struct ip_tunnel *t)
+void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
 {
 	int i;
 
 	for_each_possible_cpu(i)
 		__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
 }
+EXPORT_SYMBOL(ip_tunnel_dst_reset_all);
 
-static struct dst_entry *tunnel_dst_get(struct ip_tunnel *t)
+static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
 {
 	struct dst_entry *dst;
 
 	rcu_read_lock();
 	dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst);
-	if (dst)
+	if (dst) {
+		if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
+			rcu_read_unlock();
+			tunnel_dst_reset(t);
+			return NULL;
+		}
 		dst_hold(dst);
+	}
 	rcu_read_unlock();
-	return dst;
+	return (struct rtable *)dst;
 }
 
-static struct dst_entry *tunnel_dst_check(struct ip_tunnel *t, u32 cookie)
-{
-	struct dst_entry *dst = tunnel_dst_get(t);
-
-	if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
-		tunnel_dst_reset(t);
-		return NULL;
-	}
-
-	return dst;
-}
-
-/* Often modified stats are per cpu, other are shared (netdev->stats) */
-struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
-						struct rtnl_link_stats64 *tot)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_sw_netstats *tstats =
-						   per_cpu_ptr(dev->tstats, i);
-		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
-		unsigned int start;
-
-		do {
-			start = u64_stats_fetch_begin_bh(&tstats->syncp);
-			rx_packets = tstats->rx_packets;
-			tx_packets = tstats->tx_packets;
-			rx_bytes = tstats->rx_bytes;
-			tx_bytes = tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
-		tot->rx_packets += rx_packets;
-		tot->tx_packets += tx_packets;
-		tot->rx_bytes   += rx_bytes;
-		tot->tx_bytes   += tx_bytes;
-	}
-
-	tot->multicast = dev->stats.multicast;
-
-	tot->rx_crc_errors = dev->stats.rx_crc_errors;
-	tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
-	tot->rx_length_errors = dev->stats.rx_length_errors;
-	tot->rx_frame_errors = dev->stats.rx_frame_errors;
-	tot->rx_errors = dev->stats.rx_errors;
-
-	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
-	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
-	tot->tx_dropped = dev->stats.tx_dropped;
-	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
-	tot->tx_errors = dev->stats.tx_errors;
-
-	tot->collisions  = dev->stats.collisions;
-
-	return tot;
-}
-EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
-
 static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
 				__be16 flags, __be32 key)
 {
@@ -467,9 +416,6 @@
 
 #ifdef CONFIG_NET_IPGRE_BROADCAST
 	if (ipv4_is_multicast(iph->daddr)) {
-		/* Looped back packet, drop it! */
-		if (rt_is_output_route(skb_rtable(skb)))
-			goto drop;
 		tunnel->dev->stats.multicast++;
 		skb->pkt_type = PACKET_BROADCAST;
 	}
@@ -584,7 +530,7 @@
 	struct flowi4 fl4;
 	u8     tos, ttl;
 	__be16 df;
-	struct rtable *rt = NULL;	/* Route to the other host */
+	struct rtable *rt;		/* Route to the other host */
 	unsigned int max_headroom;	/* The extra header space needed */
 	__be32 dst;
 	int err;
@@ -657,8 +603,7 @@
 	init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
 			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
 
-	if (connected)
-		rt = (struct rtable *)tunnel_dst_check(tunnel, 0);
+	rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL;
 
 	if (!rt) {
 		rt = ip_route_output_key(tunnel->net, &fl4);
@@ -766,7 +711,7 @@
 		if (set_mtu)
 			dev->mtu = mtu;
 	}
-	tunnel_dst_reset_all(t);
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(dev);
 }
 
@@ -1095,7 +1040,7 @@
 	if (itn->fb_tunnel_dev != dev)
 		ip_tunnel_del(netdev_priv(dev));
 
-	tunnel_dst_reset_all(tunnel);
+	ip_tunnel_dst_reset_all(tunnel);
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_uninit);
 
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6156f4e..8d69626 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -148,3 +148,49 @@
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
+
+/* Often modified stats are per cpu, other are shared (netdev->stats) */
+struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
+						struct rtnl_link_stats64 *tot)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		const struct pcpu_sw_netstats *tstats =
+						   per_cpu_ptr(dev->tstats, i);
+		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin_bh(&tstats->syncp);
+			rx_packets = tstats->rx_packets;
+			tx_packets = tstats->tx_packets;
+			rx_bytes = tstats->rx_bytes;
+			tx_bytes = tstats->tx_bytes;
+		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+
+		tot->rx_packets += rx_packets;
+		tot->tx_packets += tx_packets;
+		tot->rx_bytes   += rx_bytes;
+		tot->tx_bytes   += tx_bytes;
+	}
+
+	tot->multicast = dev->stats.multicast;
+
+	tot->rx_crc_errors = dev->stats.rx_crc_errors;
+	tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
+	tot->rx_length_errors = dev->stats.rx_length_errors;
+	tot->rx_frame_errors = dev->stats.rx_frame_errors;
+	tot->rx_errors = dev->stats.rx_errors;
+
+	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
+	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
+	tot->tx_dropped = dev->stats.tx_dropped;
+	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
+	tot->tx_errors = dev->stats.tx_errors;
+
+	tot->collisions  = dev->stats.collisions;
+
+	return tot;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index efa1138..b3e86ea 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -273,7 +273,7 @@
 
 		msleep(1);
 
-		if time_before(jiffies, next_msg)
+		if (time_before(jiffies, next_msg))
 			continue;
 
 		elapsed = jiffies_to_msecs(jiffies - start);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index b9b3472..2886357 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2255,13 +2255,14 @@
 }
 
 static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
-			    u32 portid, u32 seq, struct mfc_cache *c, int cmd)
+			    u32 portid, u32 seq, struct mfc_cache *c, int cmd,
+			    int flags)
 {
 	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
 	int err;
 
-	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -2329,7 +2330,7 @@
 	if (skb == NULL)
 		goto errout;
 
-	err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+	err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
 	if (err < 0)
 		goto errout;
 
@@ -2368,7 +2369,8 @@
 				if (ipmr_fill_mroute(mrt, skb,
 						     NETLINK_CB(cb->skb).portid,
 						     cb->nlh->nlmsg_seq,
-						     mfc, RTM_NEWROUTE) < 0)
+						     mfc, RTM_NEWROUTE,
+						     NLM_F_MULTI) < 0)
 					goto done;
 next_entry:
 				e++;
@@ -2382,7 +2384,8 @@
 			if (ipmr_fill_mroute(mrt, skb,
 					     NETLINK_CB(cb->skb).portid,
 					     cb->nlh->nlmsg_seq,
-					     mfc, RTM_NEWROUTE) < 0) {
+					     mfc, RTM_NEWROUTE,
+					     NLM_F_MULTI) < 0) {
 				spin_unlock_bh(&mfc_unres_lock);
 				goto done;
 			}
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 81c6910..a26ce03 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -61,6 +61,11 @@
 	  packet transformations such as the source, destination address and
 	  source and destination ports.
 
+config NFT_REJECT_IPV4
+	depends on NF_TABLES_IPV4
+	default NFT_REJECT
+	tristate
+
 config NF_TABLES_ARP
 	depends on NF_TABLES
 	tristate "ARP nf_tables support"
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index c16be9d..90b8240 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -30,6 +30,7 @@
 obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
+obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
 obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # generic IP tables 
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index 9eea059d..574f7eb 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -229,7 +229,10 @@
 			ret = nf_ct_expect_related(rtcp_exp);
 			if (ret == 0)
 				break;
-			else if (ret != -EBUSY) {
+			else if (ret == -EBUSY) {
+				nf_ct_unexpect_related(rtp_exp);
+				continue;
+			} else if (ret < 0) {
 				nf_ct_unexpect_related(rtp_exp);
 				nated_port = 0;
 				break;
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index d551e31..7c67667 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -1198,8 +1198,8 @@
 		map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
 	} else {
 		/* DNAT replies */
-		map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip);
-		map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
+		map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip);
+		map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip);
 	}
 
 	if (map.from == map.to)
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
new file mode 100644
index 0000000..e79718a
--- /dev/null
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -0,0 +1,75 @@
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/icmp.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/nft_reject.h>
+
+void nft_reject_ipv4_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt)
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+		nf_send_unreach(pkt->skb, priv->icmp_code);
+		break;
+	case NFT_REJECT_TCP_RST:
+		nf_send_reset(pkt->skb, pkt->ops->hooknum);
+		break;
+	}
+
+	data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nft_reject_ipv4_eval);
+
+static struct nft_expr_type nft_reject_ipv4_type;
+static const struct nft_expr_ops nft_reject_ipv4_ops = {
+	.type		= &nft_reject_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+	.eval		= nft_reject_ipv4_eval,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "reject",
+	.ops		= &nft_reject_ipv4_ops,
+	.policy		= nft_reject_policy,
+	.maxattr	= NFTA_REJECT_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_reject_ipv4_module_init(void)
+{
+	return nft_register_expr(&nft_reject_ipv4_type);
+}
+
+static void __exit nft_reject_ipv4_module_exit(void)
+{
+	nft_unregister_expr(&nft_reject_ipv4_type);
+}
+
+module_init(nft_reject_ipv4_module_init);
+module_exit(nft_reject_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject");
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 25071b4..4c011ec 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1597,6 +1597,7 @@
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	RT_CACHE_STAT_INC(in_slow_tot);
 
 	rth->dst.input = ip_forward;
 	rth->dst.output = ip_output;
@@ -1695,10 +1696,11 @@
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
 	err = fib_lookup(net, &fl4, &res);
-	if (err != 0)
+	if (err != 0) {
+		if (!IN_DEV_FORWARD(in_dev))
+			err = -EHOSTUNREACH;
 		goto no_route;
-
-	RT_CACHE_STAT_INC(in_slow_tot);
+	}
 
 	if (res.type == RTN_BROADCAST)
 		goto brd_input;
@@ -1712,8 +1714,10 @@
 		goto local_input;
 	}
 
-	if (!IN_DEV_FORWARD(in_dev))
+	if (!IN_DEV_FORWARD(in_dev)) {
+		err = -EHOSTUNREACH;
 		goto no_route;
+	}
 	if (res.type != RTN_UNICAST)
 		goto martian_destination;
 
@@ -1768,6 +1772,7 @@
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	RT_CACHE_STAT_INC(in_slow_tot);
 	if (res.type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;
 		rth->dst.error= -err;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4475b3b..97c8f56 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1044,7 +1044,8 @@
 	}
 }
 
-static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
+				int *copied, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int err, flags;
@@ -1059,11 +1060,12 @@
 	if (unlikely(tp->fastopen_req == NULL))
 		return -ENOBUFS;
 	tp->fastopen_req->data = msg;
+	tp->fastopen_req->size = size;
 
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
 	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
 				    msg->msg_namelen, flags);
-	*size = tp->fastopen_req->copied;
+	*copied = tp->fastopen_req->copied;
 	tcp_free_fastopen_req(tp);
 	return err;
 }
@@ -1083,7 +1085,7 @@
 
 	flags = msg->msg_flags;
 	if (flags & MSG_FASTOPEN) {
-		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
 		else if (err)
@@ -2229,7 +2231,7 @@
 	/*	This is a (useful) BSD violating of the RFC. There is a
 	 *	problem with TCP as specified in that the other end could
 	 *	keep a socket open forever with no application left this end.
-	 *	We use a 3 minute timeout (about the same as BSD) then kill
+	 *	We use a 1 minute timeout (about the same as BSD) then kill
 	 *	our end. If they send after that then tough - BUT: long enough
 	 *	that we won't make the old 4*rto = almost no time - whoops
 	 *	reset mistake.
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index ad37bf1..2388275 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -290,8 +290,7 @@
 	left = tp->snd_cwnd - in_flight;
 	if (sk_can_gso(sk) &&
 	    left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
-	    left * tp->mss_cache < sk->sk_gso_max_size &&
-	    left < sk->sk_gso_max_segs)
+	    left < tp->xmit_size_goal_segs)
 		return true;
 	return left <= tcp_max_tso_deferred_mss(tp);
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 65cf90e..eeaac39 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -671,6 +671,7 @@
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	long m = mrtt; /* RTT */
+	u32 srtt = tp->srtt;
 
 	/*	The following amusing code comes from Jacobson's
 	 *	article in SIGCOMM '88.  Note that rtt and mdev
@@ -688,11 +689,9 @@
 	 * does not matter how to _calculate_ it. Seems, it was trap
 	 * that VJ failed to avoid. 8)
 	 */
-	if (m == 0)
-		m = 1;
-	if (tp->srtt != 0) {
-		m -= (tp->srtt >> 3);	/* m is now error in rtt est */
-		tp->srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
+	if (srtt != 0) {
+		m -= (srtt >> 3);	/* m is now error in rtt est */
+		srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
 		if (m < 0) {
 			m = -m;		/* m is now abs(error) */
 			m -= (tp->mdev >> 2);   /* similar update on mdev */
@@ -723,11 +722,12 @@
 		}
 	} else {
 		/* no previous measure. */
-		tp->srtt = m << 3;	/* take the measured time to be rtt */
+		srtt = m << 3;		/* take the measured time to be rtt */
 		tp->mdev = m << 1;	/* make sure rto = 3*rtt */
 		tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
 		tp->rtt_seq = tp->snd_nxt;
 	}
+	tp->srtt = max(1U, srtt);
 }
 
 /* Set the sk_pacing_rate to allow proper sizing of TSO packets.
@@ -746,8 +746,10 @@
 
 	rate *= max(tp->snd_cwnd, tp->packets_out);
 
-	/* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
-	 * be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
+	/* Correction for small srtt and scheduling constraints.
+	 * For small rtt, consider noise is too high, and use
+	 * the minimal value (srtt = 1 -> 125 us for HZ=1000)
+	 *
 	 * We probably need usec resolution in the future.
 	 * Note: This also takes care of possible srtt=0 case,
 	 * when tcp_rtt_estimator() was not yet called.
@@ -1943,8 +1945,9 @@
 		if (skb == tcp_send_head(sk))
 			break;
 
-		if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
+		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
 			tp->undo_marker = 0;
+
 		TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
 		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) {
 			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3cf9765..1e4eac7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2628,7 +2628,7 @@
 {
 	__be32 dest, src;
 	__u16 destp, srcp;
-	long delta = tw->tw_ttd - jiffies;
+	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
 	dest  = tw->tw_daddr;
 	src   = tw->tw_rcv_saddr;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 03d26b8..17a11e6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -698,7 +698,8 @@
 	if ((1 << sk->sk_state) &
 	    (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
 	     TCPF_CLOSE_WAIT  | TCPF_LAST_ACK))
-		tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
+		tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+			       0, GFP_ATOMIC);
 }
 /*
  * One tasklet per cpu tries to send more skbs.
@@ -766,6 +767,17 @@
 	if (flags & (1UL << TCP_TSQ_DEFERRED))
 		tcp_tsq_handler(sk);
 
+	/* Here begins the tricky part :
+	 * We are called from release_sock() with :
+	 * 1) BH disabled
+	 * 2) sk_lock.slock spinlock held
+	 * 3) socket owned by us (sk->sk_lock.owned == 1)
+	 *
+	 * But following code is meant to be called from BH handlers,
+	 * so we should keep BH disabled, but early release socket ownership
+	 */
+	sock_release_ownership(sk);
+
 	if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
 		tcp_write_timer_handler(sk);
 		__sock_put(sk);
@@ -863,8 +875,8 @@
 
 		if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
 			     fclone->fclone == SKB_FCLONE_CLONE))
-			NET_INC_STATS_BH(sock_net(sk),
-					 LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
+			NET_INC_STATS(sock_net(sk),
+				      LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
 
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
@@ -1904,7 +1916,15 @@
 
 		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
-			break;
+			/* It is possible TX completion already happened
+			 * before we set TSQ_THROTTLED, so we must
+			 * test again the condition.
+			 * We abuse smp_mb__after_clear_bit() because
+			 * there is no smp_mb__after_set_bit() yet
+			 */
+			smp_mb__after_clear_bit();
+			if (atomic_read(&sk->sk_wmem_alloc) > limit)
+				break;
 		}
 
 		limit = mss_now;
@@ -1977,7 +1997,7 @@
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * in Open state, that are either limited by cwnd or application.
 	 */
-	if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out ||
+	if (sysctl_tcp_early_retrans < 3 || !tp->srtt || !tp->packets_out ||
 	    !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
 		return false;
 
@@ -2328,6 +2348,7 @@
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned int cur_mss;
+	int err;
 
 	/* Inconslusive MTU probe */
 	if (icsk->icsk_mtup.probe_size) {
@@ -2391,11 +2412,15 @@
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
 						   GFP_ATOMIC);
-		return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-			      -ENOBUFS;
+		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+			     -ENOBUFS;
 	} else {
-		return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
+
+	if (likely(!err))
+		TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+	return err;
 }
 
 int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
@@ -2899,7 +2924,12 @@
 	space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
 		MAX_TCP_OPTION_SPACE;
 
-	syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
+	space = min_t(size_t, space, fo->size);
+
+	/* limit to order-0 allocations */
+	space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
+
+	syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
 				   sk->sk_allocation);
 	if (syn_data == NULL)
 		goto fallback;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 25f5cee..88b4023 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -17,6 +17,8 @@
 static DEFINE_SPINLOCK(udp_offload_lock);
 static struct udp_offload_priv __rcu *udp_offload_base __read_mostly;
 
+#define udp_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&udp_offload_lock))
+
 struct udp_offload_priv {
 	struct udp_offload	*offload;
 	struct rcu_head		rcu;
@@ -100,8 +102,7 @@
 
 int udp_add_offload(struct udp_offload *uo)
 {
-	struct udp_offload_priv __rcu **head = &udp_offload_base;
-	struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_KERNEL);
+	struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_ATOMIC);
 
 	if (!new_offload)
 		return -ENOMEM;
@@ -109,8 +110,8 @@
 	new_offload->offload = uo;
 
 	spin_lock(&udp_offload_lock);
-	rcu_assign_pointer(new_offload->next, rcu_dereference(*head));
-	rcu_assign_pointer(*head, new_offload);
+	new_offload->next = udp_offload_base;
+	rcu_assign_pointer(udp_offload_base, new_offload);
 	spin_unlock(&udp_offload_lock);
 
 	return 0;
@@ -130,12 +131,12 @@
 
 	spin_lock(&udp_offload_lock);
 
-	uo_priv = rcu_dereference(*head);
+	uo_priv = udp_deref_protected(*head);
 	for (; uo_priv != NULL;
-		uo_priv = rcu_dereference(*head)) {
-
+	     uo_priv = udp_deref_protected(*head)) {
 		if (uo_priv->offload == uo) {
-			rcu_assign_pointer(*head, rcu_dereference(uo_priv->next));
+			rcu_assign_pointer(*head,
+					   udp_deref_protected(uo_priv->next));
 			goto unlock;
 		}
 		head = &uo_priv->next;
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index d92e558..438a73a 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -138,6 +138,7 @@
 config IPV6_VTI
 tristate "Virtual (secure) IPv6: tunneling"
 	select IPV6_TUNNEL
+	select NET_IP_TUNNEL
 	depends on INET6_XFRM_MODE_TUNNEL
 	---help---
 	Tunneling means encapsulating data of one protocol type within
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ad23569..6c7fa08 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -133,10 +133,12 @@
 static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE];
 static DEFINE_SPINLOCK(addrconf_hash_lock);
 
-static void addrconf_verify(unsigned long);
+static void addrconf_verify(void);
+static void addrconf_verify_rtnl(void);
+static void addrconf_verify_work(struct work_struct *);
 
-static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0);
-static DEFINE_SPINLOCK(addrconf_verify_lock);
+static struct workqueue_struct *addrconf_wq;
+static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work);
 
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
@@ -151,7 +153,7 @@
 						  u32 flags, u32 noflags);
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp);
-static void addrconf_dad_timer(unsigned long data);
+static void addrconf_dad_work(struct work_struct *w);
 static void addrconf_dad_completed(struct inet6_ifaddr *ifp);
 static void addrconf_dad_run(struct inet6_dev *idev);
 static void addrconf_rs_timer(unsigned long data);
@@ -247,9 +249,9 @@
 		__in6_dev_put(idev);
 }
 
-static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp)
+static void addrconf_del_dad_work(struct inet6_ifaddr *ifp)
 {
-	if (del_timer(&ifp->dad_timer))
+	if (cancel_delayed_work(&ifp->dad_work))
 		__in6_ifa_put(ifp);
 }
 
@@ -261,12 +263,12 @@
 	mod_timer(&idev->rs_timer, jiffies + when);
 }
 
-static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp,
-				   unsigned long when)
+static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
+				   unsigned long delay)
 {
-	if (!timer_pending(&ifp->dad_timer))
+	if (!delayed_work_pending(&ifp->dad_work))
 		in6_ifa_hold(ifp);
-	mod_timer(&ifp->dad_timer, jiffies + when);
+	mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
 }
 
 static int snmp6_alloc_dev(struct inet6_dev *idev)
@@ -751,8 +753,9 @@
 
 	in6_dev_put(ifp->idev);
 
-	if (del_timer(&ifp->dad_timer))
-		pr_notice("Timer is still running, when freeing ifa=%p\n", ifp);
+	if (cancel_delayed_work(&ifp->dad_work))
+		pr_notice("delayed DAD work was pending while freeing ifa=%p\n",
+			  ifp);
 
 	if (ifp->state != INET6_IFADDR_STATE_DEAD) {
 		pr_warn("Freeing alive inet6 address %p\n", ifp);
@@ -849,8 +852,7 @@
 
 	spin_lock_init(&ifa->lock);
 	spin_lock_init(&ifa->state_lock);
-	setup_timer(&ifa->dad_timer, addrconf_dad_timer,
-		    (unsigned long)ifa);
+	INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work);
 	INIT_HLIST_NODE(&ifa->addr_lst);
 	ifa->scope = scope;
 	ifa->prefix_len = pfxlen;
@@ -990,6 +992,8 @@
 	enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP;
 	unsigned long expires;
 
+	ASSERT_RTNL();
+
 	spin_lock_bh(&ifp->state_lock);
 	state = ifp->state;
 	ifp->state = INET6_IFADDR_STATE_DEAD;
@@ -1021,7 +1025,7 @@
 
 	write_unlock_bh(&ifp->idev->lock);
 
-	addrconf_del_dad_timer(ifp);
+	addrconf_del_dad_work(ifp);
 
 	ipv6_ifa_notify(RTM_DELADDR, ifp);
 
@@ -1103,8 +1107,11 @@
 	 * Lifetime is greater than REGEN_ADVANCE time units.  In particular,
 	 * an implementation must not create a temporary address with a zero
 	 * Preferred Lifetime.
+	 * Use age calculation as in addrconf_verify to avoid unnecessary
+	 * temporary addresses being generated.
 	 */
-	if (tmp_prefered_lft <= regen_advance) {
+	age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+	if (tmp_prefered_lft <= regen_advance + age) {
 		in6_ifa_put(ifp);
 		in6_dev_put(idev);
 		ret = -1;
@@ -1601,7 +1608,7 @@
 {
 	if (ifp->flags&IFA_F_PERMANENT) {
 		spin_lock_bh(&ifp->lock);
-		addrconf_del_dad_timer(ifp);
+		addrconf_del_dad_work(ifp);
 		ifp->flags |= IFA_F_TENTATIVE;
 		if (dad_failed)
 			ifp->flags |= IFA_F_DADFAILED;
@@ -1622,20 +1629,21 @@
 			spin_unlock_bh(&ifp->lock);
 		}
 		ipv6_del_addr(ifp);
-	} else
+	} else {
 		ipv6_del_addr(ifp);
+	}
 }
 
 static int addrconf_dad_end(struct inet6_ifaddr *ifp)
 {
 	int err = -ENOENT;
 
-	spin_lock(&ifp->state_lock);
+	spin_lock_bh(&ifp->state_lock);
 	if (ifp->state == INET6_IFADDR_STATE_DAD) {
 		ifp->state = INET6_IFADDR_STATE_POSTDAD;
 		err = 0;
 	}
-	spin_unlock(&ifp->state_lock);
+	spin_unlock_bh(&ifp->state_lock);
 
 	return err;
 }
@@ -1668,7 +1676,12 @@
 		}
 	}
 
-	addrconf_dad_stop(ifp, 1);
+	spin_lock_bh(&ifp->state_lock);
+	/* transition from _POSTDAD to _ERRDAD */
+	ifp->state = INET6_IFADDR_STATE_ERRDAD;
+	spin_unlock_bh(&ifp->state_lock);
+
+	addrconf_mod_dad_work(ifp, 0);
 }
 
 /* Join to solicited addr multicast group. */
@@ -1677,6 +1690,8 @@
 {
 	struct in6_addr maddr;
 
+	ASSERT_RTNL();
+
 	if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))
 		return;
 
@@ -1688,6 +1703,8 @@
 {
 	struct in6_addr maddr;
 
+	ASSERT_RTNL();
+
 	if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP))
 		return;
 
@@ -1698,6 +1715,9 @@
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
+
+	ASSERT_RTNL();
+
 	if (ifp->prefix_len >= 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -1709,6 +1729,9 @@
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
+
+	ASSERT_RTNL();
+
 	if (ifp->prefix_len >= 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -2268,11 +2291,13 @@
 				return;
 			}
 
-			ifp->flags |= IFA_F_MANAGETEMPADDR;
 			update_lft = 0;
 			create = 1;
+			spin_lock_bh(&ifp->lock);
+			ifp->flags |= IFA_F_MANAGETEMPADDR;
 			ifp->cstamp = jiffies;
 			ifp->tokenized = tokenized;
+			spin_unlock_bh(&ifp->lock);
 			addrconf_dad_start(ifp);
 		}
 
@@ -2323,7 +2348,7 @@
 					 create, now);
 
 			in6_ifa_put(ifp);
-			addrconf_verify(0);
+			addrconf_verify();
 		}
 	}
 	inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
@@ -2472,7 +2497,7 @@
 			manage_tempaddrs(idev, ifp, valid_lft, prefered_lft,
 					 true, jiffies);
 		in6_ifa_put(ifp);
-		addrconf_verify(0);
+		addrconf_verify_rtnl();
 		return 0;
 	}
 
@@ -2783,6 +2808,8 @@
 	ipv6_addr_set(&addr,  htonl(0xFE800000), 0, 0, 0);
 	if (!ipv6_generate_eui64(addr.s6_addr + 8, dev))
 		addrconf_add_linklocal(idev, &addr);
+	else
+		addrconf_prefix_route(&addr, 64, dev, 0, 0);
 }
 #endif
 
@@ -3006,7 +3033,7 @@
 		hlist_for_each_entry_rcu(ifa, h, addr_lst) {
 			if (ifa->idev == idev) {
 				hlist_del_init_rcu(&ifa->addr_lst);
-				addrconf_del_dad_timer(ifa);
+				addrconf_del_dad_work(ifa);
 				goto restart;
 			}
 		}
@@ -3044,7 +3071,7 @@
 	while (!list_empty(&idev->addr_list)) {
 		ifa = list_first_entry(&idev->addr_list,
 				       struct inet6_ifaddr, if_list);
-		addrconf_del_dad_timer(ifa);
+		addrconf_del_dad_work(ifa);
 
 		list_del(&ifa->if_list);
 
@@ -3143,10 +3170,10 @@
 		rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1);
 
 	ifp->dad_probes = idev->cnf.dad_transmits;
-	addrconf_mod_dad_timer(ifp, rand_num);
+	addrconf_mod_dad_work(ifp, rand_num);
 }
 
-static void addrconf_dad_start(struct inet6_ifaddr *ifp)
+static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net_device *dev = idev->dev;
@@ -3198,25 +3225,68 @@
 	read_unlock_bh(&idev->lock);
 }
 
-static void addrconf_dad_timer(unsigned long data)
+static void addrconf_dad_start(struct inet6_ifaddr *ifp)
 {
-	struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data;
+	bool begin_dad = false;
+
+	spin_lock_bh(&ifp->state_lock);
+	if (ifp->state != INET6_IFADDR_STATE_DEAD) {
+		ifp->state = INET6_IFADDR_STATE_PREDAD;
+		begin_dad = true;
+	}
+	spin_unlock_bh(&ifp->state_lock);
+
+	if (begin_dad)
+		addrconf_mod_dad_work(ifp, 0);
+}
+
+static void addrconf_dad_work(struct work_struct *w)
+{
+	struct inet6_ifaddr *ifp = container_of(to_delayed_work(w),
+						struct inet6_ifaddr,
+						dad_work);
 	struct inet6_dev *idev = ifp->idev;
 	struct in6_addr mcaddr;
 
+	enum {
+		DAD_PROCESS,
+		DAD_BEGIN,
+		DAD_ABORT,
+	} action = DAD_PROCESS;
+
+	rtnl_lock();
+
+	spin_lock_bh(&ifp->state_lock);
+	if (ifp->state == INET6_IFADDR_STATE_PREDAD) {
+		action = DAD_BEGIN;
+		ifp->state = INET6_IFADDR_STATE_DAD;
+	} else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) {
+		action = DAD_ABORT;
+		ifp->state = INET6_IFADDR_STATE_POSTDAD;
+	}
+	spin_unlock_bh(&ifp->state_lock);
+
+	if (action == DAD_BEGIN) {
+		addrconf_dad_begin(ifp);
+		goto out;
+	} else if (action == DAD_ABORT) {
+		addrconf_dad_stop(ifp, 1);
+		goto out;
+	}
+
 	if (!ifp->dad_probes && addrconf_dad_end(ifp))
 		goto out;
 
-	write_lock(&idev->lock);
+	write_lock_bh(&idev->lock);
 	if (idev->dead || !(idev->if_flags & IF_READY)) {
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 		goto out;
 	}
 
 	spin_lock(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_DEAD) {
 		spin_unlock(&ifp->lock);
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 		goto out;
 	}
 
@@ -3227,7 +3297,7 @@
 
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
 		spin_unlock(&ifp->lock);
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 
 		addrconf_dad_completed(ifp);
 
@@ -3235,16 +3305,17 @@
 	}
 
 	ifp->dad_probes--;
-	addrconf_mod_dad_timer(ifp,
-			       NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
+	addrconf_mod_dad_work(ifp,
+			      NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
 	spin_unlock(&ifp->lock);
-	write_unlock(&idev->lock);
+	write_unlock_bh(&idev->lock);
 
 	/* send a neighbour solicitation for our addr */
 	addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
 	ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any);
 out:
 	in6_ifa_put(ifp);
+	rtnl_unlock();
 }
 
 /* ifp->idev must be at least read locked */
@@ -3271,7 +3342,7 @@
 	struct in6_addr lladdr;
 	bool send_rs, send_mld;
 
-	addrconf_del_dad_timer(ifp);
+	addrconf_del_dad_work(ifp);
 
 	/*
 	 *	Configure the address for reception. Now it is valid.
@@ -3512,23 +3583,23 @@
  *	Periodic address status verification
  */
 
-static void addrconf_verify(unsigned long foo)
+static void addrconf_verify_rtnl(void)
 {
 	unsigned long now, next, next_sec, next_sched;
 	struct inet6_ifaddr *ifp;
 	int i;
 
+	ASSERT_RTNL();
+
 	rcu_read_lock_bh();
-	spin_lock(&addrconf_verify_lock);
 	now = jiffies;
 	next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
 
-	del_timer(&addr_chk_timer);
+	cancel_delayed_work(&addr_chk_work);
 
 	for (i = 0; i < IN6_ADDR_HSIZE; i++) {
 restart:
-		hlist_for_each_entry_rcu_bh(ifp,
-					 &inet6_addr_lst[i], addr_lst) {
+		hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) {
 			unsigned long age;
 
 			/* When setting preferred_lft to a value not zero or
@@ -3623,13 +3694,22 @@
 
 	ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n",
 	      now, next, next_sec, next_sched);
-
-	addr_chk_timer.expires = next_sched;
-	add_timer(&addr_chk_timer);
-	spin_unlock(&addrconf_verify_lock);
+	mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now);
 	rcu_read_unlock_bh();
 }
 
+static void addrconf_verify_work(struct work_struct *w)
+{
+	rtnl_lock();
+	addrconf_verify_rtnl();
+	rtnl_unlock();
+}
+
+static void addrconf_verify(void)
+{
+	mod_delayed_work(addrconf_wq, &addr_chk_work, 0);
+}
+
 static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local,
 				     struct in6_addr **peer_pfx)
 {
@@ -3686,6 +3766,8 @@
 	bool was_managetempaddr;
 	bool had_prefixroute;
 
+	ASSERT_RTNL();
+
 	if (!valid_lft || (prefered_lft > valid_lft))
 		return -EINVAL;
 
@@ -3751,7 +3833,7 @@
 				 !was_managetempaddr, jiffies);
 	}
 
-	addrconf_verify(0);
+	addrconf_verify_rtnl();
 
 	return 0;
 }
@@ -4381,6 +4463,8 @@
 	bool update_rs = false;
 	struct in6_addr ll_addr;
 
+	ASSERT_RTNL();
+
 	if (token == NULL)
 		return -EINVAL;
 	if (ipv6_addr_any(token))
@@ -4429,7 +4513,7 @@
 	}
 
 	write_unlock_bh(&idev->lock);
-	addrconf_verify(0);
+	addrconf_verify_rtnl();
 	return 0;
 }
 
@@ -4631,6 +4715,9 @@
 {
 	struct net *net = dev_net(ifp->idev->dev);
 
+	if (event)
+		ASSERT_RTNL();
+
 	inet6_ifa_notify(event ? : RTM_NEWADDR, ifp);
 
 	switch (event) {
@@ -5239,6 +5326,12 @@
 	if (err < 0)
 		goto out_addrlabel;
 
+	addrconf_wq = create_workqueue("ipv6_addrconf");
+	if (!addrconf_wq) {
+		err = -ENOMEM;
+		goto out_nowq;
+	}
+
 	/* The addrconf netdev notifier requires that loopback_dev
 	 * has it's ipv6 private information allocated and setup
 	 * before it can bring up and give link-local addresses
@@ -5269,7 +5362,7 @@
 
 	register_netdevice_notifier(&ipv6_dev_notf);
 
-	addrconf_verify(0);
+	addrconf_verify();
 
 	rtnl_af_register(&inet6_ops);
 
@@ -5297,6 +5390,8 @@
 	rtnl_af_unregister(&inet6_ops);
 	unregister_netdevice_notifier(&ipv6_dev_notf);
 errlo:
+	destroy_workqueue(addrconf_wq);
+out_nowq:
 	unregister_pernet_subsys(&addrconf_ops);
 out_addrlabel:
 	ipv6_addr_label_cleanup();
@@ -5332,7 +5427,8 @@
 	for (i = 0; i < IN6_ADDR_HSIZE; i++)
 		WARN_ON(!hlist_empty(&inet6_addr_lst[i]));
 	spin_unlock_bh(&addrconf_hash_lock);
-
-	del_timer(&addr_chk_timer);
+	cancel_delayed_work(&addr_chk_work);
 	rtnl_unlock();
+
+	destroy_workqueue(addrconf_wq);
 }
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 140748d..8af3eb5 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -212,7 +212,7 @@
 		found = (nexthdr == target);
 
 		if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
-			if (target < 0)
+			if (target < 0 || found)
 				break;
 			return -ENOENT;
 		}
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index cf77f3a..447a7fb 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -25,11 +25,11 @@
 	int ret;
 
 	ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING);
-	if (!ret)
+	if (ret)
 		goto out;
 
 	ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS);
-	if (!ret)
+	if (ret)
 		goto out_rt;
 
 out:
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index f81f596..f2610e1 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -414,7 +414,7 @@
 	addr_type = ipv6_addr_type(&hdr->daddr);
 
 	if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) ||
-	    ipv6_anycast_destination(skb))
+	    ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr))
 		saddr = &hdr->daddr;
 
 	/*
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 1e8683b..59f95af 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -89,7 +89,7 @@
 	unsigned int unfrag_ip6hlen;
 	u8 *prevhdr;
 	int offset = 0;
-	bool tunnel;
+	bool encap, udpfrag;
 	int nhoff;
 
 	if (unlikely(skb_shinfo(skb)->gso_type &
@@ -110,8 +110,8 @@
 	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
 		goto out;
 
-	tunnel = SKB_GSO_CB(skb)->encap_level > 0;
-	if (tunnel)
+	encap = SKB_GSO_CB(skb)->encap_level > 0;
+	if (encap)
 		features = skb->dev->hw_enc_features & netif_skb_features(skb);
 	SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
 
@@ -121,6 +121,12 @@
 
 	proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
 
+	if (skb->encapsulation &&
+	    skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+		udpfrag = proto == IPPROTO_UDP && encap;
+	else
+		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment)) {
 		skb_reset_transport_header(skb);
@@ -133,13 +139,9 @@
 	for (skb = segs; skb; skb = skb->next) {
 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
 		ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h));
-		if (tunnel) {
-			skb_reset_inner_headers(skb);
-			skb->encapsulation = 1;
-		}
 		skb->network_header = (u8 *)ipv6h - skb->head;
 
-		if (!tunnel && proto == IPPROTO_UDP) {
+		if (udpfrag) {
 			unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
 			fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
 			fptr->frag_off = htons(offset);
@@ -148,6 +150,8 @@
 			offset += (ntohs(ipv6h->payload_len) -
 				   sizeof(struct frag_hdr));
 		}
+		if (encap)
+			skb_reset_inner_headers(skb);
 	}
 
 out:
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ef02b26..64d6073 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -342,6 +342,20 @@
 	return mtu;
 }
 
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu || skb->local_df)
+		return false;
+
+	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+		return true;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
 int ip6_forward(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -466,8 +480,7 @@
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
-	    (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+	if (ip6_pkt_too_big(skb, mtu)) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -517,9 +530,6 @@
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-	to->nf_trace = from->nf_trace;
-#endif
 	skb_copy_secmark(to, from);
 }
 
@@ -1091,21 +1101,19 @@
 				unsigned int fragheaderlen,
 				struct sk_buff *skb,
 				struct rt6_info *rt,
-				bool pmtuprobe)
+				unsigned int orig_mtu)
 {
 	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
 		if (skb == NULL) {
 			/* first fragment, reserve header_len */
-			*mtu = *mtu - rt->dst.header_len;
+			*mtu = orig_mtu - rt->dst.header_len;
 
 		} else {
 			/*
 			 * this fragment is not first, the headers
 			 * space is regarded as data space.
 			 */
-			*mtu = min(*mtu, pmtuprobe ?
-				   rt->dst.dev->mtu :
-				   dst_mtu(rt->dst.path));
+			*mtu = orig_mtu;
 		}
 		*maxfraglen = ((*mtu - fragheaderlen) & ~7)
 			      + fragheaderlen - sizeof(struct frag_hdr);
@@ -1122,7 +1130,7 @@
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet_cork *cork;
 	struct sk_buff *skb, *skb_prev = NULL;
-	unsigned int maxfraglen, fragheaderlen, mtu;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
 	int exthdrlen;
 	int dst_exthdrlen;
 	int hh_len;
@@ -1204,6 +1212,7 @@
 		dst_exthdrlen = 0;
 		mtu = cork->fragsize;
 	}
+	orig_mtu = mtu;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
@@ -1301,8 +1310,7 @@
 			if (skb == NULL || skb_prev == NULL)
 				ip6_append_data_mtu(&mtu, &maxfraglen,
 						    fragheaderlen, skb, rt,
-						    np->pmtudisc >=
-						    IPV6_PMTUDISC_PROBE);
+						    orig_mtu);
 
 			skb_prev = skb;
 
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 0eb4038..8737400 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2349,13 +2349,14 @@
 }
 
 static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
-			     u32 portid, u32 seq, struct mfc6_cache *c, int cmd)
+			     u32 portid, u32 seq, struct mfc6_cache *c, int cmd,
+			     int flags)
 {
 	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
 	int err;
 
-	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -2423,7 +2424,7 @@
 	if (skb == NULL)
 		goto errout;
 
-	err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+	err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
 	if (err < 0)
 		goto errout;
 
@@ -2462,7 +2463,8 @@
 				if (ip6mr_fill_mroute(mrt, skb,
 						      NETLINK_CB(cb->skb).portid,
 						      cb->nlh->nlmsg_seq,
-						      mfc, RTM_NEWROUTE) < 0)
+						      mfc, RTM_NEWROUTE,
+						      NLM_F_MULTI) < 0)
 					goto done;
 next_entry:
 				e++;
@@ -2476,7 +2478,8 @@
 			if (ip6mr_fill_mroute(mrt, skb,
 					      NETLINK_CB(cb->skb).portid,
 					      cb->nlh->nlmsg_seq,
-					      mfc, RTM_NEWROUTE) < 0) {
+					      mfc, RTM_NEWROUTE,
+					      NLM_F_MULTI) < 0) {
 				spin_unlock_bh(&mfc_unres_lock);
 				goto done;
 			}
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 35750df..4bff1f2 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -50,6 +50,11 @@
 	  packet transformations such as the source, destination address and
 	  source and destination ports.
 
+config NFT_REJECT_IPV6
+	depends on NF_TABLES_IPV6
+	default NFT_REJECT
+	tristate
+
 config IP6_NF_IPTABLES
 	tristate "IP6 tables support (required for filtering)"
 	depends on INET && IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index d1b4928..70d3dd6 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -27,6 +27,7 @@
 obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
+obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
new file mode 100644
index 0000000..0bc19fa
--- /dev/null
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
+
+void nft_reject_ipv6_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt)
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+	struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+		nf_send_unreach6(net, pkt->skb, priv->icmp_code,
+				 pkt->ops->hooknum);
+		break;
+	case NFT_REJECT_TCP_RST:
+		nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
+		break;
+	}
+
+	data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nft_reject_ipv6_eval);
+
+static struct nft_expr_type nft_reject_ipv6_type;
+static const struct nft_expr_ops nft_reject_ipv6_ops = {
+	.type		= &nft_reject_ipv6_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+	.eval		= nft_reject_ipv6_eval,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_ipv6_type __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.name		= "reject",
+	.ops		= &nft_reject_ipv6_ops,
+	.policy		= nft_reject_policy,
+	.maxattr	= NFTA_REJECT_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_reject_ipv6_module_init(void)
+{
+	return nft_register_expr(&nft_reject_ipv6_type);
+}
+
+static void __exit nft_reject_ipv6_module_exit(void)
+{
+	nft_unregister_expr(&nft_reject_ipv6_type);
+}
+
+module_init(nft_reject_ipv6_module_init);
+module_exit(nft_reject_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject");
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index fb9beb7..587bbdc 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -135,6 +135,7 @@
 	fl6.flowi6_proto = IPPROTO_ICMPV6;
 	fl6.saddr = np->saddr;
 	fl6.daddr = *daddr;
+	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_icmp_type = user_icmph.icmp6_type;
 	fl6.fl6_icmp_code = user_icmph.icmp6_code;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 11dac21..fba54a4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1513,7 +1513,7 @@
 	if (!table)
 		goto out;
 
-	rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
+	rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table);
 
 	if (!rt) {
 		err = -ENOMEM;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3dfbcf1..b4d74c8 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -475,6 +475,7 @@
 		ipip6_tunnel_unlink(sitn, tunnel);
 		ipip6_tunnel_del_prl(tunnel, NULL);
 	}
+	ip_tunnel_dst_reset_all(tunnel);
 	dev_put(dev);
 }
 
@@ -1082,6 +1083,7 @@
 		t->parms.link = p->link;
 		ipip6_tunnel_bind_dev(t->dev);
 	}
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(t->dev);
 }
 
@@ -1112,6 +1114,7 @@
 	t->ip6rd.relay_prefix = relay_prefix;
 	t->ip6rd.prefixlen = ip6rd->prefixlen;
 	t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen;
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(t->dev);
 	return 0;
 }
@@ -1271,6 +1274,7 @@
 			err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
 			break;
 		}
+		ip_tunnel_dst_reset_all(t);
 		netdev_state_change(dev);
 		break;
 
@@ -1326,6 +1330,9 @@
 
 static void ipip6_dev_free(struct net_device *dev)
 {
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+
+	free_percpu(tunnel->dst_cache);
 	free_percpu(dev->tstats);
 	free_netdev(dev);
 }
@@ -1375,6 +1382,12 @@
 		u64_stats_init(&ipip6_tunnel_stats->syncp);
 	}
 
+	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+	if (!tunnel->dst_cache) {
+		free_percpu(dev->tstats);
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
@@ -1405,6 +1418,12 @@
 		u64_stats_init(&ipip6_fb_stats->syncp);
 	}
 
+	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+	if (!tunnel->dst_cache) {
+		free_percpu(dev->tstats);
+		return -ENOMEM;
+	}
+
 	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
 	return 0;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index e7359f9..b261ee8 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -113,7 +113,7 @@
 		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
 		fptr->nexthdr = nexthdr;
 		fptr->reserved = 0;
-		ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb));
+		fptr->identification = skb_shinfo(skb)->ip6_frag_id;
 
 		/* Fragment the skb. ipv6 header and the remaining fields of the
 		 * fragment header are updated in ipv6_gso_segment()
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 994e28b..00b2a6d 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -52,18 +52,12 @@
 #include <net/p8022.h>
 #include <net/psnap.h>
 #include <net/sock.h>
+#include <net/datalink.h>
 #include <net/tcp_states.h>
+#include <net/net_namespace.h>
 
 #include <asm/uaccess.h>
 
-#ifdef CONFIG_SYSCTL
-extern void ipx_register_sysctl(void);
-extern void ipx_unregister_sysctl(void);
-#else
-#define ipx_register_sysctl()
-#define ipx_unregister_sysctl()
-#endif
-
 /* Configuration Variables */
 static unsigned char ipxcfg_max_hops = 16;
 static char ipxcfg_auto_select_primary;
@@ -84,15 +78,6 @@
 struct ipx_interface *ipx_primary_net;
 struct ipx_interface *ipx_internal_net;
 
-extern int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc,
-			    unsigned char *node);
-extern void ipxrtr_del_routes(struct ipx_interface *intrfc);
-extern int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
-			       struct iovec *iov, size_t len, int noblock);
-extern int ipxrtr_route_skb(struct sk_buff *skb);
-extern struct ipx_route *ipxrtr_lookup(__be32 net);
-extern int ipxrtr_ioctl(unsigned int cmd, void __user *arg);
-
 struct ipx_interface *ipx_interfaces_head(void)
 {
 	struct ipx_interface *rc = NULL;
@@ -1986,9 +1971,6 @@
 	.notifier_call	= ipxitf_device_event,
 };
 
-extern struct datalink_proto *make_EII_client(void);
-extern void destroy_EII_client(struct datalink_proto *);
-
 static const unsigned char ipx_8022_type = 0xE0;
 static const unsigned char ipx_snap_id[5] = { 0x0, 0x0, 0x0, 0x81, 0x37 };
 static const char ipx_EII_err_msg[] __initconst =
diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c
index 30f4519..c1f0318 100644
--- a/net/ipx/ipx_route.c
+++ b/net/ipx/ipx_route.c
@@ -20,15 +20,11 @@
 
 extern struct ipx_interface *ipx_internal_net;
 
-extern __be16 ipx_cksum(struct ipxhdr *packet, int length);
 extern struct ipx_interface *ipxitf_find_using_net(__be32 net);
 extern int ipxitf_demux_socket(struct ipx_interface *intrfc,
 			       struct sk_buff *skb, int copy);
 extern int ipxitf_demux_socket(struct ipx_interface *intrfc,
 			       struct sk_buff *skb, int copy);
-extern int ipxitf_send(struct ipx_interface *intrfc, struct sk_buff *skb,
-		       char *node);
-extern struct ipx_interface *ipxitf_find_using_net(__be32 net);
 
 struct ipx_route *ipxrtr_lookup(__be32 net)
 {
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 1a04c13..7932697 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -433,12 +433,13 @@
 	return 0;
 }
 
-static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx)
+static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx,
+								     gfp_t gfp)
 {
 	struct xfrm_user_sec_ctx *uctx = NULL;
 	int ctx_size = sec_ctx->sadb_x_ctx_len;
 
-	uctx = kmalloc((sizeof(*uctx)+ctx_size), GFP_KERNEL);
+	uctx = kmalloc((sizeof(*uctx)+ctx_size), gfp);
 
 	if (!uctx)
 		return NULL;
@@ -1124,7 +1125,7 @@
 
 	sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1];
 	if (sec_ctx != NULL) {
-		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
+		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL);
 
 		if (!uctx)
 			goto out;
@@ -2231,14 +2232,14 @@
 
 	sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1];
 	if (sec_ctx != NULL) {
-		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
+		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL);
 
 		if (!uctx) {
 			err = -ENOBUFS;
 			goto out;
 		}
 
-		err = security_xfrm_policy_alloc(&xp->security, uctx);
+		err = security_xfrm_policy_alloc(&xp->security, uctx, GFP_KERNEL);
 		kfree(uctx);
 
 		if (err)
@@ -2335,12 +2336,12 @@
 
 	sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1];
 	if (sec_ctx != NULL) {
-		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
+		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL);
 
 		if (!uctx)
 			return -ENOMEM;
 
-		err = security_xfrm_policy_alloc(&pol_ctx, uctx);
+		err = security_xfrm_policy_alloc(&pol_ctx, uctx, GFP_KERNEL);
 		kfree(uctx);
 		if (err)
 			return err;
@@ -3239,8 +3240,8 @@
 		}
 		if ((*dir = verify_sec_ctx_len(p)))
 			goto out;
-		uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
-		*dir = security_xfrm_policy_alloc(&xp->security, uctx);
+		uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_ATOMIC);
+		*dir = security_xfrm_policy_alloc(&xp->security, uctx, GFP_ATOMIC);
 		kfree(uctx);
 
 		if (*dir)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 735d0f6..c83827e 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -112,7 +112,6 @@
 	spinlock_t l2tp_session_hlist_lock;
 };
 
-static void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
 
 static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk)
@@ -1863,7 +1862,7 @@
 /* We come here whenever a session's send_seq, cookie_len or
  * l2specific_len parameters are set.
  */
-static void l2tp_session_set_header_len(struct l2tp_session *session, int version)
+void l2tp_session_set_header_len(struct l2tp_session *session, int version)
 {
 	if (version == L2TP_HDR_VER_2) {
 		session->hdr_len = 6;
@@ -1876,6 +1875,7 @@
 	}
 
 }
+EXPORT_SYMBOL_GPL(l2tp_session_set_header_len);
 
 struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
 {
@@ -2016,7 +2016,7 @@
 	if (rc)
 		goto out;
 
-	l2tp_wq = alloc_workqueue("l2tp", WQ_NON_REENTRANT | WQ_UNBOUND, 0);
+	l2tp_wq = alloc_workqueue("l2tp", WQ_UNBOUND, 0);
 	if (!l2tp_wq) {
 		pr_err("alloc_workqueue failed\n");
 		rc = -ENOMEM;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 1f01ba3..3f93ccd 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -263,6 +263,7 @@
 		      int length, int (*payload_hook)(struct sk_buff *skb));
 int l2tp_session_queue_purge(struct l2tp_session *session);
 int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
+void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 
 int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb,
 		  int hdr_len);
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 4cfd722..bd7387a 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -578,8 +578,10 @@
 	if (info->attrs[L2TP_ATTR_RECV_SEQ])
 		session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]);
 
-	if (info->attrs[L2TP_ATTR_SEND_SEQ])
+	if (info->attrs[L2TP_ATTR_SEND_SEQ]) {
 		session->send_seq = nla_get_u8(info->attrs[L2TP_ATTR_SEND_SEQ]);
+		l2tp_session_set_header_len(session, session->tunnel->version);
+	}
 
 	if (info->attrs[L2TP_ATTR_LNS_MODE])
 		session->lns_mode = nla_get_u8(info->attrs[L2TP_ATTR_LNS_MODE]);
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index be5fadf..5990919 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -254,12 +254,14 @@
 		po = pppox_sk(sk);
 		ppp_input(&po->chan, skb);
 	} else {
-		l2tp_info(session, PPPOL2TP_MSG_DATA, "%s: socket not bound\n",
-			  session->name);
+		l2tp_dbg(session, PPPOL2TP_MSG_DATA,
+			 "%s: recv %d byte data frame, passing to L2TP socket\n",
+			 session->name, data_len);
 
-		/* Not bound. Nothing we can do, so discard. */
-		atomic_long_inc(&session->stats.rx_errors);
-		kfree_skb(skb);
+		if (sock_queue_rcv_skb(sk, skb) < 0) {
+			atomic_long_inc(&session->stats.rx_errors);
+			kfree_skb(skb);
+		}
 	}
 
 	return;
@@ -1312,6 +1314,7 @@
 			po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
 				PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
 		}
+		l2tp_session_set_header_len(session, session->tunnel->version);
 		l2tp_info(session, PPPOL2TP_MSG_CONTROL,
 			  "%s: set send_seq=%d\n",
 			  session->name, session->send_seq);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index f9ae9b8..453e974 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1021,8 +1021,10 @@
 					IEEE80211_P2P_OPPPS_ENABLE_BIT;
 
 	err = ieee80211_assign_beacon(sdata, &params->beacon);
-	if (err < 0)
+	if (err < 0) {
+		ieee80211_vif_release_channel(sdata);
 		return err;
+	}
 	changed |= err;
 
 	err = drv_start_ap(sdata->local, sdata);
@@ -1032,6 +1034,7 @@
 		if (old)
 			kfree_rcu(old, rcu_head);
 		RCU_INIT_POINTER(sdata->u.ap.beacon, NULL);
+		ieee80211_vif_release_channel(sdata);
 		return err;
 	}
 
@@ -1090,8 +1093,6 @@
 	kfree(sdata->u.ap.next_beacon);
 	sdata->u.ap.next_beacon = NULL;
 
-	cancel_work_sync(&sdata->u.ap.request_smps_work);
-
 	/* turn off carrier for this interface and dependent VLANs */
 	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
 		netif_carrier_off(vlan->dev);
@@ -1103,6 +1104,7 @@
 	kfree_rcu(old_beacon, rcu_head);
 	if (old_probe_resp)
 		kfree_rcu(old_probe_resp, rcu_head);
+	sdata->u.ap.driver_smps_mode = IEEE80211_SMPS_OFF;
 
 	__sta_info_flush(sdata, true);
 	ieee80211_free_keys(sdata, true);
@@ -2638,6 +2640,24 @@
 	INIT_DELAYED_WORK(&roc->work, ieee80211_sw_roc_work);
 	INIT_LIST_HEAD(&roc->dependents);
 
+	/*
+	 * cookie is either the roc cookie (for normal roc)
+	 * or the SKB (for mgmt TX)
+	 */
+	if (!txskb) {
+		/* local->mtx protects this */
+		local->roc_cookie_counter++;
+		roc->cookie = local->roc_cookie_counter;
+		/* wow, you wrapped 64 bits ... more likely a bug */
+		if (WARN_ON(roc->cookie == 0)) {
+			roc->cookie = 1;
+			local->roc_cookie_counter++;
+		}
+		*cookie = roc->cookie;
+	} else {
+		*cookie = (unsigned long)txskb;
+	}
+
 	/* if there's one pending or we're scanning, queue this one */
 	if (!list_empty(&local->roc_list) ||
 	    local->scanning || local->radar_detect_enabled)
@@ -2772,24 +2792,6 @@
 	if (!queued)
 		list_add_tail(&roc->list, &local->roc_list);
 
-	/*
-	 * cookie is either the roc cookie (for normal roc)
-	 * or the SKB (for mgmt TX)
-	 */
-	if (!txskb) {
-		/* local->mtx protects this */
-		local->roc_cookie_counter++;
-		roc->cookie = local->roc_cookie_counter;
-		/* wow, you wrapped 64 bits ... more likely a bug */
-		if (WARN_ON(roc->cookie == 0)) {
-			roc->cookie = 1;
-			local->roc_cookie_counter++;
-		}
-		*cookie = roc->cookie;
-	} else {
-		*cookie = (unsigned long)txskb;
-	}
-
 	return 0;
 }
 
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index f43613a..0c1ecfd 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -100,6 +100,12 @@
 		}
 		max_bw = max(max_bw, width);
 	}
+
+	/* use the configured bandwidth in case of monitor interface */
+	sdata = rcu_dereference(local->monitor_sdata);
+	if (sdata && rcu_access_pointer(sdata->vif.chanctx_conf) == conf)
+		max_bw = max(max_bw, conf->def.width);
+
 	rcu_read_unlock();
 
 	return max_bw;
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index fab7b91..70dd013 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -466,7 +466,9 @@
 			     u.ap.request_smps_work);
 
 	sdata_lock(sdata);
-	__ieee80211_request_smps_ap(sdata, sdata->u.ap.driver_smps_mode);
+	if (sdata_dereference(sdata->u.ap.beacon, sdata))
+		__ieee80211_request_smps_ap(sdata,
+					    sdata->u.ap.driver_smps_mode);
 	sdata_unlock(sdata);
 }
 
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 771080e..2796a19 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -695,12 +695,9 @@
 	struct cfg80211_bss *cbss;
 	struct beacon_data *presp;
 	struct sta_info *sta;
-	int active_ibss;
 	u16 capability;
 
-	active_ibss = ieee80211_sta_active_ibss(sdata);
-
-	if (!active_ibss && !is_zero_ether_addr(ifibss->bssid)) {
+	if (!is_zero_ether_addr(ifibss->bssid)) {
 		capability = WLAN_CAPABILITY_IBSS;
 
 		if (ifibss->privacy)
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 3701930..5e44e317 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1692,14 +1692,8 @@
 void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue);
 void ieee80211_add_pending_skb(struct ieee80211_local *local,
 			       struct sk_buff *skb);
-void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local,
-				   struct sk_buff_head *skbs,
-				   void (*fn)(void *data), void *data);
-static inline void ieee80211_add_pending_skbs(struct ieee80211_local *local,
-					      struct sk_buff_head *skbs)
-{
-	ieee80211_add_pending_skbs_fn(local, skbs, NULL, NULL);
-}
+void ieee80211_add_pending_skbs(struct ieee80211_local *local,
+				struct sk_buff_head *skbs);
 void ieee80211_flush_queues(struct ieee80211_local *local,
 			    struct ieee80211_sub_if_data *sdata);
 
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 3dfd20a..ce1c443 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -418,20 +418,24 @@
 		return ret;
 	}
 
+	mutex_lock(&local->iflist_mtx);
+	rcu_assign_pointer(local->monitor_sdata, sdata);
+	mutex_unlock(&local->iflist_mtx);
+
 	mutex_lock(&local->mtx);
 	ret = ieee80211_vif_use_channel(sdata, &local->monitor_chandef,
 					IEEE80211_CHANCTX_EXCLUSIVE);
 	mutex_unlock(&local->mtx);
 	if (ret) {
+		mutex_lock(&local->iflist_mtx);
+		rcu_assign_pointer(local->monitor_sdata, NULL);
+		mutex_unlock(&local->iflist_mtx);
+		synchronize_net();
 		drv_remove_interface(local, sdata);
 		kfree(sdata);
 		return ret;
 	}
 
-	mutex_lock(&local->iflist_mtx);
-	rcu_assign_pointer(local->monitor_sdata, sdata);
-	mutex_unlock(&local->iflist_mtx);
-
 	return 0;
 }
 
@@ -770,12 +774,19 @@
 
 	ieee80211_roc_purge(local, sdata);
 
-	if (sdata->vif.type == NL80211_IFTYPE_STATION)
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_STATION:
 		ieee80211_mgd_stop(sdata);
-
-	if (sdata->vif.type == NL80211_IFTYPE_ADHOC)
+		break;
+	case NL80211_IFTYPE_ADHOC:
 		ieee80211_ibss_stop(sdata);
-
+		break;
+	case NL80211_IFTYPE_AP:
+		cancel_work_sync(&sdata->u.ap.request_smps_work);
+		break;
+	default:
+		break;
+	}
 
 	/*
 	 * Remove all stations associated with this interface.
@@ -1046,7 +1057,8 @@
 
 static u16 ieee80211_netdev_select_queue(struct net_device *dev,
 					 struct sk_buff *skb,
-					 void *accel_priv)
+					 void *accel_priv,
+					 select_queue_fallback_t fallback)
 {
 	return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
 }
@@ -1064,7 +1076,8 @@
 
 static u16 ieee80211_monitor_select_queue(struct net_device *dev,
 					  struct sk_buff *skb,
-					  void *accel_priv)
+					  void *accel_priv,
+					  select_queue_fallback_t fallback)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c
index 2802f9d..ad8b377 100644
--- a/net/mac80211/mesh_ps.c
+++ b/net/mac80211/mesh_ps.c
@@ -36,6 +36,7 @@
 				      sdata->vif.addr);
 	nullfunc->frame_control = fc;
 	nullfunc->duration_id = 0;
+	nullfunc->seq_ctrl = 0;
 	/* no address resolution for this frame -> set addr 1 immediately */
 	memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
 	memset(skb_put(skb, 2), 0, 2); /* append QoS control field */
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index fc1d824..245dce9 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -222,6 +222,7 @@
 	switch (vht_oper->chan_width) {
 	case IEEE80211_VHT_CHANWIDTH_USE_HT:
 		vht_chandef.width = chandef->width;
+		vht_chandef.center_freq1 = chandef->center_freq1;
 		break;
 	case IEEE80211_VHT_CHANWIDTH_80MHZ:
 		vht_chandef.width = NL80211_CHAN_WIDTH_80;
@@ -271,6 +272,28 @@
 	ret = 0;
 
 out:
+	/*
+	 * When tracking the current AP, don't do any further checks if the
+	 * new chandef is identical to the one we're currently using for the
+	 * connection. This keeps us from playing ping-pong with regulatory,
+	 * without it the following can happen (for example):
+	 *  - connect to an AP with 80 MHz, world regdom allows 80 MHz
+	 *  - AP advertises regdom US
+	 *  - CRDA loads regdom US with 80 MHz prohibited (old database)
+	 *  - the code below detects an unsupported channel, downgrades, and
+	 *    we disconnect from the AP in the caller
+	 *  - disconnect causes CRDA to reload world regdomain and the game
+	 *    starts anew.
+	 * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881)
+	 *
+	 * It seems possible that there are still scenarios with CSA or real
+	 * bandwidth changes where a this could happen, but those cases are
+	 * less common and wouldn't completely prevent using the AP.
+	 */
+	if (tracking &&
+	    cfg80211_chandef_identical(chandef, &sdata->vif.bss_conf.chandef))
+		return ret;
+
 	/* don't print the message below for VHT mismatch if VHT is disabled */
 	if (ret & IEEE80211_STA_DISABLE_VHT)
 		vht_chandef = *chandef;
@@ -3753,6 +3776,7 @@
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 		if (WARN_ON(!chanctx_conf)) {
 			rcu_read_unlock();
+			sta_info_free(local, new_sta);
 			return -EINVAL;
 		}
 		rate_flags = ieee80211_chandef_rate_flags(&chanctx_conf->def);
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index c24ca0d..3e57f96 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1128,6 +1128,13 @@
 	       sta->sta.addr, sta->sta.aid);
 
 	if (test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+		/*
+		 * Clear the flag only if the other one is still set
+		 * so that the TX path won't start TX'ing new frames
+		 * directly ... In the case that the driver flag isn't
+		 * set ieee80211_sta_ps_deliver_wakeup() will clear it.
+		 */
+		clear_sta_flag(sta, WLAN_STA_PS_STA);
 		ps_dbg(sta->sdata, "STA %pM aid %d driver-ps-blocked\n",
 		       sta->sta.addr, sta->sta.aid);
 		return;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index decd30c..137a192 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -91,7 +91,7 @@
 	return -ENOENT;
 }
 
-static void cleanup_single_sta(struct sta_info *sta)
+static void __cleanup_single_sta(struct sta_info *sta)
 {
 	int ac, i;
 	struct tid_ampdu_tx *tid_tx;
@@ -99,7 +99,8 @@
 	struct ieee80211_local *local = sdata->local;
 	struct ps_data *ps;
 
-	if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
+	if (test_sta_flag(sta, WLAN_STA_PS_STA) ||
+	    test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
 		if (sta->sdata->vif.type == NL80211_IFTYPE_AP ||
 		    sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 			ps = &sdata->bss->ps;
@@ -109,6 +110,7 @@
 			return;
 
 		clear_sta_flag(sta, WLAN_STA_PS_STA);
+		clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
 
 		atomic_dec(&ps->num_sta_ps);
 		sta_info_recalc_tim(sta);
@@ -139,7 +141,14 @@
 		ieee80211_purge_tx_queue(&local->hw, &tid_tx->pending);
 		kfree(tid_tx);
 	}
+}
 
+static void cleanup_single_sta(struct sta_info *sta)
+{
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct ieee80211_local *local = sdata->local;
+
+	__cleanup_single_sta(sta);
 	sta_info_free(local, sta);
 }
 
@@ -330,6 +339,7 @@
 	rcu_read_unlock();
 
 	spin_lock_init(&sta->lock);
+	spin_lock_init(&sta->ps_lock);
 	INIT_WORK(&sta->drv_unblock_wk, sta_unblock);
 	INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work);
 	mutex_init(&sta->ampdu_mlme.mtx);
@@ -487,21 +497,26 @@
 		goto out_err;
 	}
 
-	/* notify driver */
-	err = sta_info_insert_drv_state(local, sdata, sta);
-	if (err)
-		goto out_err;
-
 	local->num_sta++;
 	local->sta_generation++;
 	smp_mb();
 
+	/* simplify things and don't accept BA sessions yet */
+	set_sta_flag(sta, WLAN_STA_BLOCK_BA);
+
 	/* make the station visible */
 	sta_info_hash_add(local, sta);
 
 	list_add_rcu(&sta->list, &local->sta_list);
 
+	/* notify driver */
+	err = sta_info_insert_drv_state(local, sdata, sta);
+	if (err)
+		goto out_remove;
+
 	set_sta_flag(sta, WLAN_STA_INSERTED);
+	/* accept BA sessions now */
+	clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
 
 	ieee80211_recalc_min_chandef(sdata);
 	ieee80211_sta_debugfs_add(sta);
@@ -522,6 +537,12 @@
 		mesh_accept_plinks_update(sdata);
 
 	return 0;
+ out_remove:
+	sta_info_hash_del(local, sta);
+	list_del_rcu(&sta->list);
+	local->num_sta--;
+	synchronize_net();
+	__cleanup_single_sta(sta);
  out_err:
 	mutex_unlock(&local->sta_mtx);
 	rcu_read_lock();
@@ -1071,10 +1092,14 @@
 }
 EXPORT_SYMBOL(ieee80211_find_sta);
 
-static void clear_sta_ps_flags(void *_sta)
+/* powersave support code */
+void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 {
-	struct sta_info *sta = _sta;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct ieee80211_local *local = sdata->local;
+	struct sk_buff_head pending;
+	int filtered = 0, buffered = 0, ac;
+	unsigned long flags;
 	struct ps_data *ps;
 
 	if (sdata->vif.type == NL80211_IFTYPE_AP ||
@@ -1085,20 +1110,6 @@
 	else
 		return;
 
-	clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
-	if (test_and_clear_sta_flag(sta, WLAN_STA_PS_STA))
-		atomic_dec(&ps->num_sta_ps);
-}
-
-/* powersave support code */
-void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
-{
-	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	struct ieee80211_local *local = sdata->local;
-	struct sk_buff_head pending;
-	int filtered = 0, buffered = 0, ac;
-	unsigned long flags;
-
 	clear_sta_flag(sta, WLAN_STA_SP);
 
 	BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1);
@@ -1109,6 +1120,8 @@
 
 	skb_queue_head_init(&pending);
 
+	/* sync with ieee80211_tx_h_unicast_ps_buf */
+	spin_lock(&sta->ps_lock);
 	/* Send all buffered frames to the station */
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		int count = skb_queue_len(&pending), tmp;
@@ -1127,7 +1140,12 @@
 		buffered += tmp - count;
 	}
 
-	ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta);
+	ieee80211_add_pending_skbs(local, &pending);
+	clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
+	clear_sta_flag(sta, WLAN_STA_PS_STA);
+	spin_unlock(&sta->ps_lock);
+
+	atomic_dec(&ps->num_sta_ps);
 
 	/* This station just woke up and isn't aware of our SMPS state */
 	if (!ieee80211_smps_is_restrictive(sta->known_smps_mode,
@@ -1188,6 +1206,7 @@
 	memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
 	memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN);
 	memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN);
+	nullfunc->seq_ctrl = 0;
 
 	skb->priority = tid;
 	skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index d77ff70..d3a6d82 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -267,6 +267,7 @@
  * @drv_unblock_wk: used for driver PS unblocking
  * @listen_interval: listen interval of this station, when we're acting as AP
  * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly
+ * @ps_lock: used for powersave (when mac80211 is the AP) related locking
  * @ps_tx_buf: buffers (per AC) of frames to transmit to this station
  *	when it leaves power saving state or polls
  * @tx_filtered: buffers (per AC) of frames we already tried to
@@ -356,10 +357,8 @@
 	/* use the accessors defined below */
 	unsigned long _flags;
 
-	/*
-	 * STA powersave frame queues, no more than the internal
-	 * locking required.
-	 */
+	/* STA powersave lock and frame queues */
+	spinlock_t ps_lock;
 	struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS];
 	struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS];
 	unsigned long driver_buffered_tids;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 27c990b..4080c61 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -478,6 +478,20 @@
 		       sta->sta.addr, sta->sta.aid, ac);
 		if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
 			purge_old_ps_buffers(tx->local);
+
+		/* sync with ieee80211_sta_ps_deliver_wakeup */
+		spin_lock(&sta->ps_lock);
+		/*
+		 * STA woke up the meantime and all the frames on ps_tx_buf have
+		 * been queued to pending queue. No reordering can happen, go
+		 * ahead and Tx the packet.
+		 */
+		if (!test_sta_flag(sta, WLAN_STA_PS_STA) &&
+		    !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+			spin_unlock(&sta->ps_lock);
+			return TX_CONTINUE;
+		}
+
 		if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) {
 			struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]);
 			ps_dbg(tx->sdata,
@@ -492,6 +506,7 @@
 		info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
 		info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 		skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
+		spin_unlock(&sta->ps_lock);
 
 		if (!timer_pending(&local->sta_cleanup))
 			mod_timer(&local->sta_cleanup,
@@ -878,7 +893,7 @@
 	}
 
 	/* adjust first fragment's length */
-	skb->len = hdrlen + per_fragm;
+	skb_trim(skb, hdrlen + per_fragm);
 	return 0;
 }
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 676dc09..b8700d4 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -435,9 +435,8 @@
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 }
 
-void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local,
-				   struct sk_buff_head *skbs,
-				   void (*fn)(void *data), void *data)
+void ieee80211_add_pending_skbs(struct ieee80211_local *local,
+				struct sk_buff_head *skbs)
 {
 	struct ieee80211_hw *hw = &local->hw;
 	struct sk_buff *skb;
@@ -461,9 +460,6 @@
 		__skb_queue_tail(&local->pending[queue], skb);
 	}
 
-	if (fn)
-		fn(data);
-
 	for (i = 0; i < hw->queues; i++)
 		__ieee80211_wake_queue(hw, i,
 			IEEE80211_QUEUE_STOP_REASON_SKB_ADD);
@@ -1741,6 +1737,26 @@
 					IEEE80211_QUEUE_STOP_REASON_SUSPEND);
 
 	/*
+	 * Reconfigure sched scan if it was interrupted by FW restart or
+	 * suspend.
+	 */
+	mutex_lock(&local->mtx);
+	sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata,
+						lockdep_is_held(&local->mtx));
+	if (sched_scan_sdata && local->sched_scan_req)
+		/*
+		 * Sched scan stopped, but we don't want to report it. Instead,
+		 * we're trying to reschedule.
+		 */
+		if (__ieee80211_request_sched_scan_start(sched_scan_sdata,
+							 local->sched_scan_req))
+			sched_scan_stopped = true;
+	mutex_unlock(&local->mtx);
+
+	if (sched_scan_stopped)
+		cfg80211_sched_scan_stopped(local->hw.wiphy);
+
+	/*
 	 * If this is for hw restart things are still running.
 	 * We may want to change that later, however.
 	 */
@@ -1768,26 +1784,6 @@
 	WARN_ON(1);
 #endif
 
-	/*
-	 * Reconfigure sched scan if it was interrupted by FW restart or
-	 * suspend.
-	 */
-	mutex_lock(&local->mtx);
-	sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata,
-						lockdep_is_held(&local->mtx));
-	if (sched_scan_sdata && local->sched_scan_req)
-		/*
-		 * Sched scan stopped, but we don't want to report it. Instead,
-		 * we're trying to reschedule.
-		 */
-		if (__ieee80211_request_sched_scan_start(sched_scan_sdata,
-							 local->sched_scan_req))
-			sched_scan_stopped = true;
-	mutex_unlock(&local->mtx);
-
-	if (sched_scan_stopped)
-		cfg80211_sched_scan_stopped(local->hw.wiphy);
-
 	return 0;
 }
 
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 21211c6..d51422c 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -154,6 +154,11 @@
 		return IEEE80211_AC_BE;
 	}
 
+	if (skb->protocol == sdata->control_port_protocol) {
+		skb->priority = 7;
+		return ieee80211_downgrade_queue(sdata, skb);
+	}
+
 	/* use the data classifier to determine what 802.1d tag the
 	 * data frame has */
 	rcu_read_lock();
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index c374675..e9410d1 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -513,7 +513,6 @@
 
 config NFT_REJECT
 	depends on NF_TABLES
-	depends on NF_TABLES_IPV6 || !NF_TABLES_IPV6
 	default m if NETFILTER_ADVANCED=n
 	tristate "Netfilter nf_tables reject support"
 	help
@@ -521,6 +520,11 @@
 	  explicitly deny and notify via TCP reset/ICMP informational errors
 	  unallowed traffic.
 
+config NFT_REJECT_INET
+	depends on NF_TABLES_INET
+	default NFT_REJECT
+	tristate
+
 config NFT_COMPAT
 	depends on NF_TABLES
 	depends on NETFILTER_XTABLES
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index ee9c4de..bffdad7 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -79,6 +79,7 @@
 obj-$(CONFIG_NFT_NAT)		+= nft_nat.o
 obj-$(CONFIG_NFT_QUEUE)		+= nft_queue.o
 obj-$(CONFIG_NFT_REJECT) 	+= nft_reject.o
+obj-$(CONFIG_NFT_REJECT_INET)	+= nft_reject_inet.o
 obj-$(CONFIG_NFT_RBTREE)	+= nft_rbtree.o
 obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 59a1a85..a8eb0a8 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -871,11 +871,11 @@
 	cp->protocol	   = p->protocol;
 	ip_vs_addr_set(p->af, &cp->caddr, p->caddr);
 	cp->cport	   = p->cport;
-	ip_vs_addr_set(p->af, &cp->vaddr, p->vaddr);
-	cp->vport	   = p->vport;
-	/* proto should only be IPPROTO_IP if d_addr is a fwmark */
+	/* proto should only be IPPROTO_IP if p->vaddr is a fwmark */
 	ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
-		       &cp->daddr, daddr);
+		       &cp->vaddr, p->vaddr);
+	cp->vport	   = p->vport;
+	ip_vs_addr_set(p->af, &cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
 	cp->fwmark         = fwmark;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 8824ed0..356bef5 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -312,6 +312,21 @@
 	nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0);
 }
 
+static inline bool
+nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
+			const struct nf_conntrack_tuple *tuple,
+			u16 zone)
+{
+	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+
+	/* A conntrack can be recreated with the equal tuple,
+	 * so we need to check that the conntrack is confirmed
+	 */
+	return nf_ct_tuple_equal(tuple, &h->tuple) &&
+		nf_ct_zone(ct) == zone &&
+		nf_ct_is_confirmed(ct);
+}
+
 /*
  * Warning :
  * - Caller must take a reference on returned object
@@ -333,8 +348,7 @@
 	local_bh_disable();
 begin:
 	hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) {
-		if (nf_ct_tuple_equal(tuple, &h->tuple) &&
-		    nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) {
+		if (nf_ct_key_equal(h, tuple, zone)) {
 			NF_CT_STAT_INC(net, found);
 			local_bh_enable();
 			return h;
@@ -372,8 +386,7 @@
 			     !atomic_inc_not_zero(&ct->ct_general.use)))
 			h = NULL;
 		else {
-			if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) ||
-				     nf_ct_zone(ct) != zone)) {
+			if (unlikely(!nf_ct_key_equal(h, tuple, zone))) {
 				nf_ct_put(ct);
 				goto begin;
 			}
@@ -435,7 +448,9 @@
 			goto out;
 
 	add_timer(&ct->timeout);
-	nf_conntrack_get(&ct->ct_general);
+	smp_wmb();
+	/* The caller holds a reference to this object */
+	atomic_set(&ct->ct_general.use, 2);
 	__nf_conntrack_hash_insert(ct, hash, repl_hash);
 	NF_CT_STAT_INC(net, insert);
 	spin_unlock_bh(&nf_conntrack_lock);
@@ -449,6 +464,21 @@
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
 
+/* deletion from this larval template list happens via nf_ct_put() */
+void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl)
+{
+	__set_bit(IPS_TEMPLATE_BIT, &tmpl->status);
+	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+	nf_conntrack_get(&tmpl->ct_general);
+
+	spin_lock_bh(&nf_conntrack_lock);
+	/* Overload tuple linked list to put us in template list. */
+	hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+				 &net->ct.tmpl);
+	spin_unlock_bh(&nf_conntrack_lock);
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert);
+
 /* Confirm a connection given skb; places it in hash table */
 int
 __nf_conntrack_confirm(struct sk_buff *skb)
@@ -720,11 +750,10 @@
 		nf_ct_zone->id = zone;
 	}
 #endif
-	/*
-	 * changes to lookup keys must be done before setting refcnt to 1
+	/* Because we use RCU lookups, we set ct_general.use to zero before
+	 * this is inserted in any list.
 	 */
-	smp_wmb();
-	atomic_set(&ct->ct_general.use, 1);
+	atomic_set(&ct->ct_general.use, 0);
 	return ct;
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES
@@ -748,6 +777,11 @@
 {
 	struct net *net = nf_ct_net(ct);
 
+	/* A freed object has refcnt == 0, that's
+	 * the golden rule for SLAB_DESTROY_BY_RCU
+	 */
+	NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);
+
 	nf_ct_ext_destroy(ct);
 	nf_ct_ext_free(ct);
 	kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
@@ -843,6 +877,9 @@
 		NF_CT_STAT_INC(net, new);
 	}
 
+	/* Now it is inserted into the unconfirmed list, bump refcount */
+	nf_conntrack_get(&ct->ct_general);
+
 	/* Overload tuple linked list to put us in unconfirmed list. */
 	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
 		       &net->ct.unconfirmed);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index bb322d0..b9f0e03 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1310,27 +1310,22 @@
 }
 
 static int
-ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[])
+ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
 {
 #ifdef CONFIG_NF_NAT_NEEDED
 	int ret;
 
-	if (cda[CTA_NAT_DST]) {
-		ret = ctnetlink_parse_nat_setup(ct,
-						NF_NAT_MANIP_DST,
-						cda[CTA_NAT_DST]);
-		if (ret < 0)
-			return ret;
-	}
-	if (cda[CTA_NAT_SRC]) {
-		ret = ctnetlink_parse_nat_setup(ct,
-						NF_NAT_MANIP_SRC,
-						cda[CTA_NAT_SRC]);
-		if (ret < 0)
-			return ret;
-	}
-	return 0;
+	ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST,
+					cda[CTA_NAT_DST]);
+	if (ret < 0)
+		return ret;
+
+	ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC,
+					cda[CTA_NAT_SRC]);
+	return ret;
 #else
+	if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
+		return 0;
 	return -EOPNOTSUPP;
 #endif
 }
@@ -1659,11 +1654,9 @@
 			goto err2;
 	}
 
-	if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
-		err = ctnetlink_change_nat(ct, cda);
-		if (err < 0)
-			goto err2;
-	}
+	err = ctnetlink_setup_nat(ct, cda);
+	if (err < 0)
+		goto err2;
 
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
 	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index d3f5cd6..52ca952 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -432,15 +432,15 @@
 }
 EXPORT_SYMBOL(nf_nat_setup_info);
 
-unsigned int
-nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+static unsigned int
+__nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip)
 {
 	/* Force range to this IP; let proto decide mapping for
 	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
 	 * Use reply in case it's already been mangled (eg local packet).
 	 */
 	union nf_inet_addr ip =
-		(HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
+		(manip == NF_NAT_MANIP_SRC ?
 		ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 :
 		ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3);
 	struct nf_nat_range range = {
@@ -448,7 +448,13 @@
 		.min_addr	= ip,
 		.max_addr	= ip,
 	};
-	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
+	return nf_nat_setup_info(ct, &range, manip);
+}
+
+unsigned int
+nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+{
+	return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum));
 }
 EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding);
 
@@ -702,9 +708,9 @@
 
 static int
 nfnetlink_parse_nat(const struct nlattr *nat,
-		    const struct nf_conn *ct, struct nf_nat_range *range)
+		    const struct nf_conn *ct, struct nf_nat_range *range,
+		    const struct nf_nat_l3proto *l3proto)
 {
-	const struct nf_nat_l3proto *l3proto;
 	struct nlattr *tb[CTA_NAT_MAX+1];
 	int err;
 
@@ -714,38 +720,46 @@
 	if (err < 0)
 		return err;
 
-	rcu_read_lock();
-	l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
-	if (l3proto == NULL) {
-		err = -EAGAIN;
-		goto out;
-	}
 	err = l3proto->nlattr_to_range(tb, range);
 	if (err < 0)
-		goto out;
+		return err;
 
 	if (!tb[CTA_NAT_PROTO])
-		goto out;
+		return 0;
 
-	err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
-out:
-	rcu_read_unlock();
-	return err;
+	return nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
 }
 
+/* This function is called under rcu_read_lock() */
 static int
 nfnetlink_parse_nat_setup(struct nf_conn *ct,
 			  enum nf_nat_manip_type manip,
 			  const struct nlattr *attr)
 {
 	struct nf_nat_range range;
+	const struct nf_nat_l3proto *l3proto;
 	int err;
 
-	err = nfnetlink_parse_nat(attr, ct, &range);
+	/* Should not happen, restricted to creating new conntracks
+	 * via ctnetlink.
+	 */
+	if (WARN_ON_ONCE(nf_nat_initialized(ct, manip)))
+		return -EEXIST;
+
+	/* Make sure that L3 NAT is there by when we call nf_nat_setup_info to
+	 * attach the null binding, otherwise this may oops.
+	 */
+	l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
+	if (l3proto == NULL)
+		return -EAGAIN;
+
+	/* No NAT information has been passed, allocate the null-binding */
+	if (attr == NULL)
+		return __nf_nat_alloc_null_binding(ct, manip);
+
+	err = nfnetlink_parse_nat(attr, ct, &range, l3proto);
 	if (err < 0)
 		return err;
-	if (nf_nat_initialized(ct, manip))
-		return -EEXIST;
 
 	return nf_nat_setup_info(ct, &range, manip);
 }
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 9858e3e..52e20c9 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -363,9 +363,8 @@
 		goto err2;
 	if (!nfct_synproxy_ext_add(ct))
 		goto err2;
-	__set_bit(IPS_TEMPLATE_BIT, &ct->status);
-	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
 
+	nf_conntrack_tmpl_insert(net, ct);
 	snet->tmpl = ct;
 
 	snet->stats = alloc_percpu(struct synproxy_stats);
@@ -390,7 +389,7 @@
 {
 	struct synproxy_net *snet = synproxy_pernet(net);
 
-	nf_conntrack_free(snet->tmpl);
+	nf_ct_put(snet->tmpl);
 	synproxy_proc_exit(net);
 	free_percpu(snet->stats);
 }
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 117bbaa..adce01e 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1008,10 +1008,8 @@
 	return 0;
 }
 
-static void nf_tables_rcu_chain_destroy(struct rcu_head *head)
+static void nf_tables_chain_destroy(struct nft_chain *chain)
 {
-	struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head);
-
 	BUG_ON(chain->use > 0);
 
 	if (chain->flags & NFT_BASE_CHAIN) {
@@ -1045,7 +1043,7 @@
 	if (IS_ERR(chain))
 		return PTR_ERR(chain);
 
-	if (!list_empty(&chain->rules))
+	if (!list_empty(&chain->rules) || chain->use > 0)
 		return -EBUSY;
 
 	list_del(&chain->list);
@@ -1059,7 +1057,9 @@
 			       family);
 
 	/* Make sure all rule references are gone before this is released */
-	call_rcu(&chain->rcu_head, nf_tables_rcu_chain_destroy);
+	synchronize_rcu();
+
+	nf_tables_chain_destroy(chain);
 	return 0;
 }
 
@@ -1114,35 +1114,45 @@
 }
 EXPORT_SYMBOL_GPL(nft_unregister_expr);
 
-static const struct nft_expr_type *__nft_expr_type_get(struct nlattr *nla)
+static const struct nft_expr_type *__nft_expr_type_get(u8 family,
+						       struct nlattr *nla)
 {
 	const struct nft_expr_type *type;
 
 	list_for_each_entry(type, &nf_tables_expressions, list) {
-		if (!nla_strcmp(nla, type->name))
+		if (!nla_strcmp(nla, type->name) &&
+		    (!type->family || type->family == family))
 			return type;
 	}
 	return NULL;
 }
 
-static const struct nft_expr_type *nft_expr_type_get(struct nlattr *nla)
+static const struct nft_expr_type *nft_expr_type_get(u8 family,
+						     struct nlattr *nla)
 {
 	const struct nft_expr_type *type;
 
 	if (nla == NULL)
 		return ERR_PTR(-EINVAL);
 
-	type = __nft_expr_type_get(nla);
+	type = __nft_expr_type_get(family, nla);
 	if (type != NULL && try_module_get(type->owner))
 		return type;
 
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
 		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+		request_module("nft-expr-%u-%.*s", family,
+			       nla_len(nla), (char *)nla_data(nla));
+		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		if (__nft_expr_type_get(family, nla))
+			return ERR_PTR(-EAGAIN);
+
+		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 		request_module("nft-expr-%.*s",
 			       nla_len(nla), (char *)nla_data(nla));
 		nfnl_lock(NFNL_SUBSYS_NFTABLES);
-		if (__nft_expr_type_get(nla))
+		if (__nft_expr_type_get(family, nla))
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -1193,7 +1203,7 @@
 	if (err < 0)
 		return err;
 
-	type = nft_expr_type_get(tb[NFTA_EXPR_NAME]);
+	type = nft_expr_type_get(ctx->afi->family, tb[NFTA_EXPR_NAME]);
 	if (IS_ERR(type))
 		return PTR_ERR(type);
 
@@ -1521,9 +1531,8 @@
 	return err;
 }
 
-static void nf_tables_rcu_rule_destroy(struct rcu_head *head)
+static void nf_tables_rule_destroy(struct nft_rule *rule)
 {
-	struct nft_rule *rule = container_of(head, struct nft_rule, rcu_head);
 	struct nft_expr *expr;
 
 	/*
@@ -1538,11 +1547,6 @@
 	kfree(rule);
 }
 
-static void nf_tables_rule_destroy(struct nft_rule *rule)
-{
-	call_rcu(&rule->rcu_head, nf_tables_rcu_rule_destroy);
-}
-
 #define NFT_RULE_MAXEXPRS	128
 
 static struct nft_expr_info *info;
@@ -1809,9 +1813,6 @@
 	synchronize_rcu();
 
 	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
-		/* Delete this rule from the dirty list */
-		list_del(&rupd->list);
-
 		/* This rule was inactive in the past and just became active.
 		 * Clear the next bit of the genmask since its meaning has
 		 * changed, now it is the future.
@@ -1822,6 +1823,7 @@
 					      rupd->chain, rupd->rule,
 					      NFT_MSG_NEWRULE, 0,
 					      rupd->family);
+			list_del(&rupd->list);
 			kfree(rupd);
 			continue;
 		}
@@ -1831,7 +1833,15 @@
 		nf_tables_rule_notify(skb, rupd->nlh, rupd->table, rupd->chain,
 				      rupd->rule, NFT_MSG_DELRULE, 0,
 				      rupd->family);
+	}
+
+	/* Make sure we don't see any packet traversing old rules */
+	synchronize_rcu();
+
+	/* Now we can safely release unused old rules */
+	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
 		nf_tables_rule_destroy(rupd->rule);
+		list_del(&rupd->list);
 		kfree(rupd);
 	}
 
@@ -1844,20 +1854,26 @@
 	struct nft_rule_trans *rupd, *tmp;
 
 	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
-		/* Delete all rules from the dirty list */
-		list_del(&rupd->list);
-
 		if (!nft_rule_is_active_next(net, rupd->rule)) {
 			nft_rule_clear(net, rupd->rule);
+			list_del(&rupd->list);
 			kfree(rupd);
 			continue;
 		}
 
 		/* This rule is inactive, get rid of it */
 		list_del_rcu(&rupd->rule->list);
+	}
+
+	/* Make sure we don't see any packet accessing aborted rules */
+	synchronize_rcu();
+
+	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
 		nf_tables_rule_destroy(rupd->rule);
+		list_del(&rupd->list);
 		kfree(rupd);
 	}
+
 	return 0;
 }
 
@@ -1943,6 +1959,9 @@
 	}
 
 	if (nla[NFTA_SET_TABLE] != NULL) {
+		if (afi == NULL)
+			return -EAFNOSUPPORT;
+
 		table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]);
 		if (IS_ERR(table))
 			return PTR_ERR(table);
@@ -1989,13 +2008,13 @@
 
 			if (!sscanf(i->name, name, &tmp))
 				continue;
-			if (tmp < 0 || tmp > BITS_PER_LONG * PAGE_SIZE)
+			if (tmp < 0 || tmp >= BITS_PER_BYTE * PAGE_SIZE)
 				continue;
 
 			set_bit(tmp, inuse);
 		}
 
-		n = find_first_zero_bit(inuse, BITS_PER_LONG * PAGE_SIZE);
+		n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE);
 		free_page((unsigned long)inuse);
 	}
 
@@ -2428,6 +2447,8 @@
 	struct nft_ctx ctx;
 	int err;
 
+	if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
+		return -EAFNOSUPPORT;
 	if (nla[NFTA_SET_TABLE] == NULL)
 		return -EINVAL;
 
@@ -2435,9 +2456,6 @@
 	if (err < 0)
 		return err;
 
-	if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
-		return -EAFNOSUPPORT;
-
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
@@ -2723,6 +2741,9 @@
 		if (nla[NFTA_SET_ELEM_DATA] == NULL &&
 		    !(elem.flags & NFT_SET_ELEM_INTERVAL_END))
 			return -EINVAL;
+		if (nla[NFTA_SET_ELEM_DATA] != NULL &&
+		    elem.flags & NFT_SET_ELEM_INTERVAL_END)
+			return -EINVAL;
 	} else {
 		if (nla[NFTA_SET_ELEM_DATA] != NULL)
 			return -EINVAL;
@@ -2977,6 +2998,9 @@
 					const struct nft_set_iter *iter,
 					const struct nft_set_elem *elem)
 {
+	if (elem->flags & NFT_SET_ELEM_INTERVAL_END)
+		return 0;
+
 	switch (elem->data.verdict) {
 	case NFT_JUMP:
 	case NFT_GOTO:
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 0d879fc..90998a6 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -103,9 +103,9 @@
 	},
 };
 
-static inline void nft_trace_packet(const struct nft_pktinfo *pkt,
-				    const struct nft_chain *chain,
-				    int rulenum, enum nft_trace type)
+static void nft_trace_packet(const struct nft_pktinfo *pkt,
+			     const struct nft_chain *chain,
+			     int rulenum, enum nft_trace type)
 {
 	struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
 
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index f072fe8..108120f 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -354,13 +354,16 @@
 
 	skb = nfnetlink_alloc_skb(net, size, queue->peer_portid,
 				  GFP_ATOMIC);
-	if (!skb)
+	if (!skb) {
+		skb_tx_error(entskb);
 		return NULL;
+	}
 
 	nlh = nlmsg_put(skb, 0, 0,
 			NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
 			sizeof(struct nfgenmsg), 0);
 	if (!nlh) {
+		skb_tx_error(entskb);
 		kfree_skb(skb);
 		return NULL;
 	}
@@ -488,13 +491,15 @@
 		nla->nla_type = NFQA_PAYLOAD;
 		nla->nla_len = nla_attr_size(data_len);
 
-		skb_zerocopy(skb, entskb, data_len, hlen);
+		if (skb_zerocopy(skb, entskb, data_len, hlen))
+			goto nla_put_failure;
 	}
 
 	nlh->nlmsg_len = skb->len;
 	return skb;
 
 nla_put_failure:
+	skb_tx_error(entskb);
 	kfree_skb(skb);
 	net_err_ratelimited("nf_queue: error creating packet message\n");
 	return NULL;
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 917052e..46e2754 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -226,6 +226,7 @@
 		if (tb[NFTA_CT_DIRECTION] != NULL)
 			return -EINVAL;
 		break;
+	case NFT_CT_L3PROTOCOL:
 	case NFT_CT_PROTOCOL:
 	case NFT_CT_SRC:
 	case NFT_CT_DST:
@@ -311,8 +312,19 @@
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key)))
 		goto nla_put_failure;
-	if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir))
-		goto nla_put_failure;
+
+	switch (priv->key) {
+	case NFT_CT_PROTOCOL:
+	case NFT_CT_SRC:
+	case NFT_CT_DST:
+	case NFT_CT_PROTO_SRC:
+	case NFT_CT_PROTO_DST:
+		if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir))
+			goto nla_put_failure;
+	default:
+		break;
+	}
+
 	return 0;
 
 nla_put_failure:
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 5af7901..26c5154 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -23,7 +23,6 @@
 struct nft_log {
 	struct nf_loginfo	loginfo;
 	char			*prefix;
-	int			family;
 };
 
 static void nft_log_eval(const struct nft_expr *expr,
@@ -33,7 +32,7 @@
 	const struct nft_log *priv = nft_expr_priv(expr);
 	struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
 
-	nf_log_packet(net, priv->family, pkt->ops->hooknum, pkt->skb, pkt->in,
+	nf_log_packet(net, pkt->ops->pf, pkt->ops->hooknum, pkt->skb, pkt->in,
 		      pkt->out, &priv->loginfo, "%s", priv->prefix);
 }
 
@@ -52,8 +51,6 @@
 	struct nf_loginfo *li = &priv->loginfo;
 	const struct nlattr *nla;
 
-	priv->family = ctx->afi->family;
-
 	nla = tb[NFTA_LOG_PREFIX];
 	if (nla != NULL) {
 		priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 8a6116b..bb4ef4c 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -16,6 +16,7 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
 
 struct nft_lookup {
 	struct nft_set			*set;
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index e8254ad..425cf39 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -116,7 +116,7 @@
 				 skb->sk->sk_socket->file->f_cred->fsgid);
 		read_unlock_bh(&skb->sk->sk_callback_lock);
 		break;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	case NFT_META_RTCLASSID: {
 		const struct dst_entry *dst = skb_dst(skb);
 
@@ -199,7 +199,7 @@
 	case NFT_META_OIFTYPE:
 	case NFT_META_SKUID:
 	case NFT_META_SKGID:
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	case NFT_META_RTCLASSID:
 #endif
 #ifdef CONFIG_NETWORK_SECMARK
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index a2aeb31..85daa84 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -135,7 +135,8 @@
 	if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data))
 		return ERR_PTR(-EINVAL);
 
-	if (len <= 4 && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER)
+	if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
+	    base != NFT_PAYLOAD_LL_HEADER)
 		return &nft_payload_fast_ops;
 	else
 		return &nft_payload_ops;
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
index cbea473..e8ae2f6 100644
--- a/net/netfilter/nft_queue.c
+++ b/net/netfilter/nft_queue.c
@@ -25,7 +25,6 @@
 	u16	queuenum;
 	u16	queues_total;
 	u16	flags;
-	u8	family;
 };
 
 static void nft_queue_eval(const struct nft_expr *expr,
@@ -43,7 +42,7 @@
 			queue = priv->queuenum + cpu % priv->queues_total;
 		} else {
 			queue = nfqueue_hash(pkt->skb, queue,
-					     priv->queues_total, priv->family,
+					     priv->queues_total, pkt->ops->pf,
 					     jhash_initval);
 		}
 	}
@@ -71,7 +70,6 @@
 		return -EINVAL;
 
 	init_hashrandom(&jhash_initval);
-	priv->family = ctx->afi->family;
 	priv->queuenum = ntohs(nla_get_be16(tb[NFTA_QUEUE_NUM]));
 
 	if (tb[NFTA_QUEUE_TOTAL] != NULL)
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index ca0c1b2..e21d69d 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -69,8 +69,10 @@
 				    struct nft_rbtree_elem *rbe)
 {
 	nft_data_uninit(&rbe->key, NFT_DATA_VALUE);
-	if (set->flags & NFT_SET_MAP)
+	if (set->flags & NFT_SET_MAP &&
+	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 		nft_data_uninit(rbe->data, set->dtype);
+
 	kfree(rbe);
 }
 
@@ -108,7 +110,8 @@
 	int err;
 
 	size = sizeof(*rbe);
-	if (set->flags & NFT_SET_MAP)
+	if (set->flags & NFT_SET_MAP &&
+	    !(elem->flags & NFT_SET_ELEM_INTERVAL_END))
 		size += sizeof(rbe->data[0]);
 
 	rbe = kzalloc(size, GFP_KERNEL);
@@ -117,7 +120,8 @@
 
 	rbe->flags = elem->flags;
 	nft_data_copy(&rbe->key, &elem->key);
-	if (set->flags & NFT_SET_MAP)
+	if (set->flags & NFT_SET_MAP &&
+	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 		nft_data_copy(rbe->data, &elem->data);
 
 	err = __nft_rbtree_insert(set, rbe);
@@ -153,7 +157,8 @@
 			parent = parent->rb_right;
 		else {
 			elem->cookie = rbe;
-			if (set->flags & NFT_SET_MAP)
+			if (set->flags & NFT_SET_MAP &&
+			    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 				nft_data_copy(&elem->data, rbe->data);
 			elem->flags = rbe->flags;
 			return 0;
@@ -177,7 +182,8 @@
 
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 		nft_data_copy(&elem.key, &rbe->key);
-		if (set->flags & NFT_SET_MAP)
+		if (set->flags & NFT_SET_MAP &&
+		    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 			nft_data_copy(&elem.data, rbe->data);
 		elem.flags = rbe->flags;
 
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index 5e204711..f3448c2 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -16,65 +16,23 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
-#include <net/icmp.h>
-#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/nft_reject.h>
 
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
-#include <net/netfilter/ipv6/nf_reject.h>
-#endif
-
-struct nft_reject {
-	enum nft_reject_types	type:8;
-	u8			icmp_code;
-	u8			family;
-};
-
-static void nft_reject_eval(const struct nft_expr *expr,
-			      struct nft_data data[NFT_REG_MAX + 1],
-			      const struct nft_pktinfo *pkt)
-{
-	struct nft_reject *priv = nft_expr_priv(expr);
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
-	struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
-#endif
-	switch (priv->type) {
-	case NFT_REJECT_ICMP_UNREACH:
-		if (priv->family == NFPROTO_IPV4)
-			nf_send_unreach(pkt->skb, priv->icmp_code);
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
-		else if (priv->family == NFPROTO_IPV6)
-			nf_send_unreach6(net, pkt->skb, priv->icmp_code,
-				      pkt->ops->hooknum);
-#endif
-		break;
-	case NFT_REJECT_TCP_RST:
-		if (priv->family == NFPROTO_IPV4)
-			nf_send_reset(pkt->skb, pkt->ops->hooknum);
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
-		else if (priv->family == NFPROTO_IPV6)
-			nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
-#endif
-		break;
-	}
-
-	data[NFT_REG_VERDICT].verdict = NF_DROP;
-}
-
-static const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
+const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
 	[NFTA_REJECT_TYPE]		= { .type = NLA_U32 },
 	[NFTA_REJECT_ICMP_CODE]		= { .type = NLA_U8 },
 };
+EXPORT_SYMBOL_GPL(nft_reject_policy);
 
-static int nft_reject_init(const struct nft_ctx *ctx,
-			   const struct nft_expr *expr,
-			   const struct nlattr * const tb[])
+int nft_reject_init(const struct nft_ctx *ctx,
+		    const struct nft_expr *expr,
+		    const struct nlattr * const tb[])
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
 
 	if (tb[NFTA_REJECT_TYPE] == NULL)
 		return -EINVAL;
 
-	priv->family = ctx->afi->family;
 	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
 	switch (priv->type) {
 	case NFT_REJECT_ICMP_UNREACH:
@@ -89,8 +47,9 @@
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nft_reject_init);
 
-static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
+int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_reject *priv = nft_expr_priv(expr);
 
@@ -109,37 +68,7 @@
 nla_put_failure:
 	return -1;
 }
-
-static struct nft_expr_type nft_reject_type;
-static const struct nft_expr_ops nft_reject_ops = {
-	.type		= &nft_reject_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
-	.eval		= nft_reject_eval,
-	.init		= nft_reject_init,
-	.dump		= nft_reject_dump,
-};
-
-static struct nft_expr_type nft_reject_type __read_mostly = {
-	.name		= "reject",
-	.ops		= &nft_reject_ops,
-	.policy		= nft_reject_policy,
-	.maxattr	= NFTA_REJECT_MAX,
-	.owner		= THIS_MODULE,
-};
-
-static int __init nft_reject_module_init(void)
-{
-	return nft_register_expr(&nft_reject_type);
-}
-
-static void __exit nft_reject_module_exit(void)
-{
-	nft_unregister_expr(&nft_reject_type);
-}
-
-module_init(nft_reject_module_init);
-module_exit(nft_reject_module_exit);
+EXPORT_SYMBOL_GPL(nft_reject_dump);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_EXPR("reject");
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
new file mode 100644
index 0000000..b718a52
--- /dev/null
+++ b/net/netfilter/nft_reject_inet.c
@@ -0,0 +1,63 @@
+/*
+ * Copyright (c) 2014 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+
+static void nft_reject_inet_eval(const struct nft_expr *expr,
+				 struct nft_data data[NFT_REG_MAX + 1],
+				 const struct nft_pktinfo *pkt)
+{
+	switch (pkt->ops->pf) {
+	case NFPROTO_IPV4:
+		return nft_reject_ipv4_eval(expr, data, pkt);
+	case NFPROTO_IPV6:
+		return nft_reject_ipv6_eval(expr, data, pkt);
+	}
+}
+
+static struct nft_expr_type nft_reject_inet_type;
+static const struct nft_expr_ops nft_reject_inet_ops = {
+	.type		= &nft_reject_inet_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+	.eval		= nft_reject_inet_eval,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_inet_type __read_mostly = {
+	.family		= NFPROTO_INET,
+	.name		= "reject",
+	.ops		= &nft_reject_inet_ops,
+	.policy		= nft_reject_policy,
+	.maxattr	= NFTA_REJECT_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_reject_inet_module_init(void)
+{
+	return nft_register_expr(&nft_reject_inet_type);
+}
+
+static void __exit nft_reject_inet_module_exit(void)
+{
+	nft_unregister_expr(&nft_reject_inet_type);
+}
+
+module_init(nft_reject_inet_module_init);
+module_exit(nft_reject_inet_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(1, "reject");
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 5929be6..75747ae 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -228,12 +228,7 @@
 			goto err3;
 	}
 
-	__set_bit(IPS_TEMPLATE_BIT, &ct->status);
-	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
-
-	/* Overload tuple linked list to put us in template list. */
-	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
-				 &par->net->ct.tmpl);
+	nf_conntrack_tmpl_insert(par->net, ct);
 out:
 	info->ct = ct;
 	return 0;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index fdf5135..04748ab6 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1489,8 +1489,8 @@
 	if (addr->sa_family != AF_NETLINK)
 		return -EINVAL;
 
-	/* Only superuser is allowed to send multicasts */
-	if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+	if ((nladdr->nl_groups || nladdr->nl_pid) &&
+	    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
 	if (!nlk->portid)
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 46bda01..56db888 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -301,7 +301,7 @@
 	rc = __nci_request(ndev, nci_reset_req, 0,
 			   msecs_to_jiffies(NCI_RESET_TIMEOUT));
 
-	if (ndev->ops->setup(ndev))
+	if (ndev->ops->setup)
 		ndev->ops->setup(ndev);
 
 	if (!rc) {
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index df46928..270b77d 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -55,6 +55,7 @@
 
 #include "datapath.h"
 #include "flow.h"
+#include "flow_table.h"
 #include "flow_netlink.h"
 #include "vport-internal_dev.h"
 #include "vport-netdev.h"
@@ -160,7 +161,6 @@
 {
 	struct datapath *dp = container_of(rcu, struct datapath, rcu);
 
-	ovs_flow_tbl_destroy(&dp->table);
 	free_percpu(dp->stats_percpu);
 	release_net(ovs_dp_get_net(dp));
 	kfree(dp->ports);
@@ -464,12 +464,24 @@
 	}
 	nla->nla_len = nla_attr_size(skb->len);
 
-	skb_zerocopy(user_skb, skb, skb->len, hlen);
+	err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+	if (err)
+		goto out;
+
+	/* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */
+	if (!(dp->user_features & OVS_DP_F_UNALIGNED)) {
+		size_t plen = NLA_ALIGN(user_skb->len) - user_skb->len;
+
+		if (plen > 0)
+			memset(skb_put(user_skb, plen), 0, plen);
+	}
 
 	((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len;
 
 	err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid);
 out:
+	if (err)
+		skb_tx_error(skb);
 	kfree_skb(nskb);
 	return err;
 }
@@ -852,11 +864,8 @@
 			goto err_unlock_ovs;
 
 		/* The unmasked key has to be the same for flow updates. */
-		error = -EINVAL;
-		if (!ovs_flow_cmp_unmasked_key(flow, &match)) {
-			OVS_NLERR("Flow modification message rejected, unmasked key does not match.\n");
+		if (!ovs_flow_cmp_unmasked_key(flow, &match))
 			goto err_unlock_ovs;
-		}
 
 		/* Update actions. */
 		old_acts = ovsl_dereference(flow->sf_acts);
@@ -1079,6 +1088,7 @@
 	msgsize += nla_total_size(IFNAMSIZ);
 	msgsize += nla_total_size(sizeof(struct ovs_dp_stats));
 	msgsize += nla_total_size(sizeof(struct ovs_dp_megaflow_stats));
+	msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */
 
 	return msgsize;
 }
@@ -1168,7 +1178,7 @@
 	struct datapath *dp;
 
 	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
-	if (!dp)
+	if (IS_ERR(dp))
 		return;
 
 	WARN(dp->user_features, "Dropping previously announced user features\n");
@@ -1279,7 +1289,7 @@
 err_destroy_percpu:
 	free_percpu(dp->stats_percpu);
 err_destroy_table:
-	ovs_flow_tbl_destroy(&dp->table);
+	ovs_flow_tbl_destroy(&dp->table, false);
 err_free_dp:
 	release_net(ovs_dp_get_net(dp));
 	kfree(dp);
@@ -1306,10 +1316,13 @@
 	list_del_rcu(&dp->list_node);
 
 	/* OVSP_LOCAL is datapath internal port. We need to make sure that
-	 * all port in datapath are destroyed first before freeing datapath.
+	 * all ports in datapath are destroyed first before freeing datapath.
 	 */
 	ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));
 
+	/* RCU destroy the flow table */
+	ovs_flow_tbl_destroy(&dp->table, true);
+
 	call_rcu(&dp->rcu, destroy_dp_rcu);
 }
 
@@ -1753,11 +1766,12 @@
 	int bucket = cb->args[0], skip = cb->args[1];
 	int i, j = 0;
 
-	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
-	if (!dp)
-		return -ENODEV;
-
 	rcu_read_lock();
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		rcu_read_unlock();
+		return -ENODEV;
+	}
 	for (i = bucket; i < DP_VPORT_HASH_BUCKETS; i++) {
 		struct vport *vport;
 
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 16f4b46..2998989 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -73,6 +73,7 @@
 
 	if ((flow->key.eth.type == htons(ETH_P_IP) ||
 	     flow->key.eth.type == htons(ETH_P_IPV6)) &&
+	    flow->key.ip.frag != OVS_FRAG_TYPE_LATER &&
 	    flow->key.ip.proto == IPPROTO_TCP &&
 	    likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) {
 		tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb));
@@ -91,7 +92,7 @@
 		       unsigned long *used, __be16 *tcp_flags)
 {
 	spin_lock(&stats->lock);
-	if (time_after(stats->used, *used))
+	if (!*used || time_after(stats->used, *used))
 		*used = stats->used;
 	*tcp_flags |= stats->tcp_flags;
 	ovs_stats->n_packets += stats->packet_count;
@@ -102,30 +103,24 @@
 void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats,
 			unsigned long *used, __be16 *tcp_flags)
 {
-	int cpu, cur_cpu;
+	int cpu;
 
 	*used = 0;
 	*tcp_flags = 0;
 	memset(ovs_stats, 0, sizeof(*ovs_stats));
 
+	local_bh_disable();
 	if (!flow->stats.is_percpu) {
 		stats_read(flow->stats.stat, ovs_stats, used, tcp_flags);
 	} else {
-		cur_cpu = get_cpu();
 		for_each_possible_cpu(cpu) {
 			struct flow_stats *stats;
 
-			if (cpu == cur_cpu)
-				local_bh_disable();
-
 			stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
 			stats_read(stats, ovs_stats, used, tcp_flags);
-
-			if (cpu == cur_cpu)
-				local_bh_enable();
 		}
-		put_cpu();
 	}
+	local_bh_enable();
 }
 
 static void stats_reset(struct flow_stats *stats)
@@ -140,25 +135,17 @@
 
 void ovs_flow_stats_clear(struct sw_flow *flow)
 {
-	int cpu, cur_cpu;
+	int cpu;
 
+	local_bh_disable();
 	if (!flow->stats.is_percpu) {
 		stats_reset(flow->stats.stat);
 	} else {
-		cur_cpu = get_cpu();
-
 		for_each_possible_cpu(cpu) {
-
-			if (cpu == cur_cpu)
-				local_bh_disable();
-
 			stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu));
-
-			if (cpu == cur_cpu)
-				local_bh_enable();
 		}
-		put_cpu();
 	}
+	local_bh_enable();
 }
 
 static int check_header(struct sk_buff *skb, int len)
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index c58a0fe..3c268b3 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -153,29 +153,29 @@
 	flow_free(flow);
 }
 
-static void flow_mask_del_ref(struct sw_flow_mask *mask, bool deferred)
-{
-	if (!mask)
-		return;
-
-	BUG_ON(!mask->ref_count);
-	mask->ref_count--;
-
-	if (!mask->ref_count) {
-		list_del_rcu(&mask->list);
-		if (deferred)
-			kfree_rcu(mask, rcu);
-		else
-			kfree(mask);
-	}
-}
-
 void ovs_flow_free(struct sw_flow *flow, bool deferred)
 {
 	if (!flow)
 		return;
 
-	flow_mask_del_ref(flow->mask, deferred);
+	if (flow->mask) {
+		struct sw_flow_mask *mask = flow->mask;
+
+		/* ovs-lock is required to protect mask-refcount and
+		 * mask list.
+		 */
+		ASSERT_OVSL();
+		BUG_ON(!mask->ref_count);
+		mask->ref_count--;
+
+		if (!mask->ref_count) {
+			list_del_rcu(&mask->list);
+			if (deferred)
+				kfree_rcu(mask, rcu);
+			else
+				kfree(mask);
+		}
+	}
 
 	if (deferred)
 		call_rcu(&flow->rcu, rcu_free_flow_callback);
@@ -188,26 +188,9 @@
 	flex_array_free(buckets);
 }
 
+
 static void __table_instance_destroy(struct table_instance *ti)
 {
-	int i;
-
-	if (ti->keep_flows)
-		goto skip_flows;
-
-	for (i = 0; i < ti->n_buckets; i++) {
-		struct sw_flow *flow;
-		struct hlist_head *head = flex_array_get(ti->buckets, i);
-		struct hlist_node *n;
-		int ver = ti->node_ver;
-
-		hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
-			hlist_del(&flow->hash_node[ver]);
-			ovs_flow_free(flow, false);
-		}
-	}
-
-skip_flows:
 	free_buckets(ti->buckets);
 	kfree(ti);
 }
@@ -258,20 +241,38 @@
 
 static void table_instance_destroy(struct table_instance *ti, bool deferred)
 {
+	int i;
+
 	if (!ti)
 		return;
 
+	if (ti->keep_flows)
+		goto skip_flows;
+
+	for (i = 0; i < ti->n_buckets; i++) {
+		struct sw_flow *flow;
+		struct hlist_head *head = flex_array_get(ti->buckets, i);
+		struct hlist_node *n;
+		int ver = ti->node_ver;
+
+		hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
+			hlist_del_rcu(&flow->hash_node[ver]);
+			ovs_flow_free(flow, deferred);
+		}
+	}
+
+skip_flows:
 	if (deferred)
 		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
 	else
 		__table_instance_destroy(ti);
 }
 
-void ovs_flow_tbl_destroy(struct flow_table *table)
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred)
 {
 	struct table_instance *ti = ovsl_dereference(table->ti);
 
-	table_instance_destroy(ti, false);
+	table_instance_destroy(ti, deferred);
 }
 
 struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
@@ -504,16 +505,11 @@
 
 	mask = kmalloc(sizeof(*mask), GFP_KERNEL);
 	if (mask)
-		mask->ref_count = 0;
+		mask->ref_count = 1;
 
 	return mask;
 }
 
-static void mask_add_ref(struct sw_flow_mask *mask)
-{
-	mask->ref_count++;
-}
-
 static bool mask_equal(const struct sw_flow_mask *a,
 		       const struct sw_flow_mask *b)
 {
@@ -554,9 +550,11 @@
 		mask->key = new->key;
 		mask->range = new->range;
 		list_add_rcu(&mask->list, &tbl->mask_list);
+	} else {
+		BUG_ON(!mask->ref_count);
+		mask->ref_count++;
 	}
 
-	mask_add_ref(mask);
 	flow->mask = mask;
 	return 0;
 }
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 1996e34..baaeb10 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -60,7 +60,7 @@
 
 int ovs_flow_tbl_init(struct flow_table *);
 int ovs_flow_tbl_count(struct flow_table *table);
-void ovs_flow_tbl_destroy(struct flow_table *table);
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred);
 int ovs_flow_tbl_flush(struct flow_table *flow_table);
 
 int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 6a2bb37..48a6a93 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -308,11 +308,27 @@
 	return po->xmit == packet_direct_xmit;
 }
 
-static u16 packet_pick_tx_queue(struct net_device *dev)
+static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
 {
 	return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
 }
 
+static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	u16 queue_index;
+
+	if (ops->ndo_select_queue) {
+		queue_index = ops->ndo_select_queue(dev, skb, NULL,
+						    __packet_pick_tx_queue);
+		queue_index = netdev_cap_txqueue(dev, queue_index);
+	} else {
+		queue_index = __packet_pick_tx_queue(dev, skb);
+	}
+
+	skb_set_queue_mapping(skb, queue_index);
+}
+
 /* register_prot_hook must be invoked with the po->bind_lock held,
  * or from a context in which asynchronous accesses to the packet
  * socket is not possible (packet_create()).
@@ -2285,7 +2301,8 @@
 			}
 		}
 
-		skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
+		packet_pick_tx_queue(dev, skb);
+
 		skb->destructor = tpacket_destruct_skb;
 		__packet_set_status(po, ph, TP_STATUS_SENDING);
 		packet_inc_pending(&po->tx_ring);
@@ -2499,7 +2516,8 @@
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
-	skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
+
+	packet_pick_tx_queue(dev, skb);
 
 	if (po->has_vnet_hdr) {
 		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
@@ -3786,7 +3804,7 @@
 		 */
 			if (!tx_ring)
 				init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring);
-				break;
+			break;
 		default:
 			break;
 		}
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 1313145..a07d55e 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -273,11 +273,12 @@
 
 void qdisc_list_add(struct Qdisc *q)
 {
-	struct Qdisc *root = qdisc_dev(q)->qdisc;
+	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+		struct Qdisc *root = qdisc_dev(q)->qdisc;
 
-	WARN_ON_ONCE(root == &noop_qdisc);
-	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
+		WARN_ON_ONCE(root == &noop_qdisc);
 		list_add_tail(&q->list, &root->list);
+	}
 }
 EXPORT_SYMBOL(qdisc_list_add);
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 08ef7a4..21e2517 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -601,6 +601,7 @@
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct rb_root *array;
+	void *old_fq_root;
 	u32 idx;
 
 	if (q->fq_root && log == q->fq_trees_log)
@@ -615,13 +616,19 @@
 	for (idx = 0; idx < (1U << log); idx++)
 		array[idx] = RB_ROOT;
 
-	if (q->fq_root) {
-		fq_rehash(q, q->fq_root, q->fq_trees_log, array, log);
-		fq_free(q->fq_root);
-	}
+	sch_tree_lock(sch);
+
+	old_fq_root = q->fq_root;
+	if (old_fq_root)
+		fq_rehash(q, old_fq_root, q->fq_trees_log, array, log);
+
 	q->fq_root = array;
 	q->fq_trees_log = log;
 
+	sch_tree_unlock(sch);
+
+	fq_free(old_fq_root);
+
 	return 0;
 }
 
@@ -697,9 +704,11 @@
 		q->flow_refill_delay = usecs_to_jiffies(usecs_delay);
 	}
 
-	if (!err)
+	if (!err) {
+		sch_tree_unlock(sch);
 		err = fq_resize(sch, fq_log);
-
+		sch_tree_lock(sch);
+	}
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = fq_dequeue(sch);
 
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index a255d02..fefeeb7 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -15,6 +15,11 @@
  *
  * ECN support is added by Naeem Khademi <naeemk@ifi.uio.no>
  * University of Oslo, Norway.
+ *
+ * References:
+ * IETF draft submission: http://tools.ietf.org/html/draft-pan-aqm-pie-00
+ * IEEE  Conference on High Performance Switching and Routing 2013 :
+ * "PIE: A * Lightweight Control Scheme to Address the Bufferbloat Problem"
  */
 
 #include <linux/module.h>
@@ -36,7 +41,7 @@
 	psched_time_t target;	/* user specified target delay in pschedtime */
 	u32 tupdate;		/* timer frequency (in jiffies) */
 	u32 limit;		/* number of packets that can be enqueued */
-	u32 alpha;		/* alpha and beta are between -4 and 4 */
+	u32 alpha;		/* alpha and beta are between 0 and 32 */
 	u32 beta;		/* and are used for shift relative to 1 */
 	bool ecn;		/* true if ecn is enabled */
 	bool bytemode;		/* to scale drop early prob based on pkt size */
@@ -326,10 +331,16 @@
 	if (qdelay == 0 && qlen != 0)
 		update_prob = false;
 
-	/* Add ranges for alpha and beta, more aggressive for high dropping
-	 * mode and gentle steps for light dropping mode
-	 * In light dropping mode, take gentle steps; in medium dropping mode,
-	 * take medium steps; in high dropping mode, take big steps.
+	/* In the algorithm, alpha and beta are between 0 and 2 with typical
+	 * value for alpha as 0.125. In this implementation, we use values 0-32
+	 * passed from user space to represent this. Also, alpha and beta have
+	 * unit of HZ and need to be scaled before they can used to update
+	 * probability. alpha/beta are updated locally below by 1) scaling them
+	 * appropriately 2) scaling down by 16 to come to 0-2 range.
+	 * Please see paper for details.
+	 *
+	 * We scale alpha and beta differently depending on whether we are in
+	 * light, medium or high dropping mode.
 	 */
 	if (q->vars.prob < MAX_PROB / 100) {
 		alpha =
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 1cb413f..4f505a0 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -334,18 +334,6 @@
 			qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
 						      tb[TCA_TBF_PTAB]));
 
-	if (q->qdisc != &noop_qdisc) {
-		err = fifo_set_limit(q->qdisc, qopt->limit);
-		if (err)
-			goto done;
-	} else if (qopt->limit > 0) {
-		child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
-		if (IS_ERR(child)) {
-			err = PTR_ERR(child);
-			goto done;
-		}
-	}
-
 	buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U);
 	mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U);
 
@@ -390,6 +378,18 @@
 		goto done;
 	}
 
+	if (q->qdisc != &noop_qdisc) {
+		err = fifo_set_limit(q->qdisc, qopt->limit);
+		if (err)
+			goto done;
+	} else if (qopt->limit > 0) {
+		child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
+		if (IS_ERR(child)) {
+			err = PTR_ERR(child);
+			goto done;
+		}
+	}
+
 	sch_tree_lock(sch);
 	if (child) {
 		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 5ae6092..ee13d28 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1239,78 +1239,107 @@
 }
 
 /* Update the retran path for sending a retransmitted packet.
- * Round-robin through the active transports, else round-robin
- * through the inactive transports as this is the next best thing
- * we can try.
+ * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints:
+ *
+ *   When there is outbound data to send and the primary path
+ *   becomes inactive (e.g., due to failures), or where the
+ *   SCTP user explicitly requests to send data to an
+ *   inactive destination transport address, before reporting
+ *   an error to its ULP, the SCTP endpoint should try to send
+ *   the data to an alternate active destination transport
+ *   address if one exists.
+ *
+ *   When retransmitting data that timed out, if the endpoint
+ *   is multihomed, it should consider each source-destination
+ *   address pair in its retransmission selection policy.
+ *   When retransmitting timed-out data, the endpoint should
+ *   attempt to pick the most divergent source-destination
+ *   pair from the original source-destination pair to which
+ *   the packet was transmitted.
+ *
+ *   Note: Rules for picking the most divergent source-destination
+ *   pair are an implementation decision and are not specified
+ *   within this document.
+ *
+ * Our basic strategy is to round-robin transports in priorities
+ * according to sctp_state_prio_map[] e.g., if no such
+ * transport with state SCTP_ACTIVE exists, round-robin through
+ * SCTP_UNKNOWN, etc. You get the picture.
  */
-void sctp_assoc_update_retran_path(struct sctp_association *asoc)
+static const u8 sctp_trans_state_to_prio_map[] = {
+	[SCTP_ACTIVE]	= 3,	/* best case */
+	[SCTP_UNKNOWN]	= 2,
+	[SCTP_PF]	= 1,
+	[SCTP_INACTIVE] = 0,	/* worst case */
+};
+
+static u8 sctp_trans_score(const struct sctp_transport *trans)
 {
-	struct sctp_transport *t, *next;
-	struct list_head *head = &asoc->peer.transport_addr_list;
-	struct list_head *pos;
-
-	if (asoc->peer.transport_count == 1)
-		return;
-
-	/* Find the next transport in a round-robin fashion. */
-	t = asoc->peer.retran_path;
-	pos = &t->transports;
-	next = NULL;
-
-	while (1) {
-		/* Skip the head. */
-		if (pos->next == head)
-			pos = head->next;
-		else
-			pos = pos->next;
-
-		t = list_entry(pos, struct sctp_transport, transports);
-
-		/* We have exhausted the list, but didn't find any
-		 * other active transports.  If so, use the next
-		 * transport.
-		 */
-		if (t == asoc->peer.retran_path) {
-			t = next;
-			break;
-		}
-
-		/* Try to find an active transport. */
-
-		if ((t->state == SCTP_ACTIVE) ||
-		    (t->state == SCTP_UNKNOWN)) {
-			break;
-		} else {
-			/* Keep track of the next transport in case
-			 * we don't find any active transport.
-			 */
-			if (t->state != SCTP_UNCONFIRMED && !next)
-				next = t;
-		}
-	}
-
-	if (t)
-		asoc->peer.retran_path = t;
-	else
-		t = asoc->peer.retran_path;
-
-	pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc,
-		 &t->ipaddr.sa);
+	return sctp_trans_state_to_prio_map[trans->state];
 }
 
-/* Choose the transport for sending retransmit packet.  */
-struct sctp_transport *sctp_assoc_choose_alter_transport(
-	struct sctp_association *asoc, struct sctp_transport *last_sent_to)
+static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr,
+						    struct sctp_transport *best)
+{
+	if (best == NULL)
+		return curr;
+
+	return sctp_trans_score(curr) > sctp_trans_score(best) ? curr : best;
+}
+
+void sctp_assoc_update_retran_path(struct sctp_association *asoc)
+{
+	struct sctp_transport *trans = asoc->peer.retran_path;
+	struct sctp_transport *trans_next = NULL;
+
+	/* We're done as we only have the one and only path. */
+	if (asoc->peer.transport_count == 1)
+		return;
+	/* If active_path and retran_path are the same and active,
+	 * then this is the only active path. Use it.
+	 */
+	if (asoc->peer.active_path == asoc->peer.retran_path &&
+	    asoc->peer.active_path->state == SCTP_ACTIVE)
+		return;
+
+	/* Iterate from retran_path's successor back to retran_path. */
+	for (trans = list_next_entry(trans, transports); 1;
+	     trans = list_next_entry(trans, transports)) {
+		/* Manually skip the head element. */
+		if (&trans->transports == &asoc->peer.transport_addr_list)
+			continue;
+		if (trans->state == SCTP_UNCONFIRMED)
+			continue;
+		trans_next = sctp_trans_elect_best(trans, trans_next);
+		/* Active is good enough for immediate return. */
+		if (trans_next->state == SCTP_ACTIVE)
+			break;
+		/* We've reached the end, time to update path. */
+		if (trans == asoc->peer.retran_path)
+			break;
+	}
+
+	if (trans_next != NULL)
+		asoc->peer.retran_path = trans_next;
+
+	pr_debug("%s: association:%p updated new path to addr:%pISpc\n",
+		 __func__, asoc, &asoc->peer.retran_path->ipaddr.sa);
+}
+
+struct sctp_transport *
+sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
+				  struct sctp_transport *last_sent_to)
 {
 	/* If this is the first time packet is sent, use the active path,
 	 * else use the retran path. If the last packet was sent over the
 	 * retran path, update the retran path and use it.
 	 */
-	if (!last_sent_to)
+	if (last_sent_to == NULL) {
 		return asoc->peer.active_path;
-	else {
+	} else {
 		if (last_sent_to == asoc->peer.retran_path)
 			sctp_assoc_update_retran_path(asoc);
+
 		return asoc->peer.retran_path;
 	}
 }
@@ -1367,44 +1396,35 @@
 	return false;
 }
 
-/* Increase asoc's rwnd by len and send any window update SACK if needed. */
-void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
+/* Update asoc's rwnd for the approximated state in the buffer,
+ * and check whether SACK needs to be sent.
+ */
+void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer)
 {
+	int rx_count;
 	struct sctp_chunk *sack;
 	struct timer_list *timer;
 
-	if (asoc->rwnd_over) {
-		if (asoc->rwnd_over >= len) {
-			asoc->rwnd_over -= len;
-		} else {
-			asoc->rwnd += (len - asoc->rwnd_over);
-			asoc->rwnd_over = 0;
-		}
-	} else {
-		asoc->rwnd += len;
-	}
+	if (asoc->ep->rcvbuf_policy)
+		rx_count = atomic_read(&asoc->rmem_alloc);
+	else
+		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
 
-	/* If we had window pressure, start recovering it
-	 * once our rwnd had reached the accumulated pressure
-	 * threshold.  The idea is to recover slowly, but up
-	 * to the initial advertised window.
-	 */
-	if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) {
-		int change = min(asoc->pathmtu, asoc->rwnd_press);
-		asoc->rwnd += change;
-		asoc->rwnd_press -= change;
-	}
+	if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0)
+		asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1;
+	else
+		asoc->rwnd = 0;
 
-	pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n",
-		 __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
-		 asoc->a_rwnd);
+	pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n",
+		 __func__, asoc, asoc->rwnd, rx_count,
+		 asoc->base.sk->sk_rcvbuf);
 
 	/* Send a window update SACK if the rwnd has increased by at least the
 	 * minimum of the association's PMTU and half of the receive buffer.
 	 * The algorithm used is similar to the one described in
 	 * Section 4.2.3.3 of RFC 1122.
 	 */
-	if (sctp_peer_needs_update(asoc)) {
+	if (update_peer && sctp_peer_needs_update(asoc)) {
 		asoc->a_rwnd = asoc->rwnd;
 
 		pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u "
@@ -1426,45 +1446,6 @@
 	}
 }
 
-/* Decrease asoc's rwnd by len. */
-void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
-{
-	int rx_count;
-	int over = 0;
-
-	if (unlikely(!asoc->rwnd || asoc->rwnd_over))
-		pr_debug("%s: association:%p has asoc->rwnd:%u, "
-			 "asoc->rwnd_over:%u!\n", __func__, asoc,
-			 asoc->rwnd, asoc->rwnd_over);
-
-	if (asoc->ep->rcvbuf_policy)
-		rx_count = atomic_read(&asoc->rmem_alloc);
-	else
-		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
-
-	/* If we've reached or overflowed our receive buffer, announce
-	 * a 0 rwnd if rwnd would still be positive.  Store the
-	 * the potential pressure overflow so that the window can be restored
-	 * back to original value.
-	 */
-	if (rx_count >= asoc->base.sk->sk_rcvbuf)
-		over = 1;
-
-	if (asoc->rwnd >= len) {
-		asoc->rwnd -= len;
-		if (over) {
-			asoc->rwnd_press += asoc->rwnd;
-			asoc->rwnd = 0;
-		}
-	} else {
-		asoc->rwnd_over = len - asoc->rwnd;
-		asoc->rwnd = 0;
-	}
-
-	pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n",
-		 __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
-		 asoc->rwnd_press);
-}
 
 /* Build the bind address list for the association based on info from the
  * local endpoint and the remote peer.
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0f6259a..2b1738e 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -662,6 +662,8 @@
 	 */
 	sctp_v6_to_sk_daddr(&asoc->peer.primary_addr, newsk);
 
+	newsk->sk_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+
 	sk_refcnt_debug_inc(newsk);
 
 	if (newsk->sk_prot->init(newsk)) {
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 632090b..3a1767e 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1421,8 +1421,8 @@
 	BUG_ON(!list_empty(&chunk->list));
 	list_del_init(&chunk->transmitted_list);
 
-	/* Free the chunk skb data and the SCTP_chunk stub itself. */
-	dev_kfree_skb(chunk->skb);
+	consume_skb(chunk->skb);
+	consume_skb(chunk->auth_chunk);
 
 	SCTP_DBG_OBJCNT_DEC(chunk);
 	kmem_cache_free(sctp_chunk_cachep, chunk);
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index bd85915..5d6883f 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -495,11 +495,12 @@
 	}
 
 	/* If the transport error count is greater than the pf_retrans
-	 * threshold, and less than pathmaxrtx, then mark this transport
-	 * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1,
-	 * point 1
+	 * threshold, and less than pathmaxrtx, and if the current state
+	 * is not SCTP_UNCONFIRMED, then mark this transport as Partially
+	 * Failed, see SCTP Quick Failover Draft, section 5.1
 	 */
 	if ((transport->state != SCTP_PF) &&
+	   (transport->state != SCTP_UNCONFIRMED) &&
 	   (asoc->pf_retrans < transport->pathmaxrxt) &&
 	   (transport->error_count > asoc->pf_retrans)) {
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 483dcd7..01e0024 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -758,6 +758,12 @@
 		struct sctp_chunk auth;
 		sctp_ierror_t ret;
 
+		/* Make sure that we and the peer are AUTH capable */
+		if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
+			sctp_association_free(new_asoc);
+			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+		}
+
 		/* set-up our fake chunk so that we can process it */
 		auth.skb = chunk->auth_chunk;
 		auth.asoc = chunk->asoc;
@@ -768,10 +774,6 @@
 		auth.transport = chunk->transport;
 
 		ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
-
-		/* We can now safely free the auth_chunk clone */
-		kfree_skb(chunk->auth_chunk);
-
 		if (ret != SCTP_IERROR_NO_ERROR) {
 			sctp_association_free(new_asoc);
 			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -6176,7 +6178,7 @@
 	 * PMTU.  In cases, such as loopback, this might be a rather
 	 * large spill over.
 	 */
-	if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over ||
+	if ((!chunk->data_accepted) && (!asoc->rwnd ||
 	    (datalen > asoc->rwnd + asoc->frag_point))) {
 
 		/* If this is the next TSN, consider reneging to make
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9e91d6e..981aaf8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -64,6 +64,7 @@
 #include <linux/crypto.h>
 #include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/compat.h>
 
 #include <net/ip.h>
 #include <net/icmp.h>
@@ -1368,11 +1369,19 @@
 /*
  * New (hopefully final) interface for the API.
  * We use the sctp_getaddrs_old structure so that use-space library
- * can avoid any unnecessary allocations.   The only defferent part
+ * can avoid any unnecessary allocations. The only different part
  * is that we store the actual length of the address buffer into the
- * addrs_num structure member.  That way we can re-use the existing
+ * addrs_num structure member. That way we can re-use the existing
  * code.
  */
+#ifdef CONFIG_COMPAT
+struct compat_sctp_getaddrs_old {
+	sctp_assoc_t	assoc_id;
+	s32		addr_num;
+	compat_uptr_t	addrs;		/* struct sockaddr * */
+};
+#endif
+
 static int sctp_getsockopt_connectx3(struct sock *sk, int len,
 				     char __user *optval,
 				     int __user *optlen)
@@ -1381,16 +1390,30 @@
 	sctp_assoc_t assoc_id = 0;
 	int err = 0;
 
-	if (len < sizeof(param))
-		return -EINVAL;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task()) {
+		struct compat_sctp_getaddrs_old param32;
 
-	if (copy_from_user(&param, optval, sizeof(param)))
-		return -EFAULT;
+		if (len < sizeof(param32))
+			return -EINVAL;
+		if (copy_from_user(&param32, optval, sizeof(param32)))
+			return -EFAULT;
 
-	err = __sctp_setsockopt_connectx(sk,
-			(struct sockaddr __user *)param.addrs,
-			param.addr_num, &assoc_id);
+		param.assoc_id = param32.assoc_id;
+		param.addr_num = param32.addr_num;
+		param.addrs = compat_ptr(param32.addrs);
+	} else
+#endif
+	{
+		if (len < sizeof(param))
+			return -EINVAL;
+		if (copy_from_user(&param, optval, sizeof(param)))
+			return -EFAULT;
+	}
 
+	err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *)
+					 param.addrs, param.addr_num,
+					 &assoc_id);
 	if (err == 0 || err == -EINPROGRESS) {
 		if (copy_to_user(optval, &assoc_id, sizeof(assoc_id)))
 			return -EFAULT;
@@ -2092,12 +2115,6 @@
 		sctp_skb_pull(skb, copied);
 		skb_queue_head(&sk->sk_receive_queue, skb);
 
-		/* When only partial message is copied to the user, increase
-		 * rwnd by that amount. If all the data in the skb is read,
-		 * rwnd is updated when the event is freed.
-		 */
-		if (!sctp_ulpevent_is_notification(event))
-			sctp_assoc_rwnd_increase(event->asoc, copied);
 		goto out;
 	} else if ((event->msg_flags & MSG_NOTIFICATION) ||
 		   (event->msg_flags & MSG_EOR))
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 7135e61..35c8923 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -151,6 +151,7 @@
 	},
 	{
 		.procname	= "cookie_hmac_alg",
+		.data		= &init_net.sctp.sctp_hmac_alg,
 		.maxlen		= 8,
 		.mode		= 0644,
 		.proc_handler	= proc_sctp_do_hmac_alg,
@@ -401,15 +402,18 @@
 
 int sctp_sysctl_net_register(struct net *net)
 {
-	struct ctl_table *table;
-	int i;
+	struct ctl_table *table = sctp_net_table;
 
-	table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
-	if (!table)
-		return -ENOMEM;
+	if (!net_eq(net, &init_net)) {
+		int i;
 
-	for (i = 0; table[i].data; i++)
-		table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+		table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
+		if (!table)
+			return -ENOMEM;
+
+		for (i = 0; table[i].data; i++)
+			table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+	}
 
 	net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table);
 	return 0;
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 85c6465..8d198ae 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -989,7 +989,7 @@
 	skb = sctp_event2skb(event);
 	/* Set the owner and charge rwnd for bytes received.  */
 	sctp_ulpevent_set_owner(event, asoc);
-	sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb));
+	sctp_assoc_rwnd_update(asoc, false);
 
 	if (!skb->data_len)
 		return;
@@ -1011,6 +1011,7 @@
 {
 	struct sk_buff *skb, *frag;
 	unsigned int	len;
+	struct sctp_association *asoc;
 
 	/* Current stack structures assume that the rcv buffer is
 	 * per socket.   For UDP style sockets this is not true as
@@ -1035,8 +1036,11 @@
 	}
 
 done:
-	sctp_assoc_rwnd_increase(event->asoc, len);
+	asoc = event->asoc;
+	sctp_association_hold(asoc);
 	sctp_ulpevent_release_owner(event);
+	sctp_assoc_rwnd_update(asoc, true);
+	sctp_association_put(asoc);
 }
 
 static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event)
diff --git a/net/socket.c b/net/socket.c
index 879933a..a19ae19 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -450,16 +450,17 @@
 
 static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	struct socket *sock;
 
 	*err = -EBADF;
-	file = fget_light(fd, fput_needed);
-	if (file) {
-		sock = sock_from_file(file, err);
-		if (sock)
+	if (f.file) {
+		sock = sock_from_file(f.file, err);
+		if (likely(sock)) {
+			*fput_needed = f.flags;
 			return sock;
-		fput_light(file, *fput_needed);
+		}
+		fdput(f);
 	}
 	return NULL;
 }
@@ -1985,6 +1986,10 @@
 {
 	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
 		return -EFAULT;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	return 0;
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 6c0513a..36e431e 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -108,6 +108,7 @@
 static DEFINE_SPINLOCK(pipe_version_lock);
 static struct rpc_wait_queue pipe_version_rpc_waitqueue;
 static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue);
+static void gss_put_auth(struct gss_auth *gss_auth);
 
 static void gss_free_ctx(struct gss_cl_ctx *);
 static const struct rpc_pipe_ops gss_upcall_ops_v0;
@@ -320,6 +321,7 @@
 	if (gss_msg->ctx != NULL)
 		gss_put_ctx(gss_msg->ctx);
 	rpc_destroy_wait_queue(&gss_msg->rpc_waitqueue);
+	gss_put_auth(gss_msg->auth);
 	kfree(gss_msg);
 }
 
@@ -498,9 +500,12 @@
 	default:
 		err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name);
 		if (err)
-			goto err_free_msg;
+			goto err_put_pipe_version;
 	};
+	kref_get(&gss_auth->kref);
 	return gss_msg;
+err_put_pipe_version:
+	put_pipe_version(gss_auth->net);
 err_free_msg:
 	kfree(gss_msg);
 err:
@@ -991,6 +996,8 @@
 	gss_auth->service = gss_pseudoflavor_to_service(gss_auth->mech, flavor);
 	if (gss_auth->service == 0)
 		goto err_put_mech;
+	if (!gssd_running(gss_auth->net))
+		goto err_put_mech;
 	auth = &gss_auth->rpc_auth;
 	auth->au_cslack = GSS_CRED_SLACK >> 2;
 	auth->au_rslack = GSS_VERF_SLACK >> 2;
@@ -1062,6 +1069,12 @@
 }
 
 static void
+gss_put_auth(struct gss_auth *gss_auth)
+{
+	kref_put(&gss_auth->kref, gss_free_callback);
+}
+
+static void
 gss_destroy(struct rpc_auth *auth)
 {
 	struct gss_auth *gss_auth = container_of(auth,
@@ -1082,7 +1095,7 @@
 	gss_auth->gss_pipe[1] = NULL;
 	rpcauth_destroy_credcache(auth);
 
-	kref_put(&gss_auth->kref, gss_free_callback);
+	gss_put_auth(gss_auth);
 }
 
 /*
@@ -1253,7 +1266,7 @@
 	call_rcu(&cred->cr_rcu, gss_free_cred_callback);
 	if (ctx)
 		gss_put_ctx(ctx);
-	kref_put(&gss_auth->kref, gss_free_callback);
+	gss_put_auth(gss_auth);
 }
 
 static void
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 890a299..e860d4f 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -64,7 +64,6 @@
 	free_page((unsigned long)xbufp->head[0].iov_base);
 	xbufp = &req->rq_snd_buf;
 	free_page((unsigned long)xbufp->head[0].iov_base);
-	list_del(&req->rq_bc_pa_list);
 	kfree(req);
 }
 
@@ -168,8 +167,10 @@
 	/*
 	 * Memory allocation failed, free the temporary list
 	 */
-	list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list)
+	list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) {
+		list_del(&req->rq_bc_pa_list);
 		xprt_free_allocation(req);
+	}
 
 	dprintk("RPC:       setup backchannel transport failed\n");
 	return -ENOMEM;
@@ -198,6 +199,7 @@
 	xprt_dec_alloc_count(xprt, max_reqs);
 	list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) {
 		dprintk("RPC:        req=%p\n", req);
+		list_del(&req->rq_bc_pa_list);
 		xprt_free_allocation(req);
 		if (--max_reqs == 0)
 			break;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 80a6640..06c6ff0 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -571,7 +571,7 @@
 	}
 }
 
-int svc_alloc_arg(struct svc_rqst *rqstp)
+static int svc_alloc_arg(struct svc_rqst *rqstp)
 {
 	struct svc_serv *serv = rqstp->rq_server;
 	struct xdr_buf *arg;
@@ -612,7 +612,7 @@
 	return 0;
 }
 
-struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
+static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 {
 	struct svc_xprt *xprt;
 	struct svc_pool		*pool = rqstp->rq_pool;
@@ -691,7 +691,7 @@
 	return xprt;
 }
 
-void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
+static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
 {
 	spin_lock_bh(&serv->sv_lock);
 	set_bit(XPT_TEMP, &newxpt->xpt_flags);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 817a1e5..0addefc 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -510,6 +510,7 @@
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	struct sock *sk = transport->inet;
 	int ret = -EAGAIN;
 
 	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
@@ -527,7 +528,7 @@
 			 * window size
 			 */
 			set_bit(SOCK_NOSPACE, &transport->sock->flags);
-			transport->inet->sk_write_pending++;
+			sk->sk_write_pending++;
 			/* ...and wait for more buffer space */
 			xprt_wait_for_buffer_space(task, xs_nospace_callback);
 		}
@@ -537,6 +538,9 @@
 	}
 
 	spin_unlock_bh(&xprt->transport_lock);
+
+	/* Race breaker in case memory is freed before above code is called */
+	sk->sk_write_space(sk);
 	return ret;
 }
 
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index a38c899..574b861 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -610,8 +610,13 @@
 
 int tipc_bearer_setup(void)
 {
+	int err;
+
+	err = register_netdevice_notifier(&notifier);
+	if (err)
+		return err;
 	dev_add_pack(&tipc_packet_type);
-	return register_netdevice_notifier(&notifier);
+	return 0;
 }
 
 void tipc_bearer_cleanup(void)
diff --git a/net/tipc/config.c b/net/tipc/config.c
index c301a9a..e6d7216 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -181,7 +181,7 @@
 	if (tipc_own_addr)
 		return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
 						   " (cannot change node address once assigned)");
-	tipc_core_start_net(addr);
+	tipc_net_start(addr);
 	return tipc_cfg_reply_none();
 }
 
@@ -376,7 +376,6 @@
 	struct tipc_cfg_msg_hdr *req_hdr;
 	struct tipc_cfg_msg_hdr *rep_hdr;
 	struct sk_buff *rep_buf;
-	int ret;
 
 	/* Validate configuration message header (ignore invalid message) */
 	req_hdr = (struct tipc_cfg_msg_hdr *)buf;
@@ -398,12 +397,8 @@
 		memcpy(rep_hdr, req_hdr, sizeof(*rep_hdr));
 		rep_hdr->tcm_len = htonl(rep_buf->len);
 		rep_hdr->tcm_flags &= htons(~TCM_F_REQUEST);
-
-		ret = tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data,
-					rep_buf->len);
-		if (ret < 0)
-			pr_err("Sending cfg reply message failed, no memory\n");
-
+		tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data,
+				  rep_buf->len);
 		kfree_skb(rep_buf);
 	}
 }
diff --git a/net/tipc/core.c b/net/tipc/core.c
index f9e88d8..80c2064 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -77,37 +77,13 @@
 }
 
 /**
- * tipc_core_stop_net - shut down TIPC networking sub-systems
- */
-static void tipc_core_stop_net(void)
-{
-	tipc_net_stop();
-	tipc_bearer_cleanup();
-}
-
-/**
- * start_net - start TIPC networking sub-systems
- */
-int tipc_core_start_net(unsigned long addr)
-{
-	int res;
-
-	tipc_net_start(addr);
-	res = tipc_bearer_setup();
-	if (res < 0)
-		goto err;
-	return res;
-
-err:
-	tipc_core_stop_net();
-	return res;
-}
-
-/**
  * tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode
  */
 static void tipc_core_stop(void)
 {
+	tipc_handler_stop();
+	tipc_net_stop();
+	tipc_bearer_cleanup();
 	tipc_netlink_stop();
 	tipc_cfg_stop();
 	tipc_subscr_stop();
@@ -122,30 +98,65 @@
  */
 static int tipc_core_start(void)
 {
-	int res;
+	int err;
 
 	get_random_bytes(&tipc_random, sizeof(tipc_random));
 
-	res = tipc_handler_start();
-	if (!res)
-		res = tipc_ref_table_init(tipc_max_ports, tipc_random);
-	if (!res)
-		res = tipc_nametbl_init();
-	if (!res)
-		res = tipc_netlink_start();
-	if (!res)
-		res = tipc_socket_init();
-	if (!res)
-		res = tipc_register_sysctl();
-	if (!res)
-		res = tipc_subscr_start();
-	if (!res)
-		res = tipc_cfg_init();
-	if (res) {
-		tipc_handler_stop();
-		tipc_core_stop();
-	}
-	return res;
+	err = tipc_handler_start();
+	if (err)
+		goto out_handler;
+
+	err = tipc_ref_table_init(tipc_max_ports, tipc_random);
+	if (err)
+		goto out_reftbl;
+
+	err = tipc_nametbl_init();
+	if (err)
+		goto out_nametbl;
+
+	err = tipc_netlink_start();
+	if (err)
+		goto out_netlink;
+
+	err = tipc_socket_init();
+	if (err)
+		goto out_socket;
+
+	err = tipc_register_sysctl();
+	if (err)
+		goto out_sysctl;
+
+	err = tipc_subscr_start();
+	if (err)
+		goto out_subscr;
+
+	err = tipc_cfg_init();
+	if (err)
+		goto out_cfg;
+
+	err = tipc_bearer_setup();
+	if (err)
+		goto out_bearer;
+
+	return 0;
+out_bearer:
+	tipc_cfg_stop();
+out_cfg:
+	tipc_subscr_stop();
+out_subscr:
+	tipc_unregister_sysctl();
+out_sysctl:
+	tipc_socket_stop();
+out_socket:
+	tipc_netlink_stop();
+out_netlink:
+	tipc_nametbl_stop();
+out_nametbl:
+	tipc_ref_table_stop();
+out_reftbl:
+	tipc_handler_stop();
+out_handler:
+	return err;
 }
 
 static int __init tipc_init(void)
@@ -174,8 +185,6 @@
 
 static void __exit tipc_exit(void)
 {
-	tipc_handler_stop();
-	tipc_core_stop_net();
 	tipc_core_stop();
 	pr_info("Deactivated\n");
 }
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 1ff477b..4dfe137 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -90,7 +90,6 @@
 /*
  * Routines available to privileged subsystems
  */
-int tipc_core_start_net(unsigned long);
 int tipc_handler_start(void);
 void tipc_handler_stop(void);
 int tipc_netlink_start(void);
@@ -192,6 +191,7 @@
 
 struct tipc_skb_cb {
 	void *handle;
+	bool deferred;
 };
 
 #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
diff --git a/net/tipc/handler.c b/net/tipc/handler.c
index e4bc8a2..1fabf16 100644
--- a/net/tipc/handler.c
+++ b/net/tipc/handler.c
@@ -58,7 +58,6 @@
 
 	spin_lock_bh(&qitem_lock);
 	if (!handler_enabled) {
-		pr_err("Signal request ignored by handler\n");
 		spin_unlock_bh(&qitem_lock);
 		return -ENOPROTOOPT;
 	}
diff --git a/net/tipc/link.c b/net/tipc/link.c
index d4b5de4..da6018b 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1391,6 +1391,12 @@
 	u32 hdr_size;
 	u32 min_hdr_size;
 
+	/* If this packet comes from the defer queue, the skb has already
+	 * been validated
+	 */
+	if (unlikely(TIPC_SKB_CB(buf)->deferred))
+		return 1;
+
 	if (unlikely(buf->len < MIN_H_SIZE))
 		return 0;
 
@@ -1703,6 +1709,7 @@
 				&l_ptr->newest_deferred_in, buf)) {
 		l_ptr->deferred_inqueue_sz++;
 		l_ptr->stats.deferred_recv++;
+		TIPC_SKB_CB(buf)->deferred = true;
 		if ((l_ptr->deferred_inqueue_sz % 16) == 1)
 			tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
 	} else
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 92a1533..042e8e3 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -941,20 +941,48 @@
 	return 0;
 }
 
+/**
+ * tipc_purge_publications - remove all publications for a given type
+ *
+ * tipc_nametbl_lock must be held when calling this function
+ */
+static void tipc_purge_publications(struct name_seq *seq)
+{
+	struct publication *publ, *safe;
+	struct sub_seq *sseq;
+	struct name_info *info;
+
+	if (!seq->sseqs) {
+		nameseq_delete_empty(seq);
+		return;
+	}
+	sseq = seq->sseqs;
+	info = sseq->info;
+	list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) {
+		tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node,
+					 publ->ref, publ->key);
+	}
+}
+
 void tipc_nametbl_stop(void)
 {
 	u32 i;
+	struct name_seq *seq;
+	struct hlist_head *seq_head;
+	struct hlist_node *safe;
 
-	if (!table.types)
-		return;
-
-	/* Verify name table is empty, then release it */
+	/* Verify name table is empty and purge any lingering
+	 * publications, then release the name table
+	 */
 	write_lock_bh(&tipc_nametbl_lock);
 	for (i = 0; i < TIPC_NAMETBL_SIZE; i++) {
 		if (hlist_empty(&table.types[i]))
 			continue;
-		pr_err("nametbl_stop(): orphaned hash chain detected\n");
-		break;
+		seq_head = &table.types[i];
+		hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) {
+			tipc_purge_publications(seq);
+		}
+		continue;
 	}
 	kfree(table.types);
 	table.types = NULL;
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 9f72a63..3aaf73d 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -83,8 +83,6 @@
 	},
 };
 
-static int tipc_genl_family_registered;
-
 int tipc_netlink_start(void)
 {
 	int res;
@@ -94,16 +92,10 @@
 		pr_err("Failed to register netlink interface\n");
 		return res;
 	}
-
-	tipc_genl_family_registered = 1;
 	return 0;
 }
 
 void tipc_netlink_stop(void)
 {
-	if (!tipc_genl_family_registered)
-		return;
-
 	genl_unregister_family(&tipc_genl_family);
-	tipc_genl_family_registered = 0;
 }
diff --git a/net/tipc/ref.c b/net/tipc/ref.c
index 2a2a938..de3d593 100644
--- a/net/tipc/ref.c
+++ b/net/tipc/ref.c
@@ -126,9 +126,6 @@
  */
 void tipc_ref_table_stop(void)
 {
-	if (!tipc_ref_table.entries)
-		return;
-
 	vfree(tipc_ref_table.entries);
 	tipc_ref_table.entries = NULL;
 }
diff --git a/net/tipc/server.c b/net/tipc/server.c
index b635ca3..646a930 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -87,7 +87,6 @@
 static void tipc_conn_kref_release(struct kref *kref)
 {
 	struct tipc_conn *con = container_of(kref, struct tipc_conn, kref);
-	struct tipc_server *s = con->server;
 
 	if (con->sock) {
 		tipc_sock_release_local(con->sock);
@@ -95,10 +94,6 @@
 	}
 
 	tipc_clean_outqueues(con);
-
-	if (con->conid)
-		s->tipc_conn_shutdown(con->conid, con->usr_data);
-
 	kfree(con);
 }
 
@@ -181,6 +176,9 @@
 	struct tipc_server *s = con->server;
 
 	if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {
+		if (con->conid)
+			s->tipc_conn_shutdown(con->conid, con->usr_data);
+
 		spin_lock_bh(&s->idr_lock);
 		idr_remove(&s->conn_idr, con->conid);
 		s->idr_in_use--;
@@ -429,10 +427,12 @@
 	list_add_tail(&e->list, &con->outqueue);
 	spin_unlock_bh(&con->outqueue_lock);
 
-	if (test_bit(CF_CONNECTED, &con->flags))
+	if (test_bit(CF_CONNECTED, &con->flags)) {
 		if (!queue_work(s->send_wq, &con->swork))
 			conn_put(con);
-
+	} else {
+		conn_put(con);
+	}
 	return 0;
 }
 
@@ -573,7 +573,6 @@
 		kmem_cache_destroy(s->rcvbuf_cache);
 		return ret;
 	}
-	s->enabled = 1;
 	return ret;
 }
 
@@ -583,10 +582,6 @@
 	int total = 0;
 	int id;
 
-	if (!s->enabled)
-		return;
-
-	s->enabled = 0;
 	spin_lock_bh(&s->idr_lock);
 	for (id = 0; total < s->idr_in_use; id++) {
 		con = idr_find(&s->conn_idr, id);
diff --git a/net/tipc/server.h b/net/tipc/server.h
index 98b23f2..be817b0 100644
--- a/net/tipc/server.h
+++ b/net/tipc/server.h
@@ -56,7 +56,6 @@
  * @name: server name
  * @imp: message importance
  * @type: socket type
- * @enabled: identify whether server is launched or not
  */
 struct tipc_server {
 	struct idr conn_idr;
@@ -74,7 +73,6 @@
 	const char name[TIPC_SERVER_NAME_LEN];
 	int imp;
 	int type;
-	int enabled;
 };
 
 int tipc_conn_sendmsg(struct tipc_server *s, int conid,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index aab4948..0ed0eaa 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -70,8 +70,6 @@
 static struct proto tipc_proto;
 static struct proto tipc_proto_kern;
 
-static int sockets_enabled;
-
 /*
  * Revised TIPC socket locking policy:
  *
@@ -999,7 +997,7 @@
 
 	for (;;) {
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-		if (skb_queue_empty(&sk->sk_receive_queue)) {
+		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
 			if (sock->state == SS_DISCONNECTING) {
 				err = -ENOTCONN;
 				break;
@@ -1625,7 +1623,7 @@
 	for (;;) {
 		prepare_to_wait_exclusive(sk_sleep(sk), &wait,
 					  TASK_INTERRUPTIBLE);
-		if (skb_queue_empty(&sk->sk_receive_queue)) {
+		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
 			release_sock(sk);
 			timeo = schedule_timeout(timeo);
 			lock_sock(sk);
@@ -2027,8 +2025,6 @@
 		proto_unregister(&tipc_proto);
 		goto out;
 	}
-
-	sockets_enabled = 1;
  out:
 	return res;
 }
@@ -2038,10 +2034,6 @@
  */
 void tipc_socket_stop(void)
 {
-	if (!sockets_enabled)
-		return;
-
-	sockets_enabled = 0;
 	sock_unregister(tipc_family_ops.family);
 	proto_unregister(&tipc_proto);
 }
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 7cb0bd5..6424372 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -96,20 +96,16 @@
 {
 	struct tipc_subscriber *subscriber = sub->subscriber;
 	struct kvec msg_sect;
-	int ret;
 
 	msg_sect.iov_base = (void *)&sub->evt;
 	msg_sect.iov_len = sizeof(struct tipc_event);
-
 	sub->evt.event = htohl(event, sub->swap);
 	sub->evt.found_lower = htohl(found_lower, sub->swap);
 	sub->evt.found_upper = htohl(found_upper, sub->swap);
 	sub->evt.port.ref = htohl(port_ref, sub->swap);
 	sub->evt.port.node = htohl(node, sub->swap);
-	ret = tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL,
-				msg_sect.iov_base, msg_sect.iov_len);
-	if (ret < 0)
-		pr_err("Sending subscription event failed, no memory\n");
+	tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, msg_sect.iov_base,
+			  msg_sect.iov_len);
 }
 
 /**
@@ -153,14 +149,6 @@
 	/* The spin lock per subscriber is used to protect its members */
 	spin_lock_bh(&subscriber->lock);
 
-	/* Validate if the connection related to the subscriber is
-	 * closed (in case subscriber is terminating)
-	 */
-	if (subscriber->conid == 0) {
-		spin_unlock_bh(&subscriber->lock);
-		return;
-	}
-
 	/* Validate timeout (in case subscription is being cancelled) */
 	if (sub->timeout == TIPC_WAIT_FOREVER) {
 		spin_unlock_bh(&subscriber->lock);
@@ -215,9 +203,6 @@
 
 	spin_lock_bh(&subscriber->lock);
 
-	/* Invalidate subscriber reference */
-	subscriber->conid = 0;
-
 	/* Destroy any existing subscriptions for subscriber */
 	list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list,
 				 subscription_list) {
@@ -278,9 +263,9 @@
  *
  * Called with subscriber lock held.
  */
-static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s,
-					     struct tipc_subscriber *subscriber)
-{
+static int subscr_subscribe(struct tipc_subscr *s,
+			    struct tipc_subscriber *subscriber,
+			    struct tipc_subscription **sub_p) {
 	struct tipc_subscription *sub;
 	int swap;
 
@@ -291,23 +276,21 @@
 	if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) {
 		s->filter &= ~htohl(TIPC_SUB_CANCEL, swap);
 		subscr_cancel(s, subscriber);
-		return NULL;
+		return 0;
 	}
 
 	/* Refuse subscription if global limit exceeded */
 	if (atomic_read(&subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) {
 		pr_warn("Subscription rejected, limit reached (%u)\n",
 			TIPC_MAX_SUBSCRIPTIONS);
-		subscr_terminate(subscriber);
-		return NULL;
+		return -EINVAL;
 	}
 
 	/* Allocate subscription object */
 	sub = kmalloc(sizeof(*sub), GFP_ATOMIC);
 	if (!sub) {
 		pr_warn("Subscription rejected, no memory\n");
-		subscr_terminate(subscriber);
-		return NULL;
+		return -ENOMEM;
 	}
 
 	/* Initialize subscription object */
@@ -321,8 +304,7 @@
 	    (sub->seq.lower > sub->seq.upper)) {
 		pr_warn("Subscription rejected, illegal request\n");
 		kfree(sub);
-		subscr_terminate(subscriber);
-		return NULL;
+		return -EINVAL;
 	}
 	INIT_LIST_HEAD(&sub->nameseq_list);
 	list_add(&sub->subscription_list, &subscriber->subscription_list);
@@ -335,8 +317,8 @@
 			     (Handler)subscr_timeout, (unsigned long)sub);
 		k_start_timer(&sub->timer, sub->timeout);
 	}
-
-	return sub;
+	*sub_p = sub;
+	return 0;
 }
 
 /* Handle one termination request for the subscriber */
@@ -350,10 +332,14 @@
 				  void *usr_data, void *buf, size_t len)
 {
 	struct tipc_subscriber *subscriber = usr_data;
-	struct tipc_subscription *sub;
+	struct tipc_subscription *sub = NULL;
 
 	spin_lock_bh(&subscriber->lock);
-	sub = subscr_subscribe((struct tipc_subscr *)buf, subscriber);
+	if (subscr_subscribe((struct tipc_subscr *)buf, subscriber, &sub) < 0) {
+		spin_unlock_bh(&subscriber->lock);
+		subscr_terminate(subscriber);
+		return;
+	}
 	if (sub)
 		tipc_nametbl_subscribe(sub);
 	spin_unlock_bh(&subscriber->lock);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 29fc8be..94404f1 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -163,9 +163,8 @@
 
 static inline unsigned int unix_hash_fold(__wsum n)
 {
-	unsigned int hash = (__force unsigned int)n;
+	unsigned int hash = (__force unsigned int)csum_fold(n);
 
-	hash ^= hash>>16;
 	hash ^= hash>>8;
 	return hash&(UNIX_HASH_SIZE-1);
 }
@@ -1788,8 +1787,11 @@
 		goto out;
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}
 
@@ -1914,6 +1916,7 @@
 	struct unix_sock *u = unix_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
 	int copied = 0;
+	int noblock = flags & MSG_DONTWAIT;
 	int check_creds = 0;
 	int target;
 	int err = 0;
@@ -1929,7 +1932,7 @@
 		goto out;
 
 	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
-	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
+	timeo = sock_rcvtimeo(sk, noblock);
 
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
@@ -1941,8 +1944,11 @@
 	}
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(timeo);
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}
 
diff --git a/net/wireless/core.c b/net/wireless/core.c
index d89dee2..a3bf18d 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -203,8 +203,11 @@
 
 	rdev->opencount--;
 
-	WARN_ON(rdev->scan_req && rdev->scan_req->wdev == wdev &&
-		!rdev->scan_req->notified);
+	if (rdev->scan_req && rdev->scan_req->wdev == wdev) {
+		if (WARN_ON(!rdev->scan_req->notified))
+			rdev->scan_req->aborted = true;
+		___cfg80211_scan_done(rdev, false);
+	}
 }
 
 static int cfg80211_rfkill_set_block(void *data, bool blocked)
@@ -440,9 +443,6 @@
 	int i;
 	u16 ifmodes = wiphy->interface_modes;
 
-	/* support for 5/10 MHz is broken due to nl80211 API mess - disable */
-	wiphy->flags &= ~WIPHY_FLAG_SUPPORTS_5_10_MHZ;
-
 	/*
 	 * There are major locking problems in nl80211/mac80211 for CSA,
 	 * disable for all drivers until this has been reworked.
@@ -788,8 +788,6 @@
 	default:
 		break;
 	}
-
-	wdev->beacon_interval = 0;
 }
 
 static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
@@ -859,8 +857,11 @@
 		break;
 	case NETDEV_DOWN:
 		cfg80211_update_iface_num(rdev, wdev->iftype, -1);
-		WARN_ON(rdev->scan_req && rdev->scan_req->wdev == wdev &&
-			!rdev->scan_req->notified);
+		if (rdev->scan_req && rdev->scan_req->wdev == wdev) {
+			if (WARN_ON(!rdev->scan_req->notified))
+				rdev->scan_req->aborted = true;
+			___cfg80211_scan_done(rdev, false);
+		}
 
 		if (WARN_ON(rdev->sched_scan_req &&
 			    rdev->sched_scan_req->dev == wdev->netdev)) {
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 37ec16d..f1d193b 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -62,6 +62,7 @@
 	struct rb_root bss_tree;
 	u32 bss_generation;
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
+	struct sk_buff *scan_msg;
 	struct cfg80211_sched_scan_request *sched_scan_req;
 	unsigned long suspend_at;
 	struct work_struct scan_done_wk;
@@ -361,7 +362,8 @@
 				   struct key_params *params, int key_idx,
 				   bool pairwise, const u8 *mac_addr);
 void __cfg80211_scan_done(struct work_struct *wk);
-void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev);
+void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
+			   bool send_message);
 void __cfg80211_sched_scan_results(struct work_struct *wk);
 int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
 			       bool driver_initiated);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 7a74259..4fe2e6e 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1719,9 +1719,10 @@
 				 * We can then retry with the larger buffer.
 				 */
 				if ((ret == -ENOBUFS || ret == -EMSGSIZE) &&
-				    !skb->len &&
+				    !skb->len && !state->split &&
 				    cb->min_dump_alloc < 4096) {
 					cb->min_dump_alloc = 4096;
+					state->split_start = 0;
 					rtnl_unlock();
 					return 1;
 				}
@@ -5244,7 +5245,7 @@
 	if (!rdev->ops->scan)
 		return -EOPNOTSUPP;
 
-	if (rdev->scan_req) {
+	if (rdev->scan_req || rdev->scan_msg) {
 		err = -EBUSY;
 		goto unlock;
 	}
@@ -10011,40 +10012,31 @@
 				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
-void nl80211_send_scan_done(struct cfg80211_registered_device *rdev,
-			    struct wireless_dev *wdev)
+struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev,
+				       struct wireless_dev *wdev, bool aborted)
 {
 	struct sk_buff *msg;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
-		return;
+		return NULL;
 
 	if (nl80211_send_scan_msg(msg, rdev, wdev, 0, 0, 0,
-				  NL80211_CMD_NEW_SCAN_RESULTS) < 0) {
+				  aborted ? NL80211_CMD_SCAN_ABORTED :
+					    NL80211_CMD_NEW_SCAN_RESULTS) < 0) {
 		nlmsg_free(msg);
-		return;
+		return NULL;
 	}
 
-	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				NL80211_MCGRP_SCAN, GFP_KERNEL);
+	return msg;
 }
 
-void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev,
-			       struct wireless_dev *wdev)
+void nl80211_send_scan_result(struct cfg80211_registered_device *rdev,
+			      struct sk_buff *msg)
 {
-	struct sk_buff *msg;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return;
 
-	if (nl80211_send_scan_msg(msg, rdev, wdev, 0, 0, 0,
-				  NL80211_CMD_SCAN_ABORTED) < 0) {
-		nlmsg_free(msg);
-		return;
-	}
-
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index b1b2313..7579974 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -8,10 +8,10 @@
 void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev);
 void nl80211_send_scan_start(struct cfg80211_registered_device *rdev,
 			     struct wireless_dev *wdev);
-void nl80211_send_scan_done(struct cfg80211_registered_device *rdev,
-			    struct wireless_dev *wdev);
-void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev,
-			       struct wireless_dev *wdev);
+struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev,
+				       struct wireless_dev *wdev, bool aborted);
+void nl80211_send_scan_result(struct cfg80211_registered_device *rdev,
+			      struct sk_buff *msg);
 void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
 			     struct net_device *netdev, u32 cmd);
 void nl80211_send_sched_scan_results(struct cfg80211_registered_device *rdev,
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 9b897fc..f054137 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1700,7 +1700,7 @@
 		return;
 	case NL80211_REGDOM_SET_BY_USER:
 		treatment = reg_process_hint_user(reg_request);
-		if (treatment == REG_REQ_OK ||
+		if (treatment == REG_REQ_IGNORE ||
 		    treatment == REG_REQ_ALREADY_SET)
 			return;
 		schedule_delayed_work(&reg_timeout, msecs_to_jiffies(3142));
@@ -2373,6 +2373,7 @@
 int set_regdom(const struct ieee80211_regdomain *rd)
 {
 	struct regulatory_request *lr;
+	bool user_reset = false;
 	int r;
 
 	if (!reg_is_valid_request(rd->alpha2)) {
@@ -2389,6 +2390,7 @@
 		break;
 	case NL80211_REGDOM_SET_BY_USER:
 		r = reg_set_rd_user(rd, lr);
+		user_reset = true;
 		break;
 	case NL80211_REGDOM_SET_BY_DRIVER:
 		r = reg_set_rd_driver(rd, lr);
@@ -2402,8 +2404,14 @@
 	}
 
 	if (r) {
-		if (r == -EALREADY)
+		switch (r) {
+		case -EALREADY:
 			reg_set_request_processed();
+			break;
+		default:
+			/* Back to world regulatory in case of errors */
+			restore_regulatory_settings(user_reset);
+		}
 
 		kfree(rd);
 		return r;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index b528e31..d1ed4ae 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -161,18 +161,25 @@
 		dev->bss_generation++;
 }
 
-void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev)
+void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
+			   bool send_message)
 {
 	struct cfg80211_scan_request *request;
 	struct wireless_dev *wdev;
+	struct sk_buff *msg;
 #ifdef CONFIG_CFG80211_WEXT
 	union iwreq_data wrqu;
 #endif
 
 	ASSERT_RTNL();
 
-	request = rdev->scan_req;
+	if (rdev->scan_msg) {
+		nl80211_send_scan_result(rdev, rdev->scan_msg);
+		rdev->scan_msg = NULL;
+		return;
+	}
 
+	request = rdev->scan_req;
 	if (!request)
 		return;
 
@@ -186,18 +193,16 @@
 	if (wdev->netdev)
 		cfg80211_sme_scan_done(wdev->netdev);
 
-	if (request->aborted) {
-		nl80211_send_scan_aborted(rdev, wdev);
-	} else {
-		if (request->flags & NL80211_SCAN_FLAG_FLUSH) {
-			/* flush entries from previous scans */
-			spin_lock_bh(&rdev->bss_lock);
-			__cfg80211_bss_expire(rdev, request->scan_start);
-			spin_unlock_bh(&rdev->bss_lock);
-		}
-		nl80211_send_scan_done(rdev, wdev);
+	if (!request->aborted &&
+	    request->flags & NL80211_SCAN_FLAG_FLUSH) {
+		/* flush entries from previous scans */
+		spin_lock_bh(&rdev->bss_lock);
+		__cfg80211_bss_expire(rdev, request->scan_start);
+		spin_unlock_bh(&rdev->bss_lock);
 	}
 
+	msg = nl80211_build_scan_msg(rdev, wdev, request->aborted);
+
 #ifdef CONFIG_CFG80211_WEXT
 	if (wdev->netdev && !request->aborted) {
 		memset(&wrqu, 0, sizeof(wrqu));
@@ -211,6 +216,11 @@
 
 	rdev->scan_req = NULL;
 	kfree(request);
+
+	if (!send_message)
+		rdev->scan_msg = msg;
+	else
+		nl80211_send_scan_result(rdev, msg);
 }
 
 void __cfg80211_scan_done(struct work_struct *wk)
@@ -221,7 +231,7 @@
 			    scan_done_wk);
 
 	rtnl_lock();
-	___cfg80211_scan_done(rdev);
+	___cfg80211_scan_done(rdev, true);
 	rtnl_unlock();
 }
 
@@ -1079,7 +1089,7 @@
 	if (IS_ERR(rdev))
 		return PTR_ERR(rdev);
 
-	if (rdev->scan_req) {
+	if (rdev->scan_req || rdev->scan_msg) {
 		err = -EBUSY;
 		goto out;
 	}
@@ -1481,7 +1491,7 @@
 	if (IS_ERR(rdev))
 		return PTR_ERR(rdev);
 
-	if (rdev->scan_req)
+	if (rdev->scan_req || rdev->scan_msg)
 		return -EAGAIN;
 
 	res = ieee80211_scan_results(rdev, info, extra, data->length);
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index a635091..f04d4c3 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -67,7 +67,7 @@
 	ASSERT_RDEV_LOCK(rdev);
 	ASSERT_WDEV_LOCK(wdev);
 
-	if (rdev->scan_req)
+	if (rdev->scan_req || rdev->scan_msg)
 		return -EBUSY;
 
 	if (wdev->conn->params.channel)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 4b98b25..1d5c7bf 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1158,7 +1158,7 @@
 	if (hlist_unhashed(&pol->bydst))
 		return NULL;
 
-	hlist_del(&pol->bydst);
+	hlist_del_init(&pol->bydst);
 	hlist_del(&pol->byidx);
 	list_del(&pol->walk.all);
 	net->xfrm.policy_count[dir]--;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index a26b7aa..40f1b3e 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1159,6 +1159,11 @@
 	}
 	x->props.aalgo = orig->props.aalgo;
 
+	if (orig->aead) {
+		x->aead = xfrm_algo_aead_clone(orig->aead);
+		if (!x->aead)
+			goto error;
+	}
 	if (orig->ealg) {
 		x->ealg = xfrm_algo_clone(orig->ealg);
 		if (!x->ealg)
@@ -1201,6 +1206,9 @@
 	x->props.flags = orig->props.flags;
 	x->props.extra_flags = orig->props.extra_flags;
 
+	x->tfcpad = orig->tfcpad;
+	x->replay_maxdiff = orig->replay_maxdiff;
+	x->replay_maxage = orig->replay_maxage;
 	x->curlft.add_time = orig->curlft.add_time;
 	x->km.state = orig->km.state;
 	x->km.seq = orig->km.seq;
@@ -1215,11 +1223,12 @@
 	return NULL;
 }
 
-/* net->xfrm.xfrm_state_lock is held */
 struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
 {
 	unsigned int h;
-	struct xfrm_state *x;
+	struct xfrm_state *x = NULL;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 
 	if (m->reqid) {
 		h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
@@ -1236,7 +1245,7 @@
 					     m->old_family))
 				continue;
 			xfrm_state_hold(x);
-			return x;
+			break;
 		}
 	} else {
 		h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
@@ -1251,11 +1260,13 @@
 					     m->old_family))
 				continue;
 			xfrm_state_hold(x);
-			return x;
+			break;
 		}
 	}
 
-	return NULL;
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+	return x;
 }
 EXPORT_SYMBOL(xfrm_migrate_state_find);
 
@@ -1451,7 +1462,7 @@
 {
 	int err = 0;
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
-	struct net *net = xs_net(*dst);
+	struct net *net = xs_net(*src);
 
 	if (!afinfo)
 		return -EAFNOSUPPORT;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 1ae3ec7..2f7ddc3 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -32,11 +32,6 @@
 #include <linux/in6.h>
 #endif
 
-static inline int aead_len(struct xfrm_algo_aead *alg)
-{
-	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
-}
-
 static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type)
 {
 	struct nlattr *rt = attrs[type];
@@ -1226,7 +1221,7 @@
 		return 0;
 
 	uctx = nla_data(rt);
-	return security_xfrm_policy_alloc(&pol->security, uctx);
+	return security_xfrm_policy_alloc(&pol->security, uctx, GFP_KERNEL);
 }
 
 static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut,
@@ -1631,7 +1626,7 @@
 		if (rt) {
 			struct xfrm_user_sec_ctx *uctx = nla_data(rt);
 
-			err = security_xfrm_policy_alloc(&ctx, uctx);
+			err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL);
 			if (err)
 				return err;
 		}
@@ -1933,7 +1928,7 @@
 		if (rt) {
 			struct xfrm_user_sec_ctx *uctx = nla_data(rt);
 
-			err = security_xfrm_policy_alloc(&ctx, uctx);
+			err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL);
 			if (err)
 				return err;
 		}
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 547e15d..93a0da2 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -155,6 +155,15 @@
 # Important: no spaces around options
 ar-option = $(call try-run, $(AR) rc$(1) "$$TMP",$(1),$(2))
 
+# ld-version
+# Usage: $(call ld-version)
+# Note this is mainly for HJ Lu's 3 number binutil versions
+ld-version = $(shell $(LD) --version | $(srctree)/scripts/ld-version.sh)
+
+# ld-ifversion
+# Usage:  $(call ld-ifversion, -ge, 22252, y)
+ld-ifversion = $(shell [ $(call ld-version) $(1) $(2) ] && echo $(3))
+
 ######
 
 ###
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index d5d859c..9f0ee22 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -198,7 +198,7 @@
 $(multi-objs-y:.o=.lst) : modname = $(modname-multi)
 
 quiet_cmd_cc_s_c = CC $(quiet_modtag)  $@
-cmd_cc_s_c       = $(CC) $(c_flags) -fverbose-asm -S -o $@ $<
+cmd_cc_s_c       = $(CC) $(c_flags) $(DISABLE_LTO) -fverbose-asm -S -o $@ $<
 
 $(obj)/%.s: $(src)/%.c FORCE
 	$(call if_changed_dep,cc_s_c)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 49392ec..79c059e 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -152,6 +152,7 @@
 dtc_cpp_flags  = -Wp,-MD,$(depfile).pre.tmp -nostdinc                    \
 		 -I$(srctree)/arch/$(SRCARCH)/boot/dts                   \
 		 -I$(srctree)/arch/$(SRCARCH)/boot/dts/include           \
+		 -I$(srctree)/drivers/of/testcase-data                   \
 		 -undef -D__DTS__
 
 # Finds the multi-part object the current object will be linked into
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 0ea2a1e..464dcef 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -471,7 +471,7 @@
 
 	$camelcase_seeded = 1;
 
-	if (-d ".git") {
+	if (-e ".git") {
 		my $git_last_include_commit = `git log --no-merges --pretty=format:"%h%n" -1 -- include`;
 		chomp $git_last_include_commit;
 		$camelcase_cache = ".checkpatch-camelcase.git.$git_last_include_commit";
@@ -499,7 +499,7 @@
 		return;
 	}
 
-	if (-d ".git") {
+	if (-e ".git") {
 		$files = `git ls-files "include/*.h"`;
 		@include_files = split('\n', $files);
 	}
diff --git a/scripts/gcc-ld b/scripts/gcc-ld
new file mode 100644
index 0000000..cadab9a
--- /dev/null
+++ b/scripts/gcc-ld
@@ -0,0 +1,29 @@
+#!/bin/sh
+# run gcc with ld options
+# used as a wrapper to execute link time optimizations
+# yes virginia, this is not pretty
+
+ARGS="-nostdlib"
+
+while [ "$1" != "" ] ; do
+	case "$1" in
+	-save-temps|-m32|-m64) N="$1" ;;
+	-r) N="$1" ;;
+	-[Wg]*) N="$1" ;;
+	-[olv]|-[Ofd]*|-nostdlib) N="$1" ;;
+	--end-group|--start-group)
+		 N="-Wl,$1" ;;
+	-[RTFGhIezcbyYu]*|\
+--script|--defsym|-init|-Map|--oformat|-rpath|\
+-rpath-link|--sort-section|--section-start|-Tbss|-Tdata|-Ttext|\
+--version-script|--dynamic-list|--version-exports-symbol|--wrap|-m)
+		A="$1" ; shift ; N="-Wl,$A,$1" ;;
+	-[m]*) N="$1" ;;
+	-*) N="-Wl,$1" ;;
+	*)  N="$1" ;;
+	esac
+	ARGS="$ARGS $N"
+	shift
+done
+
+exec $CC $ARGS
diff --git a/scripts/gen_initramfs_list.sh b/scripts/gen_initramfs_list.sh
index ef47409..17fa901 100644
--- a/scripts/gen_initramfs_list.sh
+++ b/scripts/gen_initramfs_list.sh
@@ -257,7 +257,7 @@
                 && compr="lzop -9 -f"
 		echo "$output_file" | grep -q "\.lz4$" \
                 && [ -x "`which lz4 2> /dev/null`" ] \
-                && compr="lz4 -9 -f"
+                && compr="lz4 -l -9 -f"
 		echo "$output_file" | grep -q "\.cpio$" && compr="cat"
 		shift
 		;;
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 9c3986f..4198788 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -95,7 +95,7 @@
 
 my %VCS_cmds_git = (
     "execute_cmd" => \&git_execute_cmd,
-    "available" => '(which("git") ne "") && (-d ".git")',
+    "available" => '(which("git") ne "") && (-e ".git")',
     "find_signers_cmd" =>
 	"git log --no-color --follow --since=\$email_git_since " .
 	    '--numstat --no-merges ' .
diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh
new file mode 100755
index 0000000..198580d
--- /dev/null
+++ b/scripts/ld-version.sh
@@ -0,0 +1,8 @@
+#!/usr/bin/awk -f
+# extract linker version number from stdin and turn into single number
+	{
+	gsub(".*)", "");
+	split($1,a, ".");
+	print a[1]*10000000 + a[2]*100000 + a[3]*10000 + a[4]*100 + a[5];
+	exit
+	}
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 2370863..25e5cb0 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -210,8 +210,8 @@
 				range_lo < 0x9 ? "[%X-9" : "[%X",
 				range_lo);
 			sprintf(alias + strlen(alias),
-				range_hi > 0xA ? "a-%X]" : "%X]",
-				range_lo);
+				range_hi > 0xA ? "A-%X]" : "%X]",
+				range_hi);
 		}
 	}
 	if (bcdDevice_initial_digits < (sizeof(bcdDevice_lo) * 2 - 1))
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 4061098..0663556 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -623,7 +623,10 @@
 
 	switch (sym->st_shndx) {
 	case SHN_COMMON:
-		warn("\"%s\" [%s] is COMMON symbol\n", symname, mod->name);
+		if (!strncmp(symname, "__gnu_lto_", sizeof("__gnu_lto_")-1)) {
+			/* Should warn here, but modpost runs before the linker */
+		} else
+			warn("\"%s\" [%s] is COMMON symbol\n", symname, mod->name);
 		break;
 	case SHN_UNDEF:
 		/* undefined symbol */
@@ -849,6 +852,7 @@
 	".xt.lit",         /* xtensa */
 	".arcextmap*",			/* arc */
 	".gnu.linkonce.arcext*",	/* arc : modules */
+	".gnu.lto*",
 	NULL
 };
 
@@ -1455,6 +1459,10 @@
 		to = find_elf_symbol(elf, r->r_addend, sym);
 		tosym = sym_name(elf, to);
 
+		if (!strncmp(fromsym, "reference___initcall",
+				sizeof("reference___initcall")-1))
+			return;
+
 		/* check whitelist - we may ignore it */
 		if (secref_whitelist(mismatch,
 					fromsec, fromsym, tosec, tosym)) {
@@ -1502,6 +1510,16 @@
 #define R_ARM_JUMP24	29
 #endif
 
+#ifndef	R_ARM_THM_CALL
+#define	R_ARM_THM_CALL		10
+#endif
+#ifndef	R_ARM_THM_JUMP24
+#define	R_ARM_THM_JUMP24	30
+#endif
+#ifndef	R_ARM_THM_JUMP19
+#define	R_ARM_THM_JUMP19	51
+#endif
+
 static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r)
 {
 	unsigned int r_typ = ELF_R_TYPE(r->r_info);
@@ -1515,6 +1533,9 @@
 	case R_ARM_PC24:
 	case R_ARM_CALL:
 	case R_ARM_JUMP24:
+	case R_ARM_THM_CALL:
+	case R_ARM_THM_JUMP24:
+	case R_ARM_THM_JUMP19:
 		/* From ARM ABI: ((S + A) | T) - P */
 		r->r_addend = (int)(long)(elf->hdr +
 		              sechdr->sh_offset +
@@ -1680,6 +1701,19 @@
 	}
 }
 
+static char *remove_dot(char *s)
+{
+	char *end;
+	int n = strcspn(s, ".");
+
+	if (n > 0 && s[n] != 0) {
+		strtoul(s + n + 1, &end, 10);
+		if  (end > s + n + 1 && (*end == '.' || *end == 0))
+			s[n] = 0;
+	}
+	return s;
+}
+
 static void read_symbols(char *modname)
 {
 	const char *symname;
@@ -1718,7 +1752,7 @@
 	}
 
 	for (sym = info.symtab_start; sym < info.symtab_stop; sym++) {
-		symname = info.strtab + sym->st_name;
+		symname = remove_dot(info.strtab + sym->st_name);
 
 		handle_modversions(mod, &info, sym, symname);
 		handle_moddevtable(mod, &info, sym, symname);
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 51207e4..168b43d 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -127,7 +127,7 @@
 	Elf_Section  export_gpl_sec;
 	Elf_Section  export_unused_gpl_sec;
 	Elf_Section  export_gpl_future_sec;
-	const char   *strtab;
+	char         *strtab;
 	char	     *modinfo;
 	unsigned int modinfo_len;
 
diff --git a/security/Kconfig b/security/Kconfig
index e9c6ac7..beb86b5 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -103,7 +103,7 @@
 config LSM_MMAP_MIN_ADDR
 	int "Low address space for LSM to protect from user allocation"
 	depends on SECURITY && SECURITY_SELINUX
-	default 32768 if ARM
+	default 32768 if ARM || (ARM64 && COMPAT)
 	default 65536
 	help
 	  This is the portion of low virtual memory which should be protected
diff --git a/security/capability.c b/security/capability.c
index 8b4f24a..21e2b9c 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -757,7 +757,8 @@
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 static int cap_xfrm_policy_alloc_security(struct xfrm_sec_ctx **ctxp,
-					  struct xfrm_user_sec_ctx *sec_ctx)
+					  struct xfrm_user_sec_ctx *sec_ctx,
+					  gfp_t gfp)
 {
 	return 0;
 }
diff --git a/security/keys/compat.c b/security/keys/compat.c
index bbd32c7..3478965 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -65,8 +65,8 @@
  * taking a 32-bit syscall are zero.  If you can, you should call sys_keyctl()
  * directly.
  */
-asmlinkage long compat_sys_keyctl(u32 option,
-				  u32 arg2, u32 arg3, u32 arg4, u32 arg5)
+COMPAT_SYSCALL_DEFINE5(keyctl, u32, option,
+		       u32, arg2, u32, arg3, u32, arg4, u32, arg5)
 {
 	switch (option) {
 	case KEYCTL_GET_KEYRING_ID:
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index d46cbc5..2fb2576 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1000,7 +1000,11 @@
 
 	kenter("{%d}", key->serial);
 
-	BUG_ON(key != ctx->match_data);
+	/* We might get a keyring with matching index-key that is nonetheless a
+	 * different keyring. */
+	if (key != ctx->match_data)
+		return 0;
+
 	ctx->result = ERR_PTR(-EDEADLK);
 	return 1;
 }
diff --git a/security/security.c b/security/security.c
index 15b6928..919cad9 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1317,9 +1317,11 @@
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 
-int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx)
+int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
+			       struct xfrm_user_sec_ctx *sec_ctx,
+			       gfp_t gfp)
 {
-	return security_ops->xfrm_policy_alloc_security(ctxp, sec_ctx);
+	return security_ops->xfrm_policy_alloc_security(ctxp, sec_ctx, gfp);
 }
 EXPORT_SYMBOL(security_xfrm_policy_alloc);
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4b34847..b332e2c 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -668,7 +668,7 @@
 		if (flags[i] == SBLABEL_MNT)
 			continue;
 		rc = security_context_to_sid(mount_options[i],
-					     strlen(mount_options[i]), &sid);
+					     strlen(mount_options[i]), &sid, GFP_KERNEL);
 		if (rc) {
 			printk(KERN_WARNING "SELinux: security_context_to_sid"
 			       "(%s) failed for (dev %s, type %s) errno=%d\n",
@@ -2489,7 +2489,8 @@
 		if (flags[i] == SBLABEL_MNT)
 			continue;
 		len = strlen(mount_options[i]);
-		rc = security_context_to_sid(mount_options[i], len, &sid);
+		rc = security_context_to_sid(mount_options[i], len, &sid,
+					     GFP_KERNEL);
 		if (rc) {
 			printk(KERN_WARNING "SELinux: security_context_to_sid"
 			       "(%s) failed for (dev %s, type %s) errno=%d\n",
@@ -2893,7 +2894,7 @@
 	if (rc)
 		return rc;
 
-	rc = security_context_to_sid(value, size, &newsid);
+	rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL);
 	if (rc == -EINVAL) {
 		if (!capable(CAP_MAC_ADMIN)) {
 			struct audit_buffer *ab;
@@ -3050,7 +3051,7 @@
 	if (!value || !size)
 		return -EACCES;
 
-	rc = security_context_to_sid((void *)value, size, &newsid);
+	rc = security_context_to_sid((void *)value, size, &newsid, GFP_KERNEL);
 	if (rc)
 		return rc;
 
@@ -5529,7 +5530,7 @@
 			str[size-1] = 0;
 			size--;
 		}
-		error = security_context_to_sid(value, size, &sid);
+		error = security_context_to_sid(value, size, &sid, GFP_KERNEL);
 		if (error == -EINVAL && !strcmp(name, "fscreate")) {
 			if (!capable(CAP_MAC_ADMIN)) {
 				struct audit_buffer *ab;
@@ -5638,7 +5639,7 @@
 
 static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
 {
-	return security_context_to_sid(secdata, seclen, secid);
+	return security_context_to_sid(secdata, seclen, secid, GFP_KERNEL);
 }
 
 static void selinux_release_secctx(char *secdata, u32 seclen)
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 8ed8daf..ce7852c 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -134,7 +134,7 @@
 int security_sid_to_context_force(u32 sid, char **scontext, u32 *scontext_len);
 
 int security_context_to_sid(const char *scontext, u32 scontext_len,
-	u32 *out_sid);
+			    u32 *out_sid, gfp_t gfp);
 
 int security_context_to_sid_default(const char *scontext, u32 scontext_len,
 				    u32 *out_sid, u32 def_sid, gfp_t gfp_flags);
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index 48c3cc9..9f05847 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -10,7 +10,8 @@
 #include <net/flow.h>
 
 int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
-			      struct xfrm_user_sec_ctx *uctx);
+			      struct xfrm_user_sec_ctx *uctx,
+			      gfp_t gfp);
 int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
 			      struct xfrm_sec_ctx **new_ctxp);
 void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx);
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 332ac8a..2df7b90 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -17,6 +17,7 @@
 #include <linux/inet_diag.h>
 #include <linux/xfrm.h>
 #include <linux/audit.h>
+#include <linux/sock_diag.h>
 
 #include "flask.h"
 #include "av_permissions.h"
@@ -78,6 +79,7 @@
 {
 	{ TCPDIAG_GETSOCK,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 	{ DCCPDIAG_GETSOCK,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+	{ SOCK_DIAG_BY_FAMILY,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 };
 
 static struct nlmsg_perm nlmsg_xfrm_perms[] =
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 5122aff..d60c0ee 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -576,7 +576,7 @@
 	if (length)
 		goto out;
 
-	length = security_context_to_sid(buf, size, &sid);
+	length = security_context_to_sid(buf, size, &sid, GFP_KERNEL);
 	if (length)
 		goto out;
 
@@ -731,11 +731,13 @@
 	if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3)
 		goto out;
 
-	length = security_context_to_sid(scon, strlen(scon) + 1, &ssid);
+	length = security_context_to_sid(scon, strlen(scon) + 1, &ssid,
+					 GFP_KERNEL);
 	if (length)
 		goto out;
 
-	length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid);
+	length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid,
+					 GFP_KERNEL);
 	if (length)
 		goto out;
 
@@ -817,11 +819,13 @@
 		objname = namebuf;
 	}
 
-	length = security_context_to_sid(scon, strlen(scon) + 1, &ssid);
+	length = security_context_to_sid(scon, strlen(scon) + 1, &ssid,
+					 GFP_KERNEL);
 	if (length)
 		goto out;
 
-	length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid);
+	length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid,
+					 GFP_KERNEL);
 	if (length)
 		goto out;
 
@@ -878,11 +882,13 @@
 	if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3)
 		goto out;
 
-	length = security_context_to_sid(scon, strlen(scon) + 1, &ssid);
+	length = security_context_to_sid(scon, strlen(scon) + 1, &ssid,
+					 GFP_KERNEL);
 	if (length)
 		goto out;
 
-	length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid);
+	length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid,
+					 GFP_KERNEL);
 	if (length)
 		goto out;
 
@@ -934,7 +940,7 @@
 	if (sscanf(buf, "%s %s", con, user) != 2)
 		goto out;
 
-	length = security_context_to_sid(con, strlen(con) + 1, &sid);
+	length = security_context_to_sid(con, strlen(con) + 1, &sid, GFP_KERNEL);
 	if (length)
 		goto out;
 
@@ -994,11 +1000,13 @@
 	if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3)
 		goto out;
 
-	length = security_context_to_sid(scon, strlen(scon) + 1, &ssid);
+	length = security_context_to_sid(scon, strlen(scon) + 1, &ssid,
+					 GFP_KERNEL);
 	if (length)
 		goto out;
 
-	length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid);
+	length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid,
+					 GFP_KERNEL);
 	if (length)
 		goto out;
 
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index c0f4988..9c5cdc2 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -3338,10 +3338,10 @@
 	if (rc)
 		return rc;
 
-	buf[0] = ft->stype;
-	buf[1] = ft->ttype;
-	buf[2] = ft->tclass;
-	buf[3] = otype->otype;
+	buf[0] = cpu_to_le32(ft->stype);
+	buf[1] = cpu_to_le32(ft->ttype);
+	buf[2] = cpu_to_le32(ft->tclass);
+	buf[3] = cpu_to_le32(otype->otype);
 
 	rc = put_entry(buf, sizeof(u32), 4, fp);
 	if (rc)
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index c93c211..4bca494 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1232,6 +1232,10 @@
 	struct context context;
 	int rc = 0;
 
+	/* An empty security context is never valid. */
+	if (!scontext_len)
+		return -EINVAL;
+
 	if (!ss_initialized) {
 		int i;
 
@@ -1285,16 +1289,18 @@
  * @scontext: security context
  * @scontext_len: length in bytes
  * @sid: security identifier, SID
+ * @gfp: context for the allocation
  *
  * Obtains a SID associated with the security context that
  * has the string representation specified by @scontext.
  * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient
  * memory is available, or 0 on success.
  */
-int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid)
+int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid,
+			    gfp_t gfp)
 {
 	return security_context_to_sid_core(scontext, scontext_len,
-					    sid, SECSID_NULL, GFP_KERNEL, 0);
+					    sid, SECSID_NULL, gfp, 0);
 }
 
 /**
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 0462cb3..98b0426 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -78,7 +78,8 @@
  * xfrm_user_sec_ctx context.
  */
 static int selinux_xfrm_alloc_user(struct xfrm_sec_ctx **ctxp,
-				   struct xfrm_user_sec_ctx *uctx)
+				   struct xfrm_user_sec_ctx *uctx,
+				   gfp_t gfp)
 {
 	int rc;
 	const struct task_security_struct *tsec = current_security();
@@ -94,7 +95,7 @@
 	if (str_len >= PAGE_SIZE)
 		return -ENOMEM;
 
-	ctx = kmalloc(sizeof(*ctx) + str_len + 1, GFP_KERNEL);
+	ctx = kmalloc(sizeof(*ctx) + str_len + 1, gfp);
 	if (!ctx)
 		return -ENOMEM;
 
@@ -103,7 +104,7 @@
 	ctx->ctx_len = str_len;
 	memcpy(ctx->ctx_str, &uctx[1], str_len);
 	ctx->ctx_str[str_len] = '\0';
-	rc = security_context_to_sid(ctx->ctx_str, str_len, &ctx->ctx_sid);
+	rc = security_context_to_sid(ctx->ctx_str, str_len, &ctx->ctx_sid, gfp);
 	if (rc)
 		goto err;
 
@@ -282,9 +283,10 @@
  * LSM hook implementation that allocs and transfers uctx spec to xfrm_policy.
  */
 int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
-			      struct xfrm_user_sec_ctx *uctx)
+			      struct xfrm_user_sec_ctx *uctx,
+			      gfp_t gfp)
 {
-	return selinux_xfrm_alloc_user(ctxp, uctx);
+	return selinux_xfrm_alloc_user(ctxp, uctx, gfp);
 }
 
 /*
@@ -332,7 +334,7 @@
 int selinux_xfrm_state_alloc(struct xfrm_state *x,
 			     struct xfrm_user_sec_ctx *uctx)
 {
-	return selinux_xfrm_alloc_user(&x->security, uctx);
+	return selinux_xfrm_alloc_user(&x->security, uctx, GFP_KERNEL);
 }
 
 /*
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 7a20897..7403f34 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -133,7 +133,7 @@
 		kfree(data);
 	}
 	snd_card_unref(compr->card);
-	return 0;
+	return ret;
 }
 
 static int snd_compr_free(struct inode *inode, struct file *f)
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index ec4536c..dafcf82 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -932,7 +932,7 @@
 }
 EXPORT_SYMBOL_GPL(snd_hda_bus_new);
 
-#ifdef CONFIG_SND_HDA_GENERIC
+#if IS_ENABLED(CONFIG_SND_HDA_GENERIC)
 #define is_generic_config(codec) \
 	(codec->modelname && !strcmp(codec->modelname, "generic"))
 #else
@@ -1339,23 +1339,15 @@
 /*
  * Dynamic symbol binding for the codec parsers
  */
-#ifdef MODULE
-#define load_parser_sym(sym)		((int (*)(struct hda_codec *))symbol_request(sym))
-#define unload_parser_addr(addr)	symbol_put_addr(addr)
-#else
-#define load_parser_sym(sym)		(sym)
-#define unload_parser_addr(addr)	do {} while (0)
-#endif
 
 #define load_parser(codec, sym) \
-	((codec)->parser = load_parser_sym(sym))
+	((codec)->parser = (int (*)(struct hda_codec *))symbol_request(sym))
 
 static void unload_parser(struct hda_codec *codec)
 {
-	if (codec->parser) {
-		unload_parser_addr(codec->parser);
-		codec->parser = NULL;
-	}
+	if (codec->parser)
+		symbol_put_addr(codec->parser);
+	codec->parser = NULL;
 }
 
 /*
@@ -1570,7 +1562,7 @@
 EXPORT_SYMBOL_GPL(snd_hda_codec_update_widgets);
 
 
-#ifdef CONFIG_SND_HDA_CODEC_HDMI
+#if IS_ENABLED(CONFIG_SND_HDA_CODEC_HDMI)
 /* if all audio out widgets are digital, let's assume the codec as a HDMI/DP */
 static bool is_likely_hdmi_codec(struct hda_codec *codec)
 {
@@ -1620,12 +1612,20 @@
 		patch = codec->preset->patch;
 	if (!patch) {
 		unload_parser(codec); /* to be sure */
-		if (is_likely_hdmi_codec(codec))
+		if (is_likely_hdmi_codec(codec)) {
+#if IS_MODULE(CONFIG_SND_HDA_CODEC_HDMI)
 			patch = load_parser(codec, snd_hda_parse_hdmi_codec);
-#ifdef CONFIG_SND_HDA_GENERIC
-		if (!patch)
-			patch = load_parser(codec, snd_hda_parse_generic_codec);
+#elif IS_BUILTIN(CONFIG_SND_HDA_CODEC_HDMI)
+			patch = snd_hda_parse_hdmi_codec;
 #endif
+		}
+		if (!patch) {
+#if IS_MODULE(CONFIG_SND_HDA_GENERIC)
+			patch = load_parser(codec, snd_hda_parse_generic_codec);
+#elif IS_BUILTIN(CONFIG_SND_HDA_GENERIC)
+			patch = snd_hda_parse_generic_codec;
+#endif
+		}
 		if (!patch) {
 			printk(KERN_ERR "hda-codec: No codec parser is available\n");
 			return -ENODEV;
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 8321a97..d9a09bd 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -3269,7 +3269,7 @@
 	mutex_unlock(&codec->control_mutex);
 	snd_hda_codec_flush_cache(codec); /* flush the updates */
 	if (err >= 0 && spec->cap_sync_hook)
-		spec->cap_sync_hook(codec, ucontrol);
+		spec->cap_sync_hook(codec, kcontrol, ucontrol);
 	return err;
 }
 
@@ -3390,7 +3390,7 @@
 		return ret;
 
 	if (spec->cap_sync_hook)
-		spec->cap_sync_hook(codec, ucontrol);
+		spec->cap_sync_hook(codec, kcontrol, ucontrol);
 
 	return ret;
 }
@@ -3795,7 +3795,7 @@
 		return 0;
 	snd_hda_activate_path(codec, path, true, false);
 	if (spec->cap_sync_hook)
-		spec->cap_sync_hook(codec, NULL);
+		spec->cap_sync_hook(codec, NULL, NULL);
 	path_power_down_sync(codec, old_path);
 	return 1;
 }
@@ -5270,7 +5270,7 @@
 	}
 
 	if (spec->cap_sync_hook)
-		spec->cap_sync_hook(codec, NULL);
+		spec->cap_sync_hook(codec, NULL, NULL);
 }
 
 /* set right pin controls for digital I/O */
diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h
index 07f7672..c908afb 100644
--- a/sound/pci/hda/hda_generic.h
+++ b/sound/pci/hda/hda_generic.h
@@ -274,6 +274,7 @@
 	void (*init_hook)(struct hda_codec *codec);
 	void (*automute_hook)(struct hda_codec *codec);
 	void (*cap_sync_hook)(struct hda_codec *codec,
+			      struct snd_kcontrol *kcontrol,
 			      struct snd_ctl_elem_value *ucontrol);
 
 	/* PCM hooks */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index fa2879a..e354ab1 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -198,7 +198,7 @@
 #endif
 
 #if defined(CONFIG_PM) && defined(CONFIG_VGA_SWITCHEROO)
-#ifdef CONFIG_SND_HDA_CODEC_HDMI
+#if IS_ENABLED(CONFIG_SND_HDA_CODEC_HDMI)
 #define SUPPORT_VGA_SWITCHEROO
 #endif
 #endif
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index 7a426ed..8ed0bcc 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -244,6 +244,19 @@
 	}
 }
 
+/* Toshiba Satellite L40 implements EAPD in a standard way unlike others */
+static void ad1986a_fixup_eapd(struct hda_codec *codec,
+			       const struct hda_fixup *fix, int action)
+{
+	struct ad198x_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		codec->inv_eapd = 0;
+		spec->gen.keep_eapd_on = 1;
+		spec->eapd_nid = 0x1b;
+	}
+}
+
 enum {
 	AD1986A_FIXUP_INV_JACK_DETECT,
 	AD1986A_FIXUP_ULTRA,
@@ -251,6 +264,7 @@
 	AD1986A_FIXUP_3STACK,
 	AD1986A_FIXUP_LAPTOP,
 	AD1986A_FIXUP_LAPTOP_IMIC,
+	AD1986A_FIXUP_EAPD,
 };
 
 static const struct hda_fixup ad1986a_fixups[] = {
@@ -311,6 +325,10 @@
 		.chained_before = 1,
 		.chain_id = AD1986A_FIXUP_LAPTOP,
 	},
+	[AD1986A_FIXUP_EAPD] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = ad1986a_fixup_eapd,
+	},
 };
 
 static const struct snd_pci_quirk ad1986a_fixup_tbl[] = {
@@ -318,6 +336,7 @@
 	SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8100, "ASUS P5", AD1986A_FIXUP_3STACK),
 	SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8200, "ASUS M2", AD1986A_FIXUP_3STACK),
 	SND_PCI_QUIRK(0x10de, 0xcb84, "ASUS A8N-VM", AD1986A_FIXUP_3STACK),
+	SND_PCI_QUIRK(0x1179, 0xff40, "Toshiba Satellite L40", AD1986A_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x144d, 0xc01e, "FSC V2060", AD1986A_FIXUP_LAPTOP),
 	SND_PCI_QUIRK_MASK(0x144d, 0xff00, 0xc000, "Samsung", AD1986A_FIXUP_SAMSUNG),
 	SND_PCI_QUIRK(0x144d, 0xc027, "Samsung Q1", AD1986A_FIXUP_ULTRA),
@@ -472,6 +491,8 @@
 static int patch_ad1983(struct hda_codec *codec)
 {
 	struct ad198x_spec *spec;
+	static hda_nid_t conn_0c[] = { 0x08 };
+	static hda_nid_t conn_0d[] = { 0x09 };
 	int err;
 
 	err = alloc_ad_spec(codec);
@@ -479,8 +500,14 @@
 		return err;
 	spec = codec->spec;
 
+	spec->gen.mixer_nid = 0x0e;
 	spec->gen.beep_nid = 0x10;
 	set_beep_amp(spec, 0x10, 0, HDA_OUTPUT);
+
+	/* limit the loopback routes not to confuse the parser */
+	snd_hda_override_conn_list(codec, 0x0c, ARRAY_SIZE(conn_0c), conn_0c);
+	snd_hda_override_conn_list(codec, 0x0d, ARRAY_SIZE(conn_0d), conn_0d);
+
 	err = ad198x_parse_auto_config(codec, false);
 	if (err < 0)
 		goto error;
@@ -999,6 +1026,9 @@
 		spec->gen.keep_eapd_on = 1;
 		spec->gen.vmaster_mute.hook = ad_vmaster_eapd_hook;
 		spec->eapd_nid = 0x12;
+		/* Analog PC Beeper - allow firmware/ACPI beeps */
+		spec->beep_amp = HDA_COMPOSE_AMP_VAL(0x20, 3, 3, HDA_INPUT);
+		spec->gen.beep_nid = 0; /* no digital beep */
 	}
 }
 
@@ -1065,6 +1095,7 @@
 	spec = codec->spec;
 
 	spec->gen.mixer_nid = 0x20;
+	spec->gen.mixer_merge_nid = 0x21;
 	spec->gen.beep_nid = 0x10;
 	set_beep_amp(spec, 0x10, 0, HDA_OUTPUT);
 
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 54d1479..46ecdbb 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -2662,60 +2662,6 @@
 }
 
 /*
- * PCM stuffs
- */
-static void ca0132_setup_stream(struct hda_codec *codec, hda_nid_t nid,
-				 u32 stream_tag,
-				 int channel_id, int format)
-{
-	unsigned int oldval, newval;
-
-	if (!nid)
-		return;
-
-	snd_printdd(
-		   "ca0132_setup_stream: NID=0x%x, stream=0x%x, "
-		   "channel=%d, format=0x%x\n",
-		   nid, stream_tag, channel_id, format);
-
-	/* update the format-id if changed */
-	oldval = snd_hda_codec_read(codec, nid, 0,
-				    AC_VERB_GET_STREAM_FORMAT,
-				    0);
-	if (oldval != format) {
-		msleep(20);
-		snd_hda_codec_write(codec, nid, 0,
-				    AC_VERB_SET_STREAM_FORMAT,
-				    format);
-	}
-
-	oldval = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONV, 0);
-	newval = (stream_tag << 4) | channel_id;
-	if (oldval != newval) {
-		snd_hda_codec_write(codec, nid, 0,
-				    AC_VERB_SET_CHANNEL_STREAMID,
-				    newval);
-	}
-}
-
-static void ca0132_cleanup_stream(struct hda_codec *codec, hda_nid_t nid)
-{
-	unsigned int val;
-
-	if (!nid)
-		return;
-
-	snd_printdd(KERN_INFO "ca0132_cleanup_stream: NID=0x%x\n", nid);
-
-	val = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONV, 0);
-	if (!val)
-		return;
-
-	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_STREAM_FORMAT, 0);
-	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_CHANNEL_STREAMID, 0);
-}
-
-/*
  * PCM callbacks
  */
 static int ca0132_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
@@ -2726,7 +2672,7 @@
 {
 	struct ca0132_spec *spec = codec->spec;
 
-	ca0132_setup_stream(codec, spec->dacs[0], stream_tag, 0, format);
+	snd_hda_codec_setup_stream(codec, spec->dacs[0], stream_tag, 0, format);
 
 	return 0;
 }
@@ -2745,7 +2691,7 @@
 	if (spec->effects_switch[PLAY_ENHANCEMENT - EFFECT_START_NID])
 		msleep(50);
 
-	ca0132_cleanup_stream(codec, spec->dacs[0]);
+	snd_hda_codec_cleanup_stream(codec, spec->dacs[0]);
 
 	return 0;
 }
@@ -2822,10 +2768,8 @@
 					unsigned int format,
 					struct snd_pcm_substream *substream)
 {
-	struct ca0132_spec *spec = codec->spec;
-
-	ca0132_setup_stream(codec, spec->adcs[substream->number],
-			    stream_tag, 0, format);
+	snd_hda_codec_setup_stream(codec, hinfo->nid,
+				   stream_tag, 0, format);
 
 	return 0;
 }
@@ -2839,7 +2783,7 @@
 	if (spec->dsp_state == DSP_DOWNLOADING)
 		return 0;
 
-	ca0132_cleanup_stream(codec, hinfo->nid);
+	snd_hda_codec_cleanup_stream(codec, hinfo->nid);
 	return 0;
 }
 
@@ -4742,6 +4686,8 @@
 		return err;
 
 	codec->patch_ops = ca0132_patch_ops;
+	codec->pcm_format_first = 1;
+	codec->no_sticky_stream = 1;
 
 	return 0;
 }
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 4e0ec14..bcf91be 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -3291,7 +3291,8 @@
 }
 
 static void cxt_update_headset_mode_hook(struct hda_codec *codec,
-			     struct snd_ctl_elem_value *ucontrol)
+					 struct snd_kcontrol *kcontrol,
+					 struct snd_ctl_elem_value *ucontrol)
 {
 	cxt_update_headset_mode(codec);
 }
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 56a8f18..8d0a844 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -708,7 +708,8 @@
 }
 
 static void alc_inv_dmic_hook(struct hda_codec *codec,
-			     struct snd_ctl_elem_value *ucontrol)
+			      struct snd_kcontrol *kcontrol,
+			      struct snd_ctl_elem_value *ucontrol)
 {
 	alc_inv_dmic_sync(codec, false);
 }
@@ -1821,6 +1822,7 @@
 	ALC889_FIXUP_IMAC91_VREF,
 	ALC889_FIXUP_MBA11_VREF,
 	ALC889_FIXUP_MBA21_VREF,
+	ALC889_FIXUP_MP11_VREF,
 	ALC882_FIXUP_INV_DMIC,
 	ALC882_FIXUP_NO_PRIMARY_HP,
 	ALC887_FIXUP_ASUS_BASS,
@@ -2190,6 +2192,12 @@
 		.chained = true,
 		.chain_id = ALC889_FIXUP_MBP_VREF,
 	},
+	[ALC889_FIXUP_MP11_VREF] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc889_fixup_mba11_vref,
+		.chained = true,
+		.chain_id = ALC885_FIXUP_MACPRO_GPIO,
+	},
 	[ALC882_FIXUP_INV_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_inv_dmic_0x12,
@@ -2253,7 +2261,7 @@
 	SND_PCI_QUIRK(0x106b, 0x00a0, "MacBookPro 3,1", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x00a1, "Macbook", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x00a4, "MacbookPro 4,1", ALC889_FIXUP_MBP_VREF),
-	SND_PCI_QUIRK(0x106b, 0x0c00, "Mac Pro", ALC885_FIXUP_MACPRO_GPIO),
+	SND_PCI_QUIRK(0x106b, 0x0c00, "Mac Pro", ALC889_FIXUP_MP11_VREF),
 	SND_PCI_QUIRK(0x106b, 0x1000, "iMac 24", ALC885_FIXUP_MACPRO_GPIO),
 	SND_PCI_QUIRK(0x106b, 0x2800, "AppleTV", ALC885_FIXUP_MACPRO_GPIO),
 	SND_PCI_QUIRK(0x106b, 0x2c00, "MacbookPro rev3", ALC889_FIXUP_MBP_VREF),
@@ -3211,7 +3219,8 @@
 
 /* turn on/off mic-mute LED per capture hook */
 static void alc269_fixup_hp_gpio_mic_mute_hook(struct hda_codec *codec,
-			       struct snd_ctl_elem_value *ucontrol)
+					       struct snd_kcontrol *kcontrol,
+					       struct snd_ctl_elem_value *ucontrol)
 {
 	struct alc_spec *spec = codec->spec;
 	unsigned int oldval = spec->gpio_led;
@@ -3521,7 +3530,8 @@
 }
 
 static void alc_update_headset_mode_hook(struct hda_codec *codec,
-			     struct snd_ctl_elem_value *ucontrol)
+					 struct snd_kcontrol *kcontrol,
+					 struct snd_ctl_elem_value *ucontrol)
 {
 	alc_update_headset_mode(codec);
 }
@@ -3606,6 +3616,19 @@
 	}
 }
 
+static void alc_no_shutup(struct hda_codec *codec)
+{
+}
+
+static void alc_fixup_no_shutup(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		struct alc_spec *spec = codec->spec;
+		spec->shutup = alc_no_shutup;
+	}
+}
+
 static void alc_fixup_headset_mode_alc668(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
@@ -3834,6 +3857,7 @@
 	ALC269_FIXUP_HP_GPIO_LED,
 	ALC269_FIXUP_INV_DMIC,
 	ALC269_FIXUP_LENOVO_DOCK,
+	ALC269_FIXUP_NO_SHUTUP,
 	ALC286_FIXUP_SONY_MIC_NO_PRESENCE,
 	ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT,
 	ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -4010,6 +4034,10 @@
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_inv_dmic_0x12,
 	},
+	[ALC269_FIXUP_NO_SHUTUP] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_no_shutup,
+	},
 	[ALC269_FIXUP_LENOVO_DOCK] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -4243,6 +4271,7 @@
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+	SND_PCI_QUIRK(0x1025, 0x0283, "Acer TravelMate 8371", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x029b, "Acer 1810TZ", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x0349, "Acer AOD260", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x047c, "Acer AC700", ALC269_FIXUP_ACER_AC700),
@@ -4298,7 +4327,9 @@
 	SND_PCI_QUIRK(0x1028, 0x0651, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0652, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0653, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0657, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0658, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x065f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0662, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
@@ -4307,6 +4338,54 @@
 	SND_PCI_QUIRK(0x103c, 0x1973, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
+	/* ALC282 */
+	SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22a0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22b2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22b7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22bf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c1, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22cd, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22ce, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22cf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22d0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	/* ALC290 */
+	SND_PCI_QUIRK(0x103c, 0x2260, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2261, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2262, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2263, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2264, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2265, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2280, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2281, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2282, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2289, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c5, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c6, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -4322,6 +4401,7 @@
 	SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x83ce, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x8516, "ASUS X101CH", ALC269_FIXUP_ASUS_X101),
+	SND_PCI_QUIRK(0x104d, 0x90b5, "Sony VAIO Pro 11", ALC286_FIXUP_SONY_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x104d, 0x90b6, "Sony VAIO Pro 13", ALC286_FIXUP_SONY_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x104d, 0x9073, "Sony VAIO", ALC275_FIXUP_SONY_VAIO_GPIO2),
 	SND_PCI_QUIRK(0x104d, 0x907b, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
@@ -4343,6 +4423,7 @@
 	SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
 	SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -5096,12 +5177,13 @@
 	SND_PCI_QUIRK(0x1025, 0x038b, "Acer Aspire 8943G", ALC662_FIXUP_ASPIRE),
 	SND_PCI_QUIRK(0x1028, 0x05d8, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05db, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x060a, "Dell XPS 13", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0623, "Dell", ALC668_FIXUP_AUTO_MUTE),
 	SND_PCI_QUIRK(0x1028, 0x0624, "Dell", ALC668_FIXUP_AUTO_MUTE),
 	SND_PCI_QUIRK(0x1028, 0x0625, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0626, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0628, "Dell", ALC668_FIXUP_AUTO_MUTE),
-	SND_PCI_QUIRK(0x1028, 0x064e, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x064e, "Dell", ALC668_FIXUP_AUTO_MUTE),
 	SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800),
 	SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A_CHMAP),
 	SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_CHMAP),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 6998cf2..3bc29c9 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -83,6 +83,7 @@
 	STAC_DELL_M6_BOTH,
 	STAC_DELL_EQ,
 	STAC_ALIENWARE_M17X,
+	STAC_92HD89XX_HP_FRONT_JACK,
 	STAC_92HD73XX_MODELS
 };
 
@@ -97,6 +98,7 @@
 	STAC_92HD83XXX_HP_LED,
 	STAC_92HD83XXX_HP_INV_LED,
 	STAC_92HD83XXX_HP_MIC_LED,
+	STAC_HP_LED_GPIO10,
 	STAC_92HD83XXX_HEADSET_JACK,
 	STAC_92HD83XXX_HP,
 	STAC_HP_ENVY_BASS,
@@ -194,7 +196,7 @@
 	int default_polarity;
 
 	unsigned int mic_mute_led_gpio; /* capture mute LED GPIO */
-	bool mic_mute_led_on; /* current mic mute state */
+	unsigned int mic_enabled; /* current mic mute state (bitmask) */
 
 	/* stream */
 	unsigned int stream_delay;
@@ -324,19 +326,26 @@
 
 /* hook for controlling mic-mute LED GPIO */
 static void stac_capture_led_hook(struct hda_codec *codec,
-			       struct snd_ctl_elem_value *ucontrol)
+				  struct snd_kcontrol *kcontrol,
+				  struct snd_ctl_elem_value *ucontrol)
 {
 	struct sigmatel_spec *spec = codec->spec;
-	bool mute;
+	unsigned int mask;
+	bool cur_mute, prev_mute;
 
-	if (!ucontrol)
+	if (!kcontrol || !ucontrol)
 		return;
 
-	mute = !(ucontrol->value.integer.value[0] ||
-		 ucontrol->value.integer.value[1]);
-	if (spec->mic_mute_led_on != mute) {
-		spec->mic_mute_led_on = mute;
-		if (mute)
+	mask = 1U << snd_ctl_get_ioffidx(kcontrol, &ucontrol->id);
+	prev_mute = !spec->mic_enabled;
+	if (ucontrol->value.integer.value[0] ||
+	    ucontrol->value.integer.value[1])
+		spec->mic_enabled |= mask;
+	else
+		spec->mic_enabled &= ~mask;
+	cur_mute = !spec->mic_enabled;
+	if (cur_mute != prev_mute) {
+		if (cur_mute)
 			spec->gpio_data |= spec->mic_mute_led_gpio;
 		else
 			spec->gpio_data &= ~spec->mic_mute_led_gpio;
@@ -1788,6 +1797,12 @@
 	{}
 };
 
+static const struct hda_pintbl stac92hd89xx_hp_front_jack_pin_configs[] = {
+	{ 0x0a, 0x02214030 },
+	{ 0x0b, 0x02A19010 },
+	{}
+};
+
 static void stac92hd73xx_fixup_ref(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
@@ -1906,6 +1921,10 @@
 	[STAC_92HD73XX_NO_JD] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = stac92hd73xx_fixup_no_jd,
+	},
+	[STAC_92HD89XX_HP_FRONT_JACK] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = stac92hd89xx_hp_front_jack_pin_configs,
 	}
 };
 
@@ -1966,6 +1985,8 @@
 		      "Alienware M17x", STAC_ALIENWARE_M17X),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490,
 		      "Alienware M17x R3", STAC_DELL_EQ),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17,
+				"unknown HP", STAC_92HD89XX_HP_FRONT_JACK),
 	{} /* terminator */
 };
 
@@ -2110,6 +2131,17 @@
 	}
 }
 
+static void stac92hd83xxx_fixup_hp_led_gpio10(struct hda_codec *codec,
+				   const struct hda_fixup *fix, int action)
+{
+	struct sigmatel_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->gpio_led = 0x10; /* GPIO4 */
+		spec->default_polarity = 0;
+	}
+}
+
 static void stac92hd83xxx_fixup_headset_jack(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
@@ -2604,6 +2636,12 @@
 		.chained = true,
 		.chain_id = STAC_92HD83XXX_HP,
 	},
+	[STAC_HP_LED_GPIO10] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = stac92hd83xxx_fixup_hp_led_gpio10,
+		.chained = true,
+		.chain_id = STAC_92HD83XXX_HP,
+	},
 	[STAC_92HD83XXX_HEADSET_JACK] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = stac92hd83xxx_fixup_headset_jack,
@@ -2682,6 +2720,8 @@
 			  "HP", STAC_92HD83XXX_HP_cNB11_INTQUAD),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1888,
 			  "HP Envy Spectre", STAC_HP_ENVY_BASS),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1899,
+			  "HP Folio 13", STAC_HP_LED_GPIO10),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x18df,
 			  "HP Folio", STAC_HP_BNB13_EQ),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x18F8,
@@ -4462,7 +4502,7 @@
 	if (spec->mic_mute_led_gpio) {
 		spec->gpio_mask |= spec->mic_mute_led_gpio;
 		spec->gpio_dir |= spec->mic_mute_led_gpio;
-		spec->mic_mute_led_on = true;
+		spec->mic_enabled = 0;
 		spec->gpio_data |= spec->mic_mute_led_gpio;
 
 		spec->gen.cap_sync_hook = stac_capture_led_hook;
diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c
index 5799fbc..8fe3b8c 100644
--- a/sound/pci/hda/thinkpad_helper.c
+++ b/sound/pci/hda/thinkpad_helper.c
@@ -39,6 +39,7 @@
 }
 
 static void update_tpacpi_micmute_led(struct hda_codec *codec,
+				      struct snd_kcontrol *kcontrol,
 				      struct snd_ctl_elem_value *ucontrol)
 {
 	if (!ucontrol || !led_set_func)
diff --git a/sound/pci/oxygen/xonar_dg.c b/sound/pci/oxygen/xonar_dg.c
index ed6f199..4cf3200 100644
--- a/sound/pci/oxygen/xonar_dg.c
+++ b/sound/pci/oxygen/xonar_dg.c
@@ -238,11 +238,21 @@
 	cs4245_write_spi(chip, CS4245_MCLK_FREQ);
 }
 
+static inline unsigned int shift_bits(unsigned int value,
+				      unsigned int shift_from,
+				      unsigned int shift_to,
+				      unsigned int mask)
+{
+	if (shift_from < shift_to)
+		return (value << (shift_to - shift_from)) & mask;
+	else
+		return (value >> (shift_from - shift_to)) & mask;
+}
+
 unsigned int adjust_dg_dac_routing(struct oxygen *chip,
 					  unsigned int play_routing)
 {
 	struct dg *data = chip->model_data;
-	unsigned int routing = 0;
 
 	switch (data->output_sel) {
 	case PLAYBACK_DST_HP:
@@ -252,15 +262,23 @@
 			OXYGEN_PLAY_MUTE67, OXYGEN_PLAY_MUTE_MASK);
 		break;
 	case PLAYBACK_DST_MULTICH:
-		routing = (0 << OXYGEN_PLAY_DAC0_SOURCE_SHIFT) |
-			  (2 << OXYGEN_PLAY_DAC1_SOURCE_SHIFT) |
-			  (1 << OXYGEN_PLAY_DAC2_SOURCE_SHIFT) |
-			  (0 << OXYGEN_PLAY_DAC3_SOURCE_SHIFT);
 		oxygen_write8_masked(chip, OXYGEN_PLAY_ROUTING,
 			OXYGEN_PLAY_MUTE01, OXYGEN_PLAY_MUTE_MASK);
 		break;
 	}
-	return routing;
+	return (play_routing & OXYGEN_PLAY_DAC0_SOURCE_MASK) |
+	       shift_bits(play_routing,
+			  OXYGEN_PLAY_DAC2_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC1_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC1_SOURCE_MASK) |
+	       shift_bits(play_routing,
+			  OXYGEN_PLAY_DAC1_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC2_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC2_SOURCE_MASK) |
+	       shift_bits(play_routing,
+			  OXYGEN_PLAY_DAC0_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC3_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC3_SOURCE_MASK);
 }
 
 void dump_cs4245_registers(struct oxygen *chip,
diff --git a/sound/soc/blackfin/Kconfig b/sound/soc/blackfin/Kconfig
index 54f74f8..4544d8e 100644
--- a/sound/soc/blackfin/Kconfig
+++ b/sound/soc/blackfin/Kconfig
@@ -11,7 +11,7 @@
 
 config SND_BF5XX_SOC_SSM2602
 	tristate "SoC SSM2602 Audio Codec Add-On Card support"
-	depends on SND_BF5XX_I2S && (SPI_MASTER || I2C)
+	depends on SND_BF5XX_I2S && SND_SOC_I2C_AND_SPI
 	select SND_BF5XX_SOC_I2S if !BF60x
 	select SND_BF6XX_SOC_I2S if BF60x
 	select SND_SOC_SSM2602
@@ -21,10 +21,9 @@
 
 config SND_SOC_BFIN_EVAL_ADAU1701
 	tristate "Support for the EVAL-ADAU1701MINIZ board on Blackfin eval boards"
-	depends on SND_BF5XX_I2S
+	depends on SND_BF5XX_I2S && I2C
 	select SND_BF5XX_SOC_I2S
 	select SND_SOC_ADAU1701
-	select I2C
 	help
 	  Say Y if you want to add support for the Analog Devices EVAL-ADAU1701MINIZ
 	  board connected to one of the Blackfin evaluation boards like the
@@ -45,7 +44,7 @@
 
 config SND_SOC_BFIN_EVAL_ADAV80X
 	tristate "Support for the EVAL-ADAV80X boards on Blackfin eval boards"
-	depends on SND_BF5XX_I2S && (SPI_MASTER || I2C)
+	depends on SND_BF5XX_I2S && SND_SOC_I2C_AND_SPI
 	select SND_BF5XX_SOC_I2S
 	select SND_SOC_ADAV80X
 	help
@@ -58,7 +57,7 @@
 
 config SND_BF5XX_SOC_AD1836
 	tristate "SoC AD1836 Audio support for BF5xx"
-	depends on SND_BF5XX_I2S
+	depends on SND_BF5XX_I2S && SPI_MASTER
 	select SND_BF5XX_SOC_I2S
 	select SND_SOC_AD1836
 	help
@@ -66,7 +65,7 @@
 
 config SND_BF5XX_SOC_AD193X
 	tristate "SoC AD193X Audio support for Blackfin"
-	depends on SND_BF5XX_I2S
+	depends on SND_BF5XX_I2S && SND_SOC_I2C_AND_SPI
 	select SND_BF5XX_SOC_I2S
 	select SND_SOC_AD193X
 	help
diff --git a/sound/soc/codecs/88pm860x-codec.c b/sound/soc/codecs/88pm860x-codec.c
index 75d0ad5..647a72c 100644
--- a/sound/soc/codecs/88pm860x-codec.c
+++ b/sound/soc/codecs/88pm860x-codec.c
@@ -1328,6 +1328,9 @@
 	pm860x->codec = codec;
 
 	codec->control_data = pm860x->regmap;
+	ret = snd_soc_codec_set_cache_io(codec, 0, 0, SND_SOC_REGMAP);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < 4; i++) {
 		ret = request_threaded_irq(pm860x->irq[i], NULL,
diff --git a/sound/soc/codecs/ad1980.c b/sound/soc/codecs/ad1980.c
index 7257a88..34d965a 100644
--- a/sound/soc/codecs/ad1980.c
+++ b/sound/soc/codecs/ad1980.c
@@ -57,8 +57,8 @@
 static const char *ad1980_rec_sel[] = {"Mic", "CD", "NC", "AUX", "Line",
 		"Stereo Mix", "Mono Mix", "Phone"};
 
-static const struct soc_enum ad1980_cap_src =
-	SOC_ENUM_DOUBLE(AC97_REC_SEL, 8, 0, 7, ad1980_rec_sel);
+static SOC_ENUM_DOUBLE_DECL(ad1980_cap_src,
+			    AC97_REC_SEL, 8, 0, ad1980_rec_sel);
 
 static const struct snd_kcontrol_new ad1980_snd_ac97_controls[] = {
 SOC_DOUBLE("Master Playback Volume", AC97_MASTER, 8, 0, 31, 1),
diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c
index f295b65..f4d965ebc 100644
--- a/sound/soc/codecs/da732x.c
+++ b/sound/soc/codecs/da732x.c
@@ -1268,11 +1268,23 @@
 	},
 };
 
+static bool da732x_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case DA732X_REG_HPL_DAC_OFF_CNTL:
+	case DA732X_REG_HPR_DAC_OFF_CNTL:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static const struct regmap_config da732x_regmap = {
 	.reg_bits		= 8,
 	.val_bits		= 8,
 
 	.max_register		= DA732X_MAX_REG,
+	.volatile_reg		= da732x_volatile,
 	.reg_defaults		= da732x_reg_cache,
 	.num_reg_defaults	= ARRAY_SIZE(da732x_reg_cache),
 	.cache_type		= REGCACHE_RBTREE,
diff --git a/sound/soc/codecs/da9055.c b/sound/soc/codecs/da9055.c
index 52b79a4..4228126 100644
--- a/sound/soc/codecs/da9055.c
+++ b/sound/soc/codecs/da9055.c
@@ -1523,8 +1523,15 @@
 	return 0;
 }
 
+/*
+ * DO NOT change the device Ids. The naming is intentionally specific as both
+ * the CODEC and PMIC parts of this chip are instantiated separately as I2C
+ * devices (both have configurable I2C addresses, and are to all intents and
+ * purposes separate). As a result there are specific DA9055 Ids for CODEC
+ * and PMIC, which must be different to operate together.
+ */
 static const struct i2c_device_id da9055_i2c_id[] = {
-	{ "da9055", 0 },
+	{ "da9055-codec", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, da9055_i2c_id);
@@ -1532,7 +1539,7 @@
 /* I2C codec control layer */
 static struct i2c_driver da9055_i2c_driver = {
 	.driver = {
-		.name = "da9055",
+		.name = "da9055-codec",
 		.owner = THIS_MODULE,
 	},
 	.probe		= da9055_i2c_probe,
diff --git a/sound/soc/codecs/isabelle.c b/sound/soc/codecs/isabelle.c
index 5839048..cb736dd 100644
--- a/sound/soc/codecs/isabelle.c
+++ b/sound/soc/codecs/isabelle.c
@@ -140,13 +140,17 @@
 static const char *isabelle_rx2_texts[] = {"VRX2", "ARX2"};
 
 static const struct soc_enum isabelle_rx1_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 3, 1, isabelle_rx1_texts),
-	SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 5, 1, isabelle_rx1_texts),
+	SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 3,
+			ARRAY_SIZE(isabelle_rx1_texts), isabelle_rx1_texts),
+	SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 5,
+			ARRAY_SIZE(isabelle_rx1_texts), isabelle_rx1_texts),
 };
 
 static const struct soc_enum isabelle_rx2_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 2, 1, isabelle_rx2_texts),
-	SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 4, 1, isabelle_rx2_texts),
+	SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 2,
+			ARRAY_SIZE(isabelle_rx2_texts), isabelle_rx2_texts),
+	SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 4,
+			ARRAY_SIZE(isabelle_rx2_texts), isabelle_rx2_texts),
 };
 
 /* Headset DAC playback switches */
@@ -161,13 +165,17 @@
 static const char *isabelle_vtx_texts[] = {"AMIC2", "DMIC"};
 
 static const struct soc_enum isabelle_atx_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 7, 1, isabelle_atx_texts),
-	SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0, 1, isabelle_atx_texts),
+	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 7,
+			ARRAY_SIZE(isabelle_atx_texts), isabelle_atx_texts),
+	SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0,
+			ARRAY_SIZE(isabelle_atx_texts), isabelle_atx_texts),
 };
 
 static const struct soc_enum isabelle_vtx_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 6, 1, isabelle_vtx_texts),
-	SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0, 1, isabelle_vtx_texts),
+	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 6,
+			ARRAY_SIZE(isabelle_vtx_texts), isabelle_vtx_texts),
+	SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0,
+			ARRAY_SIZE(isabelle_vtx_texts), isabelle_vtx_texts),
 };
 
 static const struct snd_kcontrol_new atx_mux_controls =
@@ -183,17 +191,13 @@
 /* Left analog microphone selection */
 static const char *isabelle_amic2_texts[] = {"Sub Mic", "Aux/FM Right"};
 
-static const struct soc_enum isabelle_amic1_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 5,
-			ARRAY_SIZE(isabelle_amic1_texts),
-			isabelle_amic1_texts),
-};
+static SOC_ENUM_SINGLE_DECL(isabelle_amic1_enum,
+			    ISABELLE_AMIC_CFG_REG, 5,
+			    isabelle_amic1_texts);
 
-static const struct soc_enum isabelle_amic2_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 4,
-			ARRAY_SIZE(isabelle_amic2_texts),
-			isabelle_amic2_texts),
-};
+static SOC_ENUM_SINGLE_DECL(isabelle_amic2_enum,
+			    ISABELLE_AMIC_CFG_REG, 4,
+			    isabelle_amic2_texts);
 
 static const struct snd_kcontrol_new amic1_control =
 	SOC_DAPM_ENUM("Route", isabelle_amic1_enum);
@@ -206,16 +210,20 @@
 static const char *isabelle_st_voice_texts[] = {"VTX1", "VTX2"};
 
 static const struct soc_enum isabelle_st_audio_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA1_CFG_REG, 7, 1,
+	SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA1_CFG_REG, 7,
+			ARRAY_SIZE(isabelle_st_audio_texts),
 			isabelle_st_audio_texts),
-	SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA2_CFG_REG, 7, 1,
+	SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA2_CFG_REG, 7,
+			ARRAY_SIZE(isabelle_st_audio_texts),
 			isabelle_st_audio_texts),
 };
 
 static const struct soc_enum isabelle_st_voice_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_VTX_STPGA1_CFG_REG, 7, 1,
+	SOC_ENUM_SINGLE(ISABELLE_VTX_STPGA1_CFG_REG, 7,
+			ARRAY_SIZE(isabelle_st_voice_texts),
 			isabelle_st_voice_texts),
-	SOC_ENUM_SINGLE(ISABELLE_VTX2_STPGA2_CFG_REG, 7, 1,
+	SOC_ENUM_SINGLE(ISABELLE_VTX2_STPGA2_CFG_REG, 7,
+			ARRAY_SIZE(isabelle_st_voice_texts),
 			isabelle_st_voice_texts),
 };
 
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index 51f9b3d..9f714ea 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -336,6 +336,7 @@
 	case M98090_REG_RECORD_TDM_SLOT:
 	case M98090_REG_SAMPLE_RATE:
 	case M98090_REG_DMIC34_BIQUAD_BASE ... M98090_REG_DMIC34_BIQUAD_BASE + 0x0E:
+	case M98090_REG_REVISION_ID:
 		return true;
 	default:
 		return false;
@@ -1769,16 +1770,6 @@
 
 	switch (level) {
 	case SND_SOC_BIAS_ON:
-		if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) {
-			ret = regcache_sync(max98090->regmap);
-
-			if (ret != 0) {
-				dev_err(codec->dev,
-					"Failed to sync cache: %d\n", ret);
-				return ret;
-			}
-		}
-
 		if (max98090->jack_state == M98090_JACK_STATE_HEADSET) {
 			/*
 			 * Set to normal bias level.
@@ -1792,6 +1783,16 @@
 		break;
 
 	case SND_SOC_BIAS_STANDBY:
+		if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) {
+			ret = regcache_sync(max98090->regmap);
+			if (ret != 0) {
+				dev_err(codec->dev,
+					"Failed to sync cache: %d\n", ret);
+				return ret;
+			}
+		}
+		break;
+
 	case SND_SOC_BIAS_OFF:
 		/* Set internal pull-up to lowest power mode */
 		snd_soc_update_bits(codec, M98090_REG_JACK_DETECT,
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index a3fb411..8869249 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -2093,6 +2093,7 @@
 #ifdef CONFIG_ACPI
 static struct acpi_device_id rt5640_acpi_match[] = {
 	{ "INT33CA", 0 },
+	{ "10EC5640", 0 },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, rt5640_acpi_match);
diff --git a/sound/soc/codecs/si476x.c b/sound/soc/codecs/si476x.c
index 52e7cb0..fa2b8e0 100644
--- a/sound/soc/codecs/si476x.c
+++ b/sound/soc/codecs/si476x.c
@@ -210,7 +210,7 @@
 static int si476x_codec_probe(struct snd_soc_codec *codec)
 {
 	codec->control_data = dev_get_regmap(codec->dev->parent, NULL);
-	return 0;
+	return snd_soc_codec_set_cache_io(codec, 0, 0, SND_SOC_REGMAP);
 }
 
 static struct snd_soc_dai_ops si476x_dai_ops = {
diff --git a/sound/soc/codecs/sta32x.c b/sound/soc/codecs/sta32x.c
index 06edb39..2735361 100644
--- a/sound/soc/codecs/sta32x.c
+++ b/sound/soc/codecs/sta32x.c
@@ -187,42 +187,42 @@
 	13, 16, TLV_DB_SCALE_ITEM(-1500, 300, 0),
 };
 
-static const struct soc_enum sta32x_drc_ac_enum =
-	SOC_ENUM_SINGLE(STA32X_CONFD, STA32X_CONFD_DRC_SHIFT,
-			2, sta32x_drc_ac);
-static const struct soc_enum sta32x_auto_eq_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT,
-			3, sta32x_auto_eq_mode);
-static const struct soc_enum sta32x_auto_gc_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT,
-			4, sta32x_auto_gc_mode);
-static const struct soc_enum sta32x_auto_xo_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT,
-			16, sta32x_auto_xo_mode);
-static const struct soc_enum sta32x_preset_eq_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT,
-			32, sta32x_preset_eq_mode);
-static const struct soc_enum sta32x_limiter_ch1_enum =
-	SOC_ENUM_SINGLE(STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT,
-			3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter_ch2_enum =
-	SOC_ENUM_SINGLE(STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT,
-			3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter_ch3_enum =
-	SOC_ENUM_SINGLE(STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT,
-			3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter1_attack_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxA_SHIFT,
-			16, sta32x_limiter_attack_rate);
-static const struct soc_enum sta32x_limiter2_attack_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxA_SHIFT,
-			16, sta32x_limiter_attack_rate);
-static const struct soc_enum sta32x_limiter1_release_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxR_SHIFT,
-			16, sta32x_limiter_release_rate);
-static const struct soc_enum sta32x_limiter2_release_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxR_SHIFT,
-			16, sta32x_limiter_release_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_drc_ac_enum,
+			    STA32X_CONFD, STA32X_CONFD_DRC_SHIFT,
+			    sta32x_drc_ac);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_eq_enum,
+			    STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT,
+			    sta32x_auto_eq_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_gc_enum,
+			    STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT,
+			    sta32x_auto_gc_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_xo_enum,
+			    STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT,
+			    sta32x_auto_xo_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_preset_eq_enum,
+			    STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT,
+			    sta32x_preset_eq_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch1_enum,
+			    STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT,
+			    sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch2_enum,
+			    STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT,
+			    sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch3_enum,
+			    STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT,
+			    sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_attack_rate_enum,
+			    STA32X_L1AR, STA32X_LxA_SHIFT,
+			    sta32x_limiter_attack_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_attack_rate_enum,
+			    STA32X_L2AR, STA32X_LxA_SHIFT,
+			    sta32x_limiter_attack_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_release_rate_enum,
+			    STA32X_L1AR, STA32X_LxR_SHIFT,
+			    sta32x_limiter_release_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_release_rate_enum,
+			    STA32X_L2AR, STA32X_LxR_SHIFT,
+			    sta32x_limiter_release_rate);
 
 /* byte array controls for setting biquad, mixer, scaling coefficients;
  * for biquads all five coefficients need to be set in one go,
@@ -331,7 +331,7 @@
 
 static int sta32x_cache_sync(struct snd_soc_codec *codec)
 {
-	struct sta32x_priv *sta32x = codec->control_data;
+	struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
 	unsigned int mute;
 	int rc;
 
@@ -434,7 +434,7 @@
 SOC_ENUM("Limiter1 Attack Rate (dB/ms)", sta32x_limiter1_attack_rate_enum),
 SOC_ENUM("Limiter2 Attack Rate (dB/ms)", sta32x_limiter2_attack_rate_enum),
 SOC_ENUM("Limiter1 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum),
-SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum),
+SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter2_release_rate_enum),
 
 /* depending on mode, the attack/release thresholds have
  * two different enum definitions; provide both
diff --git a/sound/soc/codecs/wm8400.c b/sound/soc/codecs/wm8400.c
index 48dc7d2..6d684d9 100644
--- a/sound/soc/codecs/wm8400.c
+++ b/sound/soc/codecs/wm8400.c
@@ -117,19 +117,23 @@
 static const char *wm8400_digital_sidetone[] =
 	{"None", "Left ADC", "Right ADC", "Reserved"};
 
-static const struct soc_enum wm8400_left_digital_sidetone_enum =
-SOC_ENUM_SINGLE(WM8400_DIGITAL_SIDE_TONE,
-		WM8400_ADC_TO_DACL_SHIFT, 2, wm8400_digital_sidetone);
+static SOC_ENUM_SINGLE_DECL(wm8400_left_digital_sidetone_enum,
+			    WM8400_DIGITAL_SIDE_TONE,
+			    WM8400_ADC_TO_DACL_SHIFT,
+			    wm8400_digital_sidetone);
 
-static const struct soc_enum wm8400_right_digital_sidetone_enum =
-SOC_ENUM_SINGLE(WM8400_DIGITAL_SIDE_TONE,
-		WM8400_ADC_TO_DACR_SHIFT, 2, wm8400_digital_sidetone);
+static SOC_ENUM_SINGLE_DECL(wm8400_right_digital_sidetone_enum,
+			    WM8400_DIGITAL_SIDE_TONE,
+			    WM8400_ADC_TO_DACR_SHIFT,
+			    wm8400_digital_sidetone);
 
 static const char *wm8400_adcmode[] =
 	{"Hi-fi mode", "Voice mode 1", "Voice mode 2", "Voice mode 3"};
 
-static const struct soc_enum wm8400_right_adcmode_enum =
-SOC_ENUM_SINGLE(WM8400_ADC_CTRL, WM8400_ADC_HPF_CUT_SHIFT, 3, wm8400_adcmode);
+static SOC_ENUM_SINGLE_DECL(wm8400_right_adcmode_enum,
+			    WM8400_ADC_CTRL,
+			    WM8400_ADC_HPF_CUT_SHIFT,
+			    wm8400_adcmode);
 
 static const struct snd_kcontrol_new wm8400_snd_controls[] = {
 /* INMIXL */
@@ -422,9 +426,10 @@
 static const char *wm8400_ainlmux[] =
 	{"INMIXL Mix", "RXVOICE Mix", "DIFFINL Mix"};
 
-static const struct soc_enum wm8400_ainlmux_enum =
-SOC_ENUM_SINGLE( WM8400_INPUT_MIXER1, WM8400_AINLMODE_SHIFT,
-	ARRAY_SIZE(wm8400_ainlmux), wm8400_ainlmux);
+static SOC_ENUM_SINGLE_DECL(wm8400_ainlmux_enum,
+			    WM8400_INPUT_MIXER1,
+			    WM8400_AINLMODE_SHIFT,
+			    wm8400_ainlmux);
 
 static const struct snd_kcontrol_new wm8400_dapm_ainlmux_controls =
 SOC_DAPM_ENUM("Route", wm8400_ainlmux_enum);
@@ -435,9 +440,10 @@
 static const char *wm8400_ainrmux[] =
 	{"INMIXR Mix", "RXVOICE Mix", "DIFFINR Mix"};
 
-static const struct soc_enum wm8400_ainrmux_enum =
-SOC_ENUM_SINGLE( WM8400_INPUT_MIXER1, WM8400_AINRMODE_SHIFT,
-	ARRAY_SIZE(wm8400_ainrmux), wm8400_ainrmux);
+static SOC_ENUM_SINGLE_DECL(wm8400_ainrmux_enum,
+			    WM8400_INPUT_MIXER1,
+			    WM8400_AINRMODE_SHIFT,
+			    wm8400_ainrmux);
 
 static const struct snd_kcontrol_new wm8400_dapm_ainrmux_controls =
 SOC_DAPM_ENUM("Route", wm8400_ainrmux_enum);
diff --git a/sound/soc/codecs/wm8770.c b/sound/soc/codecs/wm8770.c
index 89a18d8..5bce210 100644
--- a/sound/soc/codecs/wm8770.c
+++ b/sound/soc/codecs/wm8770.c
@@ -196,8 +196,8 @@
 	"AIN5", "AIN6", "AIN7", "AIN8"
 };
 
-static const struct soc_enum ain_enum =
-	SOC_ENUM_DOUBLE(WM8770_ADCMUX, 0, 4, 8, ain_text);
+static SOC_ENUM_DOUBLE_DECL(ain_enum,
+			    WM8770_ADCMUX, 0, 4, ain_text);
 
 static const struct snd_kcontrol_new ain_mux =
 	SOC_DAPM_ENUM("Capture Mux", ain_enum);
diff --git a/sound/soc/codecs/wm8900.c b/sound/soc/codecs/wm8900.c
index e98bc70..43c2201 100644
--- a/sound/soc/codecs/wm8900.c
+++ b/sound/soc/codecs/wm8900.c
@@ -304,53 +304,53 @@
 
 static const char *mic_bias_level_txt[] = { "0.9*AVDD", "0.65*AVDD" };
 
-static const struct soc_enum mic_bias_level =
-SOC_ENUM_SINGLE(WM8900_REG_INCTL, 8, 2, mic_bias_level_txt);
+static SOC_ENUM_SINGLE_DECL(mic_bias_level,
+			    WM8900_REG_INCTL, 8, mic_bias_level_txt);
 
 static const char *dac_mute_rate_txt[] = { "Fast", "Slow" };
 
-static const struct soc_enum dac_mute_rate =
-SOC_ENUM_SINGLE(WM8900_REG_DACCTRL, 7, 2, dac_mute_rate_txt);
+static SOC_ENUM_SINGLE_DECL(dac_mute_rate,
+			    WM8900_REG_DACCTRL, 7, dac_mute_rate_txt);
 
 static const char *dac_deemphasis_txt[] = {
 	"Disabled", "32kHz", "44.1kHz", "48kHz"
 };
 
-static const struct soc_enum dac_deemphasis =
-SOC_ENUM_SINGLE(WM8900_REG_DACCTRL, 4, 4, dac_deemphasis_txt);
+static SOC_ENUM_SINGLE_DECL(dac_deemphasis,
+			    WM8900_REG_DACCTRL, 4, dac_deemphasis_txt);
 
 static const char *adc_hpf_cut_txt[] = {
 	"Hi-fi mode", "Voice mode 1", "Voice mode 2", "Voice mode 3"
 };
 
-static const struct soc_enum adc_hpf_cut =
-SOC_ENUM_SINGLE(WM8900_REG_ADCCTRL, 5, 4, adc_hpf_cut_txt);
+static SOC_ENUM_SINGLE_DECL(adc_hpf_cut,
+			    WM8900_REG_ADCCTRL, 5, adc_hpf_cut_txt);
 
 static const char *lr_txt[] = {
 	"Left", "Right"
 };
 
-static const struct soc_enum aifl_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO1, 15, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(aifl_src,
+			    WM8900_REG_AUDIO1, 15, lr_txt);
 
-static const struct soc_enum aifr_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO1, 14, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(aifr_src,
+			    WM8900_REG_AUDIO1, 14, lr_txt);
 
-static const struct soc_enum dacl_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO2, 15, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(dacl_src,
+			    WM8900_REG_AUDIO2, 15, lr_txt);
 
-static const struct soc_enum dacr_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO2, 14, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(dacr_src,
+			    WM8900_REG_AUDIO2, 14, lr_txt);
 
 static const char *sidetone_txt[] = {
 	"Disabled", "Left ADC", "Right ADC"
 };
 
-static const struct soc_enum dacl_sidetone =
-SOC_ENUM_SINGLE(WM8900_REG_SIDETONE, 2, 3, sidetone_txt);
+static SOC_ENUM_SINGLE_DECL(dacl_sidetone,
+			    WM8900_REG_SIDETONE, 2, sidetone_txt);
 
-static const struct soc_enum dacr_sidetone =
-SOC_ENUM_SINGLE(WM8900_REG_SIDETONE, 0, 3, sidetone_txt);
+static SOC_ENUM_SINGLE_DECL(dacr_sidetone,
+			    WM8900_REG_SIDETONE, 0, sidetone_txt);
 
 static const struct snd_kcontrol_new wm8900_snd_controls[] = {
 SOC_ENUM("Mic Bias Level", mic_bias_level),
@@ -496,8 +496,8 @@
 
 static const char *wm8900_lp_mux[] = { "Disabled", "Enabled" };
 
-static const struct soc_enum wm8900_lineout2_lp_mux =
-SOC_ENUM_SINGLE(WM8900_REG_LOUTMIXCTL1, 1, 2, wm8900_lp_mux);
+static SOC_ENUM_SINGLE_DECL(wm8900_lineout2_lp_mux,
+			    WM8900_REG_LOUTMIXCTL1, 1, wm8900_lp_mux);
 
 static const struct snd_kcontrol_new wm8900_lineout2_lp =
 SOC_DAPM_ENUM("Route", wm8900_lineout2_lp_mux);
diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index b7488f1..d4248e0 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -153,7 +153,7 @@
 
 			data32 &= 0xffffff;
 
-			wm8994_bulk_write(codec->control_data,
+			wm8994_bulk_write(wm8994->wm8994,
 					  data32 & 0xffffff,
 					  block_len / 2,
 					  (void *)(data + 8));
diff --git a/sound/soc/codecs/wm8993.c b/sound/soc/codecs/wm8993.c
index 433d59a..2ee23a3 100644
--- a/sound/soc/codecs/wm8993.c
+++ b/sound/soc/codecs/wm8993.c
@@ -1562,7 +1562,6 @@
 	struct wm8993_priv *wm8993 = snd_soc_codec_get_drvdata(codec);
 
 	wm8993_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	regulator_bulk_free(ARRAY_SIZE(wm8993->supplies), wm8993->supplies);
 	return 0;
 }
 
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index b9be9cb..adb7206 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -265,21 +265,21 @@
 	"2.7kHz", "1.35kHz", "675Hz", "370Hz", "180Hz", "90Hz", "45Hz"
 };
 
-static const struct soc_enum sidetone_hpf =
-	SOC_ENUM_SINGLE(WM8994_SIDETONE, 7, 7, sidetone_hpf_text);
+static SOC_ENUM_SINGLE_DECL(sidetone_hpf,
+			    WM8994_SIDETONE, 7, sidetone_hpf_text);
 
 static const char *adc_hpf_text[] = {
 	"HiFi", "Voice 1", "Voice 2", "Voice 3"
 };
 
-static const struct soc_enum aif1adc1_hpf =
-	SOC_ENUM_SINGLE(WM8994_AIF1_ADC1_FILTERS, 13, 4, adc_hpf_text);
+static SOC_ENUM_SINGLE_DECL(aif1adc1_hpf,
+			    WM8994_AIF1_ADC1_FILTERS, 13, adc_hpf_text);
 
-static const struct soc_enum aif1adc2_hpf =
-	SOC_ENUM_SINGLE(WM8994_AIF1_ADC2_FILTERS, 13, 4, adc_hpf_text);
+static SOC_ENUM_SINGLE_DECL(aif1adc2_hpf,
+			    WM8994_AIF1_ADC2_FILTERS, 13, adc_hpf_text);
 
-static const struct soc_enum aif2adc_hpf =
-	SOC_ENUM_SINGLE(WM8994_AIF2_ADC_FILTERS, 13, 4, adc_hpf_text);
+static SOC_ENUM_SINGLE_DECL(aif2adc_hpf,
+			    WM8994_AIF2_ADC_FILTERS, 13, adc_hpf_text);
 
 static const DECLARE_TLV_DB_SCALE(aif_tlv, 0, 600, 0);
 static const DECLARE_TLV_DB_SCALE(digital_tlv, -7200, 75, 1);
@@ -501,39 +501,39 @@
 	"Left", "Right"
 };
 
-static const struct soc_enum aif1adcl_src =
-	SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_1, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1adcl_src,
+			    WM8994_AIF1_CONTROL_1, 15, aif_chan_src_text);
 
-static const struct soc_enum aif1adcr_src =
-	SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_1, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1adcr_src,
+			    WM8994_AIF1_CONTROL_1, 14, aif_chan_src_text);
 
-static const struct soc_enum aif2adcl_src =
-	SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_1, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2adcl_src,
+			    WM8994_AIF2_CONTROL_1, 15, aif_chan_src_text);
 
-static const struct soc_enum aif2adcr_src =
-	SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_1, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2adcr_src,
+			    WM8994_AIF2_CONTROL_1, 14, aif_chan_src_text);
 
-static const struct soc_enum aif1dacl_src =
-	SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1dacl_src,
+			    WM8994_AIF1_CONTROL_2, 15, aif_chan_src_text);
 
-static const struct soc_enum aif1dacr_src =
-	SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1dacr_src,
+			    WM8994_AIF1_CONTROL_2, 14, aif_chan_src_text);
 
-static const struct soc_enum aif2dacl_src =
-	SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacl_src,
+			    WM8994_AIF2_CONTROL_2, 15, aif_chan_src_text);
 
-static const struct soc_enum aif2dacr_src =
-	SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacr_src,
+			    WM8994_AIF2_CONTROL_2, 14, aif_chan_src_text);
 
 static const char *osr_text[] = {
 	"Low Power", "High Performance",
 };
 
-static const struct soc_enum dac_osr =
-	SOC_ENUM_SINGLE(WM8994_OVERSAMPLING, 0, 2, osr_text);
+static SOC_ENUM_SINGLE_DECL(dac_osr,
+			    WM8994_OVERSAMPLING, 0, osr_text);
 
-static const struct soc_enum adc_osr =
-	SOC_ENUM_SINGLE(WM8994_OVERSAMPLING, 1, 2, osr_text);
+static SOC_ENUM_SINGLE_DECL(adc_osr,
+			    WM8994_OVERSAMPLING, 1, osr_text);
 
 static const struct snd_kcontrol_new wm8994_snd_controls[] = {
 SOC_DOUBLE_R_TLV("AIF1ADC1 Volume", WM8994_AIF1_ADC1_LEFT_VOLUME,
@@ -690,17 +690,20 @@
 	"30ms", "125ms", "250ms", "500ms",
 };
 
-static const struct soc_enum wm8958_aif1dac1_ng_hold =
-	SOC_ENUM_SINGLE(WM8958_AIF1_DAC1_NOISE_GATE,
-			WM8958_AIF1DAC1_NG_THR_SHIFT, 4, wm8958_ng_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif1dac1_ng_hold,
+			    WM8958_AIF1_DAC1_NOISE_GATE,
+			    WM8958_AIF1DAC1_NG_THR_SHIFT,
+			    wm8958_ng_text);
 
-static const struct soc_enum wm8958_aif1dac2_ng_hold =
-	SOC_ENUM_SINGLE(WM8958_AIF1_DAC2_NOISE_GATE,
-			WM8958_AIF1DAC2_NG_THR_SHIFT, 4, wm8958_ng_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif1dac2_ng_hold,
+			    WM8958_AIF1_DAC2_NOISE_GATE,
+			    WM8958_AIF1DAC2_NG_THR_SHIFT,
+			    wm8958_ng_text);
 
-static const struct soc_enum wm8958_aif2dac_ng_hold =
-	SOC_ENUM_SINGLE(WM8958_AIF2_DAC_NOISE_GATE,
-			WM8958_AIF2DAC_NG_THR_SHIFT, 4, wm8958_ng_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif2dac_ng_hold,
+			    WM8958_AIF2_DAC_NOISE_GATE,
+			    WM8958_AIF2DAC_NG_THR_SHIFT,
+			    wm8958_ng_text);
 
 static const struct snd_kcontrol_new wm8958_snd_controls[] = {
 SOC_SINGLE_TLV("AIF3 Boost Volume", WM8958_AIF3_CONTROL_2, 10, 3, 0, aif_tlv),
@@ -1341,8 +1344,8 @@
 	"DMIC",
 };
 
-static const struct soc_enum adc_enum =
-	SOC_ENUM_SINGLE(0, 0, 2, adc_mux_text);
+static SOC_ENUM_SINGLE_DECL(adc_enum,
+			    0, 0, adc_mux_text);
 
 static const struct snd_kcontrol_new adcl_mux =
 	SOC_DAPM_ENUM_VIRT("ADCL Mux", adc_enum);
@@ -1478,14 +1481,14 @@
 	"ADC/DMIC1", "DMIC2",
 };
 
-static const struct soc_enum sidetone1_enum =
-	SOC_ENUM_SINGLE(WM8994_SIDETONE, 0, 2, sidetone_text);
+static SOC_ENUM_SINGLE_DECL(sidetone1_enum,
+			    WM8994_SIDETONE, 0, sidetone_text);
 
 static const struct snd_kcontrol_new sidetone1_mux =
 	SOC_DAPM_ENUM("Left Sidetone Mux", sidetone1_enum);
 
-static const struct soc_enum sidetone2_enum =
-	SOC_ENUM_SINGLE(WM8994_SIDETONE, 1, 2, sidetone_text);
+static SOC_ENUM_SINGLE_DECL(sidetone2_enum,
+			    WM8994_SIDETONE, 1, sidetone_text);
 
 static const struct snd_kcontrol_new sidetone2_mux =
 	SOC_DAPM_ENUM("Right Sidetone Mux", sidetone2_enum);
@@ -1498,22 +1501,24 @@
 	"None", "ADCDAT",
 };
 
-static const struct soc_enum aif1_loopback_enum =
-	SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, WM8994_AIF1_LOOPBACK_SHIFT, 2,
-			loopback_text);
+static SOC_ENUM_SINGLE_DECL(aif1_loopback_enum,
+			    WM8994_AIF1_CONTROL_2,
+			    WM8994_AIF1_LOOPBACK_SHIFT,
+			    loopback_text);
 
 static const struct snd_kcontrol_new aif1_loopback =
 	SOC_DAPM_ENUM("AIF1 Loopback", aif1_loopback_enum);
 
-static const struct soc_enum aif2_loopback_enum =
-	SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, WM8994_AIF2_LOOPBACK_SHIFT, 2,
-			loopback_text);
+static SOC_ENUM_SINGLE_DECL(aif2_loopback_enum,
+			    WM8994_AIF2_CONTROL_2,
+			    WM8994_AIF2_LOOPBACK_SHIFT,
+			    loopback_text);
 
 static const struct snd_kcontrol_new aif2_loopback =
 	SOC_DAPM_ENUM("AIF2 Loopback", aif2_loopback_enum);
 
-static const struct soc_enum aif1dac_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 0, 2, aif1dac_text);
+static SOC_ENUM_SINGLE_DECL(aif1dac_enum,
+			    WM8994_POWER_MANAGEMENT_6, 0, aif1dac_text);
 
 static const struct snd_kcontrol_new aif1dac_mux =
 	SOC_DAPM_ENUM("AIF1DAC Mux", aif1dac_enum);
@@ -1522,8 +1527,8 @@
 	"AIF2DACDAT", "AIF3DACDAT",
 };
 
-static const struct soc_enum aif2dac_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 1, 2, aif2dac_text);
+static SOC_ENUM_SINGLE_DECL(aif2dac_enum,
+			    WM8994_POWER_MANAGEMENT_6, 1, aif2dac_text);
 
 static const struct snd_kcontrol_new aif2dac_mux =
 	SOC_DAPM_ENUM("AIF2DAC Mux", aif2dac_enum);
@@ -1532,8 +1537,8 @@
 	"AIF2ADCDAT", "AIF3DACDAT",
 };
 
-static const struct soc_enum aif2adc_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 2, 2, aif2adc_text);
+static SOC_ENUM_SINGLE_DECL(aif2adc_enum,
+			    WM8994_POWER_MANAGEMENT_6, 2, aif2adc_text);
 
 static const struct snd_kcontrol_new aif2adc_mux =
 	SOC_DAPM_ENUM("AIF2ADC Mux", aif2adc_enum);
@@ -1542,14 +1547,14 @@
 	"AIF1ADCDAT", "AIF2ADCDAT", "AIF2DACDAT", "Mono PCM",
 };
 
-static const struct soc_enum wm8994_aif3adc_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 3, 3, aif3adc_text);
+static SOC_ENUM_SINGLE_DECL(wm8994_aif3adc_enum,
+			    WM8994_POWER_MANAGEMENT_6, 3, aif3adc_text);
 
 static const struct snd_kcontrol_new wm8994_aif3adc_mux =
 	SOC_DAPM_ENUM("AIF3ADC Mux", wm8994_aif3adc_enum);
 
-static const struct soc_enum wm8958_aif3adc_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 3, 4, aif3adc_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif3adc_enum,
+			    WM8994_POWER_MANAGEMENT_6, 3, aif3adc_text);
 
 static const struct snd_kcontrol_new wm8958_aif3adc_mux =
 	SOC_DAPM_ENUM("AIF3ADC Mux", wm8958_aif3adc_enum);
@@ -1558,8 +1563,8 @@
 	"None", "AIF2ADCL", "AIF2ADCR",
 };
 
-static const struct soc_enum mono_pcm_out_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 9, 3, mono_pcm_out_text);
+static SOC_ENUM_SINGLE_DECL(mono_pcm_out_enum,
+			    WM8994_POWER_MANAGEMENT_6, 9, mono_pcm_out_text);
 
 static const struct snd_kcontrol_new mono_pcm_out_mux =
 	SOC_DAPM_ENUM("Mono PCM Out Mux", mono_pcm_out_enum);
@@ -1569,14 +1574,14 @@
 };
 
 /* Note that these two control shouldn't be simultaneously switched to AIF3 */
-static const struct soc_enum aif2dacl_src_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 7, 2, aif2dac_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacl_src_enum,
+			    WM8994_POWER_MANAGEMENT_6, 7, aif2dac_src_text);
 
 static const struct snd_kcontrol_new aif2dacl_src_mux =
 	SOC_DAPM_ENUM("AIF2DACL Mux", aif2dacl_src_enum);
 
-static const struct soc_enum aif2dacr_src_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 8, 2, aif2dac_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacr_src_enum,
+			    WM8994_POWER_MANAGEMENT_6, 8, aif2dac_src_text);
 
 static const struct snd_kcontrol_new aif2dacr_src_mux =
 	SOC_DAPM_ENUM("AIF2DACR Mux", aif2dacr_src_enum);
diff --git a/sound/soc/davinci/davinci-evm.c b/sound/soc/davinci/davinci-evm.c
index 70ff377..5e3bc3c 100644
--- a/sound/soc/davinci/davinci-evm.c
+++ b/sound/soc/davinci/davinci-evm.c
@@ -399,6 +399,7 @@
 	.driver		= {
 		.name	= "davinci_evm",
 		.owner	= THIS_MODULE,
+		.pm	= &snd_soc_pm_ops,
 		.of_match_table = of_match_ptr(davinci_evm_dt_ids),
 	},
 };
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index b7858bf..670afa2 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -263,7 +263,9 @@
 					 unsigned int fmt)
 {
 	struct davinci_mcasp *mcasp = snd_soc_dai_get_drvdata(cpu_dai);
+	int ret = 0;
 
+	pm_runtime_get_sync(mcasp->dev);
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 	case SND_SOC_DAIFMT_AC97:
@@ -317,7 +319,8 @@
 		break;
 
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
@@ -354,10 +357,12 @@
 		break;
 
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
+		break;
 	}
-
-	return 0;
+out:
+	pm_runtime_put_sync(mcasp->dev);
+	return ret;
 }
 
 static int davinci_mcasp_set_clkdiv(struct snd_soc_dai *dai, int div_id, int div)
@@ -448,7 +453,7 @@
 	return 0;
 }
 
-static int davinci_hw_common_param(struct davinci_mcasp *mcasp, int stream,
+static int mcasp_common_hw_param(struct davinci_mcasp *mcasp, int stream,
 				    int channels)
 {
 	int i;
@@ -524,12 +529,18 @@
 	return 0;
 }
 
-static void davinci_hw_param(struct davinci_mcasp *mcasp, int stream)
+static int mcasp_i2s_hw_param(struct davinci_mcasp *mcasp, int stream)
 {
 	int i, active_slots;
 	u32 mask = 0;
 	u32 busel = 0;
 
+	if ((mcasp->tdm_slots < 2) || (mcasp->tdm_slots > 32)) {
+		dev_err(mcasp->dev, "tdm slot %d not supported\n",
+			mcasp->tdm_slots);
+		return -EINVAL;
+	}
+
 	active_slots = (mcasp->tdm_slots > 31) ? 32 : mcasp->tdm_slots;
 	for (i = 0; i < active_slots; i++)
 		mask |= (1 << i);
@@ -539,35 +550,21 @@
 	if (!mcasp->dat_port)
 		busel = TXSEL;
 
-	if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		/* bit stream is MSB first  with no delay */
-		/* DSP_B mode */
-		mcasp_set_reg(mcasp, DAVINCI_MCASP_TXTDM_REG, mask);
-		mcasp_set_bits(mcasp, DAVINCI_MCASP_TXFMT_REG, busel | TXORD);
+	mcasp_set_reg(mcasp, DAVINCI_MCASP_TXTDM_REG, mask);
+	mcasp_set_bits(mcasp, DAVINCI_MCASP_TXFMT_REG, busel | TXORD);
+	mcasp_mod_bits(mcasp, DAVINCI_MCASP_TXFMCTL_REG,
+		       FSXMOD(mcasp->tdm_slots), FSXMOD(0x1FF));
 
-		if ((mcasp->tdm_slots >= 2) && (mcasp->tdm_slots <= 32))
-			mcasp_mod_bits(mcasp, DAVINCI_MCASP_TXFMCTL_REG,
-				       FSXMOD(mcasp->tdm_slots), FSXMOD(0x1FF));
-		else
-			printk(KERN_ERR "playback tdm slot %d not supported\n",
-				mcasp->tdm_slots);
-	} else {
-		/* bit stream is MSB first with no delay */
-		/* DSP_B mode */
-		mcasp_set_bits(mcasp, DAVINCI_MCASP_RXFMT_REG, busel | RXORD);
-		mcasp_set_reg(mcasp, DAVINCI_MCASP_RXTDM_REG, mask);
+	mcasp_set_reg(mcasp, DAVINCI_MCASP_RXTDM_REG, mask);
+	mcasp_set_bits(mcasp, DAVINCI_MCASP_RXFMT_REG, busel | RXORD);
+	mcasp_mod_bits(mcasp, DAVINCI_MCASP_RXFMCTL_REG,
+		       FSRMOD(mcasp->tdm_slots), FSRMOD(0x1FF));
 
-		if ((mcasp->tdm_slots >= 2) && (mcasp->tdm_slots <= 32))
-			mcasp_mod_bits(mcasp, DAVINCI_MCASP_RXFMCTL_REG,
-				       FSRMOD(mcasp->tdm_slots), FSRMOD(0x1FF));
-		else
-			printk(KERN_ERR "capture tdm slot %d not supported\n",
-				mcasp->tdm_slots);
-	}
+	return 0;
 }
 
 /* S/PDIF */
-static void davinci_hw_dit_param(struct davinci_mcasp *mcasp)
+static int mcasp_dit_hw_param(struct davinci_mcasp *mcasp)
 {
 	/* Set the TX format : 24 bit right rotation, 32 bit slot, Pad 0
 	   and LSB first */
@@ -589,6 +586,8 @@
 
 	/* Enable the DIT */
 	mcasp_set_bits(mcasp, DAVINCI_MCASP_TXDITCTL_REG, DITEN);
+
+	return 0;
 }
 
 static int davinci_mcasp_hw_params(struct snd_pcm_substream *substream,
@@ -605,13 +604,14 @@
 	u8 slots = mcasp->tdm_slots;
 	u8 active_serializers;
 	int channels;
+	int ret;
 	struct snd_interval *pcm_channels = hw_param_interval(params,
 					SNDRV_PCM_HW_PARAM_CHANNELS);
 	channels = pcm_channels->min;
 
 	active_serializers = (channels + slots - 1) / slots;
 
-	if (davinci_hw_common_param(mcasp, substream->stream, channels) == -EINVAL)
+	if (mcasp_common_hw_param(mcasp, substream->stream, channels) == -EINVAL)
 		return -EINVAL;
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		fifo_level = mcasp->txnumevt * active_serializers;
@@ -619,9 +619,12 @@
 		fifo_level = mcasp->rxnumevt * active_serializers;
 
 	if (mcasp->op_mode == DAVINCI_MCASP_DIT_MODE)
-		davinci_hw_dit_param(mcasp);
+		ret = mcasp_dit_hw_param(mcasp);
 	else
-		davinci_hw_param(mcasp, substream->stream);
+		ret = mcasp_i2s_hw_param(mcasp, substream->stream);
+
+	if (ret)
+		return ret;
 
 	switch (params_format(params)) {
 	case SNDRV_PCM_FORMAT_U8:
@@ -678,19 +681,9 @@
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
-		ret = pm_runtime_get_sync(mcasp->dev);
-		if (IS_ERR_VALUE(ret))
-			dev_err(mcasp->dev, "pm_runtime_get_sync() failed\n");
 		davinci_mcasp_start(mcasp, substream->stream);
 		break;
-
 	case SNDRV_PCM_TRIGGER_SUSPEND:
-		davinci_mcasp_stop(mcasp, substream->stream);
-		ret = pm_runtime_put_sync(mcasp->dev);
-		if (IS_ERR_VALUE(ret))
-			dev_err(mcasp->dev, "pm_runtime_put_sync() failed\n");
-		break;
-
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		davinci_mcasp_stop(mcasp, substream->stream);
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index d0c72ed..c84026c 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -326,7 +326,7 @@
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMA,
 			   ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(tx_mask));
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMB,
-			   ESAI_xSMA_xS_MASK, ESAI_xSMB_xS(tx_mask));
+			   ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(tx_mask));
 
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR,
 			   ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));
@@ -334,7 +334,7 @@
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMA,
 			   ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(rx_mask));
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMB,
-			   ESAI_xSMA_xS_MASK, ESAI_xSMB_xS(rx_mask));
+			   ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask));
 
 	esai_priv->slot_width = slot_width;
 
diff --git a/sound/soc/fsl/fsl_esai.h b/sound/soc/fsl/fsl_esai.h
index 9c9f957..75e1403 100644
--- a/sound/soc/fsl/fsl_esai.h
+++ b/sound/soc/fsl/fsl_esai.h
@@ -322,7 +322,7 @@
 #define ESAI_xSMB_xS_SHIFT	0
 #define ESAI_xSMB_xS_WIDTH	16
 #define ESAI_xSMB_xS_MASK	(((1 << ESAI_xSMB_xS_WIDTH) - 1) << ESAI_xSMB_xS_SHIFT)
-#define ESAI_xSMB_xS(v)		(((v) >> ESAI_xSMA_xS_WIDTH) & ESAI_xSMA_xS_MASK)
+#define ESAI_xSMB_xS(v)		(((v) >> ESAI_xSMA_xS_WIDTH) & ESAI_xSMB_xS_MASK)
 
 /* Port C Direction Register -- REG_ESAI_PRRC 0xF8 */
 #define ESAI_PRRC_PDC_SHIFT	0
diff --git a/sound/soc/fsl/imx-mc13783.c b/sound/soc/fsl/imx-mc13783.c
index 79cee78..a2fd732 100644
--- a/sound/soc/fsl/imx-mc13783.c
+++ b/sound/soc/fsl/imx-mc13783.c
@@ -160,7 +160,6 @@
 	.driver = {
 		.name = "imx_mc13783",
 		.owner = THIS_MODULE,
-		.pm = &snd_soc_pm_ops,
 	},
 	.probe = imx_mc13783_probe,
 	.remove = imx_mc13783_remove
diff --git a/sound/soc/fsl/imx-sgtl5000.c b/sound/soc/fsl/imx-sgtl5000.c
index f2beae7..1cb22dd 100644
--- a/sound/soc/fsl/imx-sgtl5000.c
+++ b/sound/soc/fsl/imx-sgtl5000.c
@@ -33,8 +33,7 @@
 
 static int imx_sgtl5000_dai_init(struct snd_soc_pcm_runtime *rtd)
 {
-	struct imx_sgtl5000_data *data = container_of(rtd->card,
-					struct imx_sgtl5000_data, card);
+	struct imx_sgtl5000_data *data = snd_soc_card_get_drvdata(rtd->card);
 	struct device *dev = rtd->card->dev;
 	int ret;
 
@@ -159,13 +158,15 @@
 	data->card.dapm_widgets = imx_sgtl5000_dapm_widgets;
 	data->card.num_dapm_widgets = ARRAY_SIZE(imx_sgtl5000_dapm_widgets);
 
+	platform_set_drvdata(pdev, &data->card);
+	snd_soc_card_set_drvdata(&data->card, data);
+
 	ret = devm_snd_soc_register_card(&pdev->dev, &data->card);
 	if (ret) {
 		dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret);
 		goto fail;
 	}
 
-	platform_set_drvdata(pdev, data);
 	of_node_put(ssi_np);
 	of_node_put(codec_np);
 
@@ -184,7 +185,8 @@
 
 static int imx_sgtl5000_remove(struct platform_device *pdev)
 {
-	struct imx_sgtl5000_data *data = platform_get_drvdata(pdev);
+	struct snd_soc_card *card = platform_get_drvdata(pdev);
+	struct imx_sgtl5000_data *data = snd_soc_card_get_drvdata(card);
 
 	clk_put(data->codec_clk);
 
diff --git a/sound/soc/fsl/imx-wm8962.c b/sound/soc/fsl/imx-wm8962.c
index 3fd76bc..3a3d17c 100644
--- a/sound/soc/fsl/imx-wm8962.c
+++ b/sound/soc/fsl/imx-wm8962.c
@@ -71,7 +71,7 @@
 {
 	struct snd_soc_dai *codec_dai = card->rtd[0].codec_dai;
 	struct imx_priv *priv = &card_priv;
-	struct imx_wm8962_data *data = platform_get_drvdata(priv->pdev);
+	struct imx_wm8962_data *data = snd_soc_card_get_drvdata(card);
 	struct device *dev = &priv->pdev->dev;
 	unsigned int pll_out;
 	int ret;
@@ -137,7 +137,7 @@
 {
 	struct snd_soc_dai *codec_dai = card->rtd[0].codec_dai;
 	struct imx_priv *priv = &card_priv;
-	struct imx_wm8962_data *data = platform_get_drvdata(priv->pdev);
+	struct imx_wm8962_data *data = snd_soc_card_get_drvdata(card);
 	struct device *dev = &priv->pdev->dev;
 	int ret;
 
@@ -264,13 +264,15 @@
 	data->card.late_probe = imx_wm8962_late_probe;
 	data->card.set_bias_level = imx_wm8962_set_bias_level;
 
+	platform_set_drvdata(pdev, &data->card);
+	snd_soc_card_set_drvdata(&data->card, data);
+
 	ret = devm_snd_soc_register_card(&pdev->dev, &data->card);
 	if (ret) {
 		dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret);
 		goto clk_fail;
 	}
 
-	platform_set_drvdata(pdev, data);
 	of_node_put(ssi_np);
 	of_node_put(codec_np);
 
@@ -289,7 +291,8 @@
 
 static int imx_wm8962_remove(struct platform_device *pdev)
 {
-	struct imx_wm8962_data *data = platform_get_drvdata(pdev);
+	struct snd_soc_card *card = platform_get_drvdata(pdev);
+	struct imx_wm8962_data *data = snd_soc_card_get_drvdata(card);
 
 	if (!IS_ERR(data->codec_clk))
 		clk_disable_unprepare(data->codec_clk);
diff --git a/sound/soc/omap/n810.c b/sound/soc/omap/n810.c
index 3fde9e4..d163e18 100644
--- a/sound/soc/omap/n810.c
+++ b/sound/soc/omap/n810.c
@@ -305,7 +305,9 @@
 	int err;
 	struct device *dev;
 
-	if (!(machine_is_nokia_n810() || machine_is_nokia_n810_wimax()))
+	if (!of_have_populated_dt() ||
+	    (!of_machine_is_compatible("nokia,n810") &&
+	     !of_machine_is_compatible("nokia,n810-wimax")))
 		return -ENODEV;
 
 	n810_snd_device = platform_device_alloc("soc-audio", -1);
diff --git a/sound/soc/samsung/Kconfig b/sound/soc/samsung/Kconfig
index 454f41c..3507574 100644
--- a/sound/soc/samsung/Kconfig
+++ b/sound/soc/samsung/Kconfig
@@ -59,7 +59,7 @@
 	select SND_SOC_WM8750
 	select SND_S3C2412_SOC_I2S
 	help
-	  Sat Y if you want to add support for SoC audio on the Jive.
+	  Say Y if you want to add support for SoC audio on the Jive.
 
 config SND_SOC_SAMSUNG_SMDK_WM8580
 	tristate "SoC I2S Audio support for WM8580 on SMDK"
@@ -145,11 +145,11 @@
 
 config SND_SOC_SAMSUNG_SMDK_WM9713
 	tristate "SoC AC97 Audio support for SMDK with WM9713"
-	depends on SND_SOC_SAMSUNG && (MACH_SMDK6410 || MACH_SMDKC100 || MACH_SMDKV210 || MACH_SMDKC110 || MACH_SMDKV310 || MACH_SMDKC210)
+	depends on SND_SOC_SAMSUNG && (MACH_SMDK6410 || MACH_SMDKC100 || MACH_SMDKV210 || MACH_SMDKC110)
 	select SND_SOC_WM9713
 	select SND_SAMSUNG_AC97
 	help
-	  Sat Y if you want to add support for SoC audio on the SMDK.
+	  Say Y if you want to add support for SoC audio on the SMDK.
 
 config SND_SOC_SMARTQ
 	tristate "SoC I2S Audio support for SmartQ board"
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index dc8ff13..b9dc6ac 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1218,7 +1218,7 @@
 			ret = regulator_allow_bypass(w->regulator, false);
 			if (ret != 0)
 				dev_warn(w->dapm->dev,
-					 "ASoC: Failed to bypass %s: %d\n",
+					 "ASoC: Failed to unbypass %s: %d\n",
 					 w->name, ret);
 		}
 
@@ -1228,7 +1228,7 @@
 			ret = regulator_allow_bypass(w->regulator, true);
 			if (ret != 0)
 				dev_warn(w->dapm->dev,
-					 "ASoC: Failed to unbypass %s: %d\n",
+					 "ASoC: Failed to bypass %s: %d\n",
 					 w->name, ret);
 		}
 
@@ -3210,15 +3210,11 @@
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 	const char *pin = (const char *)kcontrol->private_value;
 
-	mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
 	if (ucontrol->value.integer.value[0])
 		snd_soc_dapm_enable_pin(&card->dapm, pin);
 	else
 		snd_soc_dapm_disable_pin(&card->dapm, pin);
 
-	mutex_unlock(&card->dapm_mutex);
-
 	snd_soc_dapm_sync(&card->dapm);
 	return 0;
 }
@@ -3248,7 +3244,7 @@
 			ret = regulator_allow_bypass(w->regulator, true);
 			if (ret != 0)
 				dev_warn(w->dapm->dev,
-					 "ASoC: Failed to unbypass %s: %d\n",
+					 "ASoC: Failed to bypass %s: %d\n",
 					 w->name, ret);
 		}
 		break;
@@ -3767,22 +3763,84 @@
 }
 
 /**
+ * snd_soc_dapm_enable_pin_unlocked - enable pin.
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Enables input/output pin and its parents or children widgets iff there is
+ * a valid audio route and active audio stream.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+				   const char *pin)
+{
+	return snd_soc_dapm_set_pin(dapm, pin, 1);
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin_unlocked);
+
+/**
  * snd_soc_dapm_enable_pin - enable pin.
  * @dapm: DAPM context
  * @pin: pin name
  *
  * Enables input/output pin and its parents or children widgets iff there is
  * a valid audio route and active audio stream.
+ *
  * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
  * do any widget power switching.
  */
 int snd_soc_dapm_enable_pin(struct snd_soc_dapm_context *dapm, const char *pin)
 {
-	return snd_soc_dapm_set_pin(dapm, pin, 1);
+	int ret;
+
+	mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+	ret = snd_soc_dapm_set_pin(dapm, pin, 1);
+
+	mutex_unlock(&dapm->card->dapm_mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin);
 
 /**
+ * snd_soc_dapm_force_enable_pin_unlocked - force a pin to be enabled
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Enables input/output pin regardless of any other state.  This is
+ * intended for use with microphone bias supplies used in microphone
+ * jack detection.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+					 const char *pin)
+{
+	struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true);
+
+	if (!w) {
+		dev_err(dapm->dev, "ASoC: unknown pin %s\n", pin);
+		return -EINVAL;
+	}
+
+	dev_dbg(w->dapm->dev, "ASoC: force enable pin %s\n", pin);
+	w->connected = 1;
+	w->force = 1;
+	dapm_mark_dirty(w, "force enable");
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_force_enable_pin_unlocked);
+
+/**
  * snd_soc_dapm_force_enable_pin - force a pin to be enabled
  * @dapm: DAPM context
  * @pin: pin name
@@ -3797,39 +3855,86 @@
 int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm,
 				  const char *pin)
 {
-	struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true);
+	int ret;
 
-	if (!w) {
-		dev_err(dapm->dev, "ASoC: unknown pin %s\n", pin);
-		return -EINVAL;
-	}
+	mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
 
-	dev_dbg(w->dapm->dev, "ASoC: force enable pin %s\n", pin);
-	w->connected = 1;
-	w->force = 1;
-	dapm_mark_dirty(w, "force enable");
+	ret = snd_soc_dapm_force_enable_pin_unlocked(dapm, pin);
 
-	return 0;
+	mutex_unlock(&dapm->card->dapm_mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_force_enable_pin);
 
 /**
+ * snd_soc_dapm_disable_pin_unlocked - disable pin.
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Disables input/output pin and its parents or children widgets.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_disable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+				    const char *pin)
+{
+	return snd_soc_dapm_set_pin(dapm, pin, 0);
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin_unlocked);
+
+/**
  * snd_soc_dapm_disable_pin - disable pin.
  * @dapm: DAPM context
  * @pin: pin name
  *
  * Disables input/output pin and its parents or children widgets.
+ *
  * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
  * do any widget power switching.
  */
 int snd_soc_dapm_disable_pin(struct snd_soc_dapm_context *dapm,
 			     const char *pin)
 {
-	return snd_soc_dapm_set_pin(dapm, pin, 0);
+	int ret;
+
+	mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+	ret = snd_soc_dapm_set_pin(dapm, pin, 0);
+
+	mutex_unlock(&dapm->card->dapm_mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin);
 
 /**
+ * snd_soc_dapm_nc_pin_unlocked - permanently disable pin.
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Marks the specified pin as being not connected, disabling it along
+ * any parent or child widgets.  At present this is identical to
+ * snd_soc_dapm_disable_pin() but in future it will be extended to do
+ * additional things such as disabling controls which only affect
+ * paths through the pin.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_nc_pin_unlocked(struct snd_soc_dapm_context *dapm,
+			       const char *pin)
+{
+	return snd_soc_dapm_set_pin(dapm, pin, 0);
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_nc_pin_unlocked);
+
+/**
  * snd_soc_dapm_nc_pin - permanently disable pin.
  * @dapm: DAPM context
  * @pin: pin name
@@ -3845,7 +3950,15 @@
  */
 int snd_soc_dapm_nc_pin(struct snd_soc_dapm_context *dapm, const char *pin)
 {
-	return snd_soc_dapm_set_pin(dapm, pin, 0);
+	int ret;
+
+	mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+	ret = snd_soc_dapm_set_pin(dapm, pin, 0);
+
+	mutex_unlock(&dapm->card->dapm_mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_nc_pin);
 
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 47e1ce7..28522bd 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1989,6 +1989,7 @@
 
 		paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_PLAYBACK, &list);
 		if (paths < 0) {
+			dpcm_path_put(&list);
 			dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
 					fe->dai_link->name,  "playback");
 			mutex_unlock(&card->mutex);
@@ -2018,6 +2019,7 @@
 
 		paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_CAPTURE, &list);
 		if (paths < 0) {
+			dpcm_path_put(&list);
 			dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
 					fe->dai_link->name,  "capture");
 			mutex_unlock(&card->mutex);
@@ -2082,6 +2084,7 @@
 	fe->dpcm[stream].runtime = fe_substream->runtime;
 
 	if (dpcm_path_get(fe, stream, &list) <= 0) {
+		dpcm_path_put(&list);
 		dev_dbg(fe->dev, "ASoC: %s no valid %s route\n",
 			fe->dai_link->name, stream ? "capture" : "playback");
 	}
diff --git a/sound/soc/txx9/txx9aclc-ac97.c b/sound/soc/txx9/txx9aclc-ac97.c
index e0305a1..9edd68d 100644
--- a/sound/soc/txx9/txx9aclc-ac97.c
+++ b/sound/soc/txx9/txx9aclc-ac97.c
@@ -183,14 +183,16 @@
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		return irq;
+
+	drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	drvdata->base = devm_ioremap_resource(&pdev->dev, r);
 	if (IS_ERR(drvdata->base))
 		return PTR_ERR(drvdata->base);
 
-	drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL);
-	if (!drvdata)
-		return -ENOMEM;
 	platform_set_drvdata(pdev, drvdata);
 	drvdata->physbase = r->start;
 	if (sizeof(drvdata->physbase) > sizeof(r->start) &&
diff --git a/sound/usb/Kconfig b/sound/usb/Kconfig
index de9408b..e05a86b 100644
--- a/sound/usb/Kconfig
+++ b/sound/usb/Kconfig
@@ -14,6 +14,7 @@
 	select SND_HWDEP
 	select SND_RAWMIDI
 	select SND_PCM
+	select BITREVERSE
 	help
 	  Say Y here to include support for USB audio and USB MIDI
 	  devices.
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 44b0ba4..1bed780 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -883,6 +883,7 @@
 		}
 		break;
 
+	case USB_ID(0x046d, 0x0807): /* Logitech Webcam C500 */
 	case USB_ID(0x046d, 0x0808):
 	case USB_ID(0x046d, 0x0809):
 	case USB_ID(0x046d, 0x081b): /* HD Webcam c310 */
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 32af6b7..d1d72ff 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -328,6 +328,11 @@
 	{}
 };
 
+static const struct usbmix_name_map kef_x300a_map[] = {
+	{ 10, NULL }, /* firmware locks up (?) when we try to access this FU */
+	{ 0 }
+};
+
 /*
  * Control map entries
  */
@@ -419,6 +424,10 @@
 		.id = USB_ID(0x200c, 0x1018),
 		.map = ebox44_map,
 	},
+	{
+		.id = USB_ID(0x27ac, 0x1000),
+		.map = kef_x300a_map,
+	},
 	{ 0 } /* terminator */
 };
 
diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h
new file mode 100644
index 0000000..d026c65
--- /dev/null
+++ b/tools/include/linux/hash.h
@@ -0,0 +1,5 @@
+#include "../../../include/linux/hash.h"
+
+#ifndef _TOOLS_LINUX_HASH_H
+#define _TOOLS_LINUX_HASH_H
+#endif
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index ed2f51e..ce00f7e 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -9,8 +9,10 @@
 LIB_OBJS=
 
 LIB_H += fs/debugfs.h
+LIB_H += fs/fs.h
 
 LIB_OBJS += $(OUTPUT)fs/debugfs.o
+LIB_OBJS += $(OUTPUT)fs/fs.o
 
 LIBFILE = libapikfs.a
 
diff --git a/tools/perf/util/fs.c b/tools/lib/api/fs/fs.c
similarity index 91%
rename from tools/perf/util/fs.c
rename to tools/lib/api/fs/fs.c
index f5be1f2..5b5eb78 100644
--- a/tools/perf/util/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -1,8 +1,13 @@
+/* TODO merge/factor in debugfs.c here */
 
-/* TODO merge/factor into tools/lib/lk/debugfs.c */
+#include <errno.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/vfs.h>
 
-#include "util.h"
-#include "util/fs.h"
+#include "debugfs.h"
+#include "fs.h"
 
 static const char * const sysfs__fs_known_mountpoints[] = {
 	"/sys",
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
new file mode 100644
index 0000000..cb70495
--- /dev/null
+++ b/tools/lib/api/fs/fs.h
@@ -0,0 +1,14 @@
+#ifndef __API_FS__
+#define __API_FS__
+
+#ifndef SYSFS_MAGIC
+#define SYSFS_MAGIC            0x62656572
+#endif
+
+#ifndef PROC_SUPER_MAGIC
+#define PROC_SUPER_MAGIC       0x9fa0
+#endif
+
+const char *sysfs__mountpoint(void);
+const char *procfs__mountpoint(void);
+#endif /* __API_FS__ */
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index da8b7aa..07b0b75 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -87,8 +87,8 @@
 # We process the rest of the Makefile if this is the final invocation of make
 ifeq ($(skip-makefile),)
 
-srctree		:= $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))
-objtree		:= $(CURDIR)
+srctree		:= $(realpath $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR)))
+objtree		:= $(realpath $(CURDIR))
 src		:= $(srctree)
 obj		:= $(objtree)
 
@@ -112,7 +112,7 @@
 
 LIBLOCKDEP_VERSION = $(LL_VERSION).$(LL_PATCHLEVEL).$(LL_EXTRAVERSION)
 
-INCLUDES = -I. -I/usr/local/include -I./uinclude $(CONFIG_INCLUDES)
+INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include $(CONFIG_INCLUDES)
 
 # Set compile option CFLAGS if not set elsewhere
 CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index f8465a8..23bd69c 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -418,7 +418,7 @@
 
 __attribute__((constructor)) static void init_preload(void)
 {
-	if (__init_state != done)
+	if (__init_state == done)
 		return;
 
 #ifndef __GLIBC__
diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh
old mode 100644
new mode 100755
diff --git a/tools/lib/lockdep/uinclude/asm/hash.h b/tools/lib/lockdep/uinclude/asm/hash.h
new file mode 100644
index 0000000..d82b170b
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/asm/hash.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_GENERIC_HASH_H
+#define __ASM_GENERIC_HASH_H
+
+/* Stub */
+
+#endif /* __ASM_GENERIC_HASH_H */
diff --git a/tools/lib/lockdep/uinclude/linux/rcu.h b/tools/lib/lockdep/uinclude/linux/rcu.h
index 4c99fcb..042ee8e 100644
--- a/tools/lib/lockdep/uinclude/linux/rcu.h
+++ b/tools/lib/lockdep/uinclude/linux/rcu.h
@@ -13,4 +13,9 @@
 	return 1;
 }
 
+static inline bool rcu_is_watching(void)
+{
+	return false;
+}
+
 #endif
diff --git a/tools/net/Makefile b/tools/net/Makefile
index 004cd74..ee577ea 100644
--- a/tools/net/Makefile
+++ b/tools/net/Makefile
@@ -12,7 +12,7 @@
 
 all : bpf_jit_disasm bpf_dbg bpf_asm
 
-bpf_jit_disasm : CFLAGS = -Wall -O2
+bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm'
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
 bpf_jit_disasm : bpf_jit_disasm.o
 
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 888d511..1d78a40 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -18,6 +18,10 @@
 "perf mem -t <TYPE> report" displays the result. It invokes perf report with the
 right set of options to display a memory access profile.
 
+Note that on Intel systems the memory latency reported is the use-latency,
+not the pure load (or store latency). Use latency includes any pipeline
+queueing delays in addition to the memory subsystem latency.
+
 OPTIONS
 -------
 <command>...::
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index b715cb7..1513935 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -136,6 +136,8 @@
 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
 
+On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
+
 LINE SYNTAX
 -----------
 Line range is described by following syntax.
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index f41572d..c0c87c8 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -6,6 +6,7 @@
 tools/lib/symbol/kallsyms.h
 tools/include/asm/bug.h
 tools/include/linux/compiler.h
+tools/include/linux/hash.h
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 7257e7e..50d875d 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -7,6 +7,8 @@
 
 # Define V to have a more verbose compile.
 #
+# Define VF to have a more verbose feature check output.
+#
 # Define O to save output files in a separate directory.
 #
 # Define ARCH as name of target architecture if you want cross-builds.
@@ -55,6 +57,9 @@
 # Define NO_LIBAUDIT if you do not want libaudit support
 #
 # Define NO_LIBBIONIC if you do not want bionic support
+#
+# Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support
+# for dwarf backtrace post unwind.
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
@@ -208,7 +213,7 @@
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
 LIB_H += ../../include/uapi/linux/const.h
-LIB_H += ../../include/linux/hash.h
+LIB_H += ../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
@@ -218,9 +223,7 @@
 LIB_H += util/include/linux/kernel.h
 LIB_H += util/include/linux/list.h
 LIB_H += util/include/linux/export.h
-LIB_H += util/include/linux/magic.h
 LIB_H += util/include/linux/poison.h
-LIB_H += util/include/linux/prefetch.h
 LIB_H += util/include/linux/rbtree.h
 LIB_H += util/include/linux/rbtree_augmented.h
 LIB_H += util/include/linux/string.h
@@ -244,7 +247,6 @@
 LIB_H += util/callchain.h
 LIB_H += util/build-id.h
 LIB_H += util/debug.h
-LIB_H += util/fs.h
 LIB_H += util/pmu.h
 LIB_H += util/event.h
 LIB_H += util/evsel.h
@@ -306,7 +308,6 @@
 LIB_OBJS += $(OUTPUT)util/build-id.o
 LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
-LIB_OBJS += $(OUTPUT)util/fs.o
 LIB_OBJS += $(OUTPUT)util/pmu.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
@@ -408,6 +409,11 @@
 LIB_OBJS += $(OUTPUT)tests/code-reading.o
 LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
 LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
+ifndef NO_DWARF_UNWIND
+ifeq ($(ARCH),x86)
+LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o
+endif
+endif
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -420,6 +426,9 @@
 endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
+BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
+BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
+BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
 BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
@@ -475,8 +484,13 @@
 endif # NO_DWARF
 endif # NO_LIBELF
 
+ifndef NO_LIBDW_DWARF_UNWIND
+  LIB_OBJS += $(OUTPUT)util/unwind-libdw.o
+  LIB_H += util/unwind-libdw.h
+endif
+
 ifndef NO_LIBUNWIND
-  LIB_OBJS += $(OUTPUT)util/unwind.o
+  LIB_OBJS += $(OUTPUT)util/unwind-libunwind.o
 endif
 LIB_OBJS += $(OUTPUT)tests/keep-tracking.o
 
@@ -533,6 +547,7 @@
   ifeq ($(ARCH),x86)
     LIB_H += arch/x86/include/perf_regs.h
   endif
+  LIB_OBJS += $(OUTPUT)util/perf_regs.o
 endif
 
 ifndef NO_LIBNUMA
@@ -655,6 +670,9 @@
 		-DPYTHON='"$(PYTHON_WORD)"' \
 		$<
 
+$(OUTPUT)tests/dwarf-unwind.o: tests/dwarf-unwind.c
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -fno-optimize-sibling-calls $<
+
 $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
@@ -707,9 +725,15 @@
 # we depend the various files onto their directories.
 DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(GTK_OBJS)
 DIRECTORY_DEPS += $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h
-$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS)))
+# no need to add flex objects, because they depend on bison ones
+DIRECTORY_DEPS += $(OUTPUT)util/parse-events-bison.c
+DIRECTORY_DEPS += $(OUTPUT)util/pmu-bison.c
+
+OUTPUT_DIRECTORIES := $(sort $(dir $(DIRECTORY_DEPS)))
+
+$(DIRECTORY_DEPS): | $(OUTPUT_DIRECTORIES)
 # In the second step, we make a rule to actually create these directories
-$(sort $(dir $(DIRECTORY_DEPS))):
+$(OUTPUT_DIRECTORIES):
 	$(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null
 
 $(LIB_FILE): $(LIB_OBJS)
@@ -886,7 +910,7 @@
 clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
-	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
+	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 
diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
index fe9b61e..67e9b3d 100644
--- a/tools/perf/arch/arm/Makefile
+++ b/tools/perf/arch/arm/Makefile
@@ -3,5 +3,5 @@
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 ifndef NO_LIBUNWIND
-LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
 endif
diff --git a/tools/perf/arch/arm/util/unwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
similarity index 95%
rename from tools/perf/arch/arm/util/unwind.c
rename to tools/perf/arch/arm/util/unwind-libunwind.c
index da3dc95..729ed69 100644
--- a/tools/perf/arch/arm/util/unwind.c
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -4,7 +4,7 @@
 #include "perf_regs.h"
 #include "../../util/unwind.h"
 
-int unwind__arch_reg_id(int regnum)
+int libunwind__arch_reg_id(int regnum)
 {
 	switch (regnum) {
 	case UNW_ARM_R0:
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 8801fe0..1641542 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -3,7 +3,14 @@
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 ifndef NO_LIBUNWIND
-LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+endif
+ifndef NO_LIBDW_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o
+endif
+ifndef NO_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index e84ca76..fc819ca 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -5,14 +5,20 @@
 #include "../../util/types.h"
 #include <asm/perf_regs.h>
 
+void perf_regs_load(u64 *regs);
+
 #ifndef HAVE_ARCH_X86_64_SUPPORT
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#define PERF_REGS_MAX PERF_REG_X86_32_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
 #else
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
 		       (1ULL << PERF_REG_X86_ES) | \
 		       (1ULL << PERF_REG_X86_FS) | \
 		       (1ULL << PERF_REG_X86_GS))
 #define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#define PERF_REGS_MAX PERF_REG_X86_64_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
 #endif
 #define PERF_REG_IP PERF_REG_X86_IP
 #define PERF_REG_SP PERF_REG_X86_SP
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
new file mode 100644
index 0000000..b602ad9
--- /dev/null
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -0,0 +1,59 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_X86_SP];
+
+	map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = malloc(sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
new file mode 100644
index 0000000..99167bf
--- /dev/null
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -0,0 +1,92 @@
+
+#include <linux/linkage.h>
+
+#define AX	 0
+#define BX	 1 * 8
+#define CX	 2 * 8
+#define DX	 3 * 8
+#define SI	 4 * 8
+#define DI	 5 * 8
+#define BP	 6 * 8
+#define SP	 7 * 8
+#define IP	 8 * 8
+#define FLAGS	 9 * 8
+#define CS	10 * 8
+#define SS	11 * 8
+#define DS	12 * 8
+#define ES	13 * 8
+#define FS	14 * 8
+#define GS	15 * 8
+#define R8	16 * 8
+#define R9	17 * 8
+#define R10	18 * 8
+#define R11	19 * 8
+#define R12	20 * 8
+#define R13	21 * 8
+#define R14	22 * 8
+#define R15	23 * 8
+
+.text
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+ENTRY(perf_regs_load)
+	movq %rax, AX(%rdi)
+	movq %rbx, BX(%rdi)
+	movq %rcx, CX(%rdi)
+	movq %rdx, DX(%rdi)
+	movq %rsi, SI(%rdi)
+	movq %rdi, DI(%rdi)
+	movq %rbp, BP(%rdi)
+
+	leaq 8(%rsp), %rax /* exclude this call.  */
+	movq %rax, SP(%rdi)
+
+	movq 0(%rsp), %rax
+	movq %rax, IP(%rdi)
+
+	movq $0, FLAGS(%rdi)
+	movq $0, CS(%rdi)
+	movq $0, SS(%rdi)
+	movq $0, DS(%rdi)
+	movq $0, ES(%rdi)
+	movq $0, FS(%rdi)
+	movq $0, GS(%rdi)
+
+	movq %r8,  R8(%rdi)
+	movq %r9,  R9(%rdi)
+	movq %r10, R10(%rdi)
+	movq %r11, R11(%rdi)
+	movq %r12, R12(%rdi)
+	movq %r13, R13(%rdi)
+	movq %r14, R14(%rdi)
+	movq %r15, R15(%rdi)
+	ret
+ENDPROC(perf_regs_load)
+#else
+ENTRY(perf_regs_load)
+	push %edi
+	movl 8(%esp), %edi
+	movl %eax, AX(%edi)
+	movl %ebx, BX(%edi)
+	movl %ecx, CX(%edi)
+	movl %edx, DX(%edi)
+	movl %esi, SI(%edi)
+	pop %eax
+	movl %eax, DI(%edi)
+	movl %ebp, BP(%edi)
+
+	leal 4(%esp), %eax /* exclude this call.  */
+	movl %eax, SP(%edi)
+
+	movl 0(%esp), %eax
+	movl %eax, IP(%edi)
+
+	movl $0, FLAGS(%edi)
+	movl $0, CS(%edi)
+	movl $0, SS(%edi)
+	movl $0, DS(%edi)
+	movl $0, ES(%edi)
+	movl $0, FS(%edi)
+	movl $0, GS(%edi)
+	ret
+ENDPROC(perf_regs_load)
+#endif
diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c
new file mode 100644
index 0000000..c4b7217
--- /dev/null
+++ b/tools/perf/arch/x86/util/unwind-libdw.c
@@ -0,0 +1,51 @@
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[17];
+	unsigned nregs;
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_X86_##r);	\
+	val;							\
+})
+
+	if (user_regs->abi == PERF_SAMPLE_REGS_ABI_32) {
+		dwarf_regs[0] = REG(AX);
+		dwarf_regs[1] = REG(CX);
+		dwarf_regs[2] = REG(DX);
+		dwarf_regs[3] = REG(BX);
+		dwarf_regs[4] = REG(SP);
+		dwarf_regs[5] = REG(BP);
+		dwarf_regs[6] = REG(SI);
+		dwarf_regs[7] = REG(DI);
+		dwarf_regs[8] = REG(IP);
+		nregs = 9;
+	} else {
+		dwarf_regs[0]  = REG(AX);
+		dwarf_regs[1]  = REG(DX);
+		dwarf_regs[2]  = REG(CX);
+		dwarf_regs[3]  = REG(BX);
+		dwarf_regs[4]  = REG(SI);
+		dwarf_regs[5]  = REG(DI);
+		dwarf_regs[6]  = REG(BP);
+		dwarf_regs[7]  = REG(SP);
+		dwarf_regs[8]  = REG(R8);
+		dwarf_regs[9]  = REG(R9);
+		dwarf_regs[10] = REG(R10);
+		dwarf_regs[11] = REG(R11);
+		dwarf_regs[12] = REG(R12);
+		dwarf_regs[13] = REG(R13);
+		dwarf_regs[14] = REG(R14);
+		dwarf_regs[15] = REG(R15);
+		dwarf_regs[16] = REG(IP);
+		nregs = 17;
+	}
+
+	return dwfl_thread_state_registers(thread, 0, nregs, dwarf_regs);
+}
diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
similarity index 95%
rename from tools/perf/arch/x86/util/unwind.c
rename to tools/perf/arch/x86/util/unwind-libunwind.c
index 456a88c..3261f68 100644
--- a/tools/perf/arch/x86/util/unwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -5,7 +5,7 @@
 #include "../../util/unwind.h"
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
-int unwind__arch_reg_id(int regnum)
+int libunwind__arch_reg_id(int regnum)
 {
 	int id;
 
@@ -69,7 +69,7 @@
 	return id;
 }
 #else
-int unwind__arch_reg_id(int regnum)
+int libunwind__arch_reg_id(int regnum)
 {
 	int id;
 
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 0fdc852..eba4670 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -31,6 +31,9 @@
 extern int bench_mem_memcpy(int argc, const char **argv,
 			    const char *prefix __maybe_unused);
 extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
+extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
+extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
+extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
new file mode 100644
index 0000000..a84206e
--- /dev/null
+++ b/tools/perf/bench/futex-hash.c
@@ -0,0 +1,212 @@
+/*
+ * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
+ *
+ * futex-hash: Stress the hell out of the Linux kernel futex uaddr hashing.
+ *
+ * This program is particularly useful for measuring the kernel's futex hash
+ * table/function implementation. In order for it to make sense, use with as
+ * many threads and futexes as possible.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+static unsigned int nthreads = 0;
+static unsigned int nsecs    = 10;
+/* amount of futexes per thread */
+static unsigned int nfutexes = 1024;
+static bool fshared = false, done = false, silent = false;
+
+struct timeval start, end, runtime;
+static pthread_mutex_t thread_lock;
+static unsigned int threads_starting;
+static struct stats throughput_stats;
+static pthread_cond_t thread_parent, thread_worker;
+
+struct worker {
+	int tid;
+	u_int32_t *futex;
+	pthread_t thread;
+	unsigned long ops;
+};
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('r', "runtime", &nsecs,    "Specify runtime (in seconds)"),
+	OPT_UINTEGER('f', "futexes", &nfutexes, "Specify amount of futexes per threads"),
+	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
+	OPT_END()
+};
+
+static const char * const bench_futex_hash_usage[] = {
+	"perf bench futex hash <options>",
+	NULL
+};
+
+static void *workerfn(void *arg)
+{
+	int ret;
+	unsigned int i;
+	struct worker *w = (struct worker *) arg;
+
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	do {
+		for (i = 0; i < nfutexes; i++, w->ops++) {
+			/*
+			 * We want the futex calls to fail in order to stress
+			 * the hashing of uaddr and not measure other steps,
+			 * such as internal waitqueue handling, thus enlarging
+			 * the critical region protected by hb->lock.
+			 */
+			ret = futex_wait(&w->futex[i], 1234, NULL,
+					 fshared ? 0 : FUTEX_PRIVATE_FLAG);
+			if (!silent &&
+			    (!ret || errno != EAGAIN || errno != EWOULDBLOCK))
+				warn("Non-expected futex return call");
+		}
+	}  while (!done);
+
+	return NULL;
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	/* inform all threads that we're done for the day */
+	done = true;
+	gettimeofday(&end, NULL);
+	timersub(&end, &start, &runtime);
+}
+
+static void print_summary(void)
+{
+	unsigned long avg = avg_stats(&throughput_stats);
+	double stddev = stddev_stats(&throughput_stats);
+
+	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
+	       !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
+	       (int) runtime.tv_sec);
+}
+
+int bench_futex_hash(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	cpu_set_t cpu;
+	struct sigaction act;
+	unsigned int i, ncpus;
+	pthread_attr_t thread_attr;
+	struct worker *worker = NULL;
+
+	argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
+	if (argc) {
+		usage_with_options(bench_futex_hash_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	if (!nthreads) /* default to the number of CPUs */
+		nthreads = ncpus;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		goto errmem;
+
+	printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n",
+	       getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs);
+
+	init_stats(&throughput_stats);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	threads_starting = nthreads;
+	pthread_attr_init(&thread_attr);
+	gettimeofday(&start, NULL);
+	for (i = 0; i < nthreads; i++) {
+		worker[i].tid = i;
+		worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex));
+		if (!worker[i].futex)
+			goto errmem;
+
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		ret = pthread_create(&worker[i].thread, &thread_attr, workerfn,
+				     (void *)(struct worker *) &worker[i]);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_create");
+
+	}
+	pthread_attr_destroy(&thread_attr);
+
+	pthread_mutex_lock(&thread_lock);
+	while (threads_starting)
+		pthread_cond_wait(&thread_parent, &thread_lock);
+	pthread_cond_broadcast(&thread_worker);
+	pthread_mutex_unlock(&thread_lock);
+
+	sleep(nsecs);
+	toggle_done(0, NULL, NULL);
+
+	for (i = 0; i < nthreads; i++) {
+		ret = pthread_join(worker[i].thread, NULL);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_join");
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+
+	for (i = 0; i < nthreads; i++) {
+		unsigned long t = worker[i].ops/runtime.tv_sec;
+		update_stats(&throughput_stats, t);
+		if (!silent) {
+			if (nfutexes == 1)
+				printf("[thread %2d] futex: %p [ %ld ops/sec ]\n",
+				       worker[i].tid, &worker[i].futex[0], t);
+			else
+				printf("[thread %2d] futexes: %p ... %p [ %ld ops/sec ]\n",
+				       worker[i].tid, &worker[i].futex[0],
+				       &worker[i].futex[nfutexes-1], t);
+		}
+
+		free(worker[i].futex);
+	}
+
+	print_summary();
+
+	free(worker);
+	return ret;
+errmem:
+	err(EXIT_FAILURE, "calloc");
+}
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
new file mode 100644
index 0000000..a1625587
--- /dev/null
+++ b/tools/perf/bench/futex-requeue.c
@@ -0,0 +1,211 @@
+/*
+ * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
+ *
+ * futex-requeue: Block a bunch of threads on futex1 and requeue them
+ *                on futex2, N at a time.
+ *
+ * This program is particularly useful to measure the latency of nthread
+ * requeues without waking up any tasks -- thus mimicking a regular futex_wait.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+static u_int32_t futex1 = 0, futex2 = 0;
+
+/*
+ * How many tasks to requeue at a time.
+ * Default to 1 in order to make the kernel work more.
+ */
+static unsigned int nrequeue = 1;
+
+/*
+ * There can be significant variance from run to run,
+ * the more repeats, the more exact the overall avg and
+ * the better idea of the futex latency.
+ */
+static unsigned int repeat = 10;
+
+static pthread_t *worker;
+static bool done = 0, silent = 0;
+static pthread_mutex_t thread_lock;
+static pthread_cond_t thread_parent, thread_worker;
+static struct stats requeuetime_stats, requeued_stats;
+static unsigned int ncpus, threads_starting, nthreads = 0;
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
+	OPT_UINTEGER('r', "repeat",   &repeat,   "Specify amount of times to repeat the run"),
+	OPT_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
+	OPT_END()
+};
+
+static const char * const bench_futex_requeue_usage[] = {
+	"perf bench futex requeue <options>",
+	NULL
+};
+
+static void print_summary(void)
+{
+	double requeuetime_avg = avg_stats(&requeuetime_stats);
+	double requeuetime_stddev = stddev_stats(&requeuetime_stats);
+	unsigned int requeued_avg = avg_stats(&requeued_stats);
+
+	printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n",
+	       requeued_avg,
+	       nthreads,
+	       requeuetime_avg/1e3,
+	       rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
+}
+
+static void *workerfn(void *arg __maybe_unused)
+{
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	return NULL;
+}
+
+static void block_threads(pthread_t *w,
+			  pthread_attr_t thread_attr)
+{
+	cpu_set_t cpu;
+	unsigned int i;
+
+	threads_starting = nthreads;
+
+	/* create and block all threads */
+	for (i = 0; i < nthreads; i++) {
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	done = true;
+}
+
+int bench_futex_requeue(int argc, const char **argv,
+			const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	unsigned int i, j;
+	struct sigaction act;
+	pthread_attr_t thread_attr;
+
+	argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
+	if (argc)
+		goto err;
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	if (!nthreads)
+		nthreads = ncpus;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		err(EXIT_FAILURE, "calloc");
+
+	printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), "
+	       "%d at a time.\n\n",
+	       getpid(), nthreads, &futex1, &futex2, nrequeue);
+
+	init_stats(&requeued_stats);
+	init_stats(&requeuetime_stats);
+	pthread_attr_init(&thread_attr);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	for (j = 0; j < repeat && !done; j++) {
+		unsigned int nrequeued = 0;
+		struct timeval start, end, runtime;
+
+		/* create, launch & block all threads */
+		block_threads(worker, thread_attr);
+
+		/* make sure all threads are already blocked */
+		pthread_mutex_lock(&thread_lock);
+		while (threads_starting)
+			pthread_cond_wait(&thread_parent, &thread_lock);
+		pthread_cond_broadcast(&thread_worker);
+		pthread_mutex_unlock(&thread_lock);
+
+		usleep(100000);
+
+		/* Ok, all threads are patiently blocked, start requeueing */
+		gettimeofday(&start, NULL);
+		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue)
+			/*
+			 * Do not wakeup any tasks blocked on futex1, allowing
+			 * us to really measure futex_wait functionality.
+			 */
+			futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue,
+					  FUTEX_PRIVATE_FLAG);
+		gettimeofday(&end, NULL);
+		timersub(&end, &start, &runtime);
+
+		update_stats(&requeued_stats, nrequeued);
+		update_stats(&requeuetime_stats, runtime.tv_usec);
+
+		if (!silent) {
+			printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n",
+			       j + 1, nrequeued, nthreads, runtime.tv_usec/1e3);
+		}
+
+		/* everybody should be blocked on futex2, wake'em up */
+		nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG);
+		if (nthreads != nrequeued)
+			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
+
+		for (i = 0; i < nthreads; i++) {
+			ret = pthread_join(worker[i], NULL);
+			if (ret)
+				err(EXIT_FAILURE, "pthread_join");
+		}
+
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+	pthread_attr_destroy(&thread_attr);
+
+	print_summary();
+
+	free(worker);
+	return ret;
+err:
+	usage_with_options(bench_futex_requeue_usage, options);
+	exit(EXIT_FAILURE);
+}
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
new file mode 100644
index 0000000..d096169
--- /dev/null
+++ b/tools/perf/bench/futex-wake.c
@@ -0,0 +1,201 @@
+/*
+ * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
+ *
+ * futex-wake: Block a bunch of threads on a futex and wake'em up, N at a time.
+ *
+ * This program is particularly useful to measure the latency of nthread wakeups
+ * in non-error situations:  all waiters are queued and all wake calls wakeup
+ * one or more tasks, and thus the waitqueue is never empty.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+/* all threads will block on the same futex */
+static u_int32_t futex1 = 0;
+
+/*
+ * How many wakeups to do at a time.
+ * Default to 1 in order to make the kernel work more.
+ */
+static unsigned int nwakes = 1;
+
+/*
+ * There can be significant variance from run to run,
+ * the more repeats, the more exact the overall avg and
+ * the better idea of the futex latency.
+ */
+static unsigned int repeat = 10;
+
+pthread_t *worker;
+static bool done = 0, silent = 0;
+static pthread_mutex_t thread_lock;
+static pthread_cond_t thread_parent, thread_worker;
+static struct stats waketime_stats, wakeup_stats;
+static unsigned int ncpus, threads_starting, nthreads = 0;
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('w', "nwakes",  &nwakes,   "Specify amount of threads to wake at once"),
+	OPT_UINTEGER('r', "repeat",  &repeat,   "Specify amount of times to repeat the run"),
+	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+	OPT_END()
+};
+
+static const char * const bench_futex_wake_usage[] = {
+	"perf bench futex wake <options>",
+	NULL
+};
+
+static void *workerfn(void *arg __maybe_unused)
+{
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	return NULL;
+}
+
+static void print_summary(void)
+{
+	double waketime_avg = avg_stats(&waketime_stats);
+	double waketime_stddev = stddev_stats(&waketime_stats);
+	unsigned int wakeup_avg = avg_stats(&wakeup_stats);
+
+	printf("Wokeup %d of %d threads in %.4f ms (+-%.2f%%)\n",
+	       wakeup_avg,
+	       nthreads,
+	       waketime_avg/1e3,
+	       rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+static void block_threads(pthread_t *w,
+			  pthread_attr_t thread_attr)
+{
+	cpu_set_t cpu;
+	unsigned int i;
+
+	threads_starting = nthreads;
+
+	/* create and block all threads */
+	for (i = 0; i < nthreads; i++) {
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	done = true;
+}
+
+int bench_futex_wake(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	unsigned int i, j;
+	struct sigaction act;
+	pthread_attr_t thread_attr;
+
+	argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0);
+	if (argc) {
+		usage_with_options(bench_futex_wake_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	if (!nthreads)
+		nthreads = ncpus;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		err(EXIT_FAILURE, "calloc");
+
+	printf("Run summary [PID %d]: blocking on %d threads (at futex %p), "
+	       "waking up %d at a time.\n\n",
+	       getpid(), nthreads, &futex1, nwakes);
+
+	init_stats(&wakeup_stats);
+	init_stats(&waketime_stats);
+	pthread_attr_init(&thread_attr);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	for (j = 0; j < repeat && !done; j++) {
+		unsigned int nwoken = 0;
+		struct timeval start, end, runtime;
+
+		/* create, launch & block all threads */
+		block_threads(worker, thread_attr);
+
+		/* make sure all threads are already blocked */
+		pthread_mutex_lock(&thread_lock);
+		while (threads_starting)
+			pthread_cond_wait(&thread_parent, &thread_lock);
+		pthread_cond_broadcast(&thread_worker);
+		pthread_mutex_unlock(&thread_lock);
+
+		usleep(100000);
+
+		/* Ok, all threads are patiently blocked, start waking folks up */
+		gettimeofday(&start, NULL);
+		while (nwoken != nthreads)
+			nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG);
+		gettimeofday(&end, NULL);
+		timersub(&end, &start, &runtime);
+
+		update_stats(&wakeup_stats, nwoken);
+		update_stats(&waketime_stats, runtime.tv_usec);
+
+		if (!silent) {
+			printf("[Run %d]: Wokeup %d of %d threads in %.4f ms\n",
+			       j + 1, nwoken, nthreads, runtime.tv_usec/1e3);
+		}
+
+		for (i = 0; i < nthreads; i++) {
+			ret = pthread_join(worker[i], NULL);
+			if (ret)
+				err(EXIT_FAILURE, "pthread_join");
+		}
+
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+	pthread_attr_destroy(&thread_attr);
+
+	print_summary();
+
+	free(worker);
+	return ret;
+}
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
new file mode 100644
index 0000000..71f2844
--- /dev/null
+++ b/tools/perf/bench/futex.h
@@ -0,0 +1,71 @@
+/*
+ * Glibc independent futex library for testing kernel functionality.
+ * Shamelessly stolen from Darren Hart <dvhltc@us.ibm.com>
+ *    http://git.kernel.org/cgit/linux/kernel/git/dvhart/futextest.git/
+ */
+
+#ifndef _FUTEX_H
+#define _FUTEX_H
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <linux/futex.h>
+
+/**
+ * futex() - SYS_futex syscall wrapper
+ * @uaddr:	address of first futex
+ * @op:		futex op code
+ * @val:	typically expected value of uaddr, but varies by op
+ * @timeout:	typically an absolute struct timespec (except where noted
+ *		otherwise). Overloaded by some ops
+ * @uaddr2:	address of second futex for some ops\
+ * @val3:	varies by op
+ * @opflags:	flags to be bitwise OR'd with op, such as FUTEX_PRIVATE_FLAG
+ *
+ * futex() is used by all the following futex op wrappers. It can also be
+ * used for misuse and abuse testing. Generally, the specific op wrappers
+ * should be used instead. It is a macro instead of an static inline function as
+ * some of the types over overloaded (timeout is used for nr_requeue for
+ * example).
+ *
+ * These argument descriptions are the defaults for all
+ * like-named arguments in the following wrappers except where noted below.
+ */
+#define futex(uaddr, op, val, timeout, uaddr2, val3, opflags) \
+	syscall(SYS_futex, uaddr, op | opflags, val, timeout, uaddr2, val3)
+
+/**
+ * futex_wait() - block on uaddr with optional timeout
+ * @timeout:	relative timeout
+ */
+static inline int
+futex_wait(u_int32_t *uaddr, u_int32_t val, struct timespec *timeout, int opflags)
+{
+	return futex(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags);
+}
+
+/**
+ * futex_wake() - wake one or more tasks blocked on uaddr
+ * @nr_wake:	wake up to this many tasks
+ */
+static inline int
+futex_wake(u_int32_t *uaddr, int nr_wake, int opflags)
+{
+	return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags);
+}
+
+/**
+* futex_cmp_requeue() - requeue tasks from uaddr to uaddr2
+* @nr_wake:        wake up to this many tasks
+* @nr_requeue:        requeue up to this many tasks
+*/
+static inline int
+futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wake,
+		 int nr_requeue, int opflags)
+{
+	return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2,
+		 val, opflags);
+}
+
+#endif /* _FUTEX_H */
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index d4c83c6..97d86d8 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1593,6 +1593,7 @@
 	p->data_rand_walk		= true;
 	p->nr_loops			= -1;
 	p->init_random			= true;
+	p->run_all			= argc == 1;
 }
 
 static int run_bench_numa(const char *name, const char **argv)
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index e47f90c..1e6e777 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -12,6 +12,7 @@
  *  sched ... scheduler and IPC performance
  *  mem   ... memory access performance
  *  numa  ... NUMA scheduling and MM performance
+ *  futex ... Futex performance
  */
 #include "perf.h"
 #include "util/util.h"
@@ -54,6 +55,14 @@
 	{ NULL,		NULL,						NULL			}
 };
 
+static struct bench futex_benchmarks[] = {
+	{ "hash",	"Benchmark for futex hash table",               bench_futex_hash	},
+	{ "wake",	"Benchmark for futex wake calls",               bench_futex_wake	},
+	{ "requeue",	"Benchmark for futex requeue calls",            bench_futex_requeue	},
+	{ "all",	"Test all futex benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+
 struct collection {
 	const char	*name;
 	const char	*summary;
@@ -61,11 +70,12 @@
 };
 
 static struct collection collections[] = {
-	{ "sched",	"Scheduler and IPC benchmarks",		sched_benchmarks	},
+	{ "sched",	"Scheduler and IPC benchmarks",			sched_benchmarks	},
 	{ "mem",	"Memory access benchmarks",			mem_benchmarks		},
 #ifdef HAVE_LIBNUMA_SUPPORT
 	{ "numa",	"NUMA scheduling and MM benchmarks",		numa_benchmarks		},
 #endif
+	{"futex",       "Futex stressing benchmarks",                   futex_benchmarks        },
 	{ "all",	"All benchmarks",				NULL			},
 	{ NULL,		NULL,						NULL			}
 };
@@ -76,7 +86,7 @@
 
 /* Iterate over all benchmarks within a collection: */
 #define for_each_bench(coll, bench) \
-	for (bench = coll->benchmarks; bench->name; bench++)
+	for (bench = coll->benchmarks; bench && bench->name; bench++)
 
 static void dump_benchmarks(struct collection *coll)
 {
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index cfede86..b22dbb1 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -63,11 +63,35 @@
 	return 0;
 }
 
+static bool same_kallsyms_reloc(const char *from_dir, char *to_dir)
+{
+	char from[PATH_MAX];
+	char to[PATH_MAX];
+	const char *name;
+	u64 addr1 = 0, addr2 = 0;
+	int i;
+
+	scnprintf(from, sizeof(from), "%s/kallsyms", from_dir);
+	scnprintf(to, sizeof(to), "%s/kallsyms", to_dir);
+
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr1 = kallsyms__get_function_start(from, name);
+		if (addr1)
+			break;
+	}
+
+	if (name)
+		addr2 = kallsyms__get_function_start(to, name);
+
+	return addr1 == addr2;
+}
+
 static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
 					  size_t to_dir_sz)
 {
 	char from[PATH_MAX];
 	char to[PATH_MAX];
+	char to_subdir[PATH_MAX];
 	struct dirent *dent;
 	int ret = -1;
 	DIR *d;
@@ -86,10 +110,11 @@
 			continue;
 		scnprintf(to, sizeof(to), "%s/%s/modules", to_dir,
 			  dent->d_name);
-		if (!compare_proc_modules(from, to)) {
-			scnprintf(to, sizeof(to), "%s/%s", to_dir,
-				  dent->d_name);
-			strlcpy(to_dir, to, to_dir_sz);
+		scnprintf(to_subdir, sizeof(to_subdir), "%s/%s",
+			  to_dir, dent->d_name);
+		if (!compare_proc_modules(from, to) &&
+		    same_kallsyms_reloc(from_dir, to_subdir)) {
+			strlcpy(to_dir, to_subdir, to_dir_sz);
 			ret = 0;
 			break;
 		}
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index a77e312..204fffe 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -952,8 +952,8 @@
 				 dfmt->header_width, buf);
 }
 
-static int hpp__header(struct perf_hpp_fmt *fmt,
-		       struct perf_hpp *hpp)
+static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		       struct perf_evsel *evsel __maybe_unused)
 {
 	struct diff_hpp_fmt *dfmt =
 		container_of(fmt, struct diff_hpp_fmt, fmt);
@@ -963,7 +963,8 @@
 }
 
 static int hpp__width(struct perf_hpp_fmt *fmt,
-		      struct perf_hpp *hpp __maybe_unused)
+		      struct perf_hpp *hpp __maybe_unused,
+		      struct perf_evsel *evsel __maybe_unused)
 {
 	struct diff_hpp_fmt *dfmt =
 		container_of(fmt, struct diff_hpp_fmt, fmt);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index b346601..3a73875 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -312,7 +312,6 @@
 	sample_sw.period = sample->period;
 	sample_sw.time	 = sample->time;
 	perf_event__synthesize_sample(event_sw, evsel->attr.sample_type,
-				      evsel->attr.sample_regs_user,
 				      evsel->attr.read_format, &sample_sw,
 				      false);
 	build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index a735051..21c164b 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1691,17 +1691,15 @@
 		OPT_END()
 	};
 
-
-	const char * const kvm_usage[] = {
-		"perf kvm [<options>] {top|record|report|diff|buildid-list|stat}",
-		NULL
-	};
+	const char *const kvm_subcommands[] = { "top", "record", "report", "diff",
+						"buildid-list", "stat", NULL };
+	const char *kvm_usage[] = { NULL, NULL };
 
 	perf_host  = 0;
 	perf_guest = 1;
 
-	argc = parse_options(argc, argv, kvm_options, kvm_usage,
-			PARSE_OPT_STOP_AT_NON_OPTION);
+	argc = parse_options_subcommand(argc, argv, kvm_options, kvm_subcommands, kvm_usage,
+					PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc)
 		usage_with_options(kvm_usage, kvm_options);
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 7894888..cdcd4eb 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -268,9 +268,9 @@
 	return 0;
 }
 
-static void init_params(void)
+static int init_params(void)
 {
-	line_range__init(&params.line_range);
+	return line_range__init(&params.line_range);
 }
 
 static void cleanup_params(void)
@@ -515,9 +515,11 @@
 {
 	int ret;
 
-	init_params();
-	ret = __cmd_probe(argc, argv, prefix);
-	cleanup_params();
+	ret = init_params();
+	if (!ret) {
+		ret = __cmd_probe(argc, argv, prefix);
+		cleanup_params();
+	}
 
 	return ret;
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3c394bf..eb524f9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -287,10 +287,7 @@
 	 * have no _text sometimes.
 	 */
 	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine, "_text");
-	if (err < 0)
-		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-							 machine, "_stext");
+						 machine);
 	if (err < 0)
 		pr_err("Couldn't record guest kernel [%d]'s reference"
 		       " relocation symbol.\n", machine->pid);
@@ -457,10 +454,7 @@
 	}
 
 	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine, "_text");
-	if (err < 0)
-		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-							 machine, "_stext");
+						 machine);
 	if (err < 0)
 		pr_err("Couldn't record kernel reference relocation symbol\n"
 		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
@@ -655,7 +649,7 @@
 	return ret;
 }
 
-#ifdef HAVE_LIBUNWIND_SUPPORT
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
 static int get_stack_size(char *str, unsigned long *_size)
 {
 	char *endptr;
@@ -681,7 +675,7 @@
 	       max_size, str);
 	return -1;
 }
-#endif /* HAVE_LIBUNWIND_SUPPORT */
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
 
 int record_parse_callchain(const char *arg, struct record_opts *opts)
 {
@@ -710,7 +704,7 @@
 				       "needed for -g fp\n");
 			break;
 
-#ifdef HAVE_LIBUNWIND_SUPPORT
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
 		/* Dwarf style */
 		} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
 			const unsigned long default_stack_dump_size = 8192;
@@ -726,7 +720,7 @@
 				ret = get_stack_size(tok, &size);
 				opts->stack_dump_size = size;
 			}
-#endif /* HAVE_LIBUNWIND_SUPPORT */
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
 		} else {
 			pr_err("callchain: Unknown --call-graph option "
 			       "value: %s\n", arg);
@@ -741,7 +735,9 @@
 
 static void callchain_debug(struct record_opts *opts)
 {
-	pr_debug("callchain: type %d\n", opts->call_graph);
+	static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" };
+
+	pr_debug("callchain: type %s\n", str[opts->call_graph]);
 
 	if (opts->call_graph == CALLCHAIN_DWARF)
 		pr_debug("callchain: stack dump size %d\n",
@@ -755,6 +751,8 @@
 	struct record_opts *opts = opt->value;
 	int ret;
 
+	opts->call_graph_enabled = !unset;
+
 	/* --no-call-graph */
 	if (unset) {
 		opts->call_graph = CALLCHAIN_NONE;
@@ -775,6 +773,8 @@
 {
 	struct record_opts *opts = opt->value;
 
+	opts->call_graph_enabled = !unset;
+
 	if (opts->call_graph == CALLCHAIN_NONE)
 		opts->call_graph = CALLCHAIN_FP;
 
@@ -782,6 +782,16 @@
 	return 0;
 }
 
+static int perf_record_config(const char *var, const char *value, void *cb)
+{
+	struct record *rec = cb;
+
+	if (!strcmp(var, "record.call-graph"))
+		return record_parse_callchain(value, &rec->opts);
+
+	return perf_default_config(var, value, cb);
+}
+
 static const char * const record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
@@ -813,7 +823,7 @@
 
 #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
 
-#ifdef HAVE_LIBUNWIND_SUPPORT
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
 const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf";
 #else
 const char record_callchain_help[] = CALLCHAIN_HELP "fp";
@@ -913,6 +923,8 @@
 	if (rec->evlist == NULL)
 		return -ENOMEM;
 
+	perf_config(perf_record_config, rec);
+
 	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc && target__none(&rec->opts.target))
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3c53ec2..c8f2113 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -75,13 +75,10 @@
 	return perf_default_config(var, value, cb);
 }
 
-static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_location *al,
-				      struct perf_sample *sample, struct perf_evsel *evsel,
-				      union perf_event *event)
+static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
+				      struct perf_sample *sample, struct perf_evsel *evsel)
 {
-	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct hist_entry *he;
 	struct mem_info *mi, *mx;
 	uint64_t cost;
@@ -90,7 +87,7 @@
 	if (err)
 		return err;
 
-	mi = machine__resolve_mem(al->machine, al->thread, sample, cpumode);
+	mi = sample__resolve_mem(sample, al);
 	if (!mi)
 		return -ENOMEM;
 
@@ -113,14 +110,16 @@
 	if (!he)
 		return -ENOMEM;
 
-	err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	if (err)
-		goto out;
+	if (ui__has_annotation()) {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+		if (err)
+			goto out;
 
-	mx = he->mem_info;
-	err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
-	if (err)
-		goto out;
+		mx = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
+		if (err)
+			goto out;
+	}
 
 	evsel->hists.stats.total_period += cost;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
@@ -129,10 +128,9 @@
 	return err;
 }
 
-static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al,
+static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al,
 					 struct perf_sample *sample, struct perf_evsel *evsel)
 {
-	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	unsigned i;
 	struct hist_entry *he;
@@ -142,8 +140,7 @@
 	if (err)
 		return err;
 
-	bi = machine__resolve_bstack(al->machine, al->thread,
-				     sample->branch_stack);
+	bi = sample__resolve_bstack(sample, al);
 	if (!bi)
 		return -ENOMEM;
 
@@ -164,14 +161,18 @@
 		he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
 					1, 1, 0);
 		if (he) {
-			bx = he->branch_info;
-			err = addr_map_symbol__inc_samples(&bx->from, evsel->idx);
-			if (err)
-				goto out;
+			if (ui__has_annotation()) {
+				bx = he->branch_info;
+				err = addr_map_symbol__inc_samples(&bx->from,
+								   evsel->idx);
+				if (err)
+					goto out;
 
-			err = addr_map_symbol__inc_samples(&bx->to, evsel->idx);
-			if (err)
-				goto out;
+				err = addr_map_symbol__inc_samples(&bx->to,
+								   evsel->idx);
+				if (err)
+					goto out;
+			}
 
 			evsel->hists.stats.total_period += 1;
 			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
@@ -184,10 +185,9 @@
 	return err;
 }
 
-static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evsel,
+static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
 				  struct addr_location *al, struct perf_sample *sample)
 {
-	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	struct hist_entry *he;
 	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
@@ -205,7 +205,9 @@
 	if (err)
 		goto out;
 
-	err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	if (ui__has_annotation())
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+
 	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 out:
@@ -229,25 +231,25 @@
 		return -1;
 	}
 
-	if (al.filtered || (rep->hide_unresolved && al.sym == NULL))
+	if (rep->hide_unresolved && al.sym == NULL)
 		return 0;
 
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
 	if (sort__mode == SORT_MODE__BRANCH) {
-		ret = report__add_branch_hist_entry(tool, &al, sample, evsel);
+		ret = report__add_branch_hist_entry(rep, &al, sample, evsel);
 		if (ret < 0)
 			pr_debug("problem adding lbr entry, skipping event\n");
 	} else if (rep->mem_mode == 1) {
-		ret = report__add_mem_hist_entry(tool, &al, sample, evsel, event);
+		ret = report__add_mem_hist_entry(rep, &al, sample, evsel);
 		if (ret < 0)
 			pr_debug("problem adding mem entry, skipping event\n");
 	} else {
 		if (al.map != NULL)
 			al.map->dso->hit = 1;
 
-		ret = report__add_hist_entry(tool, evsel, &al, sample);
+		ret = report__add_hist_entry(rep, evsel, &al, sample);
 		if (ret < 0)
 			pr_debug("problem incrementing symbol period, skipping event\n");
 	}
@@ -926,7 +928,7 @@
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
-	if (use_browser == 1 && sort__has_sym) {
+	if (ui__has_annotation()) {
 		symbol_conf.priv_size = sizeof(struct annotation);
 		machines__set_symbol_filter(&session->machines,
 					    symbol__annotate_init);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 6a76a07..9ac0a49 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1124,7 +1124,7 @@
 
 	avg = work_list->total_lat / work_list->nb_atoms;
 
-	printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n",
+	printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13.6f s\n",
 	      (double)work_list->total_runtime / 1e6,
 		 work_list->nb_atoms, (double)avg / 1e6,
 		 (double)work_list->max_lat / 1e6,
@@ -1527,9 +1527,9 @@
 
 	perf_sched__sort_lat(sched);
 
-	printf("\n ---------------------------------------------------------------------------------------------------------------\n");
-	printf("  Task                  |   Runtime ms  | Switches | Average delay ms | Maximum delay ms | Maximum delay at     |\n");
-	printf(" ---------------------------------------------------------------------------------------------------------------\n");
+	printf("\n -----------------------------------------------------------------------------------------------------------------\n");
+	printf("  Task                  |   Runtime ms  | Switches | Average delay ms | Maximum delay ms | Maximum delay at       |\n");
+	printf(" -----------------------------------------------------------------------------------------------------------------\n");
 
 	next = rb_first(&sched->sorted_atom_root);
 
@@ -1541,7 +1541,7 @@
 		next = rb_next(next);
 	}
 
-	printf(" -----------------------------------------------------------------------------------------\n");
+	printf(" -----------------------------------------------------------------------------------------------------------------\n");
 	printf("  TOTAL:                |%11.3f ms |%9" PRIu64 " |\n",
 		(double)sched->all_runtime / 1e6, sched->all_count);
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 25526d6..74db256 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -494,7 +494,7 @@
 			continue;
 		}
 
-		tal.filtered = false;
+		tal.filtered = 0;
 		thread__find_addr_location(al.thread, machine, cpumode,
 					   MAP__FUNCTION, ip, &tal);
 
@@ -1238,7 +1238,7 @@
 	for (i = 0; i < old_power_args_nr; i++)
 		*p++ = strdup(old_power_args[i]);
 
-	for (j = 1; j < (unsigned int)argc; j++)
+	for (j = 0; j < (unsigned int)argc; j++)
 		*p++ = argv[j];
 
 	return cmd_record(rec_argc, rec_argv, NULL);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 76cd510..65aaa5b 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -176,7 +176,7 @@
 {
 	struct annotation *notes;
 	struct symbol *sym;
-	int err;
+	int err = 0;
 
 	if (he == NULL || he->ms.sym == NULL ||
 	    ((top->sym_filter_entry == NULL ||
@@ -190,7 +190,9 @@
 		return;
 
 	ip = he->ms.map->map_ip(he->ms.map, ip);
-	err = hist_entry__inc_addr_samples(he, counter, ip);
+
+	if (ui__has_annotation())
+		err = hist_entry__inc_addr_samples(he, counter, ip);
 
 	pthread_mutex_unlock(&notes->lock);
 
@@ -991,6 +993,16 @@
 	return record_parse_callchain_opt(opt, arg, unset);
 }
 
+static int perf_top_config(const char *var, const char *value, void *cb)
+{
+	struct perf_top *top = cb;
+
+	if (!strcmp(var, "top.call-graph"))
+		return record_parse_callchain(value, &top->record_opts);
+
+	return perf_default_config(var, value, cb);
+}
+
 static int
 parse_percent_limit(const struct option *opt, const char *arg,
 		    int unset __maybe_unused)
@@ -1115,6 +1127,8 @@
 	if (top.evlist == NULL)
 		return -ENOMEM;
 
+	perf_config(perf_top_config, &top);
+
 	argc = parse_options(argc, argv, options, top_usage, 0);
 	if (argc)
 		usage_with_options(top_usage, options);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 896f270..f954c26 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -37,6 +37,10 @@
 # define MADV_UNMERGEABLE	13
 #endif
 
+#ifndef EFD_SEMAPHORE
+# define EFD_SEMAPHORE		1
+#endif
+
 struct tp_field {
 	int offset;
 	union {
@@ -279,6 +283,11 @@
 
 #define SCA_STRARRAY syscall_arg__scnprintf_strarray
 
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches as soon as the ioctl beautifier
+ * 	  gets rewritten to support all arches.
+ */
 static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
 						 struct syscall_arg *arg)
 {
@@ -286,6 +295,7 @@
 }
 
 #define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray
+#endif /* defined(__i386__) || defined(__x86_64__) */
 
 static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
 					struct syscall_arg *arg);
@@ -815,7 +825,6 @@
 	P_SIGNUM(PIPE);
 	P_SIGNUM(ALRM);
 	P_SIGNUM(TERM);
-	P_SIGNUM(STKFLT);
 	P_SIGNUM(CHLD);
 	P_SIGNUM(CONT);
 	P_SIGNUM(STOP);
@@ -831,6 +840,15 @@
 	P_SIGNUM(IO);
 	P_SIGNUM(PWR);
 	P_SIGNUM(SYS);
+#ifdef SIGEMT
+	P_SIGNUM(EMT);
+#endif
+#ifdef SIGSTKFLT
+	P_SIGNUM(STKFLT);
+#endif
+#ifdef SIGSWI
+	P_SIGNUM(SWI);
+#endif
 	default: break;
 	}
 
@@ -839,6 +857,10 @@
 
 #define SCA_SIGNUM syscall_arg__scnprintf_signum
 
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches.
+ */
 #define TCGETS		0x5401
 
 static const char *tioctls[] = {
@@ -860,6 +882,7 @@
 };
 
 static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
+#endif /* defined(__i386__) || defined(__x86_64__) */
 
 #define STRARRAY(arg, name, array) \
 	  .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
@@ -941,9 +964,16 @@
 	{ .name	    = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
 	{ .name	    = "ioctl",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ 
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches.
+ */
 			     [1] = SCA_STRHEXARRAY, /* cmd */
 			     [2] = SCA_HEX, /* arg */ },
 	  .arg_parm	 = { [1] = &strarray__tioctls, /* cmd */ }, },
+#else
+			     [2] = SCA_HEX, /* arg */ }, },
+#endif
 	{ .name	    = "kill",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "linkat",	    .errmsg = true,
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index c48d449..c234182 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -59,6 +59,18 @@
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
 
+ifndef NO_LIBELF
+  # for linking with debug library, run like:
+  # make DEBUG=1 LIBDW_DIR=/opt/libdw/
+  ifdef LIBDW_DIR
+    LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
+    LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
+
+    FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
+    FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
+  endif
+endif
+
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
 
@@ -147,7 +159,35 @@
 	libunwind			\
 	on-exit				\
 	stackprotector-all		\
-	timerfd
+	timerfd				\
+	libdw-dwarf-unwind
+
+LIB_FEATURE_TESTS =			\
+	dwarf				\
+	glibc				\
+	gtk2				\
+	libaudit			\
+	libbfd				\
+	libelf				\
+	libnuma				\
+	libperl				\
+	libpython			\
+	libslang			\
+	libunwind			\
+	libdw-dwarf-unwind
+
+VF_FEATURE_TESTS =			\
+	backtrace			\
+	fortify-source			\
+	gtk2-infobar			\
+	libelf-getphdrnum		\
+	libelf-mmap			\
+	libpython-version		\
+	on-exit				\
+	stackprotector-all		\
+	timerfd				\
+	libunwind-debug-frame		\
+	bionic
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
@@ -161,17 +201,6 @@
 $(foreach feat,$(CORE_FEATURE_TESTS),$(call set_test_all_flags,$(feat)))
 
 #
-# So here we detect whether test-all was rebuilt, to be able
-# to skip the print-out of the long features list if the file
-# existed before and after it was built:
-#
-ifeq ($(wildcard $(OUTPUT)config/feature-checks/test-all.bin),)
-  test-all-failed := 1
-else
-  test-all-failed := 0
-endif
-
-#
 # Special fast-path for the 'all features are available' case:
 #
 $(call feature_check,all,$(MSG))
@@ -180,15 +209,6 @@
 # Just in case the build freshly failed, make sure we print the
 # feature matrix:
 #
-ifeq ($(feature-all), 0)
-  test-all-failed := 1
-endif
-
-ifeq ($(test-all-failed),1)
-  $(info )
-  $(info Auto-detecting system features:)
-endif
-
 ifeq ($(feature-all), 1)
   #
   # test-all.c passed - just set all the core feature flags to 1:
@@ -199,27 +219,6 @@
   $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
 
-#
-# Print the result of the feature test:
-#
-feature_print = $(eval $(feature_print_code)) $(info $(MSG))
-
-define feature_print_code
-  ifeq ($(feature-$(1)), 1)
-    MSG = $(shell printf '...%30s: [ \033[32mon\033[m  ]' $(1))
-  else
-    MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1))
-  endif
-endef
-
-#
-# Only print out our features if we rebuilt the testcases or if a test failed:
-#
-ifeq ($(test-all-failed), 1)
-  $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_print,$(feat)))
-  $(info )
-endif
-
 ifeq ($(feature-stackprotector-all), 1)
   CFLAGS += -fstack-protector-all
 endif
@@ -264,6 +263,7 @@
   NO_DWARF := 1
   NO_DEMANGLE := 1
   NO_LIBUNWIND := 1
+  NO_LIBDW_DWARF_UNWIND := 1
 else
   ifeq ($(feature-libelf), 0)
     ifeq ($(feature-glibc), 1)
@@ -282,13 +282,12 @@
       msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
     endif
   else
-    # for linking with debug library, run like:
-    # make DEBUG=1 LIBDW_DIR=/opt/libdw/
-    ifdef LIBDW_DIR
-      LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
-      LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
+    ifndef NO_LIBDW_DWARF_UNWIND
+      ifneq ($(feature-libdw-dwarf-unwind),1)
+        NO_LIBDW_DWARF_UNWIND := 1
+        msg := $(warning No libdw DWARF unwind found, Please install elfutils-devel/libdw-dev >= 0.158 and/or set LIBDW_DIR);
+      endif
     endif
-
     ifneq ($(feature-dwarf), 1)
       msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
       NO_DWARF := 1
@@ -324,25 +323,51 @@
 
 ifndef NO_LIBUNWIND
   ifneq ($(feature-libunwind), 1)
-    msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 1.1);
+    msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR);
     NO_LIBUNWIND := 1
+  endif
+endif
+
+dwarf-post-unwind := 1
+dwarf-post-unwind-text := BUG
+
+# setup DWARF post unwinder
+ifdef NO_LIBUNWIND
+  ifdef NO_LIBDW_DWARF_UNWIND
+    msg := $(warning Disabling post unwind, no support found.);
+    dwarf-post-unwind := 0
   else
-    ifeq ($(ARCH),arm)
-      $(call feature_check,libunwind-debug-frame)
-      ifneq ($(feature-libunwind-debug-frame), 1)
-        msg := $(warning No debug_frame support found in libunwind);
-        CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
-      endif
-    else
-      # non-ARM has no dwarf_find_debug_frame() function:
+    dwarf-post-unwind-text := libdw
+  endif
+else
+  dwarf-post-unwind-text := libunwind
+  # Enable libunwind support by default.
+  ifndef NO_LIBDW_DWARF_UNWIND
+    NO_LIBDW_DWARF_UNWIND := 1
+  endif
+endif
+
+ifeq ($(dwarf-post-unwind),1)
+  CFLAGS += -DHAVE_DWARF_UNWIND_SUPPORT
+else
+  NO_DWARF_UNWIND := 1
+endif
+
+ifndef NO_LIBUNWIND
+  ifeq ($(ARCH),arm)
+    $(call feature_check,libunwind-debug-frame)
+    ifneq ($(feature-libunwind-debug-frame), 1)
+      msg := $(warning No debug_frame support found in libunwind);
       CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
     endif
-
-    CFLAGS += -DHAVE_LIBUNWIND_SUPPORT
-    EXTLIBS += $(LIBUNWIND_LIBS)
-    CFLAGS += $(LIBUNWIND_CFLAGS)
-    LDFLAGS += $(LIBUNWIND_LDFLAGS)
-  endif # ifneq ($(feature-libunwind), 1)
+  else
+    # non-ARM has no dwarf_find_debug_frame() function:
+    CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
+  endif
+  CFLAGS  += -DHAVE_LIBUNWIND_SUPPORT
+  EXTLIBS += $(LIBUNWIND_LIBS)
+  CFLAGS  += $(LIBUNWIND_CFLAGS)
+  LDFLAGS += $(LIBUNWIND_LDFLAGS)
 endif
 
 ifndef NO_LIBAUDIT
@@ -478,7 +503,7 @@
 endif
 
 ifeq ($(feature-libbfd), 1)
-  EXTLIBS += -lbfd
+  EXTLIBS += -lbfd -lz -liberty
 endif
 
 ifdef NO_DEMANGLE
@@ -602,3 +627,84 @@
 plugindir=$(libdir)/traceevent/plugins
 plugindir_SQ= $(subst ','\'',$(plugindir))
 endif
+
+#
+# Print the result of the feature test:
+#
+feature_print_status = $(eval $(feature_print_status_code)) $(info $(MSG))
+
+define feature_print_status_code
+  ifeq ($(feature-$(1)), 1)
+    MSG = $(shell printf '...%30s: [ \033[32mon\033[m  ]' $(1))
+  else
+    MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1))
+  endif
+endef
+
+feature_print_var = $(eval $(feature_print_var_code)) $(info $(MSG))
+define feature_print_var_code
+    MSG = $(shell printf '...%30s: %s' $(1) $($(1)))
+endef
+
+feature_print_text = $(eval $(feature_print_text_code)) $(info $(MSG))
+define feature_print_text_code
+    MSG = $(shell printf '...%30s: %s' $(1) $(2))
+endef
+
+PERF_FEATURES := $(foreach feat,$(LIB_FEATURE_TESTS),feature-$(feat)($(feature-$(feat))))
+PERF_FEATURES_FILE := $(shell touch $(OUTPUT)PERF-FEATURES; cat $(OUTPUT)PERF-FEATURES)
+
+ifeq ($(dwarf-post-unwind),1)
+  PERF_FEATURES += dwarf-post-unwind($(dwarf-post-unwind-text))
+endif
+
+# The $(display_lib) controls the default detection message
+# output. It's set if:
+# - detected features differes from stored features from
+#   last build (in PERF-FEATURES file)
+# - one of the $(LIB_FEATURE_TESTS) is not detected
+# - VF is enabled
+
+ifneq ("$(PERF_FEATURES)","$(PERF_FEATURES_FILE)")
+  $(shell echo "$(PERF_FEATURES)" > $(OUTPUT)PERF-FEATURES)
+  display_lib := 1
+endif
+
+feature_check = $(eval $(feature_check_code))
+define feature_check_code
+  ifneq ($(feature-$(1)), 1)
+    display_lib := 1
+  endif
+endef
+
+$(foreach feat,$(LIB_FEATURE_TESTS),$(call feature_check,$(feat)))
+
+ifeq ($(VF),1)
+  display_lib := 1
+  display_vf := 1
+endif
+
+ifeq ($(display_lib),1)
+  $(info )
+  $(info Auto-detecting system features:)
+  $(foreach feat,$(LIB_FEATURE_TESTS),$(call feature_print_status,$(feat),))
+
+  ifeq ($(dwarf-post-unwind),1)
+    $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text))
+  endif
+endif
+
+ifeq ($(display_vf),1)
+  $(foreach feat,$(VF_FEATURE_TESTS),$(call feature_print_status,$(feat),))
+  $(info )
+  $(call feature_print_var,prefix)
+  $(call feature_print_var,bindir)
+  $(call feature_print_var,libdir)
+  $(call feature_print_var,sysconfdir)
+  $(call feature_print_var,LIBUNWIND_DIR)
+  $(call feature_print_var,LIBDW_DIR)
+endif
+
+ifeq ($(display_lib),1)
+  $(info )
+endif
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 12e5513..2da103c 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -26,7 +26,8 @@
 	test-libunwind-debug-frame.bin	\
 	test-on-exit.bin		\
 	test-stackprotector-all.bin	\
-	test-timerfd.bin
+	test-timerfd.bin		\
+	test-libdw-dwarf-unwind.bin
 
 CC := $(CROSS_COMPILE)gcc -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
@@ -121,7 +122,7 @@
 	$(BUILD) $(FLAGS_PYTHON_EMBED)
 
 test-libbfd.bin:
-	$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
 
 test-liberty.bin:
 	$(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty
@@ -141,6 +142,9 @@
 test-timerfd.bin:
 	$(BUILD)
 
+test-libdw-dwarf-unwind.bin:
+	$(BUILD)
+
 -include *.d
 
 ###############################
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index 9b8a544..fc37eb3 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -89,6 +89,10 @@
 # include "test-stackprotector-all.c"
 #undef main
 
+#define main main_test_libdw_dwarf_unwind
+# include "test-libdw-dwarf-unwind.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -111,6 +115,7 @@
 	main_test_libnuma();
 	main_test_timerfd();
 	main_test_stackprotector_all();
+	main_test_libdw_dwarf_unwind();
 
 	return 0;
 }
diff --git a/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c b/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c
new file mode 100644
index 0000000..f676a3f
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c
@@ -0,0 +1,13 @@
+
+#include <elfutils/libdwfl.h>
+
+int main(void)
+{
+	/*
+	 * This function is guarded via: __nonnull_attribute__ (1, 2).
+	 * Passing '1' as arguments value. This code is never executed,
+	 * only compiled.
+	 */
+	dwfl_thread_getframes((void *) 1, (void *) 1, NULL);
+	return 0;
+}
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index 67e5d0c..a28dca2 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -18,7 +18,7 @@
 Performance counters are accessed via special file descriptors.
 There's one file descriptor per virtual counter used.
 
-The special file descriptor is opened via the perf_event_open()
+The special file descriptor is opened via the sys_perf_event_open()
 system call:
 
    int sys_perf_event_open(struct perf_event_attr *hw_event_uptr,
@@ -82,7 +82,7 @@
 If 'raw_type' is 0, then the 'type' field says what kind of counter
 this is, with the following encoding:
 
-enum perf_event_types {
+enum perf_type_id {
 	PERF_TYPE_HARDWARE		= 0,
 	PERF_TYPE_SOFTWARE		= 1,
 	PERF_TYPE_TRACEPOINT		= 2,
@@ -95,7 +95,7 @@
  * Generalized performance counter event types, used by the hw_event.event_id
  * parameter of the sys_perf_event_open() syscall:
  */
-enum hw_event_ids {
+enum perf_hw_id {
 	/*
 	 * Common hardware events, generalized by the kernel:
 	 */
@@ -129,7 +129,7 @@
  * physical and sw events of the kernel (and allow the profiling of them as
  * well):
  */
-enum sw_event_ids {
+enum perf_sw_ids {
 	PERF_COUNT_SW_CPU_CLOCK		= 0,
 	PERF_COUNT_SW_TASK_CLOCK	= 1,
 	PERF_COUNT_SW_PAGE_FAULTS	= 2,
@@ -230,7 +230,7 @@
 The 'comm' bit allows tracking of process comm data on process creation.
 This too is recorded in the ring-buffer (see below).
 
-The 'pid' parameter to the perf_event_open() system call allows the
+The 'pid' parameter to the sys_perf_event_open() system call allows the
 counter to be specific to a task:
 
  pid == 0: if the pid parameter is zero, the counter is attached to the
@@ -260,7 +260,7 @@
 
 The 'group_fd' parameter allows counter "groups" to be set up.  A
 counter group has one counter which is the group "leader".  The leader
-is created first, with group_fd = -1 in the perf_event_open call
+is created first, with group_fd = -1 in the sys_perf_event_open call
 that creates it.  The rest of the group members are created
 subsequently, with group_fd giving the fd of the group leader.
 (A single counter on its own is created with group_fd = -1 and is
@@ -454,7 +454,6 @@
 will need at least this:
 	- asm/perf_event.h - a basic stub will suffice at first
 	- support for atomic64 types (and associated helper functions)
-	- set_perf_event_pending() implemented
 
 If your architecture does have hardware capabilities, you can override the
 weak stub hw_perf_event_init() to register hardware counters.
diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh
index 496e2ab..ae3a576 100644
--- a/tools/perf/perf-completion.sh
+++ b/tools/perf/perf-completion.sh
@@ -123,7 +123,7 @@
 		__perfcomp_colon "$evts" "$cur"
 	# List subcommands for 'perf kvm'
 	elif [[ $prev == "kvm" ]]; then
-		subcmds="top record report diff buildid-list stat"
+		subcmds=$($cmd $prev --list-cmds)
 		__perfcomp_colon "$subcmds" "$cur"
 	# List long option names
 	elif [[ $cur == --* ]];  then
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 7daa806..e18a8b5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -12,6 +12,9 @@
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 336
 #endif
+#ifndef __NR_futex
+# define __NR_futex 240
+#endif
 #endif
 
 #if defined(__x86_64__)
@@ -23,6 +26,9 @@
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 298
 #endif
+#ifndef __NR_futex
+# define __NR_futex 202
+#endif
 #endif
 
 #ifdef __powerpc__
@@ -100,8 +106,8 @@
 
 #ifdef __aarch64__
 #define mb()		asm volatile("dmb ish" ::: "memory")
-#define wmb()		asm volatile("dmb ishld" ::: "memory")
-#define rmb()		asm volatile("dmb ishst" ::: "memory")
+#define wmb()		asm volatile("dmb ishst" ::: "memory")
+#define rmb()		asm volatile("dmb ishld" ::: "memory")
 #define cpu_relax()	asm volatile("yield" ::: "memory")
 #endif
 
@@ -251,12 +257,14 @@
 enum perf_call_graph_mode {
 	CALLCHAIN_NONE,
 	CALLCHAIN_FP,
-	CALLCHAIN_DWARF
+	CALLCHAIN_DWARF,
+	CALLCHAIN_MAX
 };
 
 struct record_opts {
 	struct target target;
 	int	     call_graph;
+	bool         call_graph_enabled;
 	bool	     group;
 	bool	     inherit_stat;
 	bool	     no_buffering;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 1e67437..b11bf8a 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -115,6 +115,14 @@
 		.desc = "Test parsing with no sample_id_all bit set",
 		.func = test__parse_no_sample_id_all,
 	},
+#if defined(__x86_64__) || defined(__i386__)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "Test dwarf unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+#endif
 	{
 		.func = NULL,
 	},
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
new file mode 100644
index 0000000..c059ee8
--- /dev/null
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -0,0 +1,144 @@
+#include <linux/compiler.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include "tests.h"
+#include "debug.h"
+#include "machine.h"
+#include "event.h"
+#include "unwind.h"
+#include "perf_regs.h"
+#include "map.h"
+#include "thread.h"
+
+static int mmap_handler(struct perf_tool *tool __maybe_unused,
+			union perf_event *event,
+			struct perf_sample *sample __maybe_unused,
+			struct machine *machine)
+{
+	return machine__process_mmap_event(machine, event, NULL);
+}
+
+static int init_live_machine(struct machine *machine)
+{
+	union perf_event event;
+	pid_t pid = getpid();
+
+	return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
+						  mmap_handler, machine, true);
+}
+
+#define MAX_STACK 6
+
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+	unsigned long *cnt = (unsigned long *) arg;
+	char *symbol = entry->sym ? entry->sym->name : NULL;
+	static const char *funcs[MAX_STACK] = {
+		"test__arch_unwind_sample",
+		"unwind_thread",
+		"krava_3",
+		"krava_2",
+		"krava_1",
+		"test__dwarf_unwind"
+	};
+
+	if (*cnt >= MAX_STACK) {
+		pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
+		return -1;
+	}
+
+	if (!symbol) {
+		pr_debug("failed: got unresolved address 0x%" PRIx64 "\n",
+			 entry->ip);
+		return -1;
+	}
+
+	pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip);
+	return strcmp((const char *) symbol, funcs[(*cnt)++]);
+}
+
+__attribute__ ((noinline))
+static int unwind_thread(struct thread *thread, struct machine *machine)
+{
+	struct perf_sample sample;
+	unsigned long cnt = 0;
+	int err = -1;
+
+	memset(&sample, 0, sizeof(sample));
+
+	if (test__arch_unwind_sample(&sample, thread)) {
+		pr_debug("failed to get unwind sample\n");
+		goto out;
+	}
+
+	err = unwind__get_entries(unwind_entry, &cnt, machine, thread,
+				  &sample, MAX_STACK);
+	if (err)
+		pr_debug("unwind failed\n");
+	else if (cnt != MAX_STACK) {
+		pr_debug("got wrong number of stack entries %lu != %d\n",
+			 cnt, MAX_STACK);
+		err = -1;
+	}
+
+ out:
+	free(sample.user_stack.data);
+	free(sample.user_regs.regs);
+	return err;
+}
+
+__attribute__ ((noinline))
+static int krava_3(struct thread *thread, struct machine *machine)
+{
+	return unwind_thread(thread, machine);
+}
+
+__attribute__ ((noinline))
+static int krava_2(struct thread *thread, struct machine *machine)
+{
+	return krava_3(thread, machine);
+}
+
+__attribute__ ((noinline))
+static int krava_1(struct thread *thread, struct machine *machine)
+{
+	return krava_2(thread, machine);
+}
+
+int test__dwarf_unwind(void)
+{
+	struct machines machines;
+	struct machine *machine;
+	struct thread *thread;
+	int err = -1;
+
+	machines__init(&machines);
+
+	machine = machines__find(&machines, HOST_KERNEL_ID);
+	if (!machine) {
+		pr_err("Could not get machine\n");
+		return -1;
+	}
+
+	if (init_live_machine(machine)) {
+		pr_err("Could not init machine\n");
+		goto out;
+	}
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	thread = machine__find_thread(machine, getpid(), getpid());
+	if (!thread) {
+		pr_err("Could not get thread\n");
+		goto out;
+	}
+
+	err = krava_1(thread, machine);
+
+ out:
+	machine__delete_threads(machine);
+	machine__exit(machine);
+	machines__exit(&machines);
+	return err;
+}
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 2b6519e..7ccbc7b 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -101,6 +101,7 @@
 			.mmap = {
 				.header = { .misc = PERF_RECORD_MISC_USER, },
 				.pid = fake_mmap_info[i].pid,
+				.tid = fake_mmap_info[i].pid,
 				.start = fake_mmap_info[i].start,
 				.len = 0x1000ULL,
 				.pgoff = 0ULL,
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 00544b8..5daeae1 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -27,6 +27,7 @@
 make_no_demangle    := NO_DEMANGLE=1
 make_no_libelf      := NO_LIBELF=1
 make_no_libunwind   := NO_LIBUNWIND=1
+make_no_libdw_dwarf_unwind := NO_LIBDW_DWARF_UNWIND=1
 make_no_backtrace   := NO_BACKTRACE=1
 make_no_libnuma     := NO_LIBNUMA=1
 make_no_libaudit    := NO_LIBAUDIT=1
@@ -35,8 +36,9 @@
 make_cscope         := cscope
 make_help           := help
 make_doc            := doc
-make_perf_o         := perf.o
-make_util_map_o     := util/map.o
+make_perf_o           := perf.o
+make_util_map_o       := util/map.o
+make_util_pmu_bison_o := util/pmu-bison.o
 make_install        := install
 make_install_bin    := install-bin
 make_install_doc    := install-doc
@@ -49,6 +51,7 @@
 make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
 make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
+make_minimal        += NO_LIBDW_DWARF_UNWIND=1
 
 # $(run) contains all available tests
 run := make_pure
@@ -65,6 +68,7 @@
 run += make_no_demangle
 run += make_no_libelf
 run += make_no_libunwind
+run += make_no_libdw_dwarf_unwind
 run += make_no_backtrace
 run += make_no_libnuma
 run += make_no_libaudit
@@ -73,6 +77,7 @@
 run += make_doc
 run += make_perf_o
 run += make_util_map_o
+run += make_util_pmu_bison_o
 run += make_install
 run += make_install_bin
 # FIXME 'install-*' commented out till they're fixed
@@ -113,8 +118,9 @@
 
 test_make_python_perf_so := test -f $(PERF)/python/perf.so
 
-test_make_perf_o     := test -f $(PERF)/perf.o
-test_make_util_map_o := test -f $(PERF)/util/map.o
+test_make_perf_o           := test -f $(PERF)/perf.o
+test_make_util_map_o       := test -f $(PERF)/util/map.o
+test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o
 
 define test_dest_files
   for file in $(1); do				\
@@ -167,13 +173,10 @@
 test_make_install_pdf    := $(test_ok)
 test_make_install_pdf_O  := $(test_ok)
 
-# Kbuild tests only
-#test_make_python_perf_so_O := test -f $$TMP/tools/perf/python/perf.so
-#test_make_perf_o_O         := test -f $$TMP/tools/perf/perf.o
-#test_make_util_map_o_O     := test -f $$TMP/tools/perf/util/map.o
-
-test_make_perf_o_O     := true
-test_make_util_map_o_O := true
+test_make_python_perf_so_O    := test -f $$TMP_O/python/perf.so
+test_make_perf_o_O            := test -f $$TMP_O/perf.o
+test_make_util_map_o_O        := test -f $$TMP_O/util/map.o
+test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o
 
 test_default = test -x $(PERF)/perf
 test = $(if $(test_$1),$(test_$1),$(test_default))
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 4db0ae6..8605ff5 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -2,7 +2,7 @@
 #include "parse-events.h"
 #include "evsel.h"
 #include "evlist.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include <api/fs/debugfs.h>
 #include "tests.h"
 #include <linux/hw_breakpoint.h>
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 1b67720..0014d3c 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -22,8 +22,8 @@
 } while (0)
 
 static bool samples_same(const struct perf_sample *s1,
-			 const struct perf_sample *s2, u64 type, u64 regs_user,
-			 u64 read_format)
+			 const struct perf_sample *s2,
+			 u64 type, u64 read_format)
 {
 	size_t i;
 
@@ -95,8 +95,9 @@
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
-		size_t sz = hweight_long(regs_user) * sizeof(u64);
+		size_t sz = hweight_long(s1->user_regs.mask) * sizeof(u64);
 
+		COMP(user_regs.mask);
 		COMP(user_regs.abi);
 		if (s1->user_regs.abi &&
 		    (!s1->user_regs.regs || !s2->user_regs.regs ||
@@ -174,6 +175,7 @@
 		.branch_stack	= &branch_stack.branch_stack,
 		.user_regs	= {
 			.abi	= PERF_SAMPLE_REGS_ABI_64,
+			.mask	= sample_regs_user,
 			.regs	= user_regs,
 		},
 		.user_stack	= {
@@ -201,8 +203,7 @@
 		sample.read.one.id    = 99;
 	}
 
-	sz = perf_event__sample_event_size(&sample, sample_type,
-					   sample_regs_user, read_format);
+	sz = perf_event__sample_event_size(&sample, sample_type, read_format);
 	bufsz = sz + 4096; /* Add a bit for overrun checking */
 	event = malloc(bufsz);
 	if (!event) {
@@ -215,8 +216,7 @@
 	event->header.misc = 0;
 	event->header.size = sz;
 
-	err = perf_event__synthesize_sample(event, sample_type,
-					    sample_regs_user, read_format,
+	err = perf_event__synthesize_sample(event, sample_type, read_format,
 					    &sample, false);
 	if (err) {
 		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
@@ -244,8 +244,7 @@
 		goto out_free;
 	}
 
-	if (!samples_same(&sample, &sample_out, sample_type,
-			  sample_regs_user, read_format)) {
+	if (!samples_same(&sample, &sample_out, sample_type, read_format)) {
 		pr_debug("parsing failed for sample_type %#"PRIx64"\n",
 			 sample_type);
 		goto out_free;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index e0ac713..a24795c 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -40,5 +40,14 @@
 int test__sample_parsing(void);
 int test__keep_tracking(void);
 int test__parse_no_sample_id_all(void);
+int test__dwarf_unwind(void);
 
+#if defined(__x86_64__) || defined(__i386__)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread);
+#endif
+#endif
 #endif /* TESTS_H */
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 2bd13ed..3d90880 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -26,7 +26,6 @@
 	struct map *kallsyms_map, *vmlinux_map;
 	struct machine kallsyms, vmlinux;
 	enum map_type type = MAP__FUNCTION;
-	struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", };
 	u64 mem_start, mem_end;
 
 	/*
@@ -70,14 +69,6 @@
 	 */
 	kallsyms_map = machine__kernel_map(&kallsyms, type);
 
-	sym = map__find_symbol_by_name(kallsyms_map, ref_reloc_sym.name, NULL);
-	if (sym == NULL) {
-		pr_debug("dso__find_symbol_by_name ");
-		goto out;
-	}
-
-	ref_reloc_sym.addr = UM(sym->start);
-
 	/*
 	 * Step 5:
 	 *
@@ -89,7 +80,6 @@
 	}
 
 	vmlinux_map = machine__kernel_map(&vmlinux, type);
-	map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym;
 
 	/*
 	 * Step 6:
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index b720b92..7ec871a 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -587,95 +587,52 @@
 	bool current_entry;
 };
 
-static int __hpp__color_callchain(struct hpp_arg *arg)
+static int __hpp__overhead_callback(struct perf_hpp *hpp, bool front)
 {
-	if (!symbol_conf.use_callchain)
-		return 0;
-
-	slsmg_printf("%c ", arg->folded_sign);
-	return 2;
-}
-
-static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he,
-			    u64 (*get_field)(struct hist_entry *),
-			    int (*callchain_cb)(struct hpp_arg *))
-{
-	int ret = 0;
-	double percent = 0.0;
-	struct hists *hists = he->hists;
 	struct hpp_arg *arg = hpp->ptr;
 
-	if (hists->stats.total_period)
-		percent = 100.0 * get_field(he) / hists->stats.total_period;
+	if (arg->current_entry && arg->b->navkeypressed)
+		ui_browser__set_color(arg->b, HE_COLORSET_SELECTED);
+	else
+		ui_browser__set_color(arg->b, HE_COLORSET_NORMAL);
+
+	if (front) {
+		if (!symbol_conf.use_callchain)
+			return 0;
+
+		slsmg_printf("%c ", arg->folded_sign);
+		return 2;
+	}
+
+	return 0;
+}
+
+static int __hpp__color_callback(struct perf_hpp *hpp, bool front __maybe_unused)
+{
+	struct hpp_arg *arg = hpp->ptr;
+
+	if (!arg->current_entry || !arg->b->navkeypressed)
+		ui_browser__set_color(arg->b, HE_COLORSET_NORMAL);
+	return 0;
+}
+
+static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
+{
+	struct hpp_arg *arg = hpp->ptr;
+	int ret;
+	va_list args;
+	double percent;
+
+	va_start(args, fmt);
+	percent = va_arg(args, double);
+	va_end(args);
 
 	ui_browser__set_percent_color(arg->b, percent, arg->current_entry);
 
-	if (callchain_cb)
-		ret += callchain_cb(arg);
-
-	ret += scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent);
+	ret = scnprintf(hpp->buf, hpp->size, fmt, percent);
 	slsmg_printf("%s", hpp->buf);
 
-	if (symbol_conf.event_group) {
-		int prev_idx, idx_delta;
-		struct perf_evsel *evsel = hists_to_evsel(hists);
-		struct hist_entry *pair;
-		int nr_members = evsel->nr_members;
-
-		if (nr_members <= 1)
-			goto out;
-
-		prev_idx = perf_evsel__group_idx(evsel);
-
-		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
-			u64 period = get_field(pair);
-			u64 total = pair->hists->stats.total_period;
-
-			if (!total)
-				continue;
-
-			evsel = hists_to_evsel(pair->hists);
-			idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1;
-
-			while (idx_delta--) {
-				/*
-				 * zero-fill group members in the middle which
-				 * have no sample
-				 */
-				ui_browser__set_percent_color(arg->b, 0.0,
-							arg->current_entry);
-				ret += scnprintf(hpp->buf, hpp->size,
-						 " %6.2f%%", 0.0);
-				slsmg_printf("%s", hpp->buf);
-			}
-
-			percent = 100.0 * period / total;
-			ui_browser__set_percent_color(arg->b, percent,
-						      arg->current_entry);
-			ret += scnprintf(hpp->buf, hpp->size,
-					 " %6.2f%%", percent);
-			slsmg_printf("%s", hpp->buf);
-
-			prev_idx = perf_evsel__group_idx(evsel);
-		}
-
-		idx_delta = nr_members - prev_idx - 1;
-
-		while (idx_delta--) {
-			/*
-			 * zero-fill group members at last which have no sample
-			 */
-			ui_browser__set_percent_color(arg->b, 0.0,
-						      arg->current_entry);
-			ret += scnprintf(hpp->buf, hpp->size,
-					 " %6.2f%%", 0.0);
-			slsmg_printf("%s", hpp->buf);
-		}
-	}
-out:
-	if (!arg->current_entry || !arg->b->navkeypressed)
-		ui_browser__set_color(arg->b, HE_COLORSET_NORMAL);
-
+	advance_hpp(hpp, ret);
 	return ret;
 }
 
@@ -690,14 +647,15 @@
 				struct perf_hpp *hpp,			\
 				struct hist_entry *he)			\
 {									\
-	return __hpp__color_fmt(hpp, he, __hpp_get_##_field, _cb);	\
+	return __hpp__fmt(hpp, he, __hpp_get_##_field, _cb, " %6.2f%%",	\
+			  __hpp__slsmg_color_printf, true);		\
 }
 
-__HPP_COLOR_PERCENT_FN(overhead, period, __hpp__color_callchain)
-__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, NULL)
-__HPP_COLOR_PERCENT_FN(overhead_us, period_us, NULL)
-__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, NULL)
-__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, NULL)
+__HPP_COLOR_PERCENT_FN(overhead, period, __hpp__overhead_callback)
+__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, __hpp__color_callback)
+__HPP_COLOR_PERCENT_FN(overhead_us, period_us, __hpp__color_callback)
+__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, __hpp__color_callback)
+__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, __hpp__color_callback)
 
 #undef __HPP_COLOR_PERCENT_FN
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 5b95c44..e395ef9 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -8,16 +8,24 @@
 
 #define MAX_COLUMNS			32
 
-static int __percent_color_snprintf(char *buf, size_t size, double percent)
+static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	int ret = 0;
+	va_list args;
+	double percent;
 	const char *markup;
+	char *buf = hpp->buf;
+	size_t size = hpp->size;
+
+	va_start(args, fmt);
+	percent = va_arg(args, double);
+	va_end(args);
 
 	markup = perf_gtk__get_percent_color(percent);
 	if (markup)
 		ret += scnprintf(buf, size, markup);
 
-	ret += scnprintf(buf + ret, size - ret, " %6.2f%%", percent);
+	ret += scnprintf(buf + ret, size - ret, fmt, percent);
 
 	if (markup)
 		ret += scnprintf(buf + ret, size - ret, "</span>");
@@ -25,66 +33,6 @@
 	return ret;
 }
 
-
-static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he,
-			    u64 (*get_field)(struct hist_entry *))
-{
-	int ret;
-	double percent = 0.0;
-	struct hists *hists = he->hists;
-	struct perf_evsel *evsel = hists_to_evsel(hists);
-
-	if (hists->stats.total_period)
-		percent = 100.0 * get_field(he) / hists->stats.total_period;
-
-	ret = __percent_color_snprintf(hpp->buf, hpp->size, percent);
-
-	if (perf_evsel__is_group_event(evsel)) {
-		int prev_idx, idx_delta;
-		struct hist_entry *pair;
-		int nr_members = evsel->nr_members;
-
-		prev_idx = perf_evsel__group_idx(evsel);
-
-		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
-			u64 period = get_field(pair);
-			u64 total = pair->hists->stats.total_period;
-
-			evsel = hists_to_evsel(pair->hists);
-			idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1;
-
-			while (idx_delta--) {
-				/*
-				 * zero-fill group members in the middle which
-				 * have no sample
-				 */
-				ret += __percent_color_snprintf(hpp->buf + ret,
-								hpp->size - ret,
-								0.0);
-			}
-
-			percent = 100.0 * period / total;
-			ret += __percent_color_snprintf(hpp->buf + ret,
-							hpp->size - ret,
-							percent);
-
-			prev_idx = perf_evsel__group_idx(evsel);
-		}
-
-		idx_delta = nr_members - prev_idx - 1;
-
-		while (idx_delta--) {
-			/*
-			 * zero-fill group members at last which have no sample
-			 */
-			ret += __percent_color_snprintf(hpp->buf + ret,
-							hpp->size - ret,
-							0.0);
-		}
-	}
-	return ret;
-}
-
 #define __HPP_COLOR_PERCENT_FN(_type, _field)					\
 static u64 he_get_##_field(struct hist_entry *he)				\
 {										\
@@ -95,7 +43,8 @@
 				       struct perf_hpp *hpp,			\
 				       struct hist_entry *he)			\
 {										\
-	return __hpp__color_fmt(hpp, he, he_get_##_field);			\
+	return __hpp__fmt(hpp, he, he_get_##_field, NULL, " %6.2f%%",		\
+			  __percent_color_snprintf, true);			\
 }
 
 __HPP_COLOR_PERCENT_FN(overhead, period)
@@ -216,7 +165,6 @@
 	struct perf_hpp hpp = {
 		.buf		= s,
 		.size		= sizeof(s),
-		.ptr		= hists_to_evsel(hists),
 	};
 
 	nr_cols = 0;
@@ -243,7 +191,7 @@
 	col_idx = 0;
 
 	perf_hpp__for_each_format(fmt) {
-		fmt->header(fmt, &hpp);
+		fmt->header(fmt, &hpp, hists_to_evsel(hists));
 
 		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
 							    -1, ltrim(s),
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 78f4c92..0f403b8 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -8,16 +8,27 @@
 
 /* hist period print (hpp) functions */
 
-typedef int (*hpp_snprint_fn)(char *buf, size_t size, const char *fmt, ...);
+#define hpp__call_print_fn(hpp, fn, fmt, ...)			\
+({								\
+	int __ret = fn(hpp, fmt, ##__VA_ARGS__);		\
+	advance_hpp(hpp, __ret);				\
+	__ret;							\
+})
 
-static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
-		      u64 (*get_field)(struct hist_entry *),
-		      const char *fmt, hpp_snprint_fn print_fn,
-		      bool fmt_percent)
+int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+	       hpp_field_fn get_field, hpp_callback_fn callback,
+	       const char *fmt, hpp_snprint_fn print_fn, bool fmt_percent)
 {
-	int ret;
+	int ret = 0;
 	struct hists *hists = he->hists;
 	struct perf_evsel *evsel = hists_to_evsel(hists);
+	char *buf = hpp->buf;
+	size_t size = hpp->size;
+
+	if (callback) {
+		ret = callback(hpp, true);
+		advance_hpp(hpp, ret);
+	}
 
 	if (fmt_percent) {
 		double percent = 0.0;
@@ -26,9 +37,9 @@
 			percent = 100.0 * get_field(he) /
 				  hists->stats.total_period;
 
-		ret = print_fn(hpp->buf, hpp->size, fmt, percent);
+		ret += hpp__call_print_fn(hpp, print_fn, fmt, percent);
 	} else
-		ret = print_fn(hpp->buf, hpp->size, fmt, get_field(he));
+		ret += hpp__call_print_fn(hpp, print_fn, fmt, get_field(he));
 
 	if (perf_evsel__is_group_event(evsel)) {
 		int prev_idx, idx_delta;
@@ -52,16 +63,22 @@
 				 * zero-fill group members in the middle which
 				 * have no sample
 				 */
-				ret += print_fn(hpp->buf + ret, hpp->size - ret,
-						fmt, 0);
+				if (fmt_percent) {
+					ret += hpp__call_print_fn(hpp, print_fn,
+								  fmt, 0.0);
+				} else {
+					ret += hpp__call_print_fn(hpp, print_fn,
+								  fmt, 0ULL);
+				}
 			}
 
-			if (fmt_percent)
-				ret += print_fn(hpp->buf + ret, hpp->size - ret,
-						fmt, 100.0 * period / total);
-			else
-				ret += print_fn(hpp->buf + ret, hpp->size - ret,
-						fmt, period);
+			if (fmt_percent) {
+				ret += hpp__call_print_fn(hpp, print_fn, fmt,
+							  100.0 * period / total);
+			} else {
+				ret += hpp__call_print_fn(hpp, print_fn, fmt,
+							  period);
+			}
 
 			prev_idx = perf_evsel__group_idx(evsel);
 		}
@@ -72,41 +89,87 @@
 			/*
 			 * zero-fill group members at last which have no sample
 			 */
-			ret += print_fn(hpp->buf + ret, hpp->size - ret,
-					fmt, 0);
+			if (fmt_percent) {
+				ret += hpp__call_print_fn(hpp, print_fn,
+							  fmt, 0.0);
+			} else {
+				ret += hpp__call_print_fn(hpp, print_fn,
+							  fmt, 0ULL);
+			}
 		}
 	}
+
+	if (callback) {
+		int __ret = callback(hpp, false);
+
+		advance_hpp(hpp, __ret);
+		ret += __ret;
+	}
+
+	/*
+	 * Restore original buf and size as it's where caller expects
+	 * the result will be saved.
+	 */
+	hpp->buf = buf;
+	hpp->size = size;
+
 	return ret;
 }
 
 #define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) 		\
 static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
-			       struct perf_hpp *hpp)			\
+			       struct perf_hpp *hpp,			\
+			       struct perf_evsel *evsel)		\
 {									\
 	int len = _min_width;						\
 									\
-	if (symbol_conf.event_group) {					\
-		struct perf_evsel *evsel = hpp->ptr;			\
-									\
+	if (symbol_conf.event_group)					\
 		len = max(len, evsel->nr_members * _unit_width);	\
-	}								\
+									\
 	return scnprintf(hpp->buf, hpp->size, "%*s", len, _str);	\
 }
 
 #define __HPP_WIDTH_FN(_type, _min_width, _unit_width) 			\
 static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
-			      struct perf_hpp *hpp __maybe_unused)	\
+			      struct perf_hpp *hpp __maybe_unused,	\
+			      struct perf_evsel *evsel)			\
 {									\
 	int len = _min_width;						\
 									\
-	if (symbol_conf.event_group) {					\
-		struct perf_evsel *evsel = hpp->ptr;			\
-									\
+	if (symbol_conf.event_group)					\
 		len = max(len, evsel->nr_members * _unit_width);	\
-	}								\
+									\
 	return len;							\
 }
 
+static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
+{
+	va_list args;
+	ssize_t ssize = hpp->size;
+	double percent;
+	int ret;
+
+	va_start(args, fmt);
+	percent = va_arg(args, double);
+	ret = value_color_snprintf(hpp->buf, hpp->size, fmt, percent);
+	va_end(args);
+
+	return (ret >= ssize) ? (ssize - 1) : ret;
+}
+
+static int hpp_entry_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
+{
+	va_list args;
+	ssize_t ssize = hpp->size;
+	int ret;
+
+	va_start(args, fmt);
+	ret = vsnprintf(hpp->buf, hpp->size, fmt, args);
+	va_end(args);
+
+	return (ret >= ssize) ? (ssize - 1) : ret;
+}
+
 #define __HPP_COLOR_PERCENT_FN(_type, _field)					\
 static u64 he_get_##_field(struct hist_entry *he)				\
 {										\
@@ -116,8 +179,8 @@
 static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
-			  percent_color_snprintf, true);			\
+	return __hpp__fmt(hpp, he, he_get_##_field, NULL, " %6.2f%%",		\
+			  hpp_color_scnprintf, true);				\
 }
 
 #define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
@@ -125,8 +188,8 @@
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
-	return __hpp__fmt(hpp, he, he_get_##_field, fmt,			\
-			  scnprintf, true);					\
+	return __hpp__fmt(hpp, he, he_get_##_field, NULL, fmt,			\
+			  hpp_entry_scnprintf, true);				\
 }
 
 #define __HPP_ENTRY_RAW_FN(_type, _field)					\
@@ -139,7 +202,8 @@
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64;	\
-	return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false);	\
+	return __hpp__fmt(hpp, he, he_get_raw_##_field, NULL, fmt,		\
+			  hpp_entry_scnprintf, false);				\
 }
 
 #define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width)	\
@@ -263,15 +327,13 @@
 	struct perf_hpp_fmt *fmt;
 	struct sort_entry *se;
 	int i = 0, ret = 0;
-	struct perf_hpp dummy_hpp = {
-		.ptr	= hists_to_evsel(hists),
-	};
+	struct perf_hpp dummy_hpp;
 
 	perf_hpp__for_each_format(fmt) {
 		if (i)
 			ret += 2;
 
-		ret += fmt->width(fmt, &dummy_hpp);
+		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
 	}
 
 	list_for_each_entry(se, &hist_entry__sort_list, list)
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 831fbb7..d59893e 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -306,12 +306,6 @@
 	return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
 }
 
-static inline void advance_hpp(struct perf_hpp *hpp, int inc)
-{
-	hpp->buf  += inc;
-	hpp->size -= inc;
-}
-
 static int hist_entry__period_snprintf(struct perf_hpp *hpp,
 				       struct hist_entry *he)
 {
@@ -385,7 +379,6 @@
 	struct perf_hpp dummy_hpp = {
 		.buf	= bf,
 		.size	= sizeof(bf),
-		.ptr	= hists_to_evsel(hists),
 	};
 	bool first = true;
 	size_t linesz;
@@ -404,7 +397,7 @@
 		else
 			first = false;
 
-		fmt->header(fmt, &dummy_hpp);
+		fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
 		fprintf(fp, "%s", bf);
 	}
 
@@ -449,7 +442,7 @@
 		else
 			first = false;
 
-		width = fmt->width(fmt, &dummy_hpp);
+		width = fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
 		for (i = 0; i < width; i++)
 			fprintf(fp, ".");
 	}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 469eb67..809b4c5 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -8,6 +8,8 @@
  */
 
 #include "util.h"
+#include "ui/ui.h"
+#include "sort.h"
 #include "build-id.h"
 #include "color.h"
 #include "cache.h"
@@ -489,7 +491,7 @@
 {
 	struct annotation *notes;
 
-	if (sym == NULL || use_browser != 1 || !sort__has_sym)
+	if (sym == NULL)
 		return 0;
 
 	notes = symbol__annotation(sym);
@@ -1234,6 +1236,7 @@
 	struct dso *dso = map->dso;
 	char *filename;
 	const char *d_filename;
+	const char *evsel_name = perf_evsel__name(evsel);
 	struct annotation *notes = symbol__annotation(sym);
 	struct disasm_line *pos, *queue = NULL;
 	u64 start = map__rip_2objdump(map, sym->start);
@@ -1241,7 +1244,7 @@
 	int more = 0;
 	u64 len;
 	int width = 8;
-	int namelen;
+	int namelen, evsel_name_len, graph_dotted_len;
 
 	filename = strdup(dso->long_name);
 	if (!filename)
@@ -1254,14 +1257,17 @@
 
 	len = symbol__size(sym);
 	namelen = strlen(d_filename);
+	evsel_name_len = strlen(evsel_name);
 
 	if (perf_evsel__is_group_event(evsel))
 		width *= evsel->nr_members;
 
-	printf(" %-*.*s|	Source code & Disassembly of %s\n",
-	       width, width, "Percent", d_filename);
-	printf("-%-*.*s-------------------------------------\n",
-	       width+namelen, width+namelen, graph_dotted_line);
+	printf(" %-*.*s|	Source code & Disassembly of %s for %s\n",
+	       width, width, "Percent", d_filename, evsel_name);
+
+	graph_dotted_len = width + namelen + evsel_name_len;
+	printf("-%-*.*s-----------------------------------------\n",
+	       graph_dotted_len, graph_dotted_len, graph_dotted_line);
 
 	if (verbose)
 		symbol__annotate_hits(sym, evsel);
@@ -1399,3 +1405,8 @@
 {
 	return symbol__annotate(he->ms.sym, he->ms.map, privsize);
 }
+
+bool ui__has_annotation(void)
+{
+	return use_browser == 1 && sort__has_sym;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index b2aef59..56ad4f5 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -151,6 +151,8 @@
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void disasm__purge(struct list_head *head);
 
+bool ui__has_annotation(void);
+
 int symbol__tty_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel, bool print_lines,
 			 bool full_paths, int min_pcnt, int max_lines);
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index a9b48c4..7fe4994 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -1,5 +1,5 @@
 #include "util.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include "../perf.h"
 #include "cpumap.h"
 #include <assert.h>
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 4045d08..64453d6 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -45,8 +45,8 @@
 			debuglink--;
 		if (*debuglink == '/')
 			debuglink++;
-		filename__read_debuglink(dso->long_name, debuglink,
-					 size - (debuglink - filename));
+		ret = filename__read_debuglink(dso->long_name, debuglink,
+					       size - (debuglink - filename));
 		}
 		break;
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index cd7d6f0..ab06f1c 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -102,6 +102,16 @@
 	char		 name[0];
 };
 
+/* dso__for_each_symbol - iterate over the symbols of given type
+ *
+ * @dso: the 'struct dso *' in which symbols itereated
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @n: the 'struct rb_node *' to use as a temporary storage
+ * @type: the 'enum map_type' type of symbols
+ */
+#define dso__for_each_symbol(dso, pos, n, type)	\
+	symbols__for_each_entry(&(dso)->symbols[(type)], pos, n)
+
 static inline void dso__set_loaded(struct dso *dso, enum map_type type)
 {
 	dso->loaded |= (1 << type);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1fc1c2f..9d12aa6 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,6 +1,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "debug.h"
+#include "hist.h"
 #include "machine.h"
 #include "sort.h"
 #include "string.h"
@@ -94,14 +95,10 @@
 
 static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 					 union perf_event *event, pid_t pid,
-					 int full,
 					 perf_event__handler_t process,
 					 struct machine *machine)
 {
-	char filename[PATH_MAX];
 	size_t size;
-	DIR *tasks;
-	struct dirent dirent, *next;
 	pid_t tgid;
 
 	memset(&event->comm, 0, sizeof(event->comm));
@@ -124,57 +121,37 @@
 	event->comm.header.size = (sizeof(event->comm) -
 				(sizeof(event->comm.comm) - size) +
 				machine->id_hdr_size);
-	if (!full) {
-		event->comm.tid = pid;
+	event->comm.tid = pid;
 
-		if (process(tool, event, &synth_sample, machine) != 0)
-			return -1;
+	if (process(tool, event, &synth_sample, machine) != 0)
+		return -1;
 
-		goto out;
-	}
-
-	if (machine__is_default_guest(machine))
-		return 0;
-
-	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
-		 machine->root_dir, pid);
-
-	tasks = opendir(filename);
-	if (tasks == NULL) {
-		pr_debug("couldn't open %s\n", filename);
-		return 0;
-	}
-
-	while (!readdir_r(tasks, &dirent, &next) && next) {
-		char *end;
-		pid = strtol(dirent.d_name, &end, 10);
-		if (*end)
-			continue;
-
-		/* already have tgid; jut want to update the comm */
-		(void) perf_event__get_comm_tgid(pid, event->comm.comm,
-					 sizeof(event->comm.comm));
-
-		size = strlen(event->comm.comm) + 1;
-		size = PERF_ALIGN(size, sizeof(u64));
-		memset(event->comm.comm + size, 0, machine->id_hdr_size);
-		event->comm.header.size = (sizeof(event->comm) -
-					  (sizeof(event->comm.comm) - size) +
-					  machine->id_hdr_size);
-
-		event->comm.tid = pid;
-
-		if (process(tool, event, &synth_sample, machine) != 0) {
-			tgid = -1;
-			break;
-		}
-	}
-
-	closedir(tasks);
 out:
 	return tgid;
 }
 
+static int perf_event__synthesize_fork(struct perf_tool *tool,
+				       union perf_event *event, pid_t pid,
+				       pid_t tgid, perf_event__handler_t process,
+				       struct machine *machine)
+{
+	memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size);
+
+	/* this is really a clone event but we use fork to synthesize it */
+	event->fork.ppid = tgid;
+	event->fork.ptid = tgid;
+	event->fork.pid  = tgid;
+	event->fork.tid  = pid;
+	event->fork.header.type = PERF_RECORD_FORK;
+
+	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
+
+	if (process(tool, event, &synth_sample, machine) != 0)
+		return -1;
+
+	return 0;
+}
+
 int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid,
@@ -324,17 +301,71 @@
 
 static int __event__synthesize_thread(union perf_event *comm_event,
 				      union perf_event *mmap_event,
+				      union perf_event *fork_event,
 				      pid_t pid, int full,
 					  perf_event__handler_t process,
 				      struct perf_tool *tool,
 				      struct machine *machine, bool mmap_data)
 {
-	pid_t tgid = perf_event__synthesize_comm(tool, comm_event, pid, full,
+	char filename[PATH_MAX];
+	DIR *tasks;
+	struct dirent dirent, *next;
+	pid_t tgid;
+
+	/* special case: only send one comm event using passed in pid */
+	if (!full) {
+		tgid = perf_event__synthesize_comm(tool, comm_event, pid,
+						   process, machine);
+
+		if (tgid == -1)
+			return -1;
+
+		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+							  process, machine, mmap_data);
+	}
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
+		 machine->root_dir, pid);
+
+	tasks = opendir(filename);
+	if (tasks == NULL) {
+		pr_debug("couldn't open %s\n", filename);
+		return 0;
+	}
+
+	while (!readdir_r(tasks, &dirent, &next) && next) {
+		char *end;
+		int rc = 0;
+		pid_t _pid;
+
+		_pid = strtol(dirent.d_name, &end, 10);
+		if (*end)
+			continue;
+
+		tgid = perf_event__synthesize_comm(tool, comm_event, _pid,
+						   process, machine);
+		if (tgid == -1)
+			return -1;
+
+		if (_pid == pid) {
+			/* process the parent's maps too */
+			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+						process, machine, mmap_data);
+		} else {
+			/* only fork the tid's map, to save time */
+			rc = perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
 						 process, machine);
-	if (tgid == -1)
-		return -1;
-	return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						  process, machine, mmap_data);
+		}
+
+		if (rc)
+			return rc;
+	}
+
+	closedir(tasks);
+	return 0;
 }
 
 int perf_event__synthesize_thread_map(struct perf_tool *tool,
@@ -343,7 +374,7 @@
 				      struct machine *machine,
 				      bool mmap_data)
 {
-	union perf_event *comm_event, *mmap_event;
+	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1, thread, j;
 
 	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
@@ -354,9 +385,14 @@
 	if (mmap_event == NULL)
 		goto out_free_comm;
 
+	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
+	if (fork_event == NULL)
+		goto out_free_mmap;
+
 	err = 0;
 	for (thread = 0; thread < threads->nr; ++thread) {
 		if (__event__synthesize_thread(comm_event, mmap_event,
+					       fork_event,
 					       threads->map[thread], 0,
 					       process, tool, machine,
 					       mmap_data)) {
@@ -382,6 +418,7 @@
 			/* if not, generate events for it */
 			if (need_leader &&
 			    __event__synthesize_thread(comm_event, mmap_event,
+						       fork_event,
 						       comm_event->comm.pid, 0,
 						       process, tool, machine,
 						       mmap_data)) {
@@ -390,6 +427,8 @@
 			}
 		}
 	}
+	free(fork_event);
+out_free_mmap:
 	free(mmap_event);
 out_free_comm:
 	free(comm_event);
@@ -404,9 +443,12 @@
 	DIR *proc;
 	char proc_path[PATH_MAX];
 	struct dirent dirent, *next;
-	union perf_event *comm_event, *mmap_event;
+	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1;
 
+	if (machine__is_default_guest(machine))
+		return 0;
+
 	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
 	if (comm_event == NULL)
 		goto out;
@@ -415,14 +457,15 @@
 	if (mmap_event == NULL)
 		goto out_free_comm;
 
-	if (machine__is_default_guest(machine))
-		return 0;
+	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
+	if (fork_event == NULL)
+		goto out_free_mmap;
 
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
 	proc = opendir(proc_path);
 
 	if (proc == NULL)
-		goto out_free_mmap;
+		goto out_free_fork;
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -434,12 +477,14 @@
  		 * We may race with exiting thread, so don't stop just because
  		 * one thread couldn't be synthesized.
  		 */
-		__event__synthesize_thread(comm_event, mmap_event, pid, 1,
-					   process, tool, machine, mmap_data);
+		__event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
+					   1, process, tool, machine, mmap_data);
 	}
 
 	err = 0;
 	closedir(proc);
+out_free_fork:
+	free(fork_event);
 out_free_mmap:
 	free(mmap_event);
 out_free_comm:
@@ -470,23 +515,32 @@
 	return 1;
 }
 
+u64 kallsyms__get_function_start(const char *kallsyms_filename,
+				 const char *symbol_name)
+{
+	struct process_symbol_args args = { .name = symbol_name, };
+
+	if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0)
+		return 0;
+
+	return args.start;
+}
+
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
-				       struct machine *machine,
-				       const char *symbol_name)
+				       struct machine *machine)
 {
 	size_t size;
-	const char *filename, *mmap_name;
-	char path[PATH_MAX];
+	const char *mmap_name;
 	char name_buff[PATH_MAX];
 	struct map *map;
+	struct kmap *kmap;
 	int err;
 	/*
 	 * We should get this from /sys/kernel/sections/.text, but till that is
 	 * available use this, and after it is use this as a fallback for older
 	 * kernels.
 	 */
-	struct process_symbol_args args = { .name = symbol_name, };
 	union perf_event *event = zalloc((sizeof(event->mmap) +
 					  machine->id_hdr_size));
 	if (event == NULL) {
@@ -502,30 +556,19 @@
 		 * see kernel/perf_event.c __perf_event_mmap
 		 */
 		event->header.misc = PERF_RECORD_MISC_KERNEL;
-		filename = "/proc/kallsyms";
 	} else {
 		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-		if (machine__is_default_guest(machine))
-			filename = (char *) symbol_conf.default_guest_kallsyms;
-		else {
-			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-			filename = path;
-		}
-	}
-
-	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) {
-		free(event);
-		return -ENOENT;
 	}
 
 	map = machine->vmlinux_maps[MAP__FUNCTION];
+	kmap = map__kmap(map);
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
-			"%s%s", mmap_name, symbol_name) + 1;
+			"%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1;
 	size = PERF_ALIGN(size, sizeof(u64));
 	event->mmap.header.type = PERF_RECORD_MMAP;
 	event->mmap.header.size = (sizeof(event->mmap) -
 			(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
-	event->mmap.pgoff = args.start;
+	event->mmap.pgoff = kmap->ref_reloc_sym->addr;
 	event->mmap.start = map->start;
 	event->mmap.len   = map->end - event->mmap.start;
 	event->mmap.pid   = machine->pid;
@@ -663,7 +706,7 @@
 	al->thread = thread;
 	al->addr = addr;
 	al->cpumode = cpumode;
-	al->filtered = false;
+	al->filtered = 0;
 
 	if (machine == NULL) {
 		al->map = NULL;
@@ -689,11 +732,11 @@
 		if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
 			cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
 			!perf_guest)
-			al->filtered = true;
+			al->filtered |= (1 << HIST_FILTER__GUEST);
 		if ((cpumode == PERF_RECORD_MISC_USER ||
 			cpumode == PERF_RECORD_MISC_KERNEL) &&
 			!perf_host)
-			al->filtered = true;
+			al->filtered |= (1 << HIST_FILTER__HOST);
 
 		return;
 	}
@@ -750,9 +793,6 @@
 	if (thread == NULL)
 		return -1;
 
-	if (thread__is_filtered(thread))
-		goto out_filtered;
-
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 	/*
 	 * Have we already created the kernel maps for this machine?
@@ -770,6 +810,10 @@
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
+
+	if (thread__is_filtered(thread))
+		al->filtered |= (1 << HIST_FILTER__THREAD);
+
 	al->sym = NULL;
 	al->cpu = sample->cpu;
 
@@ -781,8 +825,9 @@
 						  dso->short_name) ||
 			       (dso->short_name != dso->long_name &&
 				strlist__has_entry(symbol_conf.dso_list,
-						   dso->long_name)))))
-			goto out_filtered;
+						   dso->long_name))))) {
+			al->filtered |= (1 << HIST_FILTER__DSO);
+		}
 
 		al->sym = map__find_symbol(al->map, al->addr,
 					   machine->symbol_filter);
@@ -790,12 +835,9 @@
 
 	if (symbol_conf.sym_list &&
 		(!al->sym || !strlist__has_entry(symbol_conf.sym_list,
-						al->sym->name)))
-		goto out_filtered;
+						al->sym->name))) {
+		al->filtered |= (1 << HIST_FILTER__SYMBOL);
+	}
 
 	return 0;
-
-out_filtered:
-	al->filtered = true;
-	return 0;
 }
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index faf6e21..38457d4 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -85,6 +85,7 @@
 
 struct regs_dump {
 	u64 abi;
+	u64 mask;
 	u64 *regs;
 };
 
@@ -214,8 +215,7 @@
 				   struct machine *machine, bool mmap_data);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
-				       struct machine *machine,
-				       const char *symbol_name);
+				       struct machine *machine);
 
 int perf_event__synthesize_modules(struct perf_tool *tool,
 				   perf_event__handler_t process,
@@ -260,9 +260,9 @@
 const char *perf_event__name(unsigned int id);
 
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
-				     u64 sample_regs_user, u64 read_format);
+				     u64 read_format);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
-				  u64 sample_regs_user, u64 read_format,
+				  u64 read_format,
 				  const struct perf_sample *sample,
 				  bool swapped);
 
@@ -279,4 +279,7 @@
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
+u64 kallsyms__get_function_start(const char *kallsyms_filename,
+				 const char *symbol_name);
+
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 55407c5..5c28d82 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -500,6 +500,34 @@
 	return ret;
 }
 
+static void
+perf_evsel__config_callgraph(struct perf_evsel *evsel,
+			     struct record_opts *opts)
+{
+	bool function = perf_evsel__is_function_event(evsel);
+	struct perf_event_attr *attr = &evsel->attr;
+
+	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
+
+	if (opts->call_graph == CALLCHAIN_DWARF) {
+		if (!function) {
+			perf_evsel__set_sample_bit(evsel, REGS_USER);
+			perf_evsel__set_sample_bit(evsel, STACK_USER);
+			attr->sample_regs_user = PERF_REGS_MASK;
+			attr->sample_stack_user = opts->stack_dump_size;
+			attr->exclude_callchain_user = 1;
+		} else {
+			pr_info("Cannot use DWARF unwind for function trace event,"
+				" falling back to framepointers.\n");
+		}
+	}
+
+	if (function) {
+		pr_info("Disabling user space callchains for function trace event.\n");
+		attr->exclude_callchain_user = 1;
+	}
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -595,17 +623,8 @@
 		attr->mmap_data = track;
 	}
 
-	if (opts->call_graph) {
-		perf_evsel__set_sample_bit(evsel, CALLCHAIN);
-
-		if (opts->call_graph == CALLCHAIN_DWARF) {
-			perf_evsel__set_sample_bit(evsel, REGS_USER);
-			perf_evsel__set_sample_bit(evsel, STACK_USER);
-			attr->sample_regs_user = PERF_REGS_MASK;
-			attr->sample_stack_user = opts->stack_dump_size;
-			attr->exclude_callchain_user = 1;
-		}
-	}
+	if (opts->call_graph_enabled)
+		perf_evsel__config_callgraph(evsel, opts);
 
 	if (target__has_cpu(&opts->target))
 		perf_evsel__set_sample_bit(evsel, CPU);
@@ -1004,7 +1023,7 @@
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-			pr_debug2("perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
+			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
 				  pid, cpus->map[cpu], group_fd, flags);
 
 			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
@@ -1013,7 +1032,7 @@
 								     group_fd, flags);
 			if (FD(evsel, cpu, thread) < 0) {
 				err = -errno;
-				pr_debug2("perf_event_open failed, error %d\n",
+				pr_debug2("sys_perf_event_open failed, error %d\n",
 					  err);
 				goto try_fallback;
 			}
@@ -1220,7 +1239,7 @@
 	memset(data, 0, sizeof(*data));
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
-	data->period = 1;
+	data->period = evsel->attr.sample_period;
 	data->weight = 0;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
@@ -1396,10 +1415,11 @@
 		array++;
 
 		if (data->user_regs.abi) {
-			u64 regs_user = evsel->attr.sample_regs_user;
+			u64 mask = evsel->attr.sample_regs_user;
 
-			sz = hweight_long(regs_user) * sizeof(u64);
+			sz = hweight_long(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
+			data->user_regs.mask = mask;
 			data->user_regs.regs = (u64 *)array;
 			array = (void *)array + sz;
 		}
@@ -1451,7 +1471,7 @@
 }
 
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
-				     u64 sample_regs_user, u64 read_format)
+				     u64 read_format)
 {
 	size_t sz, result = sizeof(struct sample_event);
 
@@ -1517,7 +1537,7 @@
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			result += sizeof(u64);
-			sz = hweight_long(sample_regs_user) * sizeof(u64);
+			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -1546,7 +1566,7 @@
 }
 
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
-				  u64 sample_regs_user, u64 read_format,
+				  u64 read_format,
 				  const struct perf_sample *sample,
 				  bool swapped)
 {
@@ -1687,7 +1707,7 @@
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			*array++ = sample->user_regs.abi;
-			sz = hweight_long(sample_regs_user) * sizeof(u64);
+			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
 			memcpy(array, sample->user_regs.regs, sz);
 			array = (void *)array + sz;
 		} else {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index f1b3256..0c9926c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -315,6 +315,24 @@
 	return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
 }
 
+/**
+ * perf_evsel__is_function_event - Return whether given evsel is a function
+ * trace event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true if event is function trace event
+ */
+static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
+{
+#define FUNCTION_EVENT "ftrace:function"
+
+	return evsel->name &&
+	       !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
+
+#undef FUNCTION_EVENT
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;
diff --git a/tools/perf/util/fs.h b/tools/perf/util/fs.h
deleted file mode 100644
index 5e09ce1..0000000
--- a/tools/perf/util/fs.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __PERF_FS
-#define __PERF_FS
-
-const char *sysfs__mountpoint(void);
-const char *procfs__mountpoint(void);
-
-#endif /* __PERF_FS */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e4e6249..f38590d 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -13,13 +13,6 @@
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he);
 
-enum hist_filter {
-	HIST_FILTER__DSO,
-	HIST_FILTER__THREAD,
-	HIST_FILTER__PARENT,
-	HIST_FILTER__SYMBOL,
-};
-
 struct callchain_param	callchain_param = {
 	.mode	= CHAIN_GRAPH_REL,
 	.min_percent = 0.5,
@@ -290,7 +283,7 @@
 		if (he->branch_info) {
 			/*
 			 * This branch info is (a part of) allocated from
-			 * machine__resolve_bstack() and will be freed after
+			 * sample__resolve_bstack() and will be freed after
 			 * adding new entries.  So we need to save a copy.
 			 */
 			he->branch_info = malloc(sizeof(*he->branch_info));
@@ -369,7 +362,7 @@
 			he_stat__add_period(&he->stat, period, weight);
 
 			/*
-			 * This mem info was allocated from machine__resolve_mem
+			 * This mem info was allocated from sample__resolve_mem
 			 * and will not be used anymore.
 			 */
 			zfree(&entry->mem_info);
@@ -429,7 +422,7 @@
 			.weight = weight,
 		},
 		.parent = sym_parent,
-		.filtered = symbol__parent_filter(sym_parent),
+		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
 		.hists	= hists,
 		.branch_info = bi,
 		.mem_info = mi,
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index a59743f..1f1f513 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -14,6 +14,15 @@
 struct addr_location;
 struct symbol;
 
+enum hist_filter {
+	HIST_FILTER__DSO,
+	HIST_FILTER__THREAD,
+	HIST_FILTER__PARENT,
+	HIST_FILTER__SYMBOL,
+	HIST_FILTER__GUEST,
+	HIST_FILTER__HOST,
+};
+
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
  * when possible sends this number in a PERF_RECORD_LOST event. The number of
@@ -132,8 +141,10 @@
 };
 
 struct perf_hpp_fmt {
-	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp);
-	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp);
+	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		      struct perf_evsel *evsel);
+	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		     struct perf_evsel *evsel);
 	int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		     struct hist_entry *he);
 	int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
@@ -166,6 +177,20 @@
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
 
+typedef u64 (*hpp_field_fn)(struct hist_entry *he);
+typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
+typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
+
+int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+	       hpp_field_fn get_field, hpp_callback_fn callback,
+	       const char *fmt, hpp_snprint_fn print_fn, bool fmt_percent);
+
+static inline void advance_hpp(struct perf_hpp *hpp, int inc)
+{
+	hpp->buf  += inc;
+	hpp->size -= inc;
+}
+
 static inline size_t perf_hpp__use_color(void)
 {
 	return !symbol_conf.field_sep;
diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h
new file mode 100644
index 0000000..d82b170b
--- /dev/null
+++ b/tools/perf/util/include/asm/hash.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_GENERIC_HASH_H
+#define __ASM_GENERIC_HASH_H
+
+/* Stub */
+
+#endif /* __ASM_GENERIC_HASH_H */
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index 45cf10a..dadfa7e 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -87,13 +87,15 @@
 	return num;
 }
 
+typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;
+
 /*
  * Find the first set bit in a memory region.
  */
 static inline unsigned long
 find_first_bit(const unsigned long *addr, unsigned long size)
 {
-	const unsigned long *p = addr;
+	long_alias_t *p = (long_alias_t *) addr;
 	unsigned long result = 0;
 	unsigned long tmp;
 
diff --git a/tools/perf/util/include/linux/hash.h b/tools/perf/util/include/linux/hash.h
deleted file mode 100644
index 201f573..0000000
--- a/tools/perf/util/include/linux/hash.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#include "../../../../include/linux/hash.h"
-
-#ifndef PERF_HASH_H
-#define PERF_HASH_H
-#endif
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index d8c927c..9844c31 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -94,12 +94,6 @@
 	return (i >= ssize) ? (ssize - 1) : i;
 }
 
-static inline unsigned long
-simple_strtoul(const char *nptr, char **endptr, int base)
-{
-	return strtoul(nptr, endptr, base);
-}
-
 int eprintf(int level,
 	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
 
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index 1d928a0..bfe0a2a 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,5 +1,4 @@
 #include <linux/kernel.h>
-#include <linux/prefetch.h>
 
 #include "../../../../include/linux/list.h"
 
diff --git a/tools/perf/util/include/linux/magic.h b/tools/perf/util/include/linux/magic.h
deleted file mode 100644
index 07d63cf..0000000
--- a/tools/perf/util/include/linux/magic.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef _PERF_LINUX_MAGIC_H_
-#define _PERF_LINUX_MAGIC_H_
-
-#ifndef DEBUGFS_MAGIC
-#define DEBUGFS_MAGIC          0x64626720
-#endif
-
-#ifndef SYSFS_MAGIC
-#define SYSFS_MAGIC            0x62656572
-#endif
-
-#ifndef PROC_SUPER_MAGIC
-#define PROC_SUPER_MAGIC       0x9fa0
-#endif
-
-#endif
diff --git a/tools/perf/util/include/linux/prefetch.h b/tools/perf/util/include/linux/prefetch.h
deleted file mode 100644
index 7841e48..0000000
--- a/tools/perf/util/include/linux/prefetch.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef PERF_LINUX_PREFETCH_H
-#define PERF_LINUX_PREFETCH_H
-
-static inline void prefetch(void *a __attribute__((unused))) { }
-
-#endif
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ded7459..a53cd0b 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -327,9 +327,10 @@
 	return __machine__findnew_thread(machine, pid, tid, true);
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t tid)
+struct thread *machine__find_thread(struct machine *machine, pid_t pid,
+				    pid_t tid)
 {
-	return __machine__findnew_thread(machine, 0, tid, false);
+	return __machine__findnew_thread(machine, pid, tid, false);
 }
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
@@ -496,19 +497,22 @@
 	return 1;
 }
 
+static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+					   size_t bufsz)
+{
+	if (machine__is_default_guest(machine))
+		scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms);
+	else
+		scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir);
+}
+
 /* Figure out the start address of kernel map from /proc/kallsyms */
 static u64 machine__get_kernel_start_addr(struct machine *machine)
 {
-	const char *filename;
-	char path[PATH_MAX];
+	char filename[PATH_MAX];
 	struct process_args args;
 
-	if (machine__is_default_guest(machine))
-		filename = (char *)symbol_conf.default_guest_kallsyms;
-	else {
-		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-		filename = path;
-	}
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
 
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return 0;
@@ -829,9 +833,25 @@
 	return 0;
 }
 
+const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
+	char filename[PATH_MAX];
+	const char *name;
+	u64 addr = 0;
+	int i;
+
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
+
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr = kallsyms__get_function_start(filename, name);
+		if (addr)
+			break;
+	}
+	if (!addr)
+		return -1;
 
 	if (kernel == NULL ||
 	    __machine__create_kernel_maps(machine, kernel) < 0)
@@ -850,6 +870,13 @@
 	 * Now that we have all the maps created, just set the ->end of them:
 	 */
 	map_groups__fixup_end(&machine->kmaps);
+
+	if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name,
+					     addr)) {
+		machine__destroy_kernel_maps(machine);
+		return -1;
+	}
+
 	return 0;
 }
 
@@ -1000,7 +1027,7 @@
 	}
 
 	thread = machine__findnew_thread(machine, event->mmap2.pid,
-					event->mmap2.pid);
+					event->mmap2.tid);
 	if (thread == NULL)
 		goto out_problem;
 
@@ -1048,7 +1075,7 @@
 	}
 
 	thread = machine__findnew_thread(machine, event->mmap.pid,
-					 event->mmap.pid);
+					 event->mmap.tid);
 	if (thread == NULL)
 		goto out_problem;
 
@@ -1088,7 +1115,9 @@
 int machine__process_fork_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample)
 {
-	struct thread *thread = machine__find_thread(machine, event->fork.tid);
+	struct thread *thread = machine__find_thread(machine,
+						     event->fork.pid,
+						     event->fork.tid);
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
@@ -1114,7 +1143,9 @@
 int machine__process_exit_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample __maybe_unused)
 {
-	struct thread *thread = machine__find_thread(machine, event->fork.tid);
+	struct thread *thread = machine__find_thread(machine,
+						     event->fork.pid,
+						     event->fork.tid);
 
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
@@ -1158,39 +1189,22 @@
 	return 0;
 }
 
-static const u8 cpumodes[] = {
-	PERF_RECORD_MISC_USER,
-	PERF_RECORD_MISC_KERNEL,
-	PERF_RECORD_MISC_GUEST_USER,
-	PERF_RECORD_MISC_GUEST_KERNEL
-};
-#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
-
 static void ip__resolve_ams(struct machine *machine, struct thread *thread,
 			    struct addr_map_symbol *ams,
 			    u64 ip)
 {
 	struct addr_location al;
-	size_t i;
-	u8 m;
 
 	memset(&al, 0, sizeof(al));
+	/*
+	 * We cannot use the header.misc hint to determine whether a
+	 * branch stack address is user, kernel, guest, hypervisor.
+	 * Branches may straddle the kernel/user/hypervisor boundaries.
+	 * Thus, we have to try consecutively until we find a match
+	 * or else, the symbol is unknown
+	 */
+	thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al);
 
-	for (i = 0; i < NCPUMODES; i++) {
-		m = cpumodes[i];
-		/*
-		 * We cannot use the header.misc hint to determine whether a
-		 * branch stack address is user, kernel, guest, hypervisor.
-		 * Branches may straddle the kernel/user/hypervisor boundaries.
-		 * Thus, we have to try consecutively until we find a match
-		 * or else, the symbol is unknown
-		 */
-		thread__find_addr_location(thread, machine, m, MAP__FUNCTION,
-				ip, &al);
-		if (al.sym)
-			goto found;
-	}
-found:
 	ams->addr = ip;
 	ams->al_addr = al.addr;
 	ams->sym = al.sym;
@@ -1212,37 +1226,35 @@
 	ams->map = al.map;
 }
 
-struct mem_info *machine__resolve_mem(struct machine *machine,
-				      struct thread *thr,
-				      struct perf_sample *sample,
-				      u8 cpumode)
+struct mem_info *sample__resolve_mem(struct perf_sample *sample,
+				     struct addr_location *al)
 {
 	struct mem_info *mi = zalloc(sizeof(*mi));
 
 	if (!mi)
 		return NULL;
 
-	ip__resolve_ams(machine, thr, &mi->iaddr, sample->ip);
-	ip__resolve_data(machine, thr, cpumode, &mi->daddr, sample->addr);
+	ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip);
+	ip__resolve_data(al->machine, al->thread, al->cpumode,
+			 &mi->daddr, sample->addr);
 	mi->data_src.val = sample->data_src;
 
 	return mi;
 }
 
-struct branch_info *machine__resolve_bstack(struct machine *machine,
-					    struct thread *thr,
-					    struct branch_stack *bs)
+struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
+					   struct addr_location *al)
 {
-	struct branch_info *bi;
 	unsigned int i;
+	const struct branch_stack *bs = sample->branch_stack;
+	struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
 
-	bi = calloc(bs->nr, sizeof(struct branch_info));
 	if (!bi)
 		return NULL;
 
 	for (i = 0; i < bs->nr; i++) {
-		ip__resolve_ams(machine, thr, &bi[i].to, bs->entries[i].to);
-		ip__resolve_ams(machine, thr, &bi[i].from, bs->entries[i].from);
+		ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from);
 		bi[i].flags = bs->entries[i].flags;
 	}
 	return bi;
@@ -1300,7 +1312,7 @@
 			continue;
 		}
 
-		al.filtered = false;
+		al.filtered = 0;
 		thread__find_addr_location(thread, machine, cpumode,
 					   MAP__FUNCTION, ip, &al);
 		if (al.sym != NULL) {
@@ -1359,8 +1371,7 @@
 		return 0;
 
 	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
-				   thread, evsel->attr.sample_regs_user,
-				   sample, max_stack);
+				   thread, sample, max_stack);
 
 }
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 4771330..c8c74a1 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -18,6 +18,8 @@
 #define	HOST_KERNEL_ID			(-1)
 #define	DEFAULT_GUEST_KERNEL_ID		(0)
 
+extern const char *ref_reloc_sym_names[];
+
 struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
@@ -39,7 +41,8 @@
 	return machine->vmlinux_maps[type];
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t tid);
+struct thread *machine__find_thread(struct machine *machine, pid_t pid,
+				    pid_t tid);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
@@ -89,12 +92,10 @@
 void machine__delete_threads(struct machine *machine);
 void machine__delete(struct machine *machine);
 
-struct branch_info *machine__resolve_bstack(struct machine *machine,
-					    struct thread *thread,
-					    struct branch_stack *bs);
-struct mem_info *machine__resolve_mem(struct machine *machine,
-				      struct thread *thread,
-				      struct perf_sample *sample, u8 cpumode);
+struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
+					   struct addr_location *al);
+struct mem_info *sample__resolve_mem(struct perf_sample *sample,
+				     struct addr_location *al);
 int machine__resolve_callchain(struct machine *machine,
 			       struct perf_evsel *evsel,
 			       struct thread *thread,
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 3b97513..39cd2d0 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -39,6 +39,7 @@
 	map->start    = start;
 	map->end      = end;
 	map->pgoff    = pgoff;
+	map->reloc    = 0;
 	map->dso      = dso;
 	map->map_ip   = map__map_ip;
 	map->unmap_ip = map__unmap_ip;
@@ -288,7 +289,7 @@
 	if (map->dso->rel)
 		return rip - map->pgoff;
 
-	return map->unmap_ip(map, rip);
+	return map->unmap_ip(map, rip) - map->reloc;
 }
 
 /**
@@ -311,7 +312,7 @@
 	if (map->dso->rel)
 		return map->unmap_ip(map, ip + map->pgoff);
 
-	return ip;
+	return ip + map->reloc;
 }
 
 void map_groups__init(struct map_groups *mg)
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 18068c6..f00f058 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -36,6 +36,7 @@
 	bool			erange_warned;
 	u32			priv;
 	u64			pgoff;
+	u64			reloc;
 	u32			maj, min; /* only valid for MMAP2 record */
 	u64			ino;      /* only valid for MMAP2 record */
 	u64			ino_generation;/* only valid for MMAP2 record */
@@ -89,6 +90,16 @@
 
 struct symbol;
 
+/* map__for_each_symbol - iterate over the symbols in the given map
+ *
+ * @map: the 'struct map *' in which symbols itereated
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @n: the 'struct rb_node *' to use as a temporary storage
+ * Note: caller must ensure map->dso is not NULL (map is loaded).
+ */
+#define map__for_each_symbol(map, pos, n)	\
+	dso__for_each_symbol(map->dso, pos, n, map->type)
+
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *map, enum map_type type,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d248fca..1e15df1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1091,12 +1091,12 @@
 static bool is_event_supported(u8 type, unsigned config)
 {
 	bool ret = true;
+	int open_return;
 	struct perf_evsel *evsel;
 	struct perf_event_attr attr = {
 		.type = type,
 		.config = config,
 		.disabled = 1,
-		.exclude_kernel = 1,
 	};
 	struct {
 		struct thread_map map;
@@ -1108,7 +1108,20 @@
 
 	evsel = perf_evsel__new(&attr);
 	if (evsel) {
-		ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+		open_return = perf_evsel__open(evsel, NULL, &tmap.map);
+		ret = open_return >= 0;
+
+		if (open_return == -EACCES) {
+			/*
+			 * This happens if the paranoid value
+			 * /proc/sys/kernel/perf_event_paranoid is set to 2
+			 * Re-run with exclude_kernel set; we don't do that
+			 * by default as some ARM machines do not support it.
+			 *
+			 */
+			evsel->attr.exclude_kernel = 1;
+			ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+		}
 		perf_evsel__delete(evsel);
 	}
 
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index d22e3f8..bf48092 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -407,7 +407,9 @@
 		if (internal_help && !strcmp(arg + 2, "help"))
 			return usage_with_options_internal(usagestr, options, 0);
 		if (!strcmp(arg + 2, "list-opts"))
-			return PARSE_OPT_LIST;
+			return PARSE_OPT_LIST_OPTS;
+		if (!strcmp(arg + 2, "list-cmds"))
+			return PARSE_OPT_LIST_SUBCMDS;
 		switch (parse_long_opt(ctx, arg + 2, options)) {
 		case -1:
 			return parse_options_usage(usagestr, options, arg + 2, 0);
@@ -433,25 +435,45 @@
 	return ctx->cpidx + ctx->argc;
 }
 
-int parse_options(int argc, const char **argv, const struct option *options,
-		  const char * const usagestr[], int flags)
+int parse_options_subcommand(int argc, const char **argv, const struct option *options,
+			const char *const subcommands[], const char *usagestr[], int flags)
 {
 	struct parse_opt_ctx_t ctx;
 
 	perf_header__set_cmdline(argc, argv);
 
+	/* build usage string if it's not provided */
+	if (subcommands && !usagestr[0]) {
+		struct strbuf buf = STRBUF_INIT;
+
+		strbuf_addf(&buf, "perf %s [<options>] {", argv[0]);
+		for (int i = 0; subcommands[i]; i++) {
+			if (i)
+				strbuf_addstr(&buf, "|");
+			strbuf_addstr(&buf, subcommands[i]);
+		}
+		strbuf_addstr(&buf, "}");
+
+		usagestr[0] = strdup(buf.buf);
+		strbuf_release(&buf);
+	}
+
 	parse_options_start(&ctx, argc, argv, flags);
 	switch (parse_options_step(&ctx, options, usagestr)) {
 	case PARSE_OPT_HELP:
 		exit(129);
 	case PARSE_OPT_DONE:
 		break;
-	case PARSE_OPT_LIST:
+	case PARSE_OPT_LIST_OPTS:
 		while (options->type != OPTION_END) {
 			printf("--%s ", options->long_name);
 			options++;
 		}
 		exit(130);
+	case PARSE_OPT_LIST_SUBCMDS:
+		for (int i = 0; subcommands[i]; i++)
+			printf("%s ", subcommands[i]);
+		exit(130);
 	default: /* PARSE_OPT_UNKNOWN */
 		if (ctx.argv[0][1] == '-') {
 			error("unknown option `%s'", ctx.argv[0] + 2);
@@ -464,6 +486,13 @@
 	return parse_options_end(&ctx);
 }
 
+int parse_options(int argc, const char **argv, const struct option *options,
+		  const char * const usagestr[], int flags)
+{
+	return parse_options_subcommand(argc, argv, options, NULL,
+					(const char **) usagestr, flags);
+}
+
 #define USAGE_OPTS_WIDTH 24
 #define USAGE_GAP         2
 
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index cbf0149..d8dac8a 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -140,6 +140,11 @@
                          const struct option *options,
                          const char * const usagestr[], int flags);
 
+extern int parse_options_subcommand(int argc, const char **argv,
+				const struct option *options,
+				const char *const subcommands[],
+				const char *usagestr[], int flags);
+
 extern NORETURN void usage_with_options(const char * const *usagestr,
                                         const struct option *options);
 
@@ -148,7 +153,8 @@
 enum {
 	PARSE_OPT_HELP = -1,
 	PARSE_OPT_DONE,
-	PARSE_OPT_LIST,
+	PARSE_OPT_LIST_OPTS,
+	PARSE_OPT_LIST_SUBCMDS,
 	PARSE_OPT_UNKNOWN,
 };
 
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
new file mode 100644
index 0000000..a3539ef
--- /dev/null
+++ b/tools/perf/util/perf_regs.c
@@ -0,0 +1,19 @@
+#include <errno.h>
+#include "perf_regs.h"
+
+int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
+{
+	int i, idx = 0;
+	u64 mask = regs->mask;
+
+	if (!(mask & (1 << id)))
+		return -EINVAL;
+
+	for (i = 0; i < id; i++) {
+		if (mask & (1 << i))
+			idx++;
+	}
+
+	*valp = regs->regs[idx];
+	return 0;
+}
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index a3d42cd..d6e8b6a 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -1,8 +1,14 @@
 #ifndef __PERF_REGS_H
 #define __PERF_REGS_H
 
+#include "types.h"
+#include "event.h"
+
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
+
+int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
+
 #else
 #define PERF_REGS_MASK	0
 
@@ -10,5 +16,12 @@
 {
 	return NULL;
 }
+
+static inline int perf_reg_value(u64 *valp __maybe_unused,
+				 struct regs_dump *regs __maybe_unused,
+				 int id __maybe_unused)
+{
+	return 0;
+}
 #endif /* HAVE_PERF_REGS_SUPPORT */
 #endif /* __PERF_REGS_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b752ecb..00a7dcb 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -3,7 +3,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <dirent.h>
-#include "fs.h"
+#include <api/fs/fs.h>
 #include <locale.h>
 #include "util.h"
 #include "pmu.h"
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a8a9b6c..0d1542f 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -70,34 +70,32 @@
 }
 
 static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
-static int convert_name_to_addr(struct perf_probe_event *pev,
-				const char *exec);
 static void clear_probe_trace_event(struct probe_trace_event *tev);
-static struct machine machine;
+static struct machine *host_machine;
 
 /* Initialize symbol maps and path of vmlinux/modules */
-static int init_vmlinux(void)
+static int init_symbol_maps(bool user_only)
 {
 	int ret;
 
 	symbol_conf.sort_by_name = true;
-	if (symbol_conf.vmlinux_name == NULL)
-		symbol_conf.try_vmlinux_path = true;
-	else
-		pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
 	ret = symbol__init();
 	if (ret < 0) {
 		pr_debug("Failed to init symbol map.\n");
 		goto out;
 	}
 
-	ret = machine__init(&machine, "", HOST_KERNEL_ID);
-	if (ret < 0)
-		goto out;
+	if (host_machine || user_only)	/* already initialized */
+		return 0;
 
-	if (machine__create_kernel_maps(&machine) < 0) {
-		pr_debug("machine__create_kernel_maps() failed.\n");
-		goto out;
+	if (symbol_conf.vmlinux_name)
+		pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
+
+	host_machine = machine__new_host();
+	if (!host_machine) {
+		pr_debug("machine__new_host() failed.\n");
+		symbol__exit();
+		ret = -1;
 	}
 out:
 	if (ret < 0)
@@ -105,21 +103,66 @@
 	return ret;
 }
 
+static void exit_symbol_maps(void)
+{
+	if (host_machine) {
+		machine__delete(host_machine);
+		host_machine = NULL;
+	}
+	symbol__exit();
+}
+
 static struct symbol *__find_kernel_function_by_name(const char *name,
 						     struct map **mapp)
 {
-	return machine__find_kernel_function_by_name(&machine, name, mapp,
+	return machine__find_kernel_function_by_name(host_machine, name, mapp,
 						     NULL);
 }
 
+static struct symbol *__find_kernel_function(u64 addr, struct map **mapp)
+{
+	return machine__find_kernel_function(host_machine, addr, mapp, NULL);
+}
+
+static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
+{
+	/* kmap->ref_reloc_sym should be set if host_machine is initialized */
+	struct kmap *kmap;
+
+	if (map__load(host_machine->vmlinux_maps[MAP__FUNCTION], NULL) < 0)
+		return NULL;
+
+	kmap = map__kmap(host_machine->vmlinux_maps[MAP__FUNCTION]);
+	return kmap->ref_reloc_sym;
+}
+
+static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
+{
+	struct ref_reloc_sym *reloc_sym;
+	struct symbol *sym;
+	struct map *map;
+
+	/* ref_reloc_sym is just a label. Need a special fix*/
+	reloc_sym = kernel_get_ref_reloc_sym();
+	if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
+		return (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
+	else {
+		sym = __find_kernel_function_by_name(name, &map);
+		if (sym)
+			return map->unmap_ip(map, sym->start) -
+				(reloc) ? 0 : map->reloc;
+	}
+	return 0;
+}
+
 static struct map *kernel_get_module_map(const char *module)
 {
 	struct rb_node *nd;
-	struct map_groups *grp = &machine.kmaps;
+	struct map_groups *grp = &host_machine->kmaps;
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
-		return machine__new_module(&machine, 0, module);
+		return machine__new_module(host_machine, 0, module);
 
 	if (!module)
 		module = "kernel";
@@ -141,7 +184,7 @@
 	const char *vmlinux_name;
 
 	if (module) {
-		list_for_each_entry(dso, &machine.kernel_dsos, node) {
+		list_for_each_entry(dso, &host_machine->kernel_dsos, node) {
 			if (strncmp(dso->short_name + 1, module,
 				    dso->short_name_len - 2) == 0)
 				goto found;
@@ -150,7 +193,7 @@
 		return NULL;
 	}
 
-	map = machine.vmlinux_maps[MAP__FUNCTION];
+	map = host_machine->vmlinux_maps[MAP__FUNCTION];
 	dso = map->dso;
 
 	vmlinux_name = symbol_conf.vmlinux_name;
@@ -173,20 +216,6 @@
 	return (dso) ? dso->long_name : NULL;
 }
 
-static int init_user_exec(void)
-{
-	int ret = 0;
-
-	symbol_conf.try_vmlinux_path = false;
-	symbol_conf.sort_by_name = true;
-	ret = symbol__init();
-
-	if (ret < 0)
-		pr_debug("Failed to init symbol map.\n");
-
-	return ret;
-}
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
 	char *ptr1, *ptr2, *exec_copy;
@@ -218,32 +247,23 @@
 	return ret;
 }
 
-static int convert_to_perf_probe_point(struct probe_trace_point *tp,
-					struct perf_probe_point *pp)
+static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 {
-	pp->function = strdup(tp->symbol);
+	int i;
 
-	if (pp->function == NULL)
-		return -ENOMEM;
-
-	pp->offset = tp->offset;
-	pp->retprobe = tp->retprobe;
-
-	return 0;
+	for (i = 0; i < ntevs; i++)
+		clear_probe_trace_event(tevs + i);
 }
 
 #ifdef HAVE_DWARF_SUPPORT
+
 /* Open new debuginfo of given module */
 static struct debuginfo *open_debuginfo(const char *module)
 {
-	const char *path;
+	const char *path = module;
 
-	/* A file path -- this is an offline module */
-	if (module && strchr(module, '/'))
-		path = module;
-	else {
+	if (!module || !strchr(module, '/')) {
 		path = kernel_get_module_path(module);
-
 		if (!path) {
 			pr_err("Failed to find path of %s module.\n",
 			       module ?: "kernel");
@@ -253,46 +273,6 @@
 	return debuginfo__new(path);
 }
 
-/*
- * Convert trace point to probe point with debuginfo
- * Currently only handles kprobes.
- */
-static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
-					struct perf_probe_point *pp)
-{
-	struct symbol *sym;
-	struct map *map;
-	u64 addr;
-	int ret = -ENOENT;
-	struct debuginfo *dinfo;
-
-	sym = __find_kernel_function_by_name(tp->symbol, &map);
-	if (sym) {
-		addr = map->unmap_ip(map, sym->start + tp->offset);
-		pr_debug("try to find %s+%ld@%" PRIx64 "\n", tp->symbol,
-			 tp->offset, addr);
-
-		dinfo = debuginfo__new_online_kernel(addr);
-		if (dinfo) {
-			ret = debuginfo__find_probe_point(dinfo,
-						 (unsigned long)addr, pp);
-			debuginfo__delete(dinfo);
-		} else {
-			pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n",
-				 addr);
-			ret = -ENOENT;
-		}
-	}
-	if (ret <= 0) {
-		pr_debug("Failed to find corresponding probes from "
-			 "debuginfo. Use kprobe event information.\n");
-		return convert_to_perf_probe_point(tp, pp);
-	}
-	pp->retprobe = tp->retprobe;
-
-	return 0;
-}
-
 static int get_text_start_address(const char *exec, unsigned long *address)
 {
 	Elf *elf;
@@ -321,12 +301,62 @@
 	return ret;
 }
 
+/*
+ * Convert trace point to probe point with debuginfo
+ */
+static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
+					    struct perf_probe_point *pp,
+					    bool is_kprobe)
+{
+	struct debuginfo *dinfo = NULL;
+	unsigned long stext = 0;
+	u64 addr = tp->address;
+	int ret = -ENOENT;
+
+	/* convert the address to dwarf address */
+	if (!is_kprobe) {
+		if (!addr) {
+			ret = -EINVAL;
+			goto error;
+		}
+		ret = get_text_start_address(tp->module, &stext);
+		if (ret < 0)
+			goto error;
+		addr += stext;
+	} else {
+		addr = kernel_get_symbol_address_by_name(tp->symbol, false);
+		if (addr == 0)
+			goto error;
+		addr += tp->offset;
+	}
+
+	pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
+		 tp->module ? : "kernel");
+
+	dinfo = open_debuginfo(tp->module);
+	if (dinfo) {
+		ret = debuginfo__find_probe_point(dinfo,
+						 (unsigned long)addr, pp);
+		debuginfo__delete(dinfo);
+	} else {
+		pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr);
+		ret = -ENOENT;
+	}
+
+	if (ret > 0) {
+		pp->retprobe = tp->retprobe;
+		return 0;
+	}
+error:
+	pr_debug("Failed to find corresponding probes from debuginfo.\n");
+	return ret ? : -ENOENT;
+}
+
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 					  int ntevs, const char *exec)
 {
 	int i, ret = 0;
-	unsigned long offset, stext = 0;
-	char buf[32];
+	unsigned long stext = 0;
 
 	if (!exec)
 		return 0;
@@ -336,16 +366,10 @@
 		return ret;
 
 	for (i = 0; i < ntevs && ret >= 0; i++) {
-		offset = tevs[i].point.address - stext;
-		offset += tevs[i].point.offset;
-		tevs[i].point.offset = 0;
-		zfree(&tevs[i].point.symbol);
-		ret = e_snprintf(buf, 32, "0x%lx", offset);
-		if (ret < 0)
-			break;
+		/* point.address is the addres of point.symbol + point.offset */
+		tevs[i].point.address -= stext;
 		tevs[i].point.module = strdup(exec);
-		tevs[i].point.symbol = strdup(buf);
-		if (!tevs[i].point.symbol || !tevs[i].point.module) {
+		if (!tevs[i].point.module) {
 			ret = -ENOMEM;
 			break;
 		}
@@ -388,12 +412,40 @@
 	return ret;
 }
 
-static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
+/* Post processing the probe events */
+static int post_process_probe_trace_events(struct probe_trace_event *tevs,
+					   int ntevs, const char *module,
+					   bool uprobe)
 {
+	struct ref_reloc_sym *reloc_sym;
+	char *tmp;
 	int i;
 
-	for (i = 0; i < ntevs; i++)
-		clear_probe_trace_event(tevs + i);
+	if (uprobe)
+		return add_exec_to_probe_trace_events(tevs, ntevs, module);
+
+	/* Note that currently ref_reloc_sym based probe is not for drivers */
+	if (module)
+		return add_module_to_probe_trace_events(tevs, ntevs, module);
+
+	reloc_sym = kernel_get_ref_reloc_sym();
+	if (!reloc_sym) {
+		pr_warning("Relocated base symbol is not found!\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ntevs; i++) {
+		if (tevs[i].point.address) {
+			tmp = strdup(reloc_sym->name);
+			if (!tmp)
+				return -ENOMEM;
+			free(tevs[i].point.symbol);
+			tevs[i].point.symbol = tmp;
+			tevs[i].point.offset = tevs[i].point.address -
+					       reloc_sym->unrelocated_addr;
+		}
+	}
+	return 0;
 }
 
 /* Try to find perf_probe_event with debuginfo */
@@ -416,21 +468,16 @@
 		return 0;
 	}
 
+	pr_debug("Try to find probe point from debuginfo.\n");
 	/* Searching trace events corresponding to a probe event */
 	ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs);
 
 	debuginfo__delete(dinfo);
 
 	if (ntevs > 0) {	/* Succeeded to find trace events */
-		pr_debug("find %d probe_trace_events.\n", ntevs);
-		if (target) {
-			if (pev->uprobes)
-				ret = add_exec_to_probe_trace_events(*tevs,
-						 ntevs, target);
-			else
-				ret = add_module_to_probe_trace_events(*tevs,
-						 ntevs, target);
-		}
+		pr_debug("Found %d probe_trace_events.\n", ntevs);
+		ret = post_process_probe_trace_events(*tevs, ntevs,
+							target, pev->uprobes);
 		if (ret < 0) {
 			clear_probe_trace_events(*tevs, ntevs);
 			zfree(tevs);
@@ -563,20 +610,16 @@
  * Show line-range always requires debuginfo to find source file and
  * line number.
  */
-int show_line_range(struct line_range *lr, const char *module)
+static int __show_line_range(struct line_range *lr, const char *module)
 {
 	int l = 1;
-	struct line_node *ln;
+	struct int_node *ln;
 	struct debuginfo *dinfo;
 	FILE *fp;
 	int ret;
 	char *tmp;
 
 	/* Search a line range */
-	ret = init_vmlinux();
-	if (ret < 0)
-		return ret;
-
 	dinfo = open_debuginfo(module);
 	if (!dinfo) {
 		pr_warning("Failed to open debuginfo file.\n");
@@ -623,8 +666,8 @@
 			goto end;
 	}
 
-	list_for_each_entry(ln, &lr->line_list, list) {
-		for (; ln->line > l; l++) {
+	intlist__for_each(ln, lr->line_list) {
+		for (; ln->i > l; l++) {
 			ret = show_one_line(fp, l - lr->offset);
 			if (ret < 0)
 				goto end;
@@ -646,6 +689,19 @@
 	return ret;
 }
 
+int show_line_range(struct line_range *lr, const char *module)
+{
+	int ret;
+
+	ret = init_symbol_maps(false);
+	if (ret < 0)
+		return ret;
+	ret = __show_line_range(lr, module);
+	exit_symbol_maps();
+
+	return ret;
+}
+
 static int show_available_vars_at(struct debuginfo *dinfo,
 				  struct perf_probe_event *pev,
 				  int max_vls, struct strfilter *_filter,
@@ -707,14 +763,15 @@
 	int i, ret = 0;
 	struct debuginfo *dinfo;
 
-	ret = init_vmlinux();
+	ret = init_symbol_maps(false);
 	if (ret < 0)
 		return ret;
 
 	dinfo = open_debuginfo(module);
 	if (!dinfo) {
 		pr_warning("Failed to open debuginfo file.\n");
-		return -ENOENT;
+		ret = -ENOENT;
+		goto out;
 	}
 
 	setup_pager();
@@ -724,23 +781,19 @@
 					     externs);
 
 	debuginfo__delete(dinfo);
+out:
+	exit_symbol_maps();
 	return ret;
 }
 
 #else	/* !HAVE_DWARF_SUPPORT */
 
-static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
-					struct perf_probe_point *pp)
+static int
+find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
+				 struct perf_probe_point *pp __maybe_unused,
+				 bool is_kprobe __maybe_unused)
 {
-	struct symbol *sym;
-
-	sym = __find_kernel_function_by_name(tp->symbol, NULL);
-	if (!sym) {
-		pr_err("Failed to find symbol %s in kernel.\n", tp->symbol);
-		return -ENOENT;
-	}
-
-	return convert_to_perf_probe_point(tp, pp);
+	return -ENOSYS;
 }
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
@@ -776,24 +829,22 @@
 
 void line_range__clear(struct line_range *lr)
 {
-	struct line_node *ln;
-
 	free(lr->function);
 	free(lr->file);
 	free(lr->path);
 	free(lr->comp_dir);
-	while (!list_empty(&lr->line_list)) {
-		ln = list_first_entry(&lr->line_list, struct line_node, list);
-		list_del(&ln->list);
-		free(ln);
-	}
+	intlist__delete(lr->line_list);
 	memset(lr, 0, sizeof(*lr));
 }
 
-void line_range__init(struct line_range *lr)
+int line_range__init(struct line_range *lr)
 {
 	memset(lr, 0, sizeof(*lr));
-	INIT_LIST_HEAD(&lr->line_list);
+	lr->line_list = intlist__new(NULL);
+	if (!lr->line_list)
+		return -ENOMEM;
+	else
+		return 0;
 }
 
 static int parse_line_num(char **ptr, int *val, const char *what)
@@ -1267,16 +1318,21 @@
 	} else
 		p = argv[1];
 	fmt1_str = strtok_r(p, "+", &fmt);
-	tp->symbol = strdup(fmt1_str);
-	if (tp->symbol == NULL) {
-		ret = -ENOMEM;
-		goto out;
+	if (fmt1_str[0] == '0')	/* only the address started with 0x */
+		tp->address = strtoul(fmt1_str, NULL, 0);
+	else {
+		/* Only the symbol-based probe has offset */
+		tp->symbol = strdup(fmt1_str);
+		if (tp->symbol == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		fmt2_str = strtok_r(NULL, "", &fmt);
+		if (fmt2_str == NULL)
+			tp->offset = 0;
+		else
+			tp->offset = strtoul(fmt2_str, NULL, 10);
 	}
-	fmt2_str = strtok_r(NULL, "", &fmt);
-	if (fmt2_str == NULL)
-		tp->offset = 0;
-	else
-		tp->offset = strtoul(fmt2_str, NULL, 10);
 
 	tev->nargs = argc - 2;
 	tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
@@ -1518,20 +1574,27 @@
 	if (buf == NULL)
 		return NULL;
 
+	len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p',
+			 tev->group, tev->event);
+	if (len <= 0)
+		goto error;
+
+	/* Uprobes must have tp->address and tp->module */
+	if (tev->uprobes && (!tp->address || !tp->module))
+		goto error;
+
+	/* Use the tp->address for uprobes */
 	if (tev->uprobes)
-		len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s:%s",
-				 tp->retprobe ? 'r' : 'p',
-				 tev->group, tev->event,
-				 tp->module, tp->symbol);
+		ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx",
+				 tp->module, tp->address);
 	else
-		len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s%s%s+%lu",
-				 tp->retprobe ? 'r' : 'p',
-				 tev->group, tev->event,
+		ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu",
 				 tp->module ?: "", tp->module ? ":" : "",
 				 tp->symbol, tp->offset);
 
-	if (len <= 0)
+	if (ret <= 0)
 		goto error;
+	len += ret;
 
 	for (i = 0; i < tev->nargs; i++) {
 		ret = synthesize_probe_trace_arg(&tev->args[i], buf + len,
@@ -1547,6 +1610,79 @@
 	return NULL;
 }
 
+static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
+					  struct perf_probe_point *pp,
+					  bool is_kprobe)
+{
+	struct symbol *sym = NULL;
+	struct map *map;
+	u64 addr;
+	int ret = -ENOENT;
+
+	if (!is_kprobe) {
+		map = dso__new_map(tp->module);
+		if (!map)
+			goto out;
+		addr = tp->address;
+		sym = map__find_symbol(map, addr, NULL);
+	} else {
+		addr = kernel_get_symbol_address_by_name(tp->symbol, true);
+		if (addr) {
+			addr += tp->offset;
+			sym = __find_kernel_function(addr, &map);
+		}
+	}
+	if (!sym)
+		goto out;
+
+	pp->retprobe = tp->retprobe;
+	pp->offset = addr - map->unmap_ip(map, sym->start);
+	pp->function = strdup(sym->name);
+	ret = pp->function ? 0 : -ENOMEM;
+
+out:
+	if (map && !is_kprobe) {
+		dso__delete(map->dso);
+		map__delete(map);
+	}
+
+	return ret;
+}
+
+static int convert_to_perf_probe_point(struct probe_trace_point *tp,
+					struct perf_probe_point *pp,
+					bool is_kprobe)
+{
+	char buf[128];
+	int ret;
+
+	ret = find_perf_probe_point_from_dwarf(tp, pp, is_kprobe);
+	if (!ret)
+		return 0;
+	ret = find_perf_probe_point_from_map(tp, pp, is_kprobe);
+	if (!ret)
+		return 0;
+
+	pr_debug("Failed to find probe point from both of dwarf and map.\n");
+
+	if (tp->symbol) {
+		pp->function = strdup(tp->symbol);
+		pp->offset = tp->offset;
+	} else if (!tp->module && !is_kprobe) {
+		ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address);
+		if (ret < 0)
+			return ret;
+		pp->function = strdup(buf);
+		pp->offset = 0;
+	}
+	if (pp->function == NULL)
+		return -ENOMEM;
+
+	pp->retprobe = tp->retprobe;
+
+	return 0;
+}
+
 static int convert_to_perf_probe_event(struct probe_trace_event *tev,
 			       struct perf_probe_event *pev, bool is_kprobe)
 {
@@ -1560,11 +1696,7 @@
 		return -ENOMEM;
 
 	/* Convert trace_point to probe_point */
-	if (is_kprobe)
-		ret = kprobe_convert_to_perf_probe(&tev->point, &pev->point);
-	else
-		ret = convert_to_perf_probe_point(&tev->point, &pev->point);
-
+	ret = convert_to_perf_probe_point(&tev->point, &pev->point, is_kprobe);
 	if (ret < 0)
 		return ret;
 
@@ -1731,7 +1863,8 @@
 }
 
 /* Show an event */
-static int show_perf_probe_event(struct perf_probe_event *pev)
+static int show_perf_probe_event(struct perf_probe_event *pev,
+				 const char *module)
 {
 	int i, ret;
 	char buf[128];
@@ -1747,6 +1880,8 @@
 		return ret;
 
 	printf("  %-20s (on %s", buf, place);
+	if (module)
+		printf(" in %s", module);
 
 	if (pev->nargs > 0) {
 		printf(" with");
@@ -1784,7 +1919,8 @@
 			ret = convert_to_perf_probe_event(&tev, &pev,
 								is_kprobe);
 			if (ret >= 0)
-				ret = show_perf_probe_event(&pev);
+				ret = show_perf_probe_event(&pev,
+							    tev.point.module);
 		}
 		clear_perf_probe_event(&pev);
 		clear_probe_trace_event(&tev);
@@ -1807,7 +1943,7 @@
 	if (fd < 0)
 		return fd;
 
-	ret = init_vmlinux();
+	ret = init_symbol_maps(false);
 	if (ret < 0)
 		return ret;
 
@@ -1820,6 +1956,7 @@
 		close(fd);
 	}
 
+	exit_symbol_maps();
 	return ret;
 }
 
@@ -1982,7 +2119,7 @@
 		group = pev->group;
 		pev->event = tev->event;
 		pev->group = tev->group;
-		show_perf_probe_event(pev);
+		show_perf_probe_event(pev, tev->point.module);
 		/* Trick here - restore current event/group */
 		pev->event = (char *)event;
 		pev->group = (char *)group;
@@ -2008,13 +2145,159 @@
 	return ret;
 }
 
+static char *looking_function_name;
+static int num_matched_functions;
+
+static int probe_function_filter(struct map *map __maybe_unused,
+				      struct symbol *sym)
+{
+	if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
+	    strcmp(looking_function_name, sym->name) == 0) {
+		num_matched_functions++;
+		return 0;
+	}
+	return 1;
+}
+
+#define strdup_or_goto(str, label)	\
+	({ char *__p = strdup(str); if (!__p) goto label; __p; })
+
+/*
+ * Find probe function addresses from map.
+ * Return an error or the number of found probe_trace_event
+ */
+static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
+					    struct probe_trace_event **tevs,
+					    int max_tevs, const char *target)
+{
+	struct map *map = NULL;
+	struct kmap *kmap = NULL;
+	struct ref_reloc_sym *reloc_sym = NULL;
+	struct symbol *sym;
+	struct rb_node *nd;
+	struct probe_trace_event *tev;
+	struct perf_probe_point *pp = &pev->point;
+	struct probe_trace_point *tp;
+	int ret, i;
+
+	/* Init maps of given executable or kernel */
+	if (pev->uprobes)
+		map = dso__new_map(target);
+	else
+		map = kernel_get_module_map(target);
+	if (!map) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Load matched symbols: Since the different local symbols may have
+	 * same name but different addresses, this lists all the symbols.
+	 */
+	num_matched_functions = 0;
+	looking_function_name = pp->function;
+	ret = map__load(map, probe_function_filter);
+	if (ret || num_matched_functions == 0) {
+		pr_err("Failed to find symbol %s in %s\n", pp->function,
+			target ? : "kernel");
+		ret = -ENOENT;
+		goto out;
+	} else if (num_matched_functions > max_tevs) {
+		pr_err("Too many functions matched in %s\n",
+			target ? : "kernel");
+		ret = -E2BIG;
+		goto out;
+	}
+
+	if (!pev->uprobes) {
+		kmap = map__kmap(map);
+		reloc_sym = kmap->ref_reloc_sym;
+		if (!reloc_sym) {
+			pr_warning("Relocated base symbol is not found!\n");
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	/* Setup result trace-probe-events */
+	*tevs = zalloc(sizeof(*tev) * num_matched_functions);
+	if (!*tevs) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = 0;
+	map__for_each_symbol(map, sym, nd) {
+		tev = (*tevs) + ret;
+		tp = &tev->point;
+		if (ret == num_matched_functions) {
+			pr_warning("Too many symbols are listed. Skip it.\n");
+			break;
+		}
+		ret++;
+
+		if (pp->offset > sym->end - sym->start) {
+			pr_warning("Offset %ld is bigger than the size of %s\n",
+				   pp->offset, sym->name);
+			ret = -ENOENT;
+			goto err_out;
+		}
+		/* Add one probe point */
+		tp->address = map->unmap_ip(map, sym->start) + pp->offset;
+		if (reloc_sym) {
+			tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out);
+			tp->offset = tp->address - reloc_sym->addr;
+		} else {
+			tp->symbol = strdup_or_goto(sym->name, nomem_out);
+			tp->offset = pp->offset;
+		}
+		tp->retprobe = pp->retprobe;
+		if (target)
+			tev->point.module = strdup_or_goto(target, nomem_out);
+		tev->uprobes = pev->uprobes;
+		tev->nargs = pev->nargs;
+		if (tev->nargs) {
+			tev->args = zalloc(sizeof(struct probe_trace_arg) *
+					   tev->nargs);
+			if (tev->args == NULL)
+				goto nomem_out;
+		}
+		for (i = 0; i < tev->nargs; i++) {
+			if (pev->args[i].name)
+				tev->args[i].name =
+					strdup_or_goto(pev->args[i].name,
+							nomem_out);
+
+			tev->args[i].value = strdup_or_goto(pev->args[i].var,
+							    nomem_out);
+			if (pev->args[i].type)
+				tev->args[i].type =
+					strdup_or_goto(pev->args[i].type,
+							nomem_out);
+		}
+	}
+
+out:
+	if (map && pev->uprobes) {
+		/* Only when using uprobe(exec) map needs to be released */
+		dso__delete(map->dso);
+		map__delete(map);
+	}
+	return ret;
+
+nomem_out:
+	ret = -ENOMEM;
+err_out:
+	clear_probe_trace_events(*tevs, num_matched_functions);
+	zfree(tevs);
+	goto out;
+}
+
 static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 					  struct probe_trace_event **tevs,
 					  int max_tevs, const char *target)
 {
-	struct symbol *sym;
-	int ret, i;
-	struct probe_trace_event *tev;
+	int ret;
 
 	if (pev->uprobes && !pev->group) {
 		/* Replace group name if not given */
@@ -2030,91 +2313,7 @@
 	if (ret != 0)
 		return ret;	/* Found in debuginfo or got an error */
 
-	if (pev->uprobes) {
-		ret = convert_name_to_addr(pev, target);
-		if (ret < 0)
-			return ret;
-	}
-
-	/* Allocate trace event buffer */
-	tev = *tevs = zalloc(sizeof(struct probe_trace_event));
-	if (tev == NULL)
-		return -ENOMEM;
-
-	/* Copy parameters */
-	tev->point.symbol = strdup(pev->point.function);
-	if (tev->point.symbol == NULL) {
-		ret = -ENOMEM;
-		goto error;
-	}
-
-	if (target) {
-		tev->point.module = strdup(target);
-		if (tev->point.module == NULL) {
-			ret = -ENOMEM;
-			goto error;
-		}
-	}
-
-	tev->point.offset = pev->point.offset;
-	tev->point.retprobe = pev->point.retprobe;
-	tev->nargs = pev->nargs;
-	tev->uprobes = pev->uprobes;
-
-	if (tev->nargs) {
-		tev->args = zalloc(sizeof(struct probe_trace_arg)
-				   * tev->nargs);
-		if (tev->args == NULL) {
-			ret = -ENOMEM;
-			goto error;
-		}
-		for (i = 0; i < tev->nargs; i++) {
-			if (pev->args[i].name) {
-				tev->args[i].name = strdup(pev->args[i].name);
-				if (tev->args[i].name == NULL) {
-					ret = -ENOMEM;
-					goto error;
-				}
-			}
-			tev->args[i].value = strdup(pev->args[i].var);
-			if (tev->args[i].value == NULL) {
-				ret = -ENOMEM;
-				goto error;
-			}
-			if (pev->args[i].type) {
-				tev->args[i].type = strdup(pev->args[i].type);
-				if (tev->args[i].type == NULL) {
-					ret = -ENOMEM;
-					goto error;
-				}
-			}
-		}
-	}
-
-	if (pev->uprobes)
-		return 1;
-
-	/* Currently just checking function name from symbol map */
-	sym = __find_kernel_function_by_name(tev->point.symbol, NULL);
-	if (!sym) {
-		pr_warning("Kernel symbol \'%s\' not found.\n",
-			   tev->point.symbol);
-		ret = -ENOENT;
-		goto error;
-	} else if (tev->point.offset > sym->end - sym->start) {
-		pr_warning("Offset specified is greater than size of %s\n",
-			   tev->point.symbol);
-		ret = -ENOENT;
-		goto error;
-
-	}
-
-	return 1;
-error:
-	clear_probe_trace_event(tev);
-	free(tev);
-	*tevs = NULL;
-	return ret;
+	return find_probe_trace_events_from_map(pev, tevs, max_tevs, target);
 }
 
 struct __event_package {
@@ -2135,12 +2334,7 @@
 	if (pkgs == NULL)
 		return -ENOMEM;
 
-	if (!pevs->uprobes)
-		/* Init vmlinux path */
-		ret = init_vmlinux();
-	else
-		ret = init_user_exec();
-
+	ret = init_symbol_maps(pevs->uprobes);
 	if (ret < 0) {
 		free(pkgs);
 		return ret;
@@ -2174,6 +2368,7 @@
 		zfree(&pkgs[i].tevs);
 	}
 	free(pkgs);
+	exit_symbol_maps();
 
 	return ret;
 }
@@ -2323,159 +2518,51 @@
 static int filter_available_functions(struct map *map __maybe_unused,
 				      struct symbol *sym)
 {
-	if (sym->binding == STB_GLOBAL &&
+	if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
 	    strfilter__compare(available_func_filter, sym->name))
 		return 0;
 	return 1;
 }
 
-static int __show_available_funcs(struct map *map)
+int show_available_funcs(const char *target, struct strfilter *_filter,
+					bool user)
 {
-	if (map__load(map, filter_available_functions)) {
-		pr_err("Failed to load map.\n");
+	struct map *map;
+	int ret;
+
+	ret = init_symbol_maps(user);
+	if (ret < 0)
+		return ret;
+
+	/* Get a symbol map */
+	if (user)
+		map = dso__new_map(target);
+	else
+		map = kernel_get_module_map(target);
+	if (!map) {
+		pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
 		return -EINVAL;
 	}
+
+	/* Load symbols with given filter */
+	available_func_filter = _filter;
+	if (map__load(map, filter_available_functions)) {
+		pr_err("Failed to load symbols in %s\n", (target) ? : "kernel");
+		goto end;
+	}
 	if (!dso__sorted_by_name(map->dso, map->type))
 		dso__sort_by_name(map->dso, map->type);
 
-	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
-	return 0;
-}
-
-static int available_kernel_funcs(const char *module)
-{
-	struct map *map;
-	int ret;
-
-	ret = init_vmlinux();
-	if (ret < 0)
-		return ret;
-
-	map = kernel_get_module_map(module);
-	if (!map) {
-		pr_err("Failed to find %s map.\n", (module) ? : "kernel");
-		return -EINVAL;
-	}
-	return __show_available_funcs(map);
-}
-
-static int available_user_funcs(const char *target)
-{
-	struct map *map;
-	int ret;
-
-	ret = init_user_exec();
-	if (ret < 0)
-		return ret;
-
-	map = dso__new_map(target);
-	ret = __show_available_funcs(map);
-	dso__delete(map->dso);
-	map__delete(map);
-	return ret;
-}
-
-int show_available_funcs(const char *target, struct strfilter *_filter,
-					bool user)
-{
+	/* Show all (filtered) symbols */
 	setup_pager();
-	available_func_filter = _filter;
-
-	if (!user)
-		return available_kernel_funcs(target);
-
-	return available_user_funcs(target);
-}
-
-/*
- * uprobe_events only accepts address:
- * Convert function and any offset to address
- */
-static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec)
-{
-	struct perf_probe_point *pp = &pev->point;
-	struct symbol *sym;
-	struct map *map = NULL;
-	char *function = NULL;
-	int ret = -EINVAL;
-	unsigned long long vaddr = 0;
-
-	if (!pp->function) {
-		pr_warning("No function specified for uprobes");
-		goto out;
-	}
-
-	function = strdup(pp->function);
-	if (!function) {
-		pr_warning("Failed to allocate memory by strdup.\n");
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	map = dso__new_map(exec);
-	if (!map) {
-		pr_warning("Cannot find appropriate DSO for %s.\n", exec);
-		goto out;
-	}
-	available_func_filter = strfilter__new(function, NULL);
-	if (map__load(map, filter_available_functions)) {
-		pr_err("Failed to load map.\n");
-		goto out;
-	}
-
-	sym = map__find_symbol_by_name(map, function, NULL);
-	if (!sym) {
-		pr_warning("Cannot find %s in DSO %s\n", function, exec);
-		goto out;
-	}
-
-	if (map->start > sym->start)
-		vaddr = map->start;
-	vaddr += sym->start + pp->offset + map->pgoff;
-	pp->offset = 0;
-
-	if (!pev->event) {
-		pev->event = function;
-		function = NULL;
-	}
-	if (!pev->group) {
-		char *ptr1, *ptr2, *exec_copy;
-
-		pev->group = zalloc(sizeof(char *) * 64);
-		exec_copy = strdup(exec);
-		if (!exec_copy) {
-			ret = -ENOMEM;
-			pr_warning("Failed to copy exec string.\n");
-			goto out;
-		}
-
-		ptr1 = strdup(basename(exec_copy));
-		if (ptr1) {
-			ptr2 = strpbrk(ptr1, "-._");
-			if (ptr2)
-				*ptr2 = '\0';
-			e_snprintf(pev->group, 64, "%s_%s", PERFPROBE_GROUP,
-					ptr1);
-			free(ptr1);
-		}
-		free(exec_copy);
-	}
-	free(pp->function);
-	pp->function = zalloc(sizeof(char *) * MAX_PROBE_ARGS);
-	if (!pp->function) {
-		ret = -ENOMEM;
-		pr_warning("Failed to allocate memory by zalloc.\n");
-		goto out;
-	}
-	e_snprintf(pp->function, MAX_PROBE_ARGS, "0x%llx", vaddr);
-	ret = 0;
-
-out:
-	if (map) {
+	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
+end:
+	if (user) {
 		dso__delete(map->dso);
 		map__delete(map);
 	}
-	if (function)
-		free(function);
+	exit_symbol_maps();
+
 	return ret;
 }
+
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index fcaf727..776c934 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -2,6 +2,7 @@
 #define _PROBE_EVENT_H
 
 #include <stdbool.h>
+#include "intlist.h"
 #include "strlist.h"
 #include "strfilter.h"
 
@@ -76,13 +77,6 @@
 	struct perf_probe_arg	*args;	/* Arguments */
 };
 
-
-/* Line number container */
-struct line_node {
-	struct list_head	list;
-	int			line;
-};
-
 /* Line range */
 struct line_range {
 	char			*file;		/* File name */
@@ -92,7 +86,7 @@
 	int			offset;		/* Start line offset */
 	char			*path;		/* Real path name */
 	char			*comp_dir;	/* Compile directory */
-	struct list_head	line_list;	/* Visible lines */
+	struct intlist		*line_list;	/* Visible lines */
 };
 
 /* List of variables */
@@ -124,7 +118,7 @@
 extern void line_range__clear(struct line_range *lr);
 
 /* Initialize line range */
-extern void line_range__init(struct line_range *lr);
+extern int line_range__init(struct line_range *lr);
 
 /* Internal use: Return kernel/module path */
 extern const char *kernel_get_module_path(const char *module);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 061edb1..df02386 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -34,7 +34,9 @@
 
 #include <linux/bitops.h>
 #include "event.h"
+#include "dso.h"
 #include "debug.h"
+#include "intlist.h"
 #include "util.h"
 #include "symbol.h"
 #include "probe-finder.h"
@@ -42,65 +44,6 @@
 /* Kprobe tracer basic type is up to u64 */
 #define MAX_BASIC_TYPE_BITS	64
 
-/* Line number list operations */
-
-/* Add a line to line number list */
-static int line_list__add_line(struct list_head *head, int line)
-{
-	struct line_node *ln;
-	struct list_head *p;
-
-	/* Reverse search, because new line will be the last one */
-	list_for_each_entry_reverse(ln, head, list) {
-		if (ln->line < line) {
-			p = &ln->list;
-			goto found;
-		} else if (ln->line == line)	/* Already exist */
-			return 1;
-	}
-	/* List is empty, or the smallest entry */
-	p = head;
-found:
-	pr_debug("line list: add a line %u\n", line);
-	ln = zalloc(sizeof(struct line_node));
-	if (ln == NULL)
-		return -ENOMEM;
-	ln->line = line;
-	INIT_LIST_HEAD(&ln->list);
-	list_add(&ln->list, p);
-	return 0;
-}
-
-/* Check if the line in line number list */
-static int line_list__has_line(struct list_head *head, int line)
-{
-	struct line_node *ln;
-
-	/* Reverse search, because new line will be the last one */
-	list_for_each_entry(ln, head, list)
-		if (ln->line == line)
-			return 1;
-
-	return 0;
-}
-
-/* Init line number list */
-static void line_list__init(struct list_head *head)
-{
-	INIT_LIST_HEAD(head);
-}
-
-/* Free line number list */
-static void line_list__free(struct list_head *head)
-{
-	struct line_node *ln;
-	while (!list_empty(head)) {
-		ln = list_first_entry(head, struct line_node, list);
-		list_del(&ln->list);
-		free(ln);
-	}
-}
-
 /* Dwarf FL wrappers */
 static char *debuginfo_path;	/* Currently dummy */
 
@@ -147,80 +90,7 @@
 	return -ENOENT;
 }
 
-#if _ELFUTILS_PREREQ(0, 148)
-/* This method is buggy if elfutils is older than 0.148 */
-static int __linux_kernel_find_elf(Dwfl_Module *mod,
-				   void **userdata,
-				   const char *module_name,
-				   Dwarf_Addr base,
-				   char **file_name, Elf **elfp)
-{
-	int fd;
-	const char *path = kernel_get_module_path(module_name);
-
-	pr_debug2("Use file %s for %s\n", path, module_name);
-	if (path) {
-		fd = open(path, O_RDONLY);
-		if (fd >= 0) {
-			*file_name = strdup(path);
-			return fd;
-		}
-	}
-	/* If failed, try to call standard method */
-	return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base,
-					  file_name, elfp);
-}
-
-static const Dwfl_Callbacks kernel_callbacks = {
-	.find_debuginfo = dwfl_standard_find_debuginfo,
-	.debuginfo_path = &debuginfo_path,
-
-	.find_elf = __linux_kernel_find_elf,
-	.section_address = dwfl_linux_kernel_module_section_address,
-};
-
-/* Get a Dwarf from live kernel image */
-static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg,
-					       Dwarf_Addr addr)
-{
-	dbg->dwfl = dwfl_begin(&kernel_callbacks);
-	if (!dbg->dwfl)
-		return -EINVAL;
-
-	/* Load the kernel dwarves: Don't care the result here */
-	dwfl_linux_kernel_report_kernel(dbg->dwfl);
-	dwfl_linux_kernel_report_modules(dbg->dwfl);
-
-	dbg->dbg = dwfl_addrdwarf(dbg->dwfl, addr, &dbg->bias);
-	/* Here, check whether we could get a real dwarf */
-	if (!dbg->dbg) {
-		pr_debug("Failed to find kernel dwarf at %lx\n",
-			 (unsigned long)addr);
-		dwfl_end(dbg->dwfl);
-		memset(dbg, 0, sizeof(*dbg));
-		return -ENOENT;
-	}
-
-	return 0;
-}
-#else
-/* With older elfutils, this just support kernel module... */
-static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg,
-					       Dwarf_Addr addr __maybe_unused)
-{
-	const char *path = kernel_get_module_path("kernel");
-
-	if (!path) {
-		pr_err("Failed to find vmlinux path\n");
-		return -ENOENT;
-	}
-
-	pr_debug2("Use file %s for debuginfo\n", path);
-	return debuginfo__init_offline_dwarf(dbg, path);
-}
-#endif
-
-struct debuginfo *debuginfo__new(const char *path)
+static struct debuginfo *__debuginfo__new(const char *path)
 {
 	struct debuginfo *dbg = zalloc(sizeof(*dbg));
 	if (!dbg)
@@ -228,21 +98,44 @@
 
 	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
 		zfree(&dbg);
-
+	if (dbg)
+		pr_debug("Open Debuginfo file: %s\n", path);
 	return dbg;
 }
 
-struct debuginfo *debuginfo__new_online_kernel(unsigned long addr)
+enum dso_binary_type distro_dwarf_types[] = {
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+struct debuginfo *debuginfo__new(const char *path)
 {
-	struct debuginfo *dbg = zalloc(sizeof(*dbg));
+	enum dso_binary_type *type;
+	char buf[PATH_MAX], nil = '\0';
+	struct dso *dso;
+	struct debuginfo *dinfo = NULL;
 
-	if (!dbg)
-		return NULL;
+	/* Try to open distro debuginfo files */
+	dso = dso__new(path);
+	if (!dso)
+		goto out;
 
-	if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0)
-		zfree(&dbg);
+	for (type = distro_dwarf_types;
+	     !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
+	     type++) {
+		if (dso__read_binary_type_filename(dso, *type, &nil,
+						   buf, PATH_MAX) < 0)
+			continue;
+		dinfo = __debuginfo__new(buf);
+	}
+	dso__delete(dso);
 
-	return dbg;
+out:
+	/* if failed to open all distro debuginfo, open given binary */
+	return dinfo ? : __debuginfo__new(path);
 }
 
 void debuginfo__delete(struct debuginfo *dbg)
@@ -880,7 +773,7 @@
 }
 
 /* Find lines which match lazy pattern */
-static int find_lazy_match_lines(struct list_head *head,
+static int find_lazy_match_lines(struct intlist *list,
 				 const char *fname, const char *pat)
 {
 	FILE *fp;
@@ -901,7 +794,7 @@
 			line[len - 1] = '\0';
 
 		if (strlazymatch(line, pat)) {
-			line_list__add_line(head, linenum);
+			intlist__add(list, linenum);
 			count++;
 		}
 		linenum++;
@@ -924,7 +817,7 @@
 	Dwarf_Die *sc_die, die_mem;
 	int ret;
 
-	if (!line_list__has_line(&pf->lcache, lineno) ||
+	if (!intlist__has_entry(pf->lcache, lineno) ||
 	    strtailcmp(fname, pf->fname) != 0)
 		return 0;
 
@@ -952,9 +845,9 @@
 {
 	int ret = 0;
 
-	if (list_empty(&pf->lcache)) {
+	if (intlist__empty(pf->lcache)) {
 		/* Matching lazy line pattern */
-		ret = find_lazy_match_lines(&pf->lcache, pf->fname,
+		ret = find_lazy_match_lines(pf->lcache, pf->fname,
 					    pf->pev->point.lazy_line);
 		if (ret <= 0)
 			return ret;
@@ -1096,7 +989,9 @@
 #endif
 
 	off = 0;
-	line_list__init(&pf->lcache);
+	pf->lcache = intlist__new(NULL);
+	if (!pf->lcache)
+		return -ENOMEM;
 
 	/* Fastpath: lookup by function name from .debug_pubnames section */
 	if (pp->function) {
@@ -1149,7 +1044,8 @@
 	}
 
 found:
-	line_list__free(&pf->lcache);
+	intlist__delete(pf->lcache);
+	pf->lcache = NULL;
 
 	return ret;
 }
@@ -1537,7 +1433,7 @@
 		if (lr->path == NULL)
 			return -ENOMEM;
 	}
-	return line_list__add_line(&lr->line_list, lineno);
+	return intlist__add(lr->line_list, lineno);
 }
 
 static int line_range_walk_cb(const char *fname, int lineno,
@@ -1565,7 +1461,7 @@
 
 	/* Update status */
 	if (ret >= 0)
-		if (!list_empty(&lf->lr->line_list))
+		if (!intlist__empty(lf->lr->line_list))
 			ret = lf->found = 1;
 		else
 			ret = 0;	/* Lines are not found */
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index ffc33cd..92590b2 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -3,6 +3,7 @@
 
 #include <stdbool.h>
 #include "util.h"
+#include "intlist.h"
 #include "probe-event.h"
 
 #define MAX_PROBE_BUFFER	1024
@@ -29,8 +30,8 @@
 	Dwarf_Addr	bias;
 };
 
+/* This also tries to open distro debuginfo */
 extern struct debuginfo *debuginfo__new(const char *path);
-extern struct debuginfo *debuginfo__new_online_kernel(unsigned long addr);
 extern void debuginfo__delete(struct debuginfo *dbg);
 
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
@@ -66,7 +67,7 @@
 	const char		*fname;		/* Real file name */
 	Dwarf_Die		cu_die;		/* Current CU */
 	Dwarf_Die		sp_die;
-	struct list_head	lcache;		/* Line cache for lazy match */
+	struct intlist		*lcache;	/* Line cache for lazy match */
 
 	/* For variable searching */
 #if _ELFUTILS_PREREQ(0, 142)
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 595bfc7..16a475a 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -17,6 +17,6 @@
 util/cgroup.c
 util/rblist.c
 util/strlist.c
-util/fs.c
+../lib/api/fs/fs.c
 util/trace-event.c
 ../../lib/rbtree.c
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 3737625..049e0a0 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -2,7 +2,7 @@
 #include "evsel.h"
 #include "cpumap.h"
 #include "parse-events.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include "util.h"
 
 typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0b39a48..55960f2 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -702,11 +702,12 @@
 	}
 }
 
-static void regs_user__printf(struct perf_sample *sample, u64 mask)
+static void regs_user__printf(struct perf_sample *sample)
 {
 	struct regs_dump *user_regs = &sample->user_regs;
 
 	if (user_regs->regs) {
+		u64 mask = user_regs->mask;
 		printf("... user regs: mask 0x%" PRIx64 "\n", mask);
 		regs_dump__printf(mask, user_regs->regs);
 	}
@@ -793,7 +794,7 @@
 	if (!dump_trace)
 		return;
 
-	printf("(IP, %d): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n",
+	printf("(IP, 0x%x): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n",
 	       event->header.misc, sample->pid, sample->tid, sample->ip,
 	       sample->period, sample->addr);
 
@@ -806,7 +807,7 @@
 		branch_stack__printf(sample);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
-		regs_user__printf(sample, evsel->attr.sample_regs_user);
+		regs_user__printf(sample);
 
 	if (sample_type & PERF_SAMPLE_STACK_USER)
 		stack_user__printf(&sample->user_stack);
@@ -1008,6 +1009,12 @@
 		if (err == 0)
 			perf_session__set_id_hdr_size(session);
 		return err;
+	case PERF_RECORD_HEADER_EVENT_TYPE:
+		/*
+		 * Depreceated, but we need to handle it for sake
+		 * of old data files create in pipe mode.
+		 */
+		return 0;
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset, SEEK_SET);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 7594567..3b7dbf5 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -151,15 +151,15 @@
 
 		gelf_getshdr(sec, shp);
 		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
-		if (!strcmp(name, str)) {
+		if (str && !strcmp(name, str)) {
 			if (idx)
 				*idx = cnt;
-			break;
+			return sec;
 		}
 		++cnt;
 	}
 
-	return sec;
+	return NULL;
 }
 
 #define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
@@ -506,6 +506,8 @@
 	/* the start of this section is a zero-terminated string */
 	strncpy(debuglink, data->d_buf, size);
 
+	err = 0;
+
 out_elf_end:
 	elf_end(elf);
 out_close:
@@ -751,6 +753,8 @@
 			if (strcmp(elf_name, kmap->ref_reloc_sym->name))
 				continue;
 			kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
+			map->reloc = kmap->ref_reloc_sym->addr -
+				     kmap->ref_reloc_sym->unrelocated_addr;
 			break;
 		}
 	}
@@ -922,6 +926,7 @@
 				  (u64)shdr.sh_offset);
 			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
 		}
+new_symbol:
 		/*
 		 * We need to figure out if the object was created from C++ sources
 		 * DWARF DW_compile_unit has this, but we don't always have access
@@ -933,7 +938,6 @@
 			if (demangled != NULL)
 				elf_name = demangled;
 		}
-new_symbol:
 		f = symbol__new(sym.st_value, sym.st_size,
 				GELF_ST_BIND(sym.st_info), elf_name);
 		free(demangled);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 39ce9ad..95e2497 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -410,7 +410,7 @@
 	return symbols__find(&dso->symbols[type], addr);
 }
 
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
 {
 	return symbols__first(&dso->symbols[type]);
 }
@@ -627,7 +627,7 @@
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
-static int dso__split_kallsyms(struct dso *dso, struct map *map,
+static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 			       symbol_filter_t filter)
 {
 	struct map_groups *kmaps = map__kmap(map)->kmaps;
@@ -692,6 +692,12 @@
 			char dso_name[PATH_MAX];
 			struct dso *ndso;
 
+			if (delta) {
+				/* Kernel was relocated at boot time */
+				pos->start -= delta;
+				pos->end -= delta;
+			}
+
 			if (count == 0) {
 				curr_map = map;
 				goto filter_symbol;
@@ -721,6 +727,10 @@
 			curr_map->map_ip = curr_map->unmap_ip = identity__map_ip;
 			map_groups__insert(kmaps, curr_map);
 			++kernel_range;
+		} else if (delta) {
+			/* Kernel was relocated at boot time */
+			pos->start -= delta;
+			pos->end -= delta;
 		}
 filter_symbol:
 		if (filter && filter(curr_map, pos)) {
@@ -976,6 +986,23 @@
 	return 0;
 }
 
+static int validate_kcore_addresses(const char *kallsyms_filename,
+				    struct map *map)
+{
+	struct kmap *kmap = map__kmap(map);
+
+	if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) {
+		u64 start;
+
+		start = kallsyms__get_function_start(kallsyms_filename,
+						     kmap->ref_reloc_sym->name);
+		if (start != kmap->ref_reloc_sym->addr)
+			return -EINVAL;
+	}
+
+	return validate_kcore_modules(kallsyms_filename, map);
+}
+
 struct kcore_mapfn_data {
 	struct dso *dso;
 	enum map_type type;
@@ -1019,8 +1046,8 @@
 					     kallsyms_filename))
 		return -EINVAL;
 
-	/* All modules must be present at their original addresses */
-	if (validate_kcore_modules(kallsyms_filename, map))
+	/* Modules and kernel must be present at their original addresses */
+	if (validate_kcore_addresses(kallsyms_filename, map))
 		return -EINVAL;
 
 	md.dso = dso;
@@ -1113,15 +1140,41 @@
 	return -EINVAL;
 }
 
+/*
+ * If the kernel is relocated at boot time, kallsyms won't match.  Compute the
+ * delta based on the relocation reference symbol.
+ */
+static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
+{
+	struct kmap *kmap = map__kmap(map);
+	u64 addr;
+
+	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name)
+		return 0;
+
+	addr = kallsyms__get_function_start(filename,
+					    kmap->ref_reloc_sym->name);
+	if (!addr)
+		return -1;
+
+	*delta = addr - kmap->ref_reloc_sym->addr;
+	return 0;
+}
+
 int dso__load_kallsyms(struct dso *dso, const char *filename,
 		       struct map *map, symbol_filter_t filter)
 {
+	u64 delta = 0;
+
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return -1;
 
 	if (dso__load_all_kallsyms(dso, filename, map) < 0)
 		return -1;
 
+	if (kallsyms__delta(map, filename, &delta))
+		return -1;
+
 	symbols__fixup_duplicate(&dso->symbols[map->type]);
 	symbols__fixup_end(&dso->symbols[map->type]);
 
@@ -1133,7 +1186,7 @@
 	if (!dso__load_kcore(dso, map, filename))
 		return dso__split_kallsyms_for_kcore(dso, map, filter);
 	else
-		return dso__split_kallsyms(dso, map, filter);
+		return dso__split_kallsyms(dso, map, delta, filter);
 }
 
 static int dso__load_perf_map(struct dso *dso, struct map *map,
@@ -1198,6 +1251,46 @@
 	return -1;
 }
 
+static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
+					   enum dso_binary_type type)
+{
+	switch (type) {
+	case DSO_BINARY_TYPE__JAVA_JIT:
+	case DSO_BINARY_TYPE__DEBUGLINK:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
+	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
+	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
+	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
+	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
+		return !kmod && dso->kernel == DSO_TYPE_USER;
+
+	case DSO_BINARY_TYPE__KALLSYMS:
+	case DSO_BINARY_TYPE__VMLINUX:
+	case DSO_BINARY_TYPE__KCORE:
+		return dso->kernel == DSO_TYPE_KERNEL;
+
+	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
+	case DSO_BINARY_TYPE__GUEST_VMLINUX:
+	case DSO_BINARY_TYPE__GUEST_KCORE:
+		return dso->kernel == DSO_TYPE_GUEST_KERNEL;
+
+	case DSO_BINARY_TYPE__GUEST_KMODULE:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+		/*
+		 * kernel modules know their symtab type - it's set when
+		 * creating a module dso in machine__new_module().
+		 */
+		return kmod && dso->symtab_type == type;
+
+	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
+		return true;
+
+	case DSO_BINARY_TYPE__NOT_FOUND:
+	default:
+		return false;
+	}
+}
+
 int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 {
 	char *name;
@@ -1208,6 +1301,7 @@
 	int ss_pos = 0;
 	struct symsrc ss_[2];
 	struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
+	bool kmod;
 
 	dso__set_loaded(dso, map->type);
 
@@ -1248,7 +1342,11 @@
 	if (!name)
 		return -1;
 
-	/* Iterate over candidate debug images.
+	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/*
+	 * Iterate over candidate debug images.
 	 * Keep track of "interesting" ones (those which have a symtab, dynsym,
 	 * and/or opd section) for processing.
 	 */
@@ -1258,6 +1356,9 @@
 
 		enum dso_binary_type symtab_type = binary_type_symtab[i];
 
+		if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type))
+			continue;
+
 		if (dso__read_binary_type_filename(dso, symtab_type,
 						   root_dir, name, PATH_MAX))
 			continue;
@@ -1283,6 +1384,8 @@
 
 			if (syms_ss && runtime_ss)
 				break;
+		} else {
+			symsrc__destroy(ss);
 		}
 
 	}
@@ -1298,15 +1401,10 @@
 	if (!runtime_ss && syms_ss)
 		runtime_ss = syms_ss;
 
-	if (syms_ss) {
-		int km;
-
-		km = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
-		     dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
-		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, km);
-	} else {
+	if (syms_ss)
+		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod);
+	else
 		ret = -1;
-	}
 
 	if (ret > 0) {
 		int nr_plt;
@@ -1424,7 +1522,7 @@
 			continue;
 		scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
 			  "%s/%s/kallsyms", dir, dent->d_name);
-		if (!validate_kcore_modules(kallsyms_filename, map)) {
+		if (!validate_kcore_addresses(kallsyms_filename, map)) {
 			strlcpy(dir, kallsyms_filename, dir_sz);
 			ret = 0;
 			break;
@@ -1479,7 +1577,7 @@
 		if (fd != -1) {
 			close(fd);
 			/* If module maps match go with /proc/kallsyms */
-			if (!validate_kcore_modules("/proc/kallsyms", map))
+			if (!validate_kcore_addresses("/proc/kallsyms", map))
 				goto proc_kallsyms;
 		}
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fffe288..501e4e7 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -79,6 +79,17 @@
 void symbol__delete(struct symbol *sym);
 void symbols__delete(struct rb_root *symbols);
 
+/* symbols__for_each_entry - iterate over symbols (rb_root)
+ *
+ * @symbols: the rb_root of symbols
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @nd: the 'struct rb_node *' to use as a temporary storage
+ */
+#define symbols__for_each_entry(symbols, pos, nd)			\
+	for (nd = rb_first(symbols);					\
+	     nd && (pos = rb_entry(nd, struct symbol, rb_node));	\
+	     nd = rb_next(nd))
+
 static inline size_t symbol__size(const struct symbol *sym)
 {
 	return sym->end - sym->start + 1;
@@ -175,7 +186,7 @@
 	struct symbol *sym;
 	u64	      addr;
 	char	      level;
-	bool	      filtered;
+	u8	      filtered;
 	u8	      cpumode;
 	s32	      cpu;
 };
@@ -223,7 +234,6 @@
 				u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name);
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0358882..3ce0498 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -142,3 +142,24 @@
 
 	return 0;
 }
+
+void thread__find_cpumode_addr_location(struct thread *thread,
+					struct machine *machine,
+					enum map_type type, u64 addr,
+					struct addr_location *al)
+{
+	size_t i;
+	const u8 const cpumodes[] = {
+		PERF_RECORD_MISC_USER,
+		PERF_RECORD_MISC_KERNEL,
+		PERF_RECORD_MISC_GUEST_USER,
+		PERF_RECORD_MISC_GUEST_KERNEL
+	};
+
+	for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
+		thread__find_addr_location(thread, machine, cpumodes[i], type,
+					   addr, al);
+		if (al->map)
+			break;
+	}
+}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 5b856bf..9b29f08 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -44,12 +44,6 @@
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
-static inline struct map *thread__find_map(struct thread *thread,
-					   enum map_type type, u64 addr)
-{
-	return thread ? map_groups__find(&thread->mg, type, addr) : NULL;
-}
-
 void thread__find_addr_map(struct thread *thread, struct machine *machine,
 			   u8 cpumode, enum map_type type, u64 addr,
 			   struct addr_location *al);
@@ -58,6 +52,11 @@
 				u8 cpumode, enum map_type type, u64 addr,
 				struct addr_location *al);
 
+void thread__find_cpumode_addr_location(struct thread *thread,
+					struct machine *machine,
+					enum map_type type, u64 addr,
+					struct addr_location *al);
+
 static inline void *thread__priv(struct thread *thread)
 {
 	return thread->priv;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index e0d6d07f..c36636f 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -126,6 +126,7 @@
 	trace_seq_init(&s);
 	pevent_event_info(&s, event, &record);
 	trace_seq_do_printf(&s);
+	trace_seq_destroy(&s);
 }
 
 void parse_proc_kallsyms(struct pevent *pevent,
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
new file mode 100644
index 0000000..67db73e
--- /dev/null
+++ b/tools/perf/util/unwind-libdw.c
@@ -0,0 +1,210 @@
+#include <linux/compiler.h>
+#include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
+#include <inttypes.h>
+#include <errno.h>
+#include "unwind.h"
+#include "unwind-libdw.h"
+#include "machine.h"
+#include "thread.h"
+#include "types.h"
+#include "event.h"
+#include "perf_regs.h"
+
+static char *debuginfo_path;
+
+static const Dwfl_Callbacks offline_callbacks = {
+	.find_debuginfo		= dwfl_standard_find_debuginfo,
+	.debuginfo_path		= &debuginfo_path,
+	.section_address	= dwfl_offline_section_address,
+};
+
+static int __report_module(struct addr_location *al, u64 ip,
+			    struct unwind_info *ui)
+{
+	Dwfl_Module *mod;
+	struct dso *dso = NULL;
+
+	thread__find_addr_location(ui->thread, ui->machine,
+				   PERF_RECORD_MISC_USER,
+				   MAP__FUNCTION, ip, al);
+
+	if (al->map)
+		dso = al->map->dso;
+
+	if (!dso)
+		return 0;
+
+	mod = dwfl_addrmodule(ui->dwfl, ip);
+	if (!mod)
+		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
+				      dso->long_name, -1, al->map->start,
+				      false);
+
+	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
+}
+
+static int report_module(u64 ip, struct unwind_info *ui)
+{
+	struct addr_location al;
+
+	return __report_module(&al, ip, ui);
+}
+
+static int entry(u64 ip, struct unwind_info *ui)
+
+{
+	struct unwind_entry e;
+	struct addr_location al;
+
+	if (__report_module(&al, ip, ui))
+		return -1;
+
+	e.ip  = ip;
+	e.map = al.map;
+	e.sym = al.sym;
+
+	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+		 al.sym ? al.sym->name : "''",
+		 ip,
+		 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
+
+	return ui->cb(&e, ui->arg);
+}
+
+static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
+{
+	/* We want only single thread to be processed. */
+	if (*thread_argp != NULL)
+		return 0;
+
+	*thread_argp = arg;
+	return dwfl_pid(dwfl);
+}
+
+static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
+			  Dwarf_Word *data)
+{
+	struct addr_location al;
+	ssize_t size;
+
+	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+			      MAP__FUNCTION, addr, &al);
+	if (!al.map) {
+		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+		return -1;
+	}
+
+	if (!al.map->dso)
+		return -1;
+
+	size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+				   addr, (u8 *) data, sizeof(*data));
+
+	return !(size == sizeof(*data));
+}
+
+static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result,
+			void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct stack_dump *stack = &ui->sample->user_stack;
+	u64 start, end;
+	int offset;
+	int ret;
+
+	ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
+	if (ret)
+		return false;
+
+	end = start + stack->size;
+
+	/* Check overflow. */
+	if (addr + sizeof(Dwarf_Word) < addr)
+		return false;
+
+	if (addr < start || addr + sizeof(Dwarf_Word) > end) {
+		ret = access_dso_mem(ui, addr, result);
+		if (ret) {
+			pr_debug("unwind: access_mem 0x%" PRIx64 " not inside range"
+				 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
+				addr, start, end);
+			return false;
+		}
+		return true;
+	}
+
+	offset  = addr - start;
+	*result = *(Dwarf_Word *)&stack->data[offset];
+	pr_debug("unwind: access_mem addr 0x%" PRIx64 ", val %lx, offset %d\n",
+		 addr, (unsigned long)*result, offset);
+	return true;
+}
+
+static const Dwfl_Thread_Callbacks callbacks = {
+	.next_thread		= next_thread,
+	.memory_read		= memory_read,
+	.set_initial_registers	= libdw__arch_set_initial_registers,
+};
+
+static int
+frame_callback(Dwfl_Frame *state, void *arg)
+{
+	struct unwind_info *ui = arg;
+	Dwarf_Addr pc;
+
+	if (!dwfl_frame_pc(state, &pc, NULL)) {
+		pr_err("%s", dwfl_errmsg(-1));
+		return DWARF_CB_ABORT;
+	}
+
+	return entry(pc, ui) || !(--ui->max_stack) ?
+	       DWARF_CB_ABORT : DWARF_CB_OK;
+}
+
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+			struct machine *machine, struct thread *thread,
+			struct perf_sample *data,
+			int max_stack)
+{
+	struct unwind_info ui = {
+		.sample		= data,
+		.thread		= thread,
+		.machine	= machine,
+		.cb		= cb,
+		.arg		= arg,
+		.max_stack	= max_stack,
+	};
+	Dwarf_Word ip;
+	int err = -EINVAL;
+
+	if (!data->user_regs.regs)
+		return -EINVAL;
+
+	ui.dwfl = dwfl_begin(&offline_callbacks);
+	if (!ui.dwfl)
+		goto out;
+
+	err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
+	if (err)
+		goto out;
+
+	err = report_module(ip, &ui);
+	if (err)
+		goto out;
+
+	if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui))
+		goto out;
+
+	err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui);
+
+	if (err && !ui.max_stack)
+		err = 0;
+
+ out:
+	if (err)
+		pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1));
+
+	dwfl_end(ui.dwfl);
+	return 0;
+}
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
new file mode 100644
index 0000000..417a142
--- /dev/null
+++ b/tools/perf/util/unwind-libdw.h
@@ -0,0 +1,21 @@
+#ifndef __PERF_UNWIND_LIBDW_H
+#define __PERF_UNWIND_LIBDW_H
+
+#include <elfutils/libdwfl.h>
+#include "event.h"
+#include "thread.h"
+#include "unwind.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg);
+
+struct unwind_info {
+	Dwfl			*dwfl;
+	struct perf_sample      *sample;
+	struct machine          *machine;
+	struct thread           *thread;
+	unwind_entry_cb_t	cb;
+	void			*arg;
+	int			max_stack;
+};
+
+#endif /* __PERF_UNWIND_LIBDW_H */
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind-libunwind.c
similarity index 92%
rename from tools/perf/util/unwind.c
rename to tools/perf/util/unwind-libunwind.c
index 742f23b..bd5768d 100644
--- a/tools/perf/util/unwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -86,7 +86,6 @@
 	struct perf_sample	*sample;
 	struct machine		*machine;
 	struct thread		*thread;
-	u64			sample_uregs;
 };
 
 #define dw_read(ptr, type, end) ({	\
@@ -391,30 +390,13 @@
 	return !(size == sizeof(*data));
 }
 
-static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id,
-		     u64 sample_regs)
-{
-	int i, idx = 0;
-
-	if (!(sample_regs & (1 << id)))
-		return -EINVAL;
-
-	for (i = 0; i < id; i++) {
-		if (sample_regs & (1 << i))
-			idx++;
-	}
-
-	*valp = regs->regs[idx];
-	return 0;
-}
-
 static int access_mem(unw_addr_space_t __maybe_unused as,
 		      unw_word_t addr, unw_word_t *valp,
 		      int __write, void *arg)
 {
 	struct unwind_info *ui = arg;
 	struct stack_dump *stack = &ui->sample->user_stack;
-	unw_word_t start, end;
+	u64 start, end;
 	int offset;
 	int ret;
 
@@ -424,8 +406,7 @@
 		return 0;
 	}
 
-	ret = reg_value(&start, &ui->sample->user_regs, PERF_REG_SP,
-			ui->sample_uregs);
+	ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
 	if (ret)
 		return ret;
 
@@ -438,8 +419,9 @@
 	if (addr < start || addr + sizeof(unw_word_t) >= end) {
 		ret = access_dso_mem(ui, addr, valp);
 		if (ret) {
-			pr_debug("unwind: access_mem %p not inside range %p-%p\n",
-				(void *)addr, (void *)start, (void *)end);
+			pr_debug("unwind: access_mem %p not inside range"
+				 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
+				 (void *) addr, start, end);
 			*valp = 0;
 			return ret;
 		}
@@ -448,8 +430,8 @@
 
 	offset = addr - start;
 	*valp  = *(unw_word_t *)&stack->data[offset];
-	pr_debug("unwind: access_mem addr %p, val %lx, offset %d\n",
-		 (void *)addr, (unsigned long)*valp, offset);
+	pr_debug("unwind: access_mem addr %p val %lx, offset %d\n",
+		 (void *) addr, (unsigned long)*valp, offset);
 	return 0;
 }
 
@@ -459,6 +441,7 @@
 {
 	struct unwind_info *ui = arg;
 	int id, ret;
+	u64 val;
 
 	/* Don't support write, I suspect we don't need it. */
 	if (__write) {
@@ -471,16 +454,17 @@
 		return 0;
 	}
 
-	id = unwind__arch_reg_id(regnum);
+	id = libunwind__arch_reg_id(regnum);
 	if (id < 0)
 		return -EINVAL;
 
-	ret = reg_value(valp, &ui->sample->user_regs, id, ui->sample_uregs);
+	ret = perf_reg_value(&val, &ui->sample->user_regs, id);
 	if (ret) {
 		pr_err("unwind: can't read reg %d\n", regnum);
 		return ret;
 	}
 
+	*valp = (unw_word_t) val;
 	pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
 	return 0;
 }
@@ -563,7 +547,7 @@
 		unw_word_t ip;
 
 		unw_get_reg(&c, UNW_REG_IP, &ip);
-		ret = entry(ip, ui->thread, ui->machine, cb, arg);
+		ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
 	}
 
 	unw_destroy_addr_space(addr_space);
@@ -572,13 +556,11 @@
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct machine *machine, struct thread *thread,
-			u64 sample_uregs, struct perf_sample *data,
-			int max_stack)
+			struct perf_sample *data, int max_stack)
 {
-	unw_word_t ip;
+	u64 ip;
 	struct unwind_info ui = {
 		.sample       = data,
-		.sample_uregs = sample_uregs,
 		.thread       = thread,
 		.machine      = machine,
 	};
@@ -587,7 +569,7 @@
 	if (!data->user_regs.regs)
 		return -EINVAL;
 
-	ret = reg_value(&ip, &data->user_regs, PERF_REG_IP, sample_uregs);
+	ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
 	if (ret)
 		return ret;
 
@@ -595,5 +577,5 @@
 	if (ret)
 		return -ENOMEM;
 
-	return get_entries(&ui, cb, arg, max_stack);
+	return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0;
 }
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index d5966f49..b031316 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -13,24 +13,25 @@
 
 typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
-#ifdef HAVE_LIBUNWIND_SUPPORT
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct machine *machine,
 			struct thread *thread,
-			u64 sample_uregs,
 			struct perf_sample *data, int max_stack);
-int unwind__arch_reg_id(int regnum);
+/* libunwind specific */
+#ifdef HAVE_LIBUNWIND_SUPPORT
+int libunwind__arch_reg_id(int regnum);
+#endif
 #else
 static inline int
 unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 		    void *arg __maybe_unused,
 		    struct machine *machine __maybe_unused,
 		    struct thread *thread __maybe_unused,
-		    u64 sample_uregs __maybe_unused,
 		    struct perf_sample *data __maybe_unused,
 		    int max_stack __maybe_unused)
 {
 	return 0;
 }
-#endif /* HAVE_LIBUNWIND_SUPPORT */
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 42ad667..9f66549 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,6 +1,6 @@
 #include "../perf.h"
 #include "util.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include <sys/mman.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
diff --git a/tools/power/x86/turbostat/.gitignore b/tools/power/x86/turbostat/.gitignore
new file mode 100644
index 0000000..7521370
--- /dev/null
+++ b/tools/power/x86/turbostat/.gitignore
@@ -0,0 +1 @@
+turbostat
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index f09641d..d1b3a36 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -5,7 +5,7 @@
 
 turbostat : turbostat.c
 CFLAGS +=	-Wall
-CFLAGS +=	-I../../../../arch/x86/include/uapi/
+CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"'
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9d77f13..77eb130 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -20,8 +20,10 @@
  */
 
 #define _GNU_SOURCE
-#include <asm/msr.h>
+#include MSRHEADER
+#include <stdarg.h>
 #include <stdio.h>
+#include <err.h>
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/wait.h>
@@ -35,13 +37,16 @@
 #include <string.h>
 #include <ctype.h>
 #include <sched.h>
+#include <cpuid.h>
 
 char *proc_stat = "/proc/stat";
 unsigned int interval_sec = 5;	/* set with -i interval_sec */
 unsigned int verbose;		/* set with -v */
 unsigned int rapl_verbose;	/* set with -R */
+unsigned int rapl_joules;	/* set with -J */
 unsigned int thermal_verbose;	/* set with -T */
-unsigned int summary_only;	/* set with -s */
+unsigned int summary_only;	/* set with -S */
+unsigned int dump_only;		/* set with -s */
 unsigned int skip_c0;
 unsigned int skip_c1;
 unsigned int do_nhm_cstates;
@@ -77,14 +82,32 @@
 double rapl_power_units, rapl_energy_units, rapl_time_units;
 double rapl_joule_counter_range;
 
-#define RAPL_PKG	(1 << 0)
-#define RAPL_CORES	(1 << 1)
-#define RAPL_GFX	(1 << 2)
-#define RAPL_DRAM	(1 << 3)
-#define RAPL_PKG_PERF_STATUS	(1 << 4)
-#define RAPL_DRAM_PERF_STATUS	(1 << 5)
-#define RAPL_PKG_POWER_INFO	(1 << 6)
-#define RAPL_CORE_POLICY	(1 << 7)
+#define RAPL_PKG		(1 << 0)
+					/* 0x610 MSR_PKG_POWER_LIMIT */
+					/* 0x611 MSR_PKG_ENERGY_STATUS */
+#define RAPL_PKG_PERF_STATUS	(1 << 1)
+					/* 0x613 MSR_PKG_PERF_STATUS */
+#define RAPL_PKG_POWER_INFO	(1 << 2)
+					/* 0x614 MSR_PKG_POWER_INFO */
+
+#define RAPL_DRAM		(1 << 3)
+					/* 0x618 MSR_DRAM_POWER_LIMIT */
+					/* 0x619 MSR_DRAM_ENERGY_STATUS */
+					/* 0x61c MSR_DRAM_POWER_INFO */
+#define RAPL_DRAM_PERF_STATUS	(1 << 4)
+					/* 0x61b MSR_DRAM_PERF_STATUS */
+
+#define RAPL_CORES		(1 << 5)
+					/* 0x638 MSR_PP0_POWER_LIMIT */
+					/* 0x639 MSR_PP0_ENERGY_STATUS */
+#define RAPL_CORE_POLICY	(1 << 6)
+					/* 0x63a MSR_PP0_POLICY */
+
+
+#define RAPL_GFX		(1 << 7)
+					/* 0x640 MSR_PP1_POWER_LIMIT */
+					/* 0x641 MSR_PP1_ENERGY_STATUS */
+					/* 0x642 MSR_PP1_POLICY */
 #define	TJMAX_DEFAULT	100
 
 #define MAX(a, b) ((a) > (b) ? (a) : (b))
@@ -234,7 +257,7 @@
 	close(fd);
 
 	if (retval != sizeof *msr) {
-		fprintf(stderr, "%s offset 0x%zx read failed\n", pathname, offset);
+		fprintf(stderr, "%s offset 0x%llx read failed\n", pathname, (unsigned long long)offset);
 		return -1;
 	}
 
@@ -296,70 +319,92 @@
 		outp += sprintf(outp, "  %%pc10");
 	}
 
-	if (do_rapl & RAPL_PKG)
-		outp += sprintf(outp, "  Pkg_W");
-	if (do_rapl & RAPL_CORES)
-		outp += sprintf(outp, "  Cor_W");
-	if (do_rapl & RAPL_GFX)
-		outp += sprintf(outp, " GFX_W");
-	if (do_rapl & RAPL_DRAM)
-		outp += sprintf(outp, " RAM_W");
-	if (do_rapl & RAPL_PKG_PERF_STATUS)
-		outp += sprintf(outp, " PKG_%%");
-	if (do_rapl & RAPL_DRAM_PERF_STATUS)
-		outp += sprintf(outp, " RAM_%%");
+	if (do_rapl && !rapl_joules) {
+		if (do_rapl & RAPL_PKG)
+			outp += sprintf(outp, "  Pkg_W");
+		if (do_rapl & RAPL_CORES)
+			outp += sprintf(outp, "  Cor_W");
+		if (do_rapl & RAPL_GFX)
+			outp += sprintf(outp, " GFX_W");
+		if (do_rapl & RAPL_DRAM)
+			outp += sprintf(outp, " RAM_W");
+		if (do_rapl & RAPL_PKG_PERF_STATUS)
+			outp += sprintf(outp, " PKG_%%");
+		if (do_rapl & RAPL_DRAM_PERF_STATUS)
+			outp += sprintf(outp, " RAM_%%");
+	} else {
+		if (do_rapl & RAPL_PKG)
+			outp += sprintf(outp, "  Pkg_J");
+		if (do_rapl & RAPL_CORES)
+			outp += sprintf(outp, "  Cor_J");
+		if (do_rapl & RAPL_GFX)
+			outp += sprintf(outp, " GFX_J");
+		if (do_rapl & RAPL_DRAM)
+			outp += sprintf(outp, " RAM_W");
+		if (do_rapl & RAPL_PKG_PERF_STATUS)
+			outp += sprintf(outp, " PKG_%%");
+		if (do_rapl & RAPL_DRAM_PERF_STATUS)
+			outp += sprintf(outp, " RAM_%%");
+		outp += sprintf(outp, " time");
 
+	}
 	outp += sprintf(outp, "\n");
 }
 
 int dump_counters(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
 {
-	fprintf(stderr, "t %p, c %p, p %p\n", t, c, p);
+	outp += sprintf(outp, "t %p, c %p, p %p\n", t, c, p);
 
 	if (t) {
-		fprintf(stderr, "CPU: %d flags 0x%x\n", t->cpu_id, t->flags);
-		fprintf(stderr, "TSC: %016llX\n", t->tsc);
-		fprintf(stderr, "aperf: %016llX\n", t->aperf);
-		fprintf(stderr, "mperf: %016llX\n", t->mperf);
-		fprintf(stderr, "c1: %016llX\n", t->c1);
-		fprintf(stderr, "msr0x%x: %08llX\n",
+		outp += sprintf(outp, "CPU: %d flags 0x%x\n",
+			t->cpu_id, t->flags);
+		outp += sprintf(outp, "TSC: %016llX\n", t->tsc);
+		outp += sprintf(outp, "aperf: %016llX\n", t->aperf);
+		outp += sprintf(outp, "mperf: %016llX\n", t->mperf);
+		outp += sprintf(outp, "c1: %016llX\n", t->c1);
+		outp += sprintf(outp, "msr0x%x: %08llX\n",
 			extra_delta_offset32, t->extra_delta32);
-		fprintf(stderr, "msr0x%x: %016llX\n",
+		outp += sprintf(outp, "msr0x%x: %016llX\n",
 			extra_delta_offset64, t->extra_delta64);
-		fprintf(stderr, "msr0x%x: %08llX\n",
+		outp += sprintf(outp, "msr0x%x: %08llX\n",
 			extra_msr_offset32, t->extra_msr32);
-		fprintf(stderr, "msr0x%x: %016llX\n",
+		outp += sprintf(outp, "msr0x%x: %016llX\n",
 			extra_msr_offset64, t->extra_msr64);
 		if (do_smi)
-			fprintf(stderr, "SMI: %08X\n", t->smi_count);
+			outp += sprintf(outp, "SMI: %08X\n", t->smi_count);
 	}
 
 	if (c) {
-		fprintf(stderr, "core: %d\n", c->core_id);
-		fprintf(stderr, "c3: %016llX\n", c->c3);
-		fprintf(stderr, "c6: %016llX\n", c->c6);
-		fprintf(stderr, "c7: %016llX\n", c->c7);
-		fprintf(stderr, "DTS: %dC\n", c->core_temp_c);
+		outp += sprintf(outp, "core: %d\n", c->core_id);
+		outp += sprintf(outp, "c3: %016llX\n", c->c3);
+		outp += sprintf(outp, "c6: %016llX\n", c->c6);
+		outp += sprintf(outp, "c7: %016llX\n", c->c7);
+		outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
 	}
 
 	if (p) {
-		fprintf(stderr, "package: %d\n", p->package_id);
-		fprintf(stderr, "pc2: %016llX\n", p->pc2);
-		fprintf(stderr, "pc3: %016llX\n", p->pc3);
-		fprintf(stderr, "pc6: %016llX\n", p->pc6);
-		fprintf(stderr, "pc7: %016llX\n", p->pc7);
-		fprintf(stderr, "pc8: %016llX\n", p->pc8);
-		fprintf(stderr, "pc9: %016llX\n", p->pc9);
-		fprintf(stderr, "pc10: %016llX\n", p->pc10);
-		fprintf(stderr, "Joules PKG: %0X\n", p->energy_pkg);
-		fprintf(stderr, "Joules COR: %0X\n", p->energy_cores);
-		fprintf(stderr, "Joules GFX: %0X\n", p->energy_gfx);
-		fprintf(stderr, "Joules RAM: %0X\n", p->energy_dram);
-		fprintf(stderr, "Throttle PKG: %0X\n", p->rapl_pkg_perf_status);
-		fprintf(stderr, "Throttle RAM: %0X\n", p->rapl_dram_perf_status);
-		fprintf(stderr, "PTM: %dC\n", p->pkg_temp_c);
+		outp += sprintf(outp, "package: %d\n", p->package_id);
+		outp += sprintf(outp, "pc2: %016llX\n", p->pc2);
+		outp += sprintf(outp, "pc3: %016llX\n", p->pc3);
+		outp += sprintf(outp, "pc6: %016llX\n", p->pc6);
+		outp += sprintf(outp, "pc7: %016llX\n", p->pc7);
+		outp += sprintf(outp, "pc8: %016llX\n", p->pc8);
+		outp += sprintf(outp, "pc9: %016llX\n", p->pc9);
+		outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
+		outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
+		outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores);
+		outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx);
+		outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram);
+		outp += sprintf(outp, "Throttle PKG: %0X\n",
+			p->rapl_pkg_perf_status);
+		outp += sprintf(outp, "Throttle RAM: %0X\n",
+			p->rapl_dram_perf_status);
+		outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
 	}
+
+	outp += sprintf(outp, "\n");
+
 	return 0;
 }
 
@@ -527,19 +572,39 @@
 		fmt6 = " %4.0f**";
 	}
 
-	if (do_rapl & RAPL_PKG)
-		outp += sprintf(outp, fmt6, p->energy_pkg * rapl_energy_units / interval_float);
-	if (do_rapl & RAPL_CORES)
-		outp += sprintf(outp, fmt6, p->energy_cores * rapl_energy_units / interval_float);
-	if (do_rapl & RAPL_GFX)
-		outp += sprintf(outp, fmt5, p->energy_gfx * rapl_energy_units / interval_float); 
-	if (do_rapl & RAPL_DRAM)
-		outp += sprintf(outp, fmt5, p->energy_dram * rapl_energy_units / interval_float);
-	if (do_rapl & RAPL_PKG_PERF_STATUS )
-		outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
-	if (do_rapl & RAPL_DRAM_PERF_STATUS )
-		outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+	if (do_rapl && !rapl_joules) {
+		if (do_rapl & RAPL_PKG)
+			outp += sprintf(outp, fmt6, p->energy_pkg * rapl_energy_units / interval_float);
+		if (do_rapl & RAPL_CORES)
+			outp += sprintf(outp, fmt6, p->energy_cores * rapl_energy_units / interval_float);
+		if (do_rapl & RAPL_GFX)
+			outp += sprintf(outp, fmt5, p->energy_gfx * rapl_energy_units / interval_float);
+		if (do_rapl & RAPL_DRAM)
+			outp += sprintf(outp, fmt5, p->energy_dram * rapl_energy_units / interval_float);
+		if (do_rapl & RAPL_PKG_PERF_STATUS)
+			outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+		if (do_rapl & RAPL_DRAM_PERF_STATUS)
+			outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+	} else {
+		if (do_rapl & RAPL_PKG)
+			outp += sprintf(outp, fmt6,
+					p->energy_pkg * rapl_energy_units);
+		if (do_rapl & RAPL_CORES)
+			outp += sprintf(outp, fmt6,
+					p->energy_cores * rapl_energy_units);
+		if (do_rapl & RAPL_GFX)
+			outp += sprintf(outp, fmt5,
+					p->energy_gfx * rapl_energy_units);
+		if (do_rapl & RAPL_DRAM)
+			outp += sprintf(outp, fmt5,
+					p->energy_dram * rapl_energy_units);
+		if (do_rapl & RAPL_PKG_PERF_STATUS)
+			outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+		if (do_rapl & RAPL_DRAM_PERF_STATUS)
+			outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+	outp += sprintf(outp, fmt5, interval_float);
 
+	}
 done:
 	outp += sprintf(outp, "\n");
 
@@ -622,12 +687,10 @@
 	old->tsc = new->tsc - old->tsc;
 
 	/* check for TSC < 1 Mcycles over interval */
-	if (old->tsc < (1000 * 1000)) {
-		fprintf(stderr, "Insanely slow TSC rate, TSC stops in idle?\n");
-		fprintf(stderr, "You can disable all c-states by booting with \"idle=poll\"\n");
-		fprintf(stderr, "or just the deep ones with \"processor.max_cstate=1\"\n");
-		exit(-3);
-	}
+	if (old->tsc < (1000 * 1000))
+		errx(-3, "Insanely slow TSC rate, TSC stops in idle?\n"
+		     "You can disable all c-states by booting with \"idle=poll\"\n"
+		     "or just the deep ones with \"processor.max_cstate=1\"");
 
 	old->c1 = new->c1 - old->c1;
 
@@ -1173,24 +1236,43 @@
 }
 
 /*
+ * Open a file, and exit on failure
+ */
+FILE *fopen_or_die(const char *path, const char *mode)
+{
+	FILE *filep = fopen(path, "r");
+	if (!filep)
+		err(1, "%s: open failed", path);
+	return filep;
+}
+
+/*
+ * Parse a file containing a single int.
+ */
+int parse_int_file(const char *fmt, ...)
+{
+	va_list args;
+	char path[PATH_MAX];
+	FILE *filep;
+	int value;
+
+	va_start(args, fmt);
+	vsnprintf(path, sizeof(path), fmt, args);
+	va_end(args);
+	filep = fopen_or_die(path, "r");
+	if (fscanf(filep, "%d", &value) != 1)
+		err(1, "%s: failed to parse number from file", path);
+	fclose(filep);
+	return value;
+}
+
+/*
  * cpu_is_first_sibling_in_core(cpu)
  * return 1 if given CPU is 1st HT sibling in the core
  */
 int cpu_is_first_sibling_in_core(int cpu)
 {
-	char path[64];
-	FILE *filep;
-	int first_cpu;
-
-	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
-	fscanf(filep, "%d", &first_cpu);
-	fclose(filep);
-	return (cpu == first_cpu);
+	return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
 }
 
 /*
@@ -1199,53 +1281,17 @@
  */
 int cpu_is_first_core_in_package(int cpu)
 {
-	char path[64];
-	FILE *filep;
-	int first_cpu;
-
-	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/core_siblings_list", cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
-	fscanf(filep, "%d", &first_cpu);
-	fclose(filep);
-	return (cpu == first_cpu);
+	return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_siblings_list", cpu);
 }
 
 int get_physical_package_id(int cpu)
 {
-	char path[80];
-	FILE *filep;
-	int pkg;
-
-	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
-	fscanf(filep, "%d", &pkg);
-	fclose(filep);
-	return pkg;
+	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu);
 }
 
 int get_core_id(int cpu)
 {
-	char path[80];
-	FILE *filep;
-	int core;
-
-	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
-	fscanf(filep, "%d", &core);
-	fclose(filep);
-	return core;
+	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
 }
 
 int get_num_ht_siblings(int cpu)
@@ -1257,11 +1303,7 @@
 	char character;
 
 	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
+	filep = fopen_or_die(path, "r");
 	/*
 	 * file format:
 	 * if a pair of number with a character between: 2 siblings (eg. 1-2, or 1,4)
@@ -1331,17 +1373,11 @@
 	int cpu_num;
 	int retval;
 
-	fp = fopen(proc_stat, "r");
-	if (fp == NULL) {
-		perror(proc_stat);
-		exit(1);
-	}
+	fp = fopen_or_die(proc_stat, "r");
 
 	retval = fscanf(fp, "cpu %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n");
-	if (retval != 0) {
-		perror("/proc/stat format");
-		exit(1);
-	}
+	if (retval != 0)
+		err(1, "%s: failed to parse format", proc_stat);
 
 	while (1) {
 		retval = fscanf(fp, "cpu%u %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n", &cpu_num);
@@ -1445,19 +1481,15 @@
 {
 	struct stat sb;
 
-	if (stat("/dev/cpu/0/msr", &sb)) {
-		fprintf(stderr, "no /dev/cpu/0/msr\n");
-		fprintf(stderr, "Try \"# modprobe msr\"\n");
-		exit(-5);
-	}
+	if (stat("/dev/cpu/0/msr", &sb))
+		err(-5, "no /dev/cpu/0/msr\n"
+		    "Try \"# modprobe msr\"");
 }
 
 void check_super_user()
 {
-	if (getuid() != 0) {
-		fprintf(stderr, "must be root\n");
-		exit(-6);
-	}
+	if (getuid() != 0)
+		errx(-6, "must be root");
 }
 
 int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model)
@@ -1479,7 +1511,7 @@
 	case 0x3A:	/* IVB */
 	case 0x3E:	/* IVB Xeon */
 	case 0x3C:	/* HSW */
-	case 0x3F:	/* HSW */
+	case 0x3F:	/* HSX */
 	case 0x45:	/* HSW */
 	case 0x46:	/* HSW */
 	case 0x37:	/* BYT */
@@ -1595,11 +1627,13 @@
 	case 0x2A:
 	case 0x3A:
 	case 0x3C:	/* HSW */
-	case 0x3F:	/* HSW */
 	case 0x45:	/* HSW */
 	case 0x46:	/* HSW */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
 		break;
+	case 0x3F:	/* HSX */
+		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+		break;
 	case 0x2D:
 	case 0x3E:
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO;
@@ -1978,7 +2012,7 @@
 
 	eax = ebx = ecx = edx = 0;
 
-	asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0));
+	__get_cpuid(0, &max_level, &ebx, &ecx, &edx);
 
 	if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
 		genuine_intel = 1;
@@ -1987,7 +2021,7 @@
 		fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
 			(char *)&ebx, (char *)&edx, (char *)&ecx);
 
-	asm("cpuid" : "=a" (fms), "=c" (ecx), "=d" (edx) : "a" (1) : "ebx");
+	__get_cpuid(1, &fms, &ebx, &ecx, &edx);
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	stepping = fms & 0xf;
@@ -1998,10 +2032,8 @@
 		fprintf(stderr, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
 			max_level, family, model, stepping, family, model, stepping);
 
-	if (!(edx & (1 << 5))) {
-		fprintf(stderr, "CPUID: no MSR\n");
-		exit(1);
-	}
+	if (!(edx & (1 << 5)))
+		errx(1, "CPUID: no MSR");
 
 	/*
 	 * check max extended function levels of CPUID.
@@ -2009,31 +2041,27 @@
 	 * This check is valid for both Intel and AMD.
 	 */
 	ebx = ecx = edx = 0;
-	asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000000));
+	__get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx);
 
-	if (max_level < 0x80000007) {
-		fprintf(stderr, "CPUID: no invariant TSC (max_level 0x%x)\n", max_level);
-		exit(1);
-	}
+	if (max_level < 0x80000007)
+		errx(1, "CPUID: no invariant TSC (max_level 0x%x)", max_level);
 
 	/*
 	 * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8
 	 * this check is valid for both Intel and AMD
 	 */
-	asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000007));
+	__get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
 	has_invariant_tsc = edx & (1 << 8);
 
-	if (!has_invariant_tsc) {
-		fprintf(stderr, "No invariant TSC\n");
-		exit(1);
-	}
+	if (!has_invariant_tsc)
+		errx(1, "No invariant TSC");
 
 	/*
 	 * APERF/MPERF is advertised by CPUID.EAX=0x6: ECX.bit0
 	 * this check is valid for both Intel and AMD
 	 */
 
-	asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x6));
+	__get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
 	has_aperf = ecx & (1 << 0);
 	do_dts = eax & (1 << 0);
 	do_ptm = eax & (1 << 6);
@@ -2047,7 +2075,7 @@
 			has_epb ? ", EPB": "");
 
 	if (!has_aperf)
-		exit(-1);
+		errx(-1, "No APERF");
 
 	do_nehalem_platform_info = genuine_intel && has_invariant_tsc;
 	do_nhm_cstates = genuine_intel;	/* all Intel w/ non-stop TSC have NHM counters */
@@ -2067,9 +2095,8 @@
 
 void usage()
 {
-	fprintf(stderr, "%s: [-v][-R][-T][-p|-P|-S][-c MSR# | -s]][-C MSR#][-m MSR#][-M MSR#][-i interval_sec | command ...]\n",
-		progname);
-	exit(1);
+	errx(1, "%s: [-v][-R][-T][-p|-P|-S][-c MSR#][-C MSR#][-m MSR#][-M MSR#][-i interval_sec | command ...]\n",
+	     progname);
 }
 
 
@@ -2112,19 +2139,15 @@
 		fprintf(stderr, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num);
 
 	cpus = calloc(1, (topo.max_cpu_num  + 1) * sizeof(struct cpu_topology));
-	if (cpus == NULL) {
-		perror("calloc cpus");
-		exit(1);
-	}
+	if (cpus == NULL)
+		err(1, "calloc cpus");
 
 	/*
 	 * Allocate and initialize cpu_present_set
 	 */
 	cpu_present_set = CPU_ALLOC((topo.max_cpu_num + 1));
-	if (cpu_present_set == NULL) {
-		perror("CPU_ALLOC");
-		exit(3);
-	}
+	if (cpu_present_set == NULL)
+		err(3, "CPU_ALLOC");
 	cpu_present_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
 	CPU_ZERO_S(cpu_present_setsize, cpu_present_set);
 	for_all_proc_cpus(mark_cpu_present);
@@ -2133,10 +2156,8 @@
 	 * Allocate and initialize cpu_affinity_set
 	 */
 	cpu_affinity_set = CPU_ALLOC((topo.max_cpu_num + 1));
-	if (cpu_affinity_set == NULL) {
-		perror("CPU_ALLOC");
-		exit(3);
-	}
+	if (cpu_affinity_set == NULL)
+		err(3, "CPU_ALLOC");
 	cpu_affinity_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
 	CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
 
@@ -2220,8 +2241,7 @@
 
 	return;
 error:
-	perror("calloc counters");
-	exit(1);
+	err(1, "calloc counters");
 }
 /*
  * init_counter()
@@ -2276,12 +2296,10 @@
 
 void allocate_output_buffer()
 {
-	output_buffer = calloc(1, (1 + topo.num_cpus) * 256);
+	output_buffer = calloc(1, (1 + topo.num_cpus) * 1024);
 	outp = output_buffer;
-	if (outp == NULL) {
-		perror("calloc");
-		exit(-1);
-	}
+	if (outp == NULL)
+		err(-1, "calloc output buffer");
 }
 
 void setup_all_buffers(void)
@@ -2292,6 +2310,7 @@
 	allocate_output_buffer();
 	for_all_proc_cpus(initialize_counters);
 }
+
 void turbostat_init()
 {
 	check_cpuid();
@@ -2335,17 +2354,13 @@
 	} else {
 
 		/* parent */
-		if (child_pid == -1) {
-			perror("fork");
-			exit(1);
-		}
+		if (child_pid == -1)
+			err(1, "fork");
 
 		signal(SIGINT, SIG_IGN);
 		signal(SIGQUIT, SIG_IGN);
-		if (waitpid(child_pid, &status, 0) == -1) {
-			perror("wait");
-			exit(status);
-		}
+		if (waitpid(child_pid, &status, 0) == -1)
+			err(status, "waitpid");
 	}
 	/*
 	 * n.b. fork_it() does not check for errors from for_all_cpus()
@@ -2364,13 +2379,30 @@
 	return status;
 }
 
+int get_and_dump_counters(void)
+{
+	int status;
+
+	status = for_all_cpus(get_counters, ODD_COUNTERS);
+	if (status)
+		return status;
+
+	status = for_all_cpus(dump_counters, ODD_COUNTERS);
+	if (status)
+		return status;
+
+	flush_stdout();
+
+	return status;
+}
+
 void cmdline(int argc, char **argv)
 {
 	int opt;
 
 	progname = argv[0];
 
-	while ((opt = getopt(argc, argv, "+pPSvi:sc:sC:m:M:RT:")) != -1) {
+	while ((opt = getopt(argc, argv, "+pPsSvi:c:C:m:M:RJT:")) != -1) {
 		switch (opt) {
 		case 'p':
 			show_core_only++;
@@ -2378,6 +2410,9 @@
 		case 'P':
 			show_pkg_only++;
 			break;
+		case 's':
+			dump_only++;
+			break;
 		case 'S':
 			summary_only++;
 			break;
@@ -2405,6 +2440,10 @@
 		case 'T':
 			tcc_activation_temp_override = atoi(optarg);
 			break;
+		case 'J':
+			rapl_joules++;
+			break;
+
 		default:
 			usage();
 		}
@@ -2416,11 +2455,15 @@
 	cmdline(argc, argv);
 
 	if (verbose)
-		fprintf(stderr, "turbostat v3.5 April 26, 2013"
+		fprintf(stderr, "turbostat v3.6 Dec 2, 2013"
 			" - Len Brown <lenb@kernel.org>\n");
 
 	turbostat_init();
 
+	/* dump counters and exit */
+	if (dump_only)
+		return get_and_dump_counters();
+
 	/*
 	 * if any params left, it must be a command to fork
 	 */
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index d664182..aa290c0 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -201,6 +201,7 @@
 
 	msgque.msq_id = msgget(msgque.key, IPC_CREAT | IPC_EXCL | 0666);
 	if (msgque.msq_id == -1) {
+		err = -errno;
 		printf("Can't create queue\n");
 		goto err_out;
 	}
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 587561d..9b17e81 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -96,6 +96,7 @@
 		echo qemu-system-ppc64
 	else
 		echo Cannot figure out what qemu command to use! 1>&2
+		echo file $1 output: $u
 		# Usually this will be one of /usr/bin/qemu-system-*
 		# Use RCU_QEMU_CMD environment variable or appropriate
 		# argument to top-level script.
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
new file mode 100755
index 0000000..829186e
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
@@ -0,0 +1,51 @@
+#!/bin/bash
+#
+# Analyze a given results directory for locktorture progress.
+#
+# Usage: sh kvm-recheck-lock.sh resdir
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (C) IBM Corporation, 2014
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+i="$1"
+if test -d $i
+then
+	:
+else
+	echo Unreadable results directory: $i
+	exit 1
+fi
+
+configfile=`echo $i | sed -e 's/^.*\///'`
+ncs=`grep "Writes:  Total:" $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* Total: //' -e 's/ .*$//'`
+if test -z "$ncs"
+then
+	echo $configfile
+else
+	title="$configfile ------- $ncs acquisitions/releases"
+	dur=`sed -e 's/^.* locktorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`
+	if test -z "$dur"
+	then
+		:
+	else
+		ncsps=`awk -v ncs=$ncs -v dur=$dur '
+			BEGIN { print ncs / dur }' < /dev/null`
+		title="$title ($ncsps per second)"
+	fi
+	echo $title
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
new file mode 100755
index 0000000..d75b1dc5
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -0,0 +1,51 @@
+#!/bin/bash
+#
+# Analyze a given results directory for rcutorture progress.
+#
+# Usage: sh kvm-recheck-rcu.sh resdir
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (C) IBM Corporation, 2014
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+i="$1"
+if test -d $i
+then
+	:
+else
+	echo Unreadable results directory: $i
+	exit 1
+fi
+
+configfile=`echo $i | sed -e 's/^.*\///'`
+ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'`
+if test -z "$ngps"
+then
+	echo $configfile
+else
+	title="$configfile ------- $ngps grace periods"
+	dur=`sed -e 's/^.* rcutorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`
+	if test -z "$dur"
+	then
+		:
+	else
+		ngpsps=`awk -v ngps=$ngps -v dur=$dur '
+			BEGIN { print ngps / dur }' < /dev/null`
+		title="$title ($ngpsps per second)"
+	fi
+	echo $title
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index baef09f..a44daaa 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 #
-# Given the results directories for previous KVM runs of rcutorture,
+# Given the results directories for previous KVM-based torture runs,
 # check the build and console output for errors.  Given a directory
 # containing results directories, this recursively checks them all.
 #
@@ -27,11 +27,18 @@
 PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
 for rd in "$@"
 do
+	firsttime=1
 	dirs=`find $rd -name Make.defconfig.out -print | sort | sed -e 's,/[^/]*$,,' | sort -u`
 	for i in $dirs
 	do
-		configfile=`echo $i | sed -e 's/^.*\///'`
-		echo $configfile
+		if test -n "$firsttime"
+		then
+			firsttime=""
+			resdir=`echo $i | sed -e 's,/$,,' -e 's,/[^/]*$,,'`
+			head -1 $resdir/log
+		fi
+		TORTURE_SUITE="`cat $i/../TORTURE_SUITE`"
+		kvm-recheck-${TORTURE_SUITE}.sh $i
 		configcheck.sh $i/.config $i/ConfigFragment
 		parse-build.sh $i/Make.out $configfile
 		parse-rcutorture.sh $i/console.log $configfile
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
similarity index 79%
rename from tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
rename to tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 151b237..94b28bb 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -6,15 +6,15 @@
 # Execute this in the source tree.  Do not run it as a background task
 # because qemu does not seem to like that much.
 #
-# Usage: sh kvm-test-1-rcu.sh config builddir resdir minutes qemu-args bootargs
+# Usage: sh kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args
 #
-# qemu-args defaults to "" -- you will want "-nographic" if running headless.
-# bootargs defaults to	"root=/dev/sda noapic selinux=0 console=ttyS0"
-#			"initcall_debug debug rcutorture.stat_interval=15"
-#			"rcutorture.shutdown_secs=$((minutes * 60))"
-#			"rcutorture.rcutorture_runnable=1"
+# qemu-args defaults to "-nographic", along with arguments specifying the
+#			number of CPUs and other options generated from
+#			the underlying CPU architecture.
+# boot_args defaults to value returned by the per_version_boot_params
+#			shell function.
 #
-# Anything you specify for either qemu-args or bootargs is appended to
+# Anything you specify for either qemu-args or boot_args is appended to
 # the default values.  The "-smp" value is deduced from the contents of
 # the config fragment.
 #
@@ -40,32 +40,34 @@
 
 grace=120
 
-T=/tmp/kvm-test-1-rcu.sh.$$
+T=/tmp/kvm-test-1-run.sh.$$
 trap 'rm -rf $T' 0
 
 . $KVM/bin/functions.sh
 . $KVPATH/ver_functions.sh
 
 config_template=${1}
+config_dir=`echo $config_template | sed -e 's,/[^/]*$,,'`
 title=`echo $config_template | sed -e 's/^.*\///'`
 builddir=${2}
 if test -z "$builddir" -o ! -d "$builddir" -o ! -w "$builddir"
 then
-	echo "kvm-test-1-rcu.sh :$builddir: Not a writable directory, cannot build into it"
+	echo "kvm-test-1-run.sh :$builddir: Not a writable directory, cannot build into it"
 	exit 1
 fi
 resdir=${3}
 if test -z "$resdir" -o ! -d "$resdir" -o ! -w "$resdir"
 then
-	echo "kvm-test-1-rcu.sh :$resdir: Not a writable directory, cannot build into it"
+	echo "kvm-test-1-run.sh :$resdir: Not a writable directory, cannot store results into it"
 	exit 1
 fi
 cp $config_template $resdir/ConfigFragment
 echo ' ---' `date`: Starting build
 echo ' ---' Kconfig fragment at: $config_template >> $resdir/log
-cat << '___EOF___' >> $T
-CONFIG_RCU_TORTURE_TEST=y
-___EOF___
+if test -r "$config_dir/CFcommon"
+then
+	cat < $config_dir/CFcommon >> $T
+fi
 # Optimizations below this point
 # CONFIG_USB=n
 # CONFIG_SECURITY=n
@@ -96,11 +98,23 @@
 	cp $builddir/.config $resdir
 	cp $builddir/arch/x86/boot/bzImage $resdir
 	parse-build.sh $resdir/Make.out $title
+	if test -f $builddir.wait
+	then
+		mv $builddir.wait $builddir.ready
+	fi
 else
 	cp $builddir/Make*.out $resdir
 	echo Build failed, not running KVM, see $resdir.
+	if test -f $builddir.wait
+	then
+		mv $builddir.wait $builddir.ready
+	fi
 	exit 1
 fi
+while test -f $builddir.ready
+do
+	sleep 1
+done
 minutes=$4
 seconds=$(($minutes * 60))
 qemu_args=$5
@@ -111,9 +125,10 @@
 echo ' ---' `date`: Starting kernel
 
 # Determine the appropriate flavor of qemu command.
-QEMU="`identify_qemu $builddir/vmlinux.o`"
+QEMU="`identify_qemu $builddir/vmlinux`"
 
 # Generate -smp qemu argument.
+qemu_args="-nographic $qemu_args"
 cpu_count=`configNR_CPUS.sh $config_template`
 vcpus=`identify_qemu_vcpus`
 if test $cpu_count -gt $vcpus
@@ -133,12 +148,8 @@
 
 # Pull in Kconfig-fragment boot parameters
 boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
-# Generate CPU-hotplug boot parameters
-boot_args="`rcutorture_param_onoff "$boot_args" $builddir/.config`"
-# Generate rcu_barrier() boot parameter
-boot_args="`rcutorture_param_n_barrier_cbs "$boot_args"`"
-# Pull in standard rcutorture boot arguments
-boot_args="$boot_args rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1"
+# Generate kernel-version-specific boot parameters
+boot_args="`per_version_boot_params "$boot_args" $builddir/.config $seconds`"
 
 echo $QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
 if test -n "$RCU_BUILDONLY"
@@ -188,5 +199,5 @@
 fi
 
 cp $builddir/console.log $resdir
-parse-rcutorture.sh $resdir/console.log $title
+parse-${TORTURE_SUITE}torture.sh $resdir/console.log $title
 parse-console.sh $resdir/console.log $title
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 1b7923b..5a78cbf 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -30,14 +30,21 @@
 scriptname=$0
 args="$*"
 
+T=/tmp/kvm.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
 dur=30
+dryrun=""
 KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
 PATH=${KVM}/bin:$PATH; export PATH
 builddir="${KVM}/b1"
 RCU_INITRD="$KVM/initrd"; export RCU_INITRD
 RCU_KMAKE_ARG=""; export RCU_KMAKE_ARG
+TORTURE_SUITE=rcu
 resdir=""
 configs=""
+cpus=0
 ds=`date +%Y.%m.%d-%H:%M:%S`
 kversion=""
 
@@ -49,7 +56,9 @@
 	echo "       --builddir absolute-pathname"
 	echo "       --buildonly"
 	echo "       --configs \"config-file list\""
+	echo "       --cpus N"
 	echo "       --datestamp string"
+	echo "       --dryrun sched|script"
 	echo "       --duration minutes"
 	echo "       --interactive"
 	echo "       --kmake-arg kernel-make-arguments"
@@ -58,8 +67,9 @@
 	echo "       --no-initrd"
 	echo "       --qemu-args qemu-system-..."
 	echo "       --qemu-cmd qemu-system-..."
-	echo "       --results absolute-pathname"
 	echo "       --relbuilddir relative-pathname"
+	echo "       --results absolute-pathname"
+	echo "       --torture rcu"
 	exit 1
 }
 
@@ -85,11 +95,21 @@
 		configs="$2"
 		shift
 		;;
+	--cpus)
+		checkarg --cpus "(number)" "$#" "$2" '^[0-9]*$' '^--'
+		cpus=$2
+		shift
+		;;
 	--datestamp)
 		checkarg --datestamp "(relative pathname)" "$#" "$2" '^[^/]*$' '^--'
 		ds=$2
 		shift
 		;;
+	--dryrun)
+		checkarg --dryrun "sched|script" $# "$2" 'sched\|script' '^--'
+		dryrun=$2
+		shift
+		;;
 	--duration)
 		checkarg --duration "(minutes)" $# "$2" '^[0-9]*$' '^error'
 		dur=$2
@@ -138,6 +158,11 @@
 		resdir=$2
 		shift
 		;;
+	--torture)
+		checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\)$' '^--'
+		TORTURE_SUITE=$2
+		shift
+		;;
 	*)
 		echo Unknown argument $1
 		usage
@@ -146,7 +171,7 @@
 	shift
 done
 
-CONFIGFRAG=${KVM}/configs; export CONFIGFRAG
+CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG
 KVPATH=${CONFIGFRAG}/$kversion; export KVPATH
 
 if test -z "$configs"
@@ -157,54 +182,231 @@
 if test -z "$resdir"
 then
 	resdir=$KVM/res
-	if ! test -e $resdir
-	then
-		mkdir $resdir || :
-	fi
-else
+fi
+
+if test "$dryrun" = ""
+then
 	if ! test -e $resdir
 	then
 		mkdir -p "$resdir" || :
 	fi
-fi
-mkdir $resdir/$ds
-touch $resdir/$ds/log
-echo $scriptname $args >> $resdir/$ds/log
+	mkdir $resdir/$ds
 
-pwd > $resdir/$ds/testid.txt
-if test -d .git
-then
-	git status >> $resdir/$ds/testid.txt
-	git rev-parse HEAD >> $resdir/$ds/testid.txt
-fi
-builddir=$KVM/b1
-if ! test -e $builddir
-then
-	mkdir $builddir || :
+	# Be noisy only if running the script.
+	echo Results directory: $resdir/$ds
+	echo $scriptname $args
+
+	touch $resdir/$ds/log
+	echo $scriptname $args >> $resdir/$ds/log
+	echo ${TORTURE_SUITE} > $resdir/$ds/TORTURE_SUITE
+
+	pwd > $resdir/$ds/testid.txt
+	if test -d .git
+	then
+		git status >> $resdir/$ds/testid.txt
+		git rev-parse HEAD >> $resdir/$ds/testid.txt
+	fi
 fi
 
+# Create a file of test-name/#cpus pairs, sorted by decreasing #cpus.
+touch $T/cfgcpu
 for CF in $configs
 do
-	# Running TREE01 multiple times creates TREE01, TREE01.2, TREE01.3, ...
-	rd=$resdir/$ds/$CF
-	if test -d "${rd}"
+	if test -f "$CONFIGFRAG/$kversion/$CF"
 	then
-		n="`ls -d "${rd}"* | grep '\.[0-9]\+$' |
-			sed -e 's/^.*\.\([0-9]\+\)/\1/' |
-			sort -k1n | tail -1`"
-		if test -z "$n"
-		then
-			rd="${rd}.2"
-		else
-			n="`expr $n + 1`"
-			rd="${rd}.${n}"
-		fi
+		echo $CF `configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF` >> $T/cfgcpu
+	else
+		echo "The --configs file $CF does not exist, terminating."
+		exit 1
 	fi
-	mkdir "${rd}"
-	echo Results directory: $rd
-	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic $RCU_QEMU_ARG" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1 $RCU_BOOTARGS"
 done
+sort -k2nr $T/cfgcpu > $T/cfgcpu.sort
+
+# Use a greedy bin-packing algorithm, sorting the list accordingly.
+awk < $T/cfgcpu.sort > $T/cfgcpu.pack -v ncpus=$cpus '
+BEGIN {
+	njobs = 0;
+}
+
+{
+	# Read file of tests and corresponding required numbers of CPUs.
+	cf[njobs] = $1;
+	cpus[njobs] = $2;
+	njobs++;
+}
+
+END {
+	alldone = 0;
+	batch = 0;
+	nc = -1;
+
+	# Each pass through the following loop creates on test batch
+	# that can be executed concurrently given ncpus.  Note that a
+	# given test that requires more than the available CPUs will run in
+	# their own batch.  Such tests just have to make do with what
+	# is available.
+	while (nc != ncpus) {
+		batch++;
+		nc = ncpus;
+
+		# Each pass through the following loop considers one
+		# test for inclusion in the current batch.
+		for (i = 0; i < njobs; i++) {
+			if (done[i])
+				continue; # Already part of a batch.
+			if (nc >= cpus[i] || nc == ncpus) {
+
+				# This test fits into the current batch.
+				done[i] = batch;
+				nc -= cpus[i];
+				if (nc <= 0)
+					break; # Too-big test in its own batch.
+			}
+		}
+	}
+
+	# Dump out the tests in batch order.
+	for (b = 1; b <= batch; b++)
+		for (i = 0; i < njobs; i++)
+			if (done[i] == b)
+				print cf[i], cpus[i];
+}'
+
+# Generate a script to execute the tests in appropriate batches.
+cat << ___EOF___ > $T/script
+TORTURE_SUITE="$TORTURE_SUITE"; export TORTURE_SUITE
+___EOF___
+awk < $T/cfgcpu.pack \
+	-v CONFIGDIR="$CONFIGFRAG/$kversion/" \
+	-v KVM="$KVM" \
+	-v ncpus=$cpus \
+	-v rd=$resdir/$ds/ \
+	-v dur=$dur \
+	-v RCU_QEMU_ARG=$RCU_QEMU_ARG \
+	-v RCU_BOOTARGS=$RCU_BOOTARGS \
+'BEGIN {
+	i = 0;
+}
+
+{
+	cf[i] = $1;
+	cpus[i] = $2;
+	i++;
+}
+
+# Dump out the scripting required to run one test batch.
+function dump(first, pastlast)
+{
+	print "echo ----Start batch: `date`";
+	print "echo ----Start batch: `date` >> " rd "/log";
+	jn=1
+	for (j = first; j < pastlast; j++) {
+		builddir=KVM "/b" jn
+		cpusr[jn] = cpus[j];
+		if (cfrep[cf[j]] == "") {
+			cfr[jn] = cf[j];
+			cfrep[cf[j]] = 1;
+		} else {
+			cfrep[cf[j]]++;
+			cfr[jn] = cf[j] "." cfrep[cf[j]];
+		}
+		if (cpusr[jn] > ncpus && ncpus != 0)
+			ovf = "(!)";
+		else
+			ovf = "";
+		print "echo ", cfr[jn], cpusr[jn] ovf ": Starting build. `date`";
+		print "echo ", cfr[jn], cpusr[jn] ovf ": Starting build. `date` >> " rd "/log";
+		print "rm -f " builddir ".*";
+		print "touch " builddir ".wait";
+		print "mkdir " builddir " > /dev/null 2>&1 || :";
+		print "mkdir " rd cfr[jn] " || :";
+		print "kvm-test-1-run.sh " CONFIGDIR cf[j], builddir, rd cfr[jn], dur " \"" RCU_QEMU_ARG "\" \"" RCU_BOOTARGS "\" > " rd cfr[jn]  "/kvm-test-1-run.sh.out 2>&1 &"
+		print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date`";
+		print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date` >> " rd "/log";
+		print "while test -f " builddir ".wait"
+		print "do"
+		print "\tsleep 1"
+		print "done"
+		print "echo ", cfr[jn], cpusr[jn] ovf ": Build complete. `date`";
+		print "echo ", cfr[jn], cpusr[jn] ovf ": Build complete. `date` >> " rd "/log";
+		jn++;
+	}
+	for (j = 1; j < jn; j++) {
+		builddir=KVM "/b" j
+		print "rm -f " builddir ".ready"
+		print "echo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`";
+		print "echo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log";
+	}
+	print "wait"
+	print "echo ---- All kernel runs complete. `date`";
+	print "echo ---- All kernel runs complete. `date` >> " rd "/log";
+	for (j = 1; j < jn; j++) {
+		builddir=KVM "/b" j
+		print "echo ----", cfr[j], cpusr[j] ovf ": Build/run results:";
+		print "echo ----", cfr[j], cpusr[j] ovf ": Build/run results: >> " rd "/log";
+		print "cat " rd cfr[j]  "/kvm-test-1-run.sh.out";
+		print "cat " rd cfr[j]  "/kvm-test-1-run.sh.out >> " rd "/log";
+	}
+}
+
+END {
+	njobs = i;
+	nc = ncpus;
+	first = 0;
+
+	# Each pass through the following loop considers one test.
+	for (i = 0; i < njobs; i++) {
+		if (ncpus == 0) {
+			# Sequential test specified, each test its own batch.
+			dump(i, i + 1);
+			first = i;
+		} else if (nc < cpus[i] && i != 0) {
+			# Out of CPUs, dump out a batch.
+			dump(first, i);
+			first = i;
+			nc = ncpus;
+		}
+		# Account for the CPUs needed by the current test.
+		nc -= cpus[i];
+	}
+	# Dump the last batch.
+	if (ncpus != 0)
+		dump(first, i);
+}' >> $T/script
+
+if test "$dryrun" = script
+then
+	# Dump out the script, but define the environment variables that
+	# it needs to run standalone.
+	echo CONFIGFRAG="$CONFIGFRAG; export CONFIGFRAG"
+	echo KVM="$KVM; export KVM"
+	echo KVPATH="$KVPATH; export KVPATH"
+	echo PATH="$PATH; export PATH"
+	echo RCU_BUILDONLY="$RCU_BUILDONLY; export RCU_BUILDONLY"
+	echo RCU_INITRD="$RCU_INITRD; export RCU_INITRD"
+	echo RCU_KMAKE_ARG="$RCU_KMAKE_ARG; export RCU_KMAKE_ARG"
+	echo RCU_QEMU_CMD="$RCU_QEMU_CMD; export RCU_QEMU_CMD"
+	echo RCU_QEMU_INTERACTIVE="$RCU_QEMU_INTERACTIVE; export RCU_QEMU_INTERACTIVE"
+	echo RCU_QEMU_MAC="$RCU_QEMU_MAC; export RCU_QEMU_MAC"
+	echo "mkdir -p "$resdir" || :"
+	echo "mkdir $resdir/$ds"
+	cat $T/script
+	exit 0
+elif test "$dryrun" = sched
+then
+	# Extract the test run schedule from the script.
+	egrep 'start batch|Starting build\.' $T/script |
+		sed -e 's/:.*$//' -e 's/^echo //'
+	exit 0
+else
+	# Not a dryru, so run the script.
+	sh $T/script
+fi
+
 # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier
 
+echo
+echo
 echo " --- `date` Test summary:"
+echo Results directory: $resdir/$ds
 kvm-recheck.sh $resdir/$ds
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P b/tools/testing/selftests/rcutorture/configs/lock/BUSTED
similarity index 63%
copy from tools/testing/selftests/rcutorture/configs/SRCU-P
copy to tools/testing/selftests/rcutorture/configs/lock/BUSTED
index 6650e00..1d1da14 100644
--- a/tools/testing/selftests/rcutorture/configs/SRCU-P
+++ b/tools/testing/selftests/rcutorture/configs/lock/BUSTED
@@ -1,8 +1,6 @@
-CONFIG_RCU_TRACE=n
 CONFIG_SMP=y
-CONFIG_NR_CPUS=8
+CONFIG_NR_CPUS=4
 CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/BUSTED.boot b/tools/testing/selftests/rcutorture/configs/lock/BUSTED.boot
new file mode 100644
index 0000000..6386c15
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/BUSTED.boot
@@ -0,0 +1 @@
+locktorture.torture_type=lock_busted
diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
new file mode 100644
index 0000000..a061b22
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
@@ -0,0 +1 @@
+LOCK01
diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFcommon b/tools/testing/selftests/rcutorture/configs/lock/CFcommon
new file mode 100644
index 0000000..e372dc2
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/CFcommon
@@ -0,0 +1,2 @@
+CONFIG_LOCK_TORTURE_TEST=y
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P b/tools/testing/selftests/rcutorture/configs/lock/LOCK01
similarity index 73%
copy from tools/testing/selftests/rcutorture/configs/SRCU-P
copy to tools/testing/selftests/rcutorture/configs/lock/LOCK01
index 6650e00..a9625e3 100644
--- a/tools/testing/selftests/rcutorture/configs/SRCU-P
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK01
@@ -1,8 +1,6 @@
-CONFIG_RCU_TRACE=n
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
 CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
new file mode 100644
index 0000000..9746ea1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
@@ -0,0 +1,43 @@
+#!/bin/bash
+#
+# Kernel-version-dependent shell functions for the rest of the scripts.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (C) IBM Corporation, 2014
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+# locktorture_param_onoff bootparam-string config-file
+#
+# Adds onoff locktorture module parameters to kernels having it.
+locktorture_param_onoff () {
+	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
+	then
+		echo CPU-hotplug kernel, adding locktorture onoff. 1>&2
+		echo locktorture.onoff_interval=3 locktorture.onoff_holdoff=30
+	fi
+}
+
+# per_version_boot_params bootparam-string config-file seconds
+#
+# Adds per-version torture-module parameters to kernels supporting them.
+per_version_boot_params () {
+	echo $1 `locktorture_param_onoff "$1" "$2"` \
+		locktorture.stat_interval=15 \
+		locktorture.shutdown_secs=$3 \
+		locktorture.locktorture_runnable=1 \
+		locktorture.verbose=1
+}
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED
similarity index 75%
copy from tools/testing/selftests/rcutorture/configs/SRCU-P
copy to tools/testing/selftests/rcutorture/configs/rcu/BUSTED
index 6650e00..48d8a24 100644
--- a/tools/testing/selftests/rcutorture/configs/SRCU-P
+++ b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED
@@ -1,8 +1,7 @@
 CONFIG_RCU_TRACE=n
 CONFIG_SMP=y
-CONFIG_NR_CPUS=8
+CONFIG_NR_CPUS=4
 CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot
new file mode 100644
index 0000000..6804f9d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=rcu_busted
diff --git a/tools/testing/selftests/rcutorture/configs/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/CFLIST
rename to tools/testing/selftests/rcutorture/configs/rcu/CFLIST
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
new file mode 100644
index 0000000..d2d2a86
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
@@ -0,0 +1,2 @@
+CONFIG_RCU_TORTURE_TEST=y
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
similarity index 75%
rename from tools/testing/selftests/rcutorture/configs/SRCU-N
rename to tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
index 10a0e27..9fbb41b 100644
--- a/tools/testing/selftests/rcutorture/configs/SRCU-N
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
@@ -1,8 +1,7 @@
 CONFIG_RCU_TRACE=n
 CONFIG_SMP=y
-CONFIG_NR_CPUS=8
+CONFIG_NR_CPUS=4
 CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-N.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/SRCU-N.boot
rename to tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P
similarity index 86%
rename from tools/testing/selftests/rcutorture/configs/SRCU-P
rename to tools/testing/selftests/rcutorture/configs/rcu/SRCU-P
index 6650e00..4b6f272 100644
--- a/tools/testing/selftests/rcutorture/configs/SRCU-P
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P
@@ -5,4 +5,3 @@
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/SRCU-P.boot
rename to tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
diff --git a/tools/testing/selftests/rcutorture/configs/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
similarity index 92%
rename from tools/testing/selftests/rcutorture/configs/TINY01
rename to tools/testing/selftests/rcutorture/configs/rcu/TINY01
index 0c2823f..0a63e07 100644
--- a/tools/testing/selftests/rcutorture/configs/TINY01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
@@ -10,4 +10,3 @@
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_PREEMPT_COUNT=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
similarity index 92%
rename from tools/testing/selftests/rcutorture/configs/TINY02
rename to tools/testing/selftests/rcutorture/configs/rcu/TINY02
index e5072d7..f4feaee 100644
--- a/tools/testing/selftests/rcutorture/configs/TINY02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
@@ -10,4 +10,3 @@
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_PREEMPT_COUNT=y
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
similarity index 95%
rename from tools/testing/selftests/rcutorture/configs/TREE01
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE01
index 141119a..9c827ec 100644
--- a/tools/testing/selftests/rcutorture/configs/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -20,4 +20,3 @@
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/TREE01.boot
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
diff --git a/tools/testing/selftests/rcutorture/configs/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
similarity index 92%
rename from tools/testing/selftests/rcutorture/configs/TREE02
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE02
index 2d4d096..1a777b5 100644
--- a/tools/testing/selftests/rcutorture/configs/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -7,7 +7,7 @@
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n 
+CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=n
 CONFIG_HOTPLUG_CPU=n
 CONFIG_SUSPEND=n
@@ -23,4 +23,3 @@
 CONFIG_RCU_CPU_STALL_VERBOSE=y
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
similarity index 95%
rename from tools/testing/selftests/rcutorture/configs/TREE03
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE03
index a47de5b..c1f111c 100644
--- a/tools/testing/selftests/rcutorture/configs/TREE03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
@@ -20,4 +20,3 @@
 CONFIG_RCU_BOOST=y
 CONFIG_RCU_BOOST_PRIO=2
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
similarity index 96%
rename from tools/testing/selftests/rcutorture/configs/TREE04
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 8d839b8..7dbd27c 100644
--- a/tools/testing/selftests/rcutorture/configs/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -22,4 +22,3 @@
 CONFIG_RCU_CPU_STALL_INFO=y
 CONFIG_RCU_CPU_STALL_VERBOSE=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE04.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/TREE04.boot
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
diff --git a/tools/testing/selftests/rcutorture/configs/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
similarity index 96%
rename from tools/testing/selftests/rcutorture/configs/TREE05
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE05
index b5ba72e..d0f32e5 100644
--- a/tools/testing/selftests/rcutorture/configs/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -22,4 +22,3 @@
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE05.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/TREE05.boot
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
diff --git a/tools/testing/selftests/rcutorture/configs/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
similarity index 96%
rename from tools/testing/selftests/rcutorture/configs/TREE06
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE06
index 7c95ab4..2e477df 100644
--- a/tools/testing/selftests/rcutorture/configs/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -23,4 +23,3 @@
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
similarity index 95%
rename from tools/testing/selftests/rcutorture/configs/TREE07
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE07
index 1467404..042f86e 100644
--- a/tools/testing/selftests/rcutorture/configs/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -21,4 +21,3 @@
 CONFIG_RCU_CPU_STALL_INFO=y
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
similarity index 96%
rename from tools/testing/selftests/rcutorture/configs/TREE08
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE08
index 7d097a6..3438cee 100644
--- a/tools/testing/selftests/rcutorture/configs/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -23,4 +23,3 @@
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
similarity index 96%
rename from tools/testing/selftests/rcutorture/configs/TREE08-T
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
index 442c4e4..bf4523d 100644
--- a/tools/testing/selftests/rcutorture/configs/TREE08-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
@@ -23,4 +23,3 @@
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
similarity index 95%
rename from tools/testing/selftests/rcutorture/configs/TREE09
rename to tools/testing/selftests/rcutorture/configs/rcu/TREE09
index 0d1ec0d..81e4f7c 100644
--- a/tools/testing/selftests/rcutorture/configs/TREE09
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
@@ -18,4 +18,3 @@
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/CFLIST
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/CFLIST
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/CFLIST
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N1-S-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/N1-S-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N2-2-t-nh-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/N2-2-t-nh-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/N2-2-t-nh-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N3-3-T-nh-SD-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/N3-3-T-nh-SD-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/N3-3-T-nh-SD-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N4-A-t-NH-sd-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/N4-A-t-NH-sd-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/N4-A-t-NH-sd-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N5-U-T-NH-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/N5-U-T-NH-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/N5-U-T-NH-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT1-nh
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/NT1-nh
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT1-nh
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT3-NH
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/NT3-NH
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/P2-2-t-nh-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/P3-3-T-nh-SD-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/P4-A-t-NH-sd-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/P5-U-T-NH-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT1-nh
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/PT1-nh
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT1-nh
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT2-NH
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v0.0/PT2-NH
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT2-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh
similarity index 70%
rename from tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh
rename to tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh
index e805253..5ace37a 100644
--- a/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh
@@ -20,16 +20,14 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-# rcutorture_param_n_barrier_cbs bootparam-string
+# per_version_boot_params bootparam-string config-file seconds
 #
-# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
-rcutorture_param_n_barrier_cbs () {
-	echo $1
-}
-
-# rcutorture_param_onoff bootparam-string config-file
-#
-# Adds onoff rcutorture module parameters to kernels having it.
-rcutorture_param_onoff () {
-	echo $1
+# Adds per-version torture-module parameters to kernels supporting them.
+# Which old kernels do not.
+per_version_boot_params () {
+	echo	rcutorture.stat_interval=15 \
+		rcutorture.shutdown_secs=$3 \
+		rcutorture.rcutorture_runnable=1 \
+		rcutorture.test_no_idle_hz=1 \
+		rcutorture.verbose=1
 }
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/CFLIST
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/CFLIST
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/CFLIST
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N1-S-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/N1-S-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/N1-S-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N2-2-t-nh-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/N2-2-t-nh-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/N2-2-t-nh-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N3-3-T-nh-SD-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/N3-3-T-nh-SD-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/N3-3-T-nh-SD-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N4-A-t-NH-sd-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/N4-A-t-NH-sd-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/N4-A-t-NH-sd-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N5-U-T-NH-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/N5-U-T-NH-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/N5-U-T-NH-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N6---t-nh-SD-smp-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/N6---t-nh-SD-smp-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/N6---t-nh-SD-smp-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N7-4-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/N7-4-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/N7-4-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N8-2-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N8-2-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/N8-2-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/N8-2-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT1-nh
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/NT1-nh
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT1-nh
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT3-NH
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/NT3-NH
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/P1-S-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/P2-2-t-nh-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/P3-3-T-nh-SD-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/P4-A-t-NH-sd-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/P5-U-T-NH-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/P6---t-nh-SD-smp-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-all b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-all
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-none b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-none
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT1-nh
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/PT1-nh
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT1-nh
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT2-NH
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.12/PT2-NH
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT2-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/CFLIST
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/CFLIST
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/CFLIST
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N1-S-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/N1-S-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/N1-S-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N2-2-t-nh-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/N2-2-t-nh-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/N2-2-t-nh-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N3-3-T-nh-SD-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/N3-3-T-nh-SD-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/N3-3-T-nh-SD-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N4-A-t-NH-sd-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/N4-A-t-NH-sd-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/N4-A-t-NH-sd-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N5-U-T-NH-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/N5-U-T-NH-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/N5-U-T-NH-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT1-nh
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/NT1-nh
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT1-nh
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT3-NH
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/NT3-NH
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/P1-S-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/P2-2-t-nh-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/P3-3-T-nh-SD-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/P4-A-t-NH-sd-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/P5-U-T-NH-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT1-nh
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/PT1-nh
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT1-nh
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT2-NH
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.3/PT2-NH
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT2-NH
diff --git a/tools/testing/selftests/rcutorture/configs/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh
similarity index 72%
rename from tools/testing/selftests/rcutorture/configs/ver_functions.sh
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh
index 5e40ead..bae5569 100644
--- a/tools/testing/selftests/rcutorture/configs/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh
@@ -20,18 +20,6 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-# rcutorture_param_n_barrier_cbs bootparam-string
-#
-# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
-rcutorture_param_n_barrier_cbs () {
-	if echo $1 | grep -q "rcutorture\.n_barrier_cbs"
-	then
-		echo $1
-	else
-		echo $1 rcutorture.n_barrier_cbs=4
-	fi
-}
-
 # rcutorture_param_onoff bootparam-string config-file
 #
 # Adds onoff rcutorture module parameters to kernels having it.
@@ -39,8 +27,18 @@
 	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
 	then
 		echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
-		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
-	else
-		echo $1
+		echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
 	fi
 }
+
+# per_version_boot_params bootparam-string config-file seconds
+#
+# Adds per-version torture-module parameters to kernels supporting them.
+per_version_boot_params () {
+	echo $1 `rcutorture_param_onoff "$1" "$2"` \
+		rcutorture.stat_interval=15 \
+		rcutorture.shutdown_secs=$3 \
+		rcutorture.rcutorture_runnable=1 \
+		rcutorture.test_no_idle_hz=1 \
+		rcutorture.verbose=1
+}
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/CFLIST
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/CFLIST
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/CFLIST
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N1-S-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/N1-S-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/N1-S-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N2-2-t-nh-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/N2-2-t-nh-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/N2-2-t-nh-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N3-3-T-nh-SD-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/N3-3-T-nh-SD-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/N3-3-T-nh-SD-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N4-A-t-NH-sd-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/N4-A-t-NH-sd-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/N4-A-t-NH-sd-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N5-U-T-NH-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/N5-U-T-NH-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/N5-U-T-NH-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT1-nh
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/NT1-nh
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT1-nh
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT3-NH
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/NT3-NH
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/P1-S-T-NH-SD-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/P2-2-t-nh-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/P3-3-T-nh-SD-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/P4-A-t-NH-sd-SMP-HP
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/P5-U-T-NH-sd-SMP-hp
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT1-nh
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/PT1-nh
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT1-nh
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT2-NH
similarity index 100%
rename from tools/testing/selftests/rcutorture/configs/v3.5/PT2-NH
rename to tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT2-NH
diff --git a/tools/testing/selftests/rcutorture/configs/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh
similarity index 72%
copy from tools/testing/selftests/rcutorture/configs/ver_functions.sh
copy to tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh
index 5e40ead..8977d8d 100644
--- a/tools/testing/selftests/rcutorture/configs/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh
@@ -26,9 +26,9 @@
 rcutorture_param_n_barrier_cbs () {
 	if echo $1 | grep -q "rcutorture\.n_barrier_cbs"
 	then
-		echo $1
+		:
 	else
-		echo $1 rcutorture.n_barrier_cbs=4
+		echo rcutorture.n_barrier_cbs=4
 	fi
 }
 
@@ -39,8 +39,19 @@
 	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
 	then
 		echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
-		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
-	else
-		echo $1
+		echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
 	fi
 }
+
+# per_version_boot_params bootparam-string config-file seconds
+#
+# Adds per-version torture-module parameters to kernels supporting them.
+per_version_boot_params () {
+	echo $1 `rcutorture_param_onoff "$1" "$2"` \
+		`rcutorture_param_n_barrier_cbs "$1"` \
+		rcutorture.stat_interval=15 \
+		rcutorture.shutdown_secs=$3 \
+		rcutorture.rcutorture_runnable=1 \
+		rcutorture.test_no_idle_hz=1 \
+		rcutorture.verbose=1
+}
diff --git a/tools/testing/selftests/rcutorture/configs/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
similarity index 72%
copy from tools/testing/selftests/rcutorture/configs/ver_functions.sh
copy to tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index 5e40ead..8977d8d 100644
--- a/tools/testing/selftests/rcutorture/configs/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -26,9 +26,9 @@
 rcutorture_param_n_barrier_cbs () {
 	if echo $1 | grep -q "rcutorture\.n_barrier_cbs"
 	then
-		echo $1
+		:
 	else
-		echo $1 rcutorture.n_barrier_cbs=4
+		echo rcutorture.n_barrier_cbs=4
 	fi
 }
 
@@ -39,8 +39,19 @@
 	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
 	then
 		echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
-		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
-	else
-		echo $1
+		echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
 	fi
 }
+
+# per_version_boot_params bootparam-string config-file seconds
+#
+# Adds per-version torture-module parameters to kernels supporting them.
+per_version_boot_params () {
+	echo $1 `rcutorture_param_onoff "$1" "$2"` \
+		`rcutorture_param_n_barrier_cbs "$1"` \
+		rcutorture.stat_interval=15 \
+		rcutorture.shutdown_secs=$3 \
+		rcutorture.rcutorture_runnable=1 \
+		rcutorture.test_no_idle_hz=1 \
+		rcutorture.verbose=1
+}
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh
deleted file mode 100644
index c37432f..0000000
--- a/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh
+++ /dev/null
@@ -1,41 +0,0 @@
-#!/bin/bash
-#
-# Kernel-version-dependent shell functions for the rest of the scripts.
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
-# Copyright (C) IBM Corporation, 2013
-#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-
-# rcutorture_param_n_barrier_cbs bootparam-string
-#
-# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
-rcutorture_param_n_barrier_cbs () {
-	echo $1
-}
-
-# rcutorture_param_onoff bootparam-string config-file
-#
-# Adds onoff rcutorture module parameters to kernels having it.
-rcutorture_param_onoff () {
-	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
-	then
-		echo CPU-hotplug kernel, adding rcutorture onoff.
-		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
-	else
-		echo $1
-	fi
-}
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh
deleted file mode 100644
index 6a5f13a..0000000
--- a/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh
+++ /dev/null
@@ -1,46 +0,0 @@
-#!/bin/bash
-#
-# Kernel-version-dependent shell functions for the rest of the scripts.
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
-# Copyright (C) IBM Corporation, 2013
-#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-
-# rcutorture_param_n_barrier_cbs bootparam-string
-#
-# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
-rcutorture_param_n_barrier_cbs () {
-	if echo $1 | grep -q "rcutorture\.n_barrier_cbs"
-	then
-		echo $1
-	else
-		echo $1 rcutorture.n_barrier_cbs=4
-	fi
-}
-
-# rcutorture_param_onoff bootparam-string config-file
-#
-# Adds onoff rcutorture module parameters to kernels having it.
-rcutorture_param_onoff () {
-	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
-	then
-		echo CPU-hotplug kernel, adding rcutorture onoff.
-		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
-	else
-		echo $1
-	fi
-}
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-Kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
similarity index 100%
rename from tools/testing/selftests/rcutorture/doc/TREE_RCU-Kconfig.txt
rename to tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index be456ce..8ca405c 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -24,6 +24,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/uaccess.h>
 
 #include <linux/irqchip/arm-gic.h>
 
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 88b2fe3..00d8642 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -154,17 +154,13 @@
 	list_add_tail(&dev->list, &kvm->coalesced_zones);
 	mutex_unlock(&kvm->slots_lock);
 
-	return ret;
+	return 0;
 
 out_free_dev:
 	mutex_unlock(&kvm->slots_lock);
-
 	kfree(dev);
 
-	if (dev == NULL)
-		return -ENXIO;
-
-	return 0;
+	return ret;
 }
 
 int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 03a0381..b5ec7fb 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -102,7 +102,7 @@
 static void mark_page_dirty_in_slot(struct kvm *kvm,
 				    struct kvm_memory_slot *memslot, gfn_t gfn);
 
-bool kvm_rebooting;
+__visible bool kvm_rebooting;
 EXPORT_SYMBOL_GPL(kvm_rebooting);
 
 static bool largepages_enabled = true;